SIEMENS INDUSTRY SOFTWARE LIMITED (United Kingdom)
SIEMENS INDUSTRY SOFTWARE INC. (USA)
SIEMENS INDUSTRY SOFTWARE NV (Belgium)
Inventor
Chemin, Jovana
Makem, Jonathan
Fogg, Harry
Mukherjee, Nilanjan
Abstract
A computer-implemented method for generating a finite element mesh of a component for the numerical solution of partial differential equations for the description of technical-physical circumstances to which the component is subjected in its intended operation. The invention further relates to a method for improving the components design and generating the component. Furthermore, the invention relates to a system for performing such method. Furthermore, the invention relates to a computer-readable medium encoded with executable instructions, that when executed, cause the computer system to carry out a method according to the invention.
A computer-implemented method for generating domain specific training data for a large language model includes providing a domain specific ontology relating to the domain, providing domain specific information relating to the domain, and processing the domain specific information in a data processing-pipeline for structuring data for training of the large language model. The domain specific ontology is provided as a recognition pattern in a step of the data processing-pipeline, such that the structured training data includes domain specific ontology annotations.
A computer-implemented method for modeling acoustics of an object as a numerical simulation model in an unbounded domain to determine a field variable within a control volume of the unbounded domain includes providing a coordinate system mapping positions in the control volume. A geometrical specification of a sound source is provided in the control volume based on the coordinate system. To improve efficiency of numerically modelling transient acoustics wave propagation phenomena in unbounded domains, a convex shape is constructed around the sound source using Quickhull algorithm, infinite elements are extruded starting from the convex shape, and the coordinate system is transformed into a field variable coordinate system by mapping a radial coordinate of the coordinate system to an auxiliary coordinate extending from the convex shape to the infinite elements. Field shape functions are constructed using the auxiliary coordinate, and the field variable is determined by solving the numerical simulation model.
The invention relates to an Electrical multipole connector arrangement for connecting at least three terminals (TRM) of a first (CNF) connector (CNC) to an equivalent number of terminals (TRM) of a second (CNS) connector (CNC), when both connectors (CNC) are plugged into each other, wherein the first (CNF) connector (CNC) has a recess (RCS), and the second (CNS) connector (CNC) has a protrusion (PRT), both of which interlock when plugged in, wherein at least either the protrusion (PRT) or the recess (RCS) or both are so tapered (TPS) that even if both connectors (CNC) are to some extent misaligned during the beginning of the mating process, the protrusion (PRT) meets the recess (RCS). It is proposed, that at least one of both connectors (CNC) is supported (SPT) in a floating manner to enable compensation of a misalignment during the mating process.
H01R 13/639 - Additional means for holding or locking coupling parts together after engagement
H05K 5/00 - Casings, cabinets or drawers for electric apparatus
H01R 13/631 - Additional means for facilitating engagement or disengagement of coupling parts, e.g. aligning or guiding means, levers, gas pressure for engagement only
H01R 13/514 - BasesCases formed as a modular block or assembly, i.e. composed of co-operating parts provided with contact members or holding contact members between them
5.
METHODS AND SYSTEMS OF DETERMINING THE STATIC STIFFNESS OF A BODY STRUCTURE
A method and system for determining the static stiffness of a body structure from dynamic data are disclosed. The method and system include providing dynamic data and defining flexible-body modes of the dynamic data of the body structure. To overcome the limitations of conventional methods and systems, the method and system further include: performing a modal decomposition of all defined flexible-body modes into contributions of rigid-body modes and a residual term. The modal decomposition of the body structure is defined as Formula (I), wherein Rj is a residual term for the jth flexible mode, such that the residual term results as free of inertial effects. The method and system further include determining the residual term Rj from the modal decomposition and determining the static stiffness from the residual terms Rj.
A system and method for managing one or more adversarial agents (404) used for testing of an autonomous vehicle is disclosed. The method comprises obtaining, by a processing unit (120), offline data for initializing the one or more adversarial agents from one or more first sources, wherein the offline data comprises at least one of real data and statistical simulation data. The method further comprises using a feedback-based learning algorithm to train one or more adversarial agents (404) based on the offline data and expert inputs received from a second source, wherein the one or more adversarial agents (404) are trainable computational models that model behavior of one or more entities that affect behavior of autonomous vehicles in a physical environment. The method further comprises deploying the trained adversarial agents (404) onto a test execution platform for testing of a system-under-test, wherein the system-under-test is associated with an autonomous vehicle-to-be-tested.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Disclosed is a method (100) and a system (200) for generating test scenarios to validate the behaviour competencies of autonomous vehicles. The method involves receiving a behavioural competency defined in natural language pertaining to a given operation of the autonomous vehicles. This competency is parsed into objects, representative of the Operational Design Domain (ODD), and events, representative of the Object and Event Detection and Response (OEDR). These objects and events are then transformed into a data structure (300). Subsequently, this data structure is mapped to a hierarchy of search queries representing relationships and interactions among the objects and events. The hierarchy of search queries is provided to a scenario extraction tool (10), which leverages the hierarchical queries, extracts relevant scenarios from real-world data, to validate behaviour of the autonomous vehicles for the given operation thereof.
The invention relates to a computer-implemented method computer product, computer-readable medium, and system for determining acoustic parameters of an object's (OBJ) emission and/or scattering within a predetermined frequency range (FRG), by applying Boundary Element Method (BEM) to the object, comprising splitting said object's (OBJ) surface into surface elements (ESF) and assigning boundary conditions (BCD) to said surface elements (ESF), further comprising •Providing polynomial shape functions (SFC) over each of said elements (ESF) for mapping geometry and acoustic parameters to said elements (ESF), wherein for each surface element (ESF) the order (SFO) of said shape functions (SFC) is determined by an adaptivity module (ADM), •Assembling the elements (ESF) of said surface by recombining the shape functions (SFC) obtaining a system matrix (SMX), •Solving said system matrix (SMX), •Determining said acoustic parameters (PRT) from said shape functions (SFC).
A method (200) and a system (300) for managing a data model (100A- 100C) are disclosed. The method involves extracting characteristic sets (600) from each of the versions, where a characteristic set groups objects that share common properties. The characteristic sets are then organized in a hierarchical manner based on the shared properties, with the characteristic sets sharing a relatively greater number of properties are placed higher in the corresponding hierarchical order and vice-versa, forming two characteristic set lattices (700) for the respective versions of the data model. The comparison function is applied to identify the differences between a first characteristic set lattice (810) and a second characteristic set lattice (820). A difference report is generated based on the comparison, providing an overview of the additions, deletions, and modifications that occurred between the two versions of the data model.
Method of determining acoustic parameters of an object's (OBJ) emission and/or scattering, in particular for improving acoustic properties of said object (OBJ), comprising: (a) defining a model (MDL) including said object (OBJ), a sound source (SCR), and a surrounding area, (b) processing said model (MDL) obtaining a result (RST), (c) post-processing the result (RST) by assigning to said field points (PTS) at least one parameter (PRM) determined from calculating the Helmholtz-Kirchhoff integral from said result (RST). To improve the accuracy and efficiency the post-processing comprises the additional steps: (d) identifying field points (PTS) as near field singularity field points (NEP) of potential lower result (RST) accuracy (ACR), (c) determining for said near field singularity field points (NEP) respectively an associated model mesh element (AME), by determining a local projection from said near field singularity field point (NEP) to the object's (OBJ) surface by calculating a minimum normal distance (MND) to the object's (OBJ) surface, wherein the associated model mesh element (AME) being the touchdown point of the local projection, (f) determining for said near field singularity field points (NEP) respectively a ratio (RTO) of the minimum normal distance (MND) to said element size (ESZ) of the associated model mesh element (AME), (g) calculating the Helmholtz-Kirchhoff integral by: (g11) providing a relation (PCR) of quadrature order (QOD) and said ratio (RTO), (g2) determine the respective quadrature order (QOD) by applying said relation (PCR), (g3) calculating the Helmholtz-Kirchhoff integral from said result (RST).
A system and method for managing testing of an autonomous vehicle is disclosed herein. The method comprises obtaining a training dataset from a source, by a processing unit (120). Further, one or more adversarial agents (204) and a software stack (206) associated with an autonomous vehicle (212) are synchronously trained based on the training dataset. Each of the adversarial agents (204) are configured to mimic one or more entities (210) that impact behavior of the autonomous vehicle in a real-world environment. Further, a virtual testing environment comprising the trained one or more adversarial agents (204), is configured based on a user request. The virtual testing environment is then deployed onto a test execution platform for enabling testing of a dynamic behavior of at least another autonomous vehicle in response to one or more safety-critical scenarios simulated by the virtual testing environment.
G06F 11/36 - Prevention of errors by analysis, debugging or testing of software
G06N 20/10 - Machine learning using kernel methods, e.g. support vector machines [SVM]
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
0N0NN, by minimizing a difference between an estimated battery temperature and said measured temperature, wherein the estimated battery temperature is obtained by modeling, with said battery thermal model, a heat generated by the battery during said charge and discharge cycle; d) outputting (250), by said identification algorithm, the determined EHC as function of the SoC.
G01R 31/367 - Software therefor, e.g. for battery testing using modelling or look-up tables
G01R 31/374 - Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] with means for correcting the measurement for temperature or ageing
G01R 31/392 - Determining battery ageing or deterioration, e.g. state of health
H01M 10/48 - Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
13.
METHOD TO OPERATE A VEHICLE, METHOD TO TEST AN AUTONOMOUS DRIVING SYSTEM, SYSTEM WITH A VEHICLE
A method of operating a vehicle includes: sensing the vehicle's surroundings and vehicle's operating parameters by sensors; supporting the vehicle's driving by a first autonomous driving control receiving the sensed surroundings and the sensed operating parameters and the first autonomous driving control generating vehicle driving commands for controlling the vehicle's driving; simulating the vehicle operation by a digital twin of the vehicle that includes a second autonomous driving control generating vehicle operation control commands for controlling the digital twin's driving; aligning the vehicle simulation with the vehicle's driving by feedback of the sensed vehicle's surroundings and the sensed vehicle's operating parameters; and evaluating a detachment criterium and changing the operating mode of the vehicle simulation from being aligned with the vehicle's driving to a detachment of the simulation allowing a deviation of the simulated values to at least one of the sensed vehicle's surroundings and/or sensed vehicle's operating parameters.
The invention relates to a Computer-implemented method for labelling of user action (UAC) data in a user environment (ENV), in particular wherein said user environment (ENV) is a computer (CMP) implemented user interactive (UIA) environment (ENV), characterized in comprising the steps of: a) providing a pre-trained user action (UAC) pattern recognition model (PRM), wherein the pattern recognition model (PRM) is designed in such a way that the pattern recognition model (PRM), from a part-sequence of user actions (UAC) including a user action (UAC) pattern (APT) known to the pattern recognition model (PRM), recognizes the user action (UAC) pattern (APT) known to the pat-tern recognition model (PRM), and outputs the user action (UAC) pattern (APT) or a label associated with the user action (UAC) pattern (APT), b) logging of user actions (UAC), c) analyzing the logged user actions (UAC) by said user action (UAC) pattern recognition model (PRM) for user action (UAC) patterns (APT) known to the pattern recognition model (PRM), d) generating of a user interaction (UIA) in case of not detecting a known user action (UAC) pattern (APT) in a sequence (SQC) of user actions (UAC) as the user interaction (UIA) requesting information about the past sequence (SQC) of user actions (UAC), e) labelling the past sequence (SQC) of user actions (UAC) using the information received from the information request, f) storing the labelled sequence (SQC) of user actions (UAC) in a user action (UAC) sequence (SQC) database (DBS), g) training the pattern recognition model (PRM) using the user action (UAC) sequence (SQC) and corresponding labels of the user action (UAC) sequence (SQC) database (DBS).
system (200) and method (100) for performing root-cause analysis of an anomalous behaviour in an asset are disclosed. The method comprises implementing, by a processor (204), a knowledge graph (600) comprising at least one of simulation data from a design phase of the asset and diagnosis data for past anomalous behaviour(s) of the asset, in form of verification requests. The method further comprises configuring, by the processor, an user-interface to receive an input indicative of symptoms related to the anomalous behaviour in the asset. The method further comprises generating, by the processor, a vectorized sub-graph based on the received input. The method further comprises searching, by the processor, the knowledge graph to identify one or more verification requests matching the generated vectorized sub-graph. The method further comprises providing, by the processor, an output comprising the identified one or more verification requests.
A computer-implemented method for the simulation of a process by co-simulation by coupling more than one simulation model processing a sub-system as a component of the simulation. The method includes communicating the co-simulation step size of enhanced simulation models from the co-simulation master to the respective enhanced simulation model via an Inter Process Communication interface via the enhanced simulation models' Functional Mock-up Units for model exchange, the co-simulation master controlling the co-simulation step size via the inter process communication interface addressing the Functional Mock-up Unit for model exchange using DoStep-semantic instructions, the Functional Mock-up Unit for model exchange triggering event handling calls of the enhanced simulation model by notifying events to the enhanced simulation model initiated by the DoStep-semantic instructions received from the Inter Process Communication interface such that the co-simulation master controls or synchronizes the enhanced simulation model executions by using model exchange events.
A system, device, and method for testing autonomous vehicles are disclosed. A device for testing a plurality of components of at least one autonomous vehicle includes a communication module including a set of interfaces communicatively couplable to the plurality of components of the at least one autonomous vehicle. The device also includes a processing unit communicatively coupled to the communication module and capable of mapping simulation instances to the set of interfaces of the communication module. The simulation instances include simulated sensor data and/or vehicle dynamics data reflecting behavior of the at least one autonomous vehicle.
G07C 5/08 - Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle, or waiting time
A method for modelling a thermal environment of an electronic device is provided. The method includes obtaining a volumetric mesh representation of a region of three-dimensional space including the electronic device and a surrounding medium. A computational model for modelling the thermal environment of the region of space is determined based on the mesh representation and a set of thermal parameters for the plurality of mesh cells, and the computational model is evaluated to determine the thermal environment in each mesh cell of the mesh representation. The computational model includes an embedding of a boundary condition independent reduced order model of at least one component of the electronic device into a model of the surrounding medium.
A system and method of predicting behavior of at least one electric machine is provided, wherein the method includes: generating a simulated-dataset including simulated design results, (e.g., individually), for electromagnetic properties, structural properties, and acoustic properties of the electric machine, wherein the simulated-dataset is generated by simulating at least one operating condition of the electric machine on parametric models generated from design parameters of the electric machine; training artificial neural network models using the design parameters and the simulated design results output from the parametric models in response to at least one operating condition of the electric machine; and predicting behavior of the electric machine by orchestrating execution of the artificial neural network models for custom design parameters.
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
G05B 13/04 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
20.
PREDICTING A MATERIAL PROPERTY, GENERATING A COMPONENT, COMPONENT, SYSTEM
A method for predicting a material property of a component made by additive manufacturing includes: defining an area of interest and generating a mesh in the area of interest; providing a temperature model during the additive manufacturing process; providing a process parameter set; calculating a thermal history in the area of interest based on the process parameter set using the temperature model; and determining a solidification gradient and a solidification front velocity in the area of interest from the thermal history. To obtain reasonable material predictions, the method may further include: reducing the data set of solidification gradients (SGR) and solidification front velocities; determining microstructure characteristics for the reduced data set by microstructural modelling; determining the material property for the reduced data set using a material property model; and interpolating of material property from the solidification gradient and solidification front velocity for the nodes within the area of interest.
The invention relates to an electrical constant current circuit (CCC) in particular for supplying electrical power to a sensor, the circuit (CCC) comprising - a power supply input terminal (INT), - a constant current output terminal (OUT), - a first transistor (TRF) - a shunt-type voltage reference (RVS), - wherein the base of the first transistor (TRF) being biased by the shunt-type voltage reference (SVR) in series with the base-emitter junction of the second transistor (TRS), - wherein the emitter of the first transistor (TRF) being connected to the power supply input terminal (INT) via a current set resistor (RST), - wherein the collector of the first transistor (TRF) being connected to said output terminal (OUT) through a Schottky diode (SKD). The improved temperature stability, initial accuracy, drop out voltage and power consumption the invention proposes: - that the circuit (CCC) comprises a second transistor (TRS) in the line between the base of the first transistor (TRF) and the shunt-type voltage reference (SVR), - wherein the second transistor's (TRS) base and collector are connected to the first transistor's (TRF) base.
G05F 3/18 - Regulating voltage or current wherein the variable is DC using uncontrolled devices with non-linear characteristics being semiconductor devices using Zener diodes
G05F 3/22 - Regulating voltage or current wherein the variable is DC using uncontrolled devices with non-linear characteristics being semiconductor devices using diode-transistor combinations wherein the transistors are of the bipolar type only
A method for generating a test coupon specification for predicting fatigue life of a component includes determining a load condition for the component, providing a component design, and performing a strength analysis of the component design under the load condition determining a critical area of the component and a stress-related parameter of the critical area. The method includes providing a material condition of the component at least for the critical area of the component. To assist an end-user in determining which are optimal tests to be performed in order to obtain most relevant data for fatigue prediction of a specific component, the method also includes providing a material model and providing, as an input to the material model, the stress-related parameter, and the material condition. The material model generates, as an output, a test coupon specification for being tested in a testing machine.
A system and a method for analyzing the motions of a mechanical structure. The System includes (a) accelerometers provided as standard accelerometers to measurement-points of the mechanical structure, (b) at least three accelerometers provided as reference accelerometers to measurement-points of the mechanical structure, (c) at least one shaker being attached to the mechanical structure for moving the structure periodically within a first frequency range, and at least one data processing system being configured to: (d) receiving measurements from the accelerometers at the measurement-points when periodically moving the structure within the first frequency range by the at least one shaker. To provide accurate and quick calibration the at least one data processing system is further configured to calibrate the accelerometers' positions and orientations by the following steps: (e) determining from the measurements of the at least three reference accelerometers rigid body motions, (f) determining positions and orientations of reference accelerometers from the rigid body motions, and (g) determining positions and orientations of standard accelerometers from the rigid body motions.
A computer implemented method of determining a transfer function (TRF) of a module (MDL). To improve an accuracy, the method includes measuring a first set-of-sensors-output (SO1) applied to the module (MDL) and measuring a second set-of-sensors-output (SO2), deducing a transfer function (TRF) of the module (MDL), wherein a transfer-function matrix (MTM) is a quadratic n-dimensional matrix for the n degrees of freedom (DOF), selecting a submatrix (SBM), determining for the selected submatrix (SBM) a corresponding rotational matrix (RTM) which improves the symmetry of the submatrix (SBM), generating a main rotational matrix (MRM) to transform the main transfer-function matrix (MTM), and providing the transfer function (TRF) with the transformed transfer-function matrix (TTM).
The invention relates to a computer-implemented method for training a predefined system model (MDL) of a parametrized system (SYS), wherein scenarios (SCN) are a parameter set defining a system (SYS) state and/or system (SYS) operation, the method comprising: (a) providing said system model (MDL), (b) providing a first set (IST) of scenarios (SCN), (c) selecting a sub-set (SST) of scenarios (SCN), (d) acquiring system (SYS) test data (TDT) for the subset (SST) of scenarios (SCN), (e) generating system model (MDL) data for the subset (SST) of scenarios (SCN), (f) determining a modeling error (MER) of the system model (MDL) by comparing the test data (TDT) with the system model (MDL) data. To reduce the model training complexity the method according to the invention proposes the additional steps: (g) generating and/or training an error prediction model (EPM) on basis of the modeling errors (MER) determined, (h) determining an error prediction (ERP) by the error prediction model (EPM) for the first set (IST) of scenarios (SCN), (i) selecting a certain portion of the first set (IST) of scenarios (SCN) with the highest error prediction (ERP) determined by the error prediction model (EPM) as top error scenarios (TES), (j) acquiring system (SYS) test data (TDT) for the selected top error scenarios (TES), (k) training said system model (MDL) with the acquired system (SYS) test data (TDT) for the selected top error scenarios (TES).
G06F 11/36 - Prevention of errors by analysis, debugging or testing of software
G06F 30/20 - Design optimisation, verification or simulation
G05B 13/04 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
26.
COMPUTER IMPLEMENTED METHOD OF DETERMINING A TRANSFER FUNCTION OF A MODULE OR A COMPONENT AND GENERATING SUCH COMPONENT
A transfer function (TRF) of a module (MDL) is determined. To improve accuracy of such methods, the following acts are used: a. measuring a first set-of-sensors-output (SO1) and a second set-of-sensors-output (SO2) respectively using sensors (SS1, SS2) applied to said module (MDL), b. identifying parameters (ICH) relating to mass and/or inertia and/or damping and/or stiffness of said module (MDL) by rigid body estimation (RBE) from said measurements, c. fitting a first model (RB1) to identified inertia characteristics/parameters (ICH), d. generating a synthetic second set-of-sensors-output (ST2) of said second set-of-sensors (SS2) by said first model (RB1), e. comparing said synthetic second set-of-sensors-output (SO2) with said measurements, and f. estimating a Euler-angle correction (EAC) for said second set-of-sensors (SS2).
The invention relates to a computer-implemented method for generating and training a system model (MDL) of a parametrized system (SYS), wherein scenarios (SCN) are a parameter set characterizing a system (SYS) state and/or system (SYS) operation, the method comprising: (a) providing a first set (IST) of scenarios (SCN) of said system (SYS), (b) reducing the number of scenarios (SCN) of the first set (IST) by selecting a core-set (SST) of scenarios (SCN) for system model (MDL) generation from the first set (IST). To reduce the model generation and training complexity the method according to the invention step (b) is performed by choosing scenarios (SCN) which are representative for the first set (IST) of scenarios (SCN) and further comprising the step (c) generating and training a system model (MDL) based on the core-set (SST) of scenarios (SCN). The invention further deals with selecting a controller, a system and a computer-system.
A computer-implemented method for resolving closed loops in automatic fault tree analysis of a multi-component system includes: a. modeling the multi-component system using a fault tree; b. back-tracing failure propagation paths from an output element of the fault tree; c. checking if the respective failure propagation path contains a closed loop by identifying a downstream element of the respective failure propagation path having a dependency of its output value on an output value of an upstream element; d. setting the input value corresponding to a loop interconnection of each such downstream element to Boolean TRUE; e. identifying any Boolean AND-gate having no Boolean TRUE as output value; cutting off any Boolean TRUE input to any identified Boolean AND-gate between the respective downstream element and the respective upstream element; and f. setting the input value of each respective downstream element corresponding to the loop interconnection to Boolean FALSE.
The invention relates to a method for generating a model of a system (TFC), with the steps: (a) providing an engineering system (EGT) with library elements (LET), where the library elements (LET) are defined by interaction (IAC) and a function model (FCM), wherein said interaction (IAC) is defined by ports (PRT), incoming port entity (PET) types, outgoing port entity (PET) types, wherein said function model (FCM) generates outgoing port entities (PET) from incoming port entities (PET), (b) providing a design (DSG) of the system (TFC) comprising defined system components (DSC) of a specified plant area (SPA); (c) selecting library elements (LET) for the defined system components (DSC); (d) linking interactions (IAC) of different selected library elements (LET) according to the design (DSG). To better enable undetailed drafting and explorative working the invention proposes that the system (TFC) comprises at least one undefined plant area (UDA) whose interaction (IAC) with the specified plant area (SPA) is specified, the method further comprising: (e) linking the interaction (IAC) of the selected library elements (LET) to the interaction (IAC) of the undefined plant area (UDA) by providing a non-specific library element (ULE), (f) generating a function model (FCM) for the non-specific library element (ULE) for determining outgoing port entities (PET) from incoming port entities (PET) using the Buckingham Pi theorem.
G05B 17/02 - Systems involving the use of models or simulators of said systems electric
G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
30.
Generating unknown-unsafe scenarios, improving automated vehicles, and computer system
A computer-implemented method for generating unknown-unsafe scenarios for assessing and improving the safety of automated vehicles includes a first process of providing a plurality of different scenarios. To improve the safety of automated vehicles and the efficiency of designing these, a second process of reducing the plurality of different scenarios to scenarios that are unknown-unsafe scenarios is provided.
A method of determining operational performance parameters of a device (e.g., of a vehicle) with device mounted sensors and computer-implemented models. Further, a system, such as a virtual sensor applied to a device, such as a vehicle, for determining operational performance parameters of the device is provided. The system includes device mounted sensors and at least one processing unit configured to execute the computer-implemented method to generate an output parameter set. Measured data may be combined, and calculated parameters may be provided to a Kalman-filter to enable virtual sensing of unobservable parameters.
G07C 5/08 - Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle, or waiting time
A computer-implemented method of engineering design includes performing a simulation for a design under test of the design interacting in a real-world environment, in a computer processor, generating simulation data from performance of the simulation, storing the generated simulation data in a computer memory, extracting the generated simulation data to train a first inverse model neural network, and generating a plurality of design parameters from the inverse model neural network. A visualization representative of the generated plurality of design parameters for display to a user allows an expert user to evaluate the suggested design parameters and select some or all of the suggested design parameters. For existing designs more data is available for the simulation than for a new design. The inverse model for a new design may be augmented by transferring stored knowledge in a pre-existing inverse model to the model for the new design.
Numerical modular simulation of a system includes: (a) disaggregating said system into at least two subunit simulation subsystems, and (b) simulating the respective subunits stepwise repeatedly generating subsystem-step-output from subsystem-step-input during a respective subsystem-time-step (SMP). To improve accuracy and performance, said method includes the additional steps: (c) transmitting subsystem-step-inputs to a receiving subsystem and simulating this subsystem over a delay-time before its subsystem-step-outputs are generated, (d) receiving connection interface variables from a sending subsystem including at least one of: numerical data, at least parameters of a data-prediction-model of said numerical data, or a data-prediction-model assigned to said numerical data, (e) predicting said numerical data by a data-prediction-model over said delay-time to obtain predicted numerical data of said interface variables provided by said sending subsystem, and (f) starting the next simulation step of said receiving subsystem generating the next subsystem-step-output from subsystem-step-input, wherein said subsystem-step-input includes said predicted numerical data.
A scenario identification system and a computer implemented method for identifying one or more critical scenarios from vehicle data associated with one or more vehicles are provided. The scenario identification system obtains at least the inertial measurement unit (IMU) data from the vehicle data, derives one or more IMU-based driving parameters from the IMU data, and analyzes the IMU-based driving parameters based on one or more predefined thresholds for identifying the critical scenario(s).
G07C 5/08 - Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle, or waiting time
G07C 5/00 - Registering or indicating the working of vehicles
G08G 1/01 - Detecting movement of traffic to be counted or controlled
35.
Method and Apparatus for Obtaining a Composite Laminate
A method and apparatus for obtaining a composite laminate that has plies each composed of a matrix and a filler includes receiving a model and load conditions of a mechanical part to be produced from the composite laminate, predicting properties of a candidate laminate based on features thereof by machine learning, evaluating a performance of the mechanical part produced in accordance with the model from the candidate laminate when subject to the load conditions, based on the predicted properties, optimizing the performance of the mechanical part by varying the features of the candidate laminate and repeating the predicting and evaluating steps until a desired performance is achieved; and determining the candidate laminate thus optimized as the composite laminate for manufacturing the mechanical part, where the method and apparatus can automatically obtain an optimum composite material for a given design task.
G06F 30/17 - Mechanical parametric or variational design
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
A system (100) and method for enabling transfer learning-based optimization is disclosed. The method comprises receiving from a client device (110), by a processing unit, an input indicative of a target optimization task, wherein the target optimization task is associated with an unsolved optimization problem. Further, similarity between the target optimization task and at least one source optimization task is determined by applying a predefined similarity checking logic. The source optimization task is associated with a solved optimization problem and a complete optimization history thereof, Furthermore, complexity scores are computed for the source optimization task and the target optimization task, subject the outcome of the application of the similarity checking logic, to determine whether the source optimization task is more complex than the target optimization task. If yes, transfer learning is initiated by adapting a target optimizer, for solving the unsolved optimization problem, based on an initial population and one or more model parameters associated with a source optimizer employed in the source optimization task.
A computer-implemented method of generating a digital twin. To improve the efficiency of handling a digital twin the method includes the steps of: providing a digital twin modular system, the digital twin modular system being characterized by digital twin modules being adapted or being adaptable to digital twin features, the digital twin features relating to at least one of calculation properties, scope of simulation, model architecture, communication safety, accessibility, data storage, encryption functions, resource allocation, hardware requirements, providing a tuning module, wherein the tuning module includes a tuning module parameter set, wherein the tuning module parameter-set includes tuning module parameters respectively corresponding to at least one digital twin feature generating a digital twin by using the tuning module performing the steps of selecting, configuring, and combining digital twin modules of the digital twin modular system according to the tuning module parameters.
A computer-implemented method for modelling an object subjected to boundary conditions from an object model that defines a component by a three-dimensional boundary representing format is provided. The method includes providing boundary conditions including loads and/or constraints to the object, and providing the object model. The boundary representation of the object model is tessellated, obtaining an object tessellation. An approximate convex decomposition is applied to the object tessellation, obtaining three-dimensional cells respectively defined from each other by splitting planes. A numerical model is generated by applying a discontinuous Galerkin method to the three-dimensional cells. Determination of a load capacity, an improvement of the design, or the generation, in each case, of the component, are provided.
A method and a device for configuring a controller and to a method and a controller for controlling a technical system by means of a data-based control model is provided, in particular a model based on reinforcement learning. This data-based control model is configured using a model-predictive control model. Configuration parameters of the data-based control model are set by mapping the model-predictive control model onto the data-based control model in such a way that the data-based control model reproduces the output data of the model predictive control model depending on state data of the technical system read in, and determines optimized control parameters configured in this way. A computationally intensive training procedure for configuring the data-based control model can thus be avoided.
G05B 13/04 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
40.
MACHINE LEARNING-BASED SYSTEM ARCHITECTURE DETERMINATION
Examples of techniques for machine learning-based system architecture determination are described herein. An aspect includes receiving a system architecture specification corresponding to a system design, and a plurality of topological variants of the system architecture specification. Another aspect includes determining a system architecture graph based on the system architecture specification. Another aspect includes classifying, by a neural network-based classifier, each of the topological variants as a feasible architecture or an infeasible architecture based on the system architecture graph. Another aspect includes identifying a subset of the feasible architectures as system design candidates based on performance predictions.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
41.
COMPUTING PLATFORM FOR SIMULATING AN INDUSTRIAL SYSTEM AND METHOD OF MANAGING THE SIMULATION
A computing platform for simulating an industrial system and a method of managing the simulation are disclosed. The method relates to generating at least one instance of a simulation model of the industrial system. The method includes: generating the instance using a contiguous memory allocator for a dynamic memory region associated with a first processor of the heterogenous processors; enabling a second processor to use the instance in the dynamic memory region based on a memory pointer associated with the address of a copy of the instance; and simulating the industrial system by the second processor by accessing the instance-copy.
A method and system for performing seamless analysis of geometric components in multi-domain collaborative simulation environments. A method includes generating a simulation interface object corresponding to a geometric component in a first simulation environment. The simulation interface object includes load and boundary conditions associated with the geometric component. The method includes dynamically accessing the load and boundary conditions associated with the geometric component in a second simulation environment via the simulation interface object. The first simulation environment and the second simulation environment correspond to different domains. The method includes performing analysis of the geometric component in the second simulation environment based on the load and boundary conditions. Moreover, the method includes generating results of the analysis of the geometric component on a graphical user interface associated with the second simulation environment.
G06F 30/12 - Geometric CAD characterised by design entry means specially adapted for CAD, e.g. graphical user interfaces [GUI] specially adapted for CAD
G06F 30/20 - Design optimisation, verification or simulation
43.
METHOD TO OPERATE A VEHICLE, METHOD TO TEST AN AUTONOMOUS DRIVING SYSTEM, SYSTEM WITH A VEHICLE
The invention relates to a method of operating a vehicle, comprising: (a) sensing the vehicle's surroundings (VSR) and vehicle's operating parameters (VOP) by sensors (SNR), (b) supporting said vehicle's driving by a first autonomous driving control (ADF 1.0) receiving said sensed vehicle's surroundings (VSR) and sensed vehicle's operating parameters (VOP) and said first autonomous driving control (ADF 1.0) generating vehicle driving commands (VOC) for at least partly controlling the vehicle's driving. To overcome the deficiencies of conventional methods of testing autonomous driving systems the invention proposes the additional steps: (c) simulating the vehicle operation by a digital twin (DTM) of said vehicle, said digital twin (DTM) comprising a second autonomous driving control (ADF X.Y) generating vehicle operation control commands (VOC) for at least partly controlling the digital twin's (DTM) driving, (d) aligning the vehicle simulation with the vehicle's driving by feedback of said sensed vehicle's surroundings (VSR) and said sensed vehicle's operating parameters (VOP), (e) evaluating a detachment criterium (DOR) and in case said criterium (DOR) is met changing the operating mode of said vehicle simulation or of at least a copy of said vehicle simulation from being aligned with the vehicle's driving to a detachment of the simulation allowing a deviation of the simulated values to at least one of said sensed vehicle's surroundings (VSR) and/or sensed vehicle's operating parameters (VOP). The invention further relates to a system comprising a vehicle (VHC), the system being prepared to perform said method.
Method of determining acoustic parameters of an object's (OBJ) emission and/or scattering, in particular for improving acoustic properties of said object (OBJ), comprising : (a) defining a model (MDL) including said object (OBJ), a sound source (SCR), and a surrounding area, (b) processing said model (MDL) obtaining a result (RST), (c) post-processing the result (RST) by assigning to said field points (PTS) at least one parameter (PRM) determined from calculating the Helmholtz-Kirchhoff integral from said result (RST). To improve the accuracy and efficiency the post-processing comprises the additional steps: (d) identifying field points (PTS) as near field singularity field points (NEP) of potential lower result (RST) accuracy (ACR), (e) determining for said near field singularity field points (NEP) respectively an associated model mesh element (AME), by determining a local projection from said near field singularity field point (NEP) to the object's (OBJ) surface by calculating a minimum normal distance (MND) to the object ' s (OBJ) surface, wherein the associated model mesh element (AME) being the touchdown point of the local projection, (f) determining for said near field singularity field points (NEP) respectively a ratio (RTO) of the minimum normal distance (MND) to said element size (ESZ) of the associated model mesh element (AME), (g) calculating the Helmholtz-Kirchhoff integral by: (g1l) providing a relation (PCR) of quadrature order (QOD) and said ratio (RTO), (g2) determine the respective quadrature order (QOD) by applying said relation (PCR), (g3) calculating the Helmholtz-Kirchhoff integral from said result (RST).
G06F 30/15 - Vehicle, aircraft or watercraft design
G06F 30/23 - Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
G06F 30/28 - Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
45.
METHOD OF DETERMINING THE STATIC STIFFNESS OF A BODY STRUCTURE, SYSTEM
The invention relates to a computer-implemented method computer product, computer-readable medium, and system for determining acoustic parameters of an object's (OBJ) emission and/or scattering within a predetermined frequency range (FRG), by applying Boundary Element Method (BEM) to the object, comprising splitting said object's (OBJ) surface into surface elements (ESF) and assigning boundary conditions (BCD) to said surface elements (ESF), further comprising • Providing polynomial shape functions (SFC) over each of said elements (ESF) for mapping geometry and acoustic parameters to said elements (ESF), wherein for each surface element (ESF) the order (SFO) of said shape functions (SFC) is determined by an adaptivity module (ADM), • Assembling the elements (ESF) of said surface by recombining the shape functions (SFC) obtaining a system matrix (SMX), • Solving said system matrix (SMX), • Determining said acoustic parameters (PRT) from said shape functions (SFC).
A method for improving the topology of a component (CPT), comprising: (a) providing a component (CPT) load case (LDC) including boundary conditions (BCD) for said component (CPT), (b) providing a starting component design (CDG), (c) segmenting said component design (CDG) into unit cells (VXL), (d) generating a surrogate model (SGM) that relates these quantities to each other: possible unit cell stiffness tensors (VST), a unit cell average density (VAD), wherein for a given unit cell average density (VAD) variations of said unit cell stiffness tensor (VST) are parameterized by said surrogate model (SGM), (e) using said surrogate model (SGM) for improving or optimizing at least one specific unit cell parameter (VXP) for each unit cell (VXL) towards an optimization target (OTG), and (f) changing said component design (CDG) by amending a material mass distribution (MMD) according to optimizing results of step (e).
A computer-implemented method for modelling variations of repeating parts of a component is disclosed herein. The method includes providing parameter sets for part configurations of a plurality of different of parts, wherein the parameters of each parameter set respectively define the part configuration of a part; selecting a selection of the part configurations; providing a part model for each part configuration of the selection, wherein the part model relates forces and displacements to locations of the respective part; and building an approximator, wherein the approximator is provided for interpolating the part models to approximate a part model of a part configuration that does not belong to the selection of the part configurations.
42 - Scientific, technological and industrial services, research and design
Goods & Services
Software as a service featuring software for computer aided
engineering in the field of engineering analysis and
testing; platform as a service featuring computer software
platforms for computer aided engineering in the field of
engineering analysis and testing.
A computer-implemented method is provided for predicting a fatigue response of a material. The method includes receiving a user input specifying one or more surface roughness parameters that characterize a surface of a material for which fatigue life is to be predicted. The method further includes generating at least one realistic virtual surface profile from the specified one or more surface roughness parameters. The method further includes predicting fatigue life of the material in dependence of a stress field applied to the generated virtual surface profile. In accordance with specific embodiments, the prediction of the fatigue life may be carried out using finite element analysis based simulations, machine learning methods, or combinations thereof.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
G06F 30/23 - Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
51.
METHOD AND SYSTEM FOR AUTOMATED SUPPORT OF A DESIGN OF A TECHNICAL SYSTEM
A machine learning model processes a current partial design of a technical system and a candidate component for a next design step of designing the technical system. The model computes a probability distribution, which is a probability distribution over changes of a design KPI if the candidate component is added to the current partial design, with the design KPI describing a property of the technical system, and a predicted impact value predicting an absolute value of the design KPI or a change of the design KPI if the candidate component is added to the current partial design. These predictions (for partial designs that cannot be processed by a simulation environment due to their incompleteness) can drastically shorten the feedback loop between engineers in charge of designing a new technical system/product and a simulation environment used for estimating the performance characteristics of the product.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
G06F 30/12 - Geometric CAD characterised by design entry means specially adapted for CAD, e.g. graphical user interfaces [GUI] specially adapted for CAD
42 - Scientific, technological and industrial services, research and design
Goods & Services
(1) Software as a service featuring software for computer aided engineering in the field of engineering analysis and testing; platform as a service featuring computer software platforms for computer aided engineering in the field of engineering analysis and testing.
53.
METHOD AND SYSTEM FOR GENERATING A TEST COUPON SPECIFICATION FOR PREDICTING FATIGUE LIFE OF A COMPONENT
The invention relates to a method and a system for carrying out the method for generating a test coupon (COP) specification (TCS) for predicting fatigue life of a component (CMP), comprising: (a) determining a load condition (LDC) for said component (CMP), (b) providing a component (CMP) design (CDS), (c) performing a strength analysis of the component (CMP) design under said load condition (LDC) determining: (i) a critical area (CRA) of the component (CMP), (ii) at least one stress-related parameter (SRP) of said critical area (CRA), (d) providing at least one material condition (MCD) of said component (CMP) at least for said critical area of the component (CMP). To assist an end-user in determining which are the optimal tests to be performed in order to obtain the most relevant data for fatigue prediction of a specific component the method is characterized by the additional steps: (e) providing a material model (MTM) (f) providing as an input to said material model (MTM): (i) said at least one stress-related parameter (SRP) and (ii) said at least one material condition (MCD) (g) said material model (MTM) generating as an output: (i) a test coupon specification (TCS) for being tested in a testing machine.
G01N 3/02 - Investigating strength properties of solid materials by application of mechanical stress Details
G06F 30/17 - Mechanical parametric or variational design
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
54.
METHOD FOR GENERATING A STRUCTURE MESH, USE OF A STRUCTURE MESH, COMPUTER PROGRAM, AND COMPUTER-READABLE MEDIUM
A method for generating a structure mesh of a structure that is to be built-up in a three-dimensional build-up volume in an additive manufacturing build-up process. The structure includes at least one specimen and at least one support for supporting the at least one specimen on a boundary of the build-up volume. The structure mesh may be used in simulating the additive manufacturing build-up process of the structure 2. A use of a structure mesh 9, a computer program, and a computer-readable medium are also provided.
The invention relates to a system (SYS) and a method for analyzing the motions of a mechanical structure (STR), comprising: (a) accelerometers (ACC) provided as standard accelerometers (SAC) to measurement-points (MPI) of said mechanical structure (STR), (b) at least three accelerometers (ACC) provided as reference accelerometers (RAC) to measurement-points (MPI) of said mechanical structure (STR), (c) at least one shaker (SHK) being attached to said mechanical structure (STR) for moving the structure (STR) periodically within a first frequency range (FR1), further comprising at least one data processing system (DPS) being prepared to: (d) receiving measurements from said accelerometers (ACC) at the measurement-points when periodically moving the structure (STR) within said first frequency range (FR1) by said at least one shaker (SHK). To enable accurate and quick calibration the invention proposes that said at least one data processing system (DPS) is further prepared to calibrate the accelerometers' (ACC) positions and orientations by the following steps: (e) determining from said measurements of said at least three reference accelerometers (RAC) rigid body motions (RBM), (f) determining positions and orientations of reference accelerometers (ACC) from said rigid body motions (RBM), (g) determining positions and orientations of standard accelerometers (SAC) from said rigid body motions (RBM).
G01C 21/12 - NavigationNavigational instruments not provided for in groups by using measurement of speed or acceleration executed aboard the object being navigatedDead reckoning
One or more ring closures of a fault tree are provided. For each one of the one or more ring closures: at least one respective edge the respective ring closure is replaced in the fault tree by a respective variable to obtain a placeholder fault tree and a normalized representation of the placeholder fault tree is determined.
A method is disclosed for generating a component mesh of a component that may be built-up layer by layer in an additive manufacturing build-up process. The method includes providing a three-dimensional initial component mesh composed of initial mesh elements of uniform shape which include initial mesh nodes and initial mesh edges extending between the initial mesh nodes; slicing the initial component mesh by at least one cutting plane such that initial mesh elements are divided into at least two resulting mesh elements, wherein at the intersection points of the at least one cutting plane with edges of initial mesh elements resulting mesh nodes are defined; determining the position of each initial mesh element with respect to each cutting plane and thus which initial mesh element is divided into resulting mesh elements and which is not; and determining the shape of each resulting mesh element.
The invention relates to a method of determining a transfer function (TRF) of a module (MDL). To improve accuracy of such methods the invention proposes the steps: a. measuring a first set-of-sensors-output (SOI) applied to said module (MDL) and measuring a second set-of-sensors-output (SO2); b. deducing a transfer function (TRF) of said module (MDL), wherein a transfer-function matrix (MTM) is a quadratic n-dimensional matrix for said n degrees of freedom (DOF); c. selecting a submatrix (SBM); d. determining for said selected submatrix (SBM) a corresponding rotational matrix (RTM) which improves the symmetry of the submatrix (SBM); e. generating a main rotational matrix (MRM) to transform said main transfer-function matrix (MTM); f. providing the transfer function (TRF) with said transformed transfer-function matrix (TTM).
Computer implemented method of determining a transfer function of a module or a component and generating such component The invention relates to a method of determining a transfer function (TRF) of a module (MDL). To improve accuracy of such methods the invention proposes the steps: a. measuring a first set-of-sensors-output (SO1) and a second set-of-sensors-output (SO2) respectively using sensors (SS1, SS2) applied to said module (MDL), b. identifying parameters (ICH) relating to mass and/or inertia and/or damping and/or stiffness of said module (MDL) by rigid body estimation (RBE) from said measurements, c. fitting a first model (RB1) to identified inertia characteristics/parameters (ICH), d. generating a synthetic second set-of-sensors-output (ST2) of said second set-of-sensors (SS2) by said first model (RB1), e. comparing said synthetic second set-of-sensors-output (SO2) with said measurements, f. estimating a Euler-angle correction (EAC) for said second set-of-sensors (SS2).
The invention relates to a method of determining operational performance parameters of a device, in particular of a vehicle (VCL), with device mounted sensors (SNS) and computer-implemented models (MDS MD2). Further, the invention relates to a system (SYS), in particular to a virtual sensor (VRS) applied to a device, in particular to a vehicle (VCL), for determining operational performance parameters of said device, said system comprising device mounted sensors (SNS) at least one processing unit (CPU) adapted to execute the above mentioned computer-implemented method to generate an output parameter set (PSO). The invention proposes to combine measured data and with calculated parameters to be provided to a Kalman-filter (EKF) to enable virtual sensing of unobservable parameters.
B60W 40/12 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to parameters of the vehicle itself
B60W 40/10 - Estimation or calculation of driving parameters for road vehicle drive control systems not related to the control of a particular sub-unit related to vehicle motion
B60W 50/00 - Details of control systems for road vehicle drive control not related to the control of a particular sub-unit
61.
DRIVING ASSISTANCE SYSTEM AND METHOD OF CONTROLLING AUTONOMOUS VEHICLES
Driving assistance systema and method of controlling at least one autonomous vehicle (112, 350) are disclosed. The method comprising determining one or more driving trajectories for at least one vehicle (370) in a region of interest (360) based on time-shifted step functions generated from a driving state of the at least one vehicle (370); selecting at least one driving trajectory from the driving trajectories based on a falsification optimization of the driving trajectories; and controlling the autonomous vehicle (112, 350) based on the at least one driving trajectory.
A method is provided for storing data to and retrieving data from at least one data storage. The method includes receiving data to be stored, selecting only part of the received data to obtain reduced data, storing the reduced data on the at least one data storage, receiving a request for retrieval of the data, using at least one compressive sensing reconstruction algorithm to generate reconstructed data from the reduced data, and providing the reconstructed data as the requested data. The disclosure furthermore relates to a system for storing and retrieving data, the use of the compressive sensing technique, a computer program, and a computer readable medium.
A machine learning module is provided which is trained to generate from a design data record specifying a design variant of a product, a first performance signal quantifying a predictive performance of the design variant and a predictive uncertainty of the predictive performance. A variety of design data records each specifying a design variant of the product is generated. For a respective design data record, the following steps are performed: a first performance signal and a corresponding predictive uncertainty are generated, depending on the predictive uncertainty, a simulation yielding a second performance signal quantifying a simulated performance of the corresponding design variant is either run or skipped, and a performance value is derived from the second performance signal if the simulation is run or, otherwise, from the first performance signal. Depending on the derived performance values, a performance-optimizing design data record is determined and output to control the production plant.
G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
42 - Scientific, technological and industrial services, research and design
Goods & Services
Software as a Service featuring software for computer aided engineering in the field of engineering analysis and testing; Platform as a Service featuring computer software platforms for computer aided engineering in the field of engineering analysis and testing.
65.
SYSTEM AND METHOD OF PREDICTING BEHAVIOR OF ELECTRIC MACHINES
The present invention relates to system and method of predicting behavior of at least one electric machine, the method comprising: generating a simulated-dataset comprising simulated design results (132, 134, 136 and 138), preferably individually, for electromagnetic properties, structural properties and acoustic properties of the electric machine, wherein the simulated-dataset is generated by simulating at least one operating condition (130) of the electric machine on parametric models (122, 124, 126) generated from design parameters of the electric machine; training artificial neural network models (ANNs) (142, 144, 146) using the design parameters (120) and the simulated design results (132, 134, 136 and 138) output from the parametric models (122, 124, 126) in response to at least one operating condition of the electric machine; and predicting behavior of the electric machine by orchestrating execution of the artificial neural network models for custom design parameters (180).
A method for retrieval of multi spectral bidirectional reflectance distribution function (BRDF) parameters by using red-green-blue-depth (RGB-D) data includes capturing, by an RGB-D camera, at least one image of one or more objects in a scene. The captured at least one image of the one or more objects includes RGB-D data including color and geometry information of the objects. A processing unit reconstructs the captured at least one image of the one or more objects to one or more 3D reconstructions by using the RGB-D data. A deep neural network classifies the BRDF of a surface of the one or more objects based on the 3D reconstructions. The deep neural network includes an input layer, an output layer, and at least one hidden layer between the input layer and the output layer. The multi spectral BRDF parameters are retrieved by approximating the classified BRDF by using an iterative optimization method.
H04N 9/77 - Circuits for processing the brightness signal and the chrominance signal relative to each other, e.g. adjusting the phase of the brightness signal relative to the colour signal, correcting differential gain or differential phase
H04N 23/12 - Cameras or camera modules comprising electronic image sensorsControl thereof for generating image signals from different wavelengths with one sensor only
67.
Method and apparatus for estimating electromagnetic forces active in an electric machine
A method and apparatus for estimating electromagnetic forces active in an electric machine. The method includes the steps of: measuring at least one first operation parameter of the electric machine while the electric machine is operated under at least one operational condition, and estimating electromagnetic forces active in an electric machine during operation of the electric machine by multiplying the measured at least one first operation parameter and a respective second operation parameter provided by a stored structural/vibro-acoustic model.
G01H 1/00 - Measuring vibrations in solids by using direct conduction to the detector
H02K 11/20 - Structural association of dynamo-electric machines with electric components or with devices for shielding, monitoring or protection for measuring, monitoring, testing, protecting or switching
68.
COMPUTER-IMPLEMENTED METHOD AND DEVICE FOR RESOLVING CLOSED LOOPS IN AUTOMATIC FAULT TREE ANALYSIS OF A MULTI-COMPONENT SYSTEM
A computer-system (CPS) and a computer-implemented method for numerical modular simulation of a system (SYS), comprising: (a) disaggregating said system (SYS) into at least two subunit (SSY) simulation subsystems (SMN), (b) simulating the respective subunits (SSY) stepwise repeatedly generating subsystem-step-output (MSO) from subsystem-step-input (MSI) during a respective subsystem-time-step (SMP). To improve accuracy and performance said method comprises the additional steps: (c) transmitting subsystem-step-inputs (MSI) to a receiving subsystem (SMR) and simulating this subsystem (SMN) over a delay-time (DLT) before its subsystem-step-outputs (MSO) are generated, (d) receiving connection interface variables (TRD) from a sending subsystem (SMS) comprising at least one of: - numerical data (DTA), - at least parameters of a data-prediction-model (DEM) of said numerical data (DTA), - a data-prediction-model (DEM) assigned to said numerical data (DTA), (e) predicting said numerical data (DTA) by a data-prediction-model (DEM) over said delay-time (DLT) to obtain predicted numerical data (EDT) of said interface variables (TRD) provided by said sending subsystem (SMS), (f) starting the next simulation step of said receiving subsystem (SMR) generating the next subsystem-step-output (MSO) from subsystem-step-input (MSI), wherein said subsystem-step-input (MSI) comprises said predicted numerical data (EDT).
G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
G06F 9/455 - EmulationInterpretationSoftware simulation, e.g. virtualisation or emulation of application or operating system execution engines
G06F 30/20 - Design optimisation, verification or simulation
G06F 30/23 - Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
G06F 30/33 - Design verification, e.g. functional simulation or model checking
G06F 30/367 - Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
G16H 50/50 - ICT specially adapted for medical diagnosis, medical simulation or medical data miningICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
G05B 19/18 - Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
70.
GENERATING A DIGITAL TWIN, METHOD, SYSTEM, COMPUTER PROGRAM PRODUCT
The invention relates to a computer-implemented method of generating a digital twin (DTW). To improve the efficiency of handling a digital twin (DTW) said method comprises the steps of: a.) providing a digital twin modular system (DTS), said digital-twin modular system (DTS) being characterized by digital-twin-modules (DTM) being adapted or being adaptable to digital-twin-features (DTE), said digital-twin-features (DTE) relating to at least one of calculation properties (CPR), scope of simulation (SCS), model architecture (MAT), communication safety (CMS), accessibility (ACB), data storage (DST), encryption functions (ECF), resource allocation (RAL), hardware requirements (HRQ), b.) providing a tuning module (TMD), wherein said tuning module (TMD) comprises a tuning module parameter-set (TMS), wherein said tuning module parameter-set (TMS) comprises tuning module parameters (TMP) respectively corresponding to at least one digital twin feature (DTF), c.) generating a digital twin (DTW) by using said tuning module (TMD) performing the steps of selecting, configuring, and combining digital-twin-modules (DTM) of said digital twin modular system (DTS) according to said tuning module parameters (TMP). Furthermore, a system, a computer program product respectively a computer-readable medium applying the computer-implemented method is provided.
G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
A method and system for computer-implemented simulation of radar raw data, where the radar raw data are generated for a synthetic MIMO radar system including a transmitter array of several transmitters for transmitting radar signals and a receiver array of several receivers for receiving radar echoes of the radar signals. In this method, ray tracing of a radar signal sent from a preset transmitting position within the transmitter array and received at a preset receiving position within the receiver array is performed based on a 3D model of a virtual area adjacent to the MIMO radar system, where the ray tracing determines propagations of a plurality of rays within the radar signal from the preset transmitting position to the preset receiving position. The propagation of each ray is dependent on a first angle and a second angle describing the direction of a respective ray at the preset transmitting position. By using first-order derivatives with respect to the first angle and the second angle, propagations of a plurality of modified rays originating from a respective transmitter and received at a respective receiver are determined based on a linear approximation. The modified rays are processed in order to determine the radar raw data.
A method and a system for fatigue life prediction of additive manufactured components accounting for localized material properties. The method and the system is employed for prediction of fatigue life properties of an additive manufactured element, with a data collection step in which several data points for maximum stress vs. cycles to failure for different given processing steps of the element are collected, with a training step in which a Machine Learning system is trained with the collected data, and with an evaluation step in which the trained Machine Learning system is confronted with actual processing steps and used to predict the fatigue life properties of the element.
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
B33Y 50/00 - Data acquisition or data processing for additive manufacturing
The disclosure relates to a method for simulating sensor data of a continuous wave (CW) Light Detection and Ranging (lidar) sensor. The method includes generating a ray set comprising at least one ray, based on a CW signal, where each ray in the ray set has an emission starting time and an emission duration. The method further includes propagating, for each ray in the ray set, the ray through a simulated scene including at least one object; computing, for each ray in the ray set, a signal contribution of the propagated ray at a detection location in the simulated scene; generating an output signal, based on mixing the CW signal with the computed signal contributions of the rays in the ray set; and at least one of storing and outputting the output signal.
42 - Scientific, technological and industrial services, research and design
Goods & Services
Software as a Service featuring software for computer aided engineering in the field of engineering analysis and testing; Platform as a Service featuring computer software platforms for computer aided engineering in the field of engineering analysis and testing
A computer-implemented method of modifying a finite element mesh. The method includes providing an original-input-orphan-mesh, selecting and extracting at least a part of the original-input-orphan-mesh as an orphan-element-patch-object, generating faces on the orphan-element-patch-object as a faces-on-mesh-object geometry, generating a new mesh patch element based on the faces-on-mesh-object-geometry and at least one changed meshing-parameter. The changed meshing-parameter is assigned to generate a new mesh patch element that is different to the corresponding original-input-orphan-mesh. The method further includes generating an amended orphan mesh by replacing the orphan-element-patch-object of the original-input-orphan-mesh by the new mesh patch element.
A method for generating a fault tree of a multi-component system is provided. The multicomponent system includes a logical-functional system layer and a physical system layer as different layers of abstraction. The physical system layer may correspond, for example, to software and/or hardware implementing the functional aspects of the logical-functional system layer. The method first provides a logical-functional fault tree for the logical-functional system layer and a physical fault tree for the physical system layer, the latter having elements corresponding to elements in the logical-functional fault tree. Next, a mixed-layer fault tree is generated by combining aspects of both fault trees in a systematic way. The disclosed is particularly relevant for analyzing safety-critical systems. However, the present concepts are not limited to these applications and may be applied to general use cases where fault tree analysis is applicable.
G06F 30/3323 - Design verification, e.g. functional simulation or model checking using formal methods, e.g. equivalence checking or property checking
G06F 30/3308 - Design verification, e.g. functional simulation or model checking using simulation
G06F 30/367 - Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
G06F 30/398 - Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM]
G01R 31/28 - Testing of electronic circuits, e.g. by signal tracer
G06F 119/02 - Reliability analysis or reliability optimisationFailure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
77.
METHOD AND APPARATUS FOR OBTAINING A COMPOSITE LAMINATE
A method for obtaining a composite laminate (1) composed of plies (2, 21-28) each composed of a matrix (3) and a filler (4) includes: receiving a model (5) and load conditions (7) of a mechanical part (6) to be produced from the composite laminate (1); predicting properties (95) of a candidate composite laminate based on features (85) thereof by machine learning (10); evaluating a performance of the mechanical part (6) produced according to the model from the candidate laminate when subject to the load conditions (7), based on the predicted properties (95); optimizing the performance of the mechanical part (6) by varying the features (85) of the candidate laminate and repeating the predicting and evaluating steps until a desired performance is achieved; and determining the candidate laminate thus optimized as the composite laminate (1) for manufacturing the mechanical part. A corresponding apparatus is also proposed.
G06F 30/17 - Mechanical parametric or variational design
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
The invention relates to a method and to a device for configuring a controller, and to a method and to a controller for controlling a technical system by means of a data-based control model, in particular a model based on reinforcement learning. This data-based control model (RL) is configured on the basis of a model-predictive control model (MPC). Configuration parameters of the data-based control model are set by mapping the model-predictive control model onto the data-based control model in such a way that the data-based control model reproduces the output data of the model-predictive control model, depending on read state data of the technical system, and determines optimised control parameters configured in this way. A computationally intensive training method for configuring the data-based control model can thus be avoided.
G05B 13/02 - Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
79.
MACHINE LEARNING-BASED SYSTEM ARCHITECTURE DETERMINATION
Examples of techniques for machine learning-based system architecture determination are described herein. An aspect includes receiving a system architecture specification corresponding to a system design, and a plurality of topological variants of the system architecture specification. Another aspect includes determining a system architecture graph based on the system architecture specification. Another aspect includes classifying, by a neural network-based classifier, each of the topological variants as a feasible architecture or an infeasible architecture based on the system architecture graph. Another aspect includes identifying a subset of the feasible architectures as system design candidates based on performance predictions.
System, apparatus and method for generating automatically a component fault tree of an investigated system (140) is disclosed. The system (140) comprises at least one of software components (142) and hardware components (144)The method comprising/initiating the steps of generating the component fault tree (132), wherein input and output failure modes of the component fault tree (132) are generated and interconnected based on failure modes of a component (142) in the system (140), wherein the component (142) is one of the software components (142) and the hardware components (144); connecting the input failure modes (IFM) of the component fault tree (132) to the output failure modes (OFM) of the component fault tree (132) via internal failure propagation paths based on, preferably automatically generated, pessimistic propagation path of the failure propagation; and refining the input failure modes (IFM) by generating a failure simulation of at least one failure using the component fault tree (132).
A computer-implemented method is provided for predicting a fatigue response of a material. The method includes receiving a user input specifying one or more surface roughness parameters that characterize a surface of a material for which fatigue life is to be predicted. The method further includes generating at least one realistic virtual surface profile from the specified one or more surface roughness parameters. The method further includes predicting fatigue life of the material in dependence of a stress field applied to the generated virtual surface profile. In accordance with specific embodiments, the prediction of the fatigue life may be carried out using finite element analysis based simulations, machine learning methods, or combinations thereof.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Systems and methods for synchronizing programs for simulation of a technical system. The programs including a first simulation program and a second simulation program. The first simulation program simulates the kinematics of the technical system and the second simulation program simulates a control of the operation of the technical system. The first simulation program outputs values of a first variable at first-time points between first-time intervals according to a first frequency in virtual simulated time and the second simulation program outputs values of a second variable at second time points between second time intervals according to a second frequency in virtual simulated time, the first frequency being lower than the second frequency. Values of the first variable at second time points between two successive first-time points are determined based on an approximation, where the second simulation program uses the approximated values in order to determine values of the second variable at second time points between the two successive first-time points. An error is determined based on the absolute value of the difference between a first integral value as seen from the first simulation program and a second integral value as seen from the second simulation program. A warning is output by a user interface in case that the error exceeds a predetermined threshold.
G06F 30/20 - Design optimisation, verification or simulation
83.
Method for producing a test data record, method for testing, method for operating a system, apparatus, control system, computer program product, computer-readable medium, production and use
g) and/or sensor data and action regions associated with the sensor data. The invention furthermore relates to a method for operating a system for the automated, image-dependent control of a device and an apparatus for carrying out the aforementioned method. Finally, the invention relates to a control system for a device which comprises such an apparatus, and a computer program product, a computer-readable medium, the production of a data storage device and the use of an artificial intelligence (8).
G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
G06F 18/214 - Generating training patternsBootstrap methods, e.g. bagging or boosting
G06N 3/044 - Recurrent networks, e.g. Hopfield networks
84.
Method and system for controlling an autonomous vehicle device to repeatedly follow a same predetermined trajectory
A method for controlling an autonomous vehicle to repeatedly follow a same predetermined trajectory comprises: a) receiving a target trajectory signal indicative of the predetermined trajectory; b) generating a control signal adapted to steer the vehicle along the predetermined trajectory; and, for at least one of a number of iterations: c) steering the vehicle along the predetermined trajectory by feeding the control signal to the vehicle; d) measuring an actual trajectory followed by the vehicle in response to being steered according to the control signal; e) recording an actual trajectory signal indicative of the measured actual trajectory; f) using an iterative learning controller to determine an altered control signal using the control signal, the actual trajectory signal and the target trajectory signal. The method allows to improve a tracking performance during a subsequent iteration.
Method and apparatus for detecting vibrational and/or acoustic transfers in a mechanical system A method and apparatus for detecting vibro-acoustic transfers in a mechanical system are provided. The method comprises: while operating the mechanical system, acquiring, at each of multiple input points, an input signal indicative of a mechanical load acting on the input point, and acquiring, at a response point, a response signal indicative of a mechanical response; training a neural network device using the input signals acquired at the input points and using the response signal acquired at the response point; and, for each of the input points: providing only the input signal acquired at the respective input point to the trained neural network device and obtaining, from the neural network device, a contribution signal indicative of a predicted contribution of the respective input signal to the response signal. Vibro-acoustic transfers may be detected solely based on operational data, thereby reducing time and a cost for performing a transfer analysis.
The invention refers to a method for generating a component mesh (2) of a component (1), in particular a layered component mesh (2) of a component (1), especially a component (1) which is to be build-up layer by layer in an additive manufacturing build-up process, wherein the component mesh (2) can be used in simulating the component (1) and/or the additive manufacturing build-up process of the component (1), wherein the method comprises the steps of: a) providing a three-dimensional initial component mesh (4) composed of initial mesh elements (5) of uniform shape which consist of initial mesh nodes (6) and initial mesh edges (7) extending between the initial mesh nodes (6); b) slicing the initial component mesh (4) by at least one cutting plane (8) such that initial mesh elements (5) are divided into at least two resulting mesh elements (9), wherein at the intersection points of the at least one cutting plane (8) with edges (7) of initial mesh elements (5) resulting mesh nodes (10) are defined; and c) determining the position of each initial mesh element (5) with respect to each cutting plane (8) and thus which initial mesh element (5) is divided into resulting mesh elements (9) and which is not, and determining the shape of each resulting mesh element (9). The invention furthermore relates to a use of a component mesh (2), a computer program and a computer-readable medium.
A method is provided for storing data to and retrieving data from at least one data storage. The method includes receiving data to be stored, selecting only part of the received data to obtain reduced data, storing the reduced data on the at least one data storage, receiving a request for retrieval of the data, using at least one compressive sensing reconstruction algorithm to generate reconstructed data from the reduced data, and providing the reconstructed data as the requested data. The disclosure furthermore relates to a system for storing and retrieving data, the use of the compressive sensing technique, a computer program, and a computer readable medium.
Method for generating a structure mesh, use of a structure mesh, computer program and computer-readable medium The invention relates to a method for generating a structure mesh (9) of a structure (2) which is to be build-up in a three- dimensional build-up volume (1) in an additive manufacturing build-up process and which comprises at least one specimen 6a,b and at least one support (8) for supporting the at least one specimen (6a,b) on a boundary (5) of the build-up volume (1), wherein the structure mesh (9) can be used in simulating the additive manufacturing build-up process of the structure (2). The invention furthermore relates to a use of a structure mesh (9), a computer program and a computer-readable medium.
tottottottot) and a respective second operation pa- rameter provided by a stored structural/vibro-acoustic model (M). Due to the present invention, electromagnetic forces within an electric machine, in particular in the air gaps between the stator and rotor of the electric machine can be measured and disturbing noises and/or vibration resulting from the electromagnetic forces can be identified as well as eliminated.
One or more ring closures (180) of a fault tree (101, 102) are detected. For each one of the one or more ring closures (180): at least one respective edge (146) of the respective ring closure (180) is replaced in the fault tree (101, 102) by a respective variable (611) to obtain a placeholder fault tree (601) and a normalized representation of the placeholder fault tree (601) is determined.
A system and method for accelerated simulation setup includes receiving a description of a new problem for simulation, extracting input data and output data of previous simulation results, generating a representation of data based on the extracted input data and output data, and quantifying similarities between the new problem and the extracted input data and output data to identify a candidate simulation for the new problem. A machine learning component infers a solution output for the new problem based on extrapolation or interpolation of outputs of the candidate simulation, thereby conserving resources by eliminating a simulation generation and execution. Alternatively, an efficient simulation setup can be generated using the queried knowledge, input variables, and input parameters corresponding to the candidate simulation.
The invention concerns a method for determining a spatial distribution of phases (SP) of a product (100) to be manufactured by additive manufacturing. To improve the prediction of spatial distribution of phases (SP) in the product (100) manufactured by additive manufacturing techniques the proposed method comprises the following steps: determining (S2) one or more areas (A1,...,A4) of the product (100), determining (S3) a temperature progression (T1,...,T4) for each of the areas (A1,...,A4) and determining (S4) the spatial distribution of phases (SP) by correlating the temperature progression (T1,...,T4) to the phase (P1,...,P4) in each of the areas (A1,...,A4). Furthermore, the invention addresses the problem of manufacturing a product (100) with a predetermined target spatial distribution (TSP) of phases. The invention further concerns a method for manufacturing a product (100) with a target phase composition and a product (100) comprising a spatial distribution of phases (SP) according to the method.
The invention relates to a method and a system for Fatigue life prediction of additive manufactured components accounting for localized material properties. The method and the system is employed for prediction of Fatigue life properties of an Additive manufactured element, with a data collection step (1a, 1b) in which several data points for maximum stress vs. cycles to failure for different given processing steps of the element are collected, with a training step (2) in which a Machine Learning system is trained with the collected data, and with an evaluation step (5, 6) in which the trained Machine Learning system is confronted with actual processing steps and used to predict the Fatigue life properties of the element.
The present invention is related to a method of and system for optimising operation of a ship as well as a ship comprising said system. By means of a digital twin of the ship and a model of the response of the environment of the ship a virtual behaviour of the ship is simulated. The virtual behaviour of the ship is optimised according to at least one predefined threshold. An optimised virtual operation state of the ship according to the optimised virtual behaviour of the ship is used to adjust the real operation state of the ship.
The present invention pertains to a method for generating a fault tree of a multi-component system. The multicomponent system comprises a logical-functional system layer and a physical system layer as different layers of abstraction. The physical system layer may correspond, for example, to software and/or hardware implementing the functional aspects of the logical-functional system layer. The method first provides a logical-functional fault tree for the logical-functional system layer and a physical fault tree for the physical system layer, the latter having elements corresponding to elements in the logical-functional fault tree. Next, a mixed-layer fault tree is generated by combining aspects of both fault trees in a systematic way. The present invention is particularly relevant for analyzing safety-critical systems. However, the present concepts are not limited to these applications and may be applied to general use cases where fault tree analysis is applicable. The solution of the present invention advantageously provides a systematic approach to generate fault trees taking into account both the logical-functional and the technical-physical aspects of a multi-component system. The resulting fault tree can thus be easily extended, modified and/or reused during a system's life-cycle.
A method and system for calibrating an integrated volume acceleration sensor of a loudspeaker, wherein the method includes driving the loudspeaker with a calibration signal and meanwhile generating a sensor output signal by the integrated volume acceleration sensor measuring a volume acceleration over time of a motion element fixed to a moving part of the loudspeaker and/or of the moving part while the loudspeaker is driven with the calibration signal as well as generating a reference output signal by a reference sensor measuring the volume acceleration over time of the motion element and/or of the moving part of the loudspeaker while the loudspeaker is driven with the calibration signal, and additionally includes calculating a calibration value for the integrated volume acceleration sensor based on a ratio of the sensor output signal and the reference output signal and based on a predetermined reference calibration value of the reference sensor.
Provided is a system for safety analysis of failure behavior for a unit including two or more components with at least one inport for receiving failure data and one outport for transmitting failure data, wherein for the analysis of the failures data of the components and/or the unit a safety contract is used, and wherein the safety contract is generated automatically by a model-based safety analysis model comprising separate SAM modules which are related to the components of the unit.
A method and apparatus for verifying a software system is disclosed. In one embodiment, a data processing apparatus (100) includes a processing unit (102), and a memory unit (104) communicatively coupled to the processing unit (102). The memory unit (104) includes a simulation module (116), and a verification module (118). The simulation module (116) is configured to perform simulation of the software system for a first set of steps based on a first set of input values. The verification module (118) is configured to instantaneously determine a state of the software system is which verification of the software system is to be initiated. The verification module (118) is configured to initiate verification of the software system at the determined state, perform verification of the software system for a second set of steps based on a second set of input values, and output results of the verification of the software system on a display unit (110).
A Control method for layerwise additive manufacturing of a component (10) is provided, the method comprising the following steps: - a) measuring a displacement (D) of an as-manufactured layer (L) of the component (10) during a build job in an additive manufacturing device (100), - b) determining an inherent strain of the layer (L) from the determined displacement (D), - c) calculating a residual stress and/or a distortion, based on the determined inherent strain of the layer and - d) adapting of a substrate temperature based on the calculated residual stress and/or the calculated distortion. Further, an according computer program product is provided and a control apparatus module being configured to carry out steps of the method.
Method and apparatus for detecting vibrational and/or acoustic transfers in a mechanical system A method and apparatus for detecting vibro-acoustic transfers in a mechanical system are provided. The method comprises: while operating the mechanical system, acquiring, at each of multiple input points, an input signal indicative of a mechanical load acting on the input point, and acquiring, at a response point, a response signal indicative of a mechanical response; training a neural network device using the input signals acquired at the input points and using the response signal acquired at the response point; and, for each of the input points: providing only the input signal acquired at the respective input point to the trained neural network device and obtaining, from the neural network device, a contribution signal indicative of a predicted contribution of the respective input signal to the response signal. Vibro-acoustic transfers may be detected solely based on operational data, thereby reducing time and a cost for performing a transfer analysis.
