EP3921780A1 - Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches system - Google Patents
Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches systemInfo
- Publication number
- EP3921780A1 EP3921780A1 EP20718179.3A EP20718179A EP3921780A1 EP 3921780 A1 EP3921780 A1 EP 3921780A1 EP 20718179 A EP20718179 A EP 20718179A EP 3921780 A1 EP3921780 A1 EP 3921780A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- model
- computer
- technical system
- text
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000013528 artificial neural network Methods 0.000 claims description 79
- 238000004088 simulation Methods 0.000 claims description 57
- 238000012549 training Methods 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000005094 computer simulation Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
Definitions
- the invention relates to a computer-implemented method and a device for generating a computer-readable model for a technical system by means of an artificial neural network, in particular by means of Generative Adversarial Neural Networks. Furthermore, the invention is directed to a computer program product for carrying out the steps of a method according to the invention.
- Computer-aided simulations can be used as a digital planning instrument for technical systems, e.g. Plants or factories. For example, planning drafts can be validated using simulations.
- computer simulations can be used during the operating phase of a system, for example to implement assistance systems during operation.
- simulation tools or simulation tools are known with which simulation models can be created manually by a simulation expert from existing simulation component libraries.
- the creation of a simulation model on the basis of an available factory plan and available factory data generally requires a high level of specialist knowledge on the part of the simulation expert, as the latter must first determine and / or create suitable simulation components for mapping the real factory components. Therefore, the creation of a simulation model can be time-consuming, error-prone and / or qualitatively different.
- Generative Adversarial Networks comprise two artificial neural networks that are trained in such a way that one of the neural Networks candidates are created (the generator), the second neural network evaluates these candidates (the Discriminator).
- Generative adversarial networks can be used, for example, to generate photorealistic images, videos or sequences.
- the invention relates to a computer-implemented method for generating a computer-readable model for a technical system, comprising the method steps:
- the text-based specification data specifying at least one system condition
- a first neural network which is trained by means of a second neural network, based on text-based specification data for a technical system, model components based on their model components to select from a variety of model components and from the selected model components to select a computer-readable model for the to generate technical systems in such a way that model data of the computer-readable model meet at least one system condition specified in the text-based specification data,
- “computer-aided” or “computer-implemented” can be understood to mean, for example, an implementation of the method, in which a processor in particular carries out at least one method step of the method.
- “computer-readable” can be understood to mean, for example, a data record which is designed in such a way that it can be read and / or interpreted by a computer are readable and processable.
- a computer-readable model can be, for example, a formal model or a computer-aided simulation model.
- the invention enables the creation of a computer-readable model for a technical system, which is set up in such a way as to form and / or simulate the real technical system with the aid of a computer.
- a computer-aided simulation or computer simulation is used, for example, to map and analyze physical processes of the technical system.
- a technical system can, for example, be a plant or a factory plant or a machine, such as a generator or a motor, or a machine tool, etc.
- a technical system comprises a large number of components.
- Components of the real technical system can be hardware and / or software components.
- Model components are corresponding to images of the real components. Model components can in particular be referred to as simulation components, which are preferably designed in such a way that physical and / or functional processes and / or properties of the real component can be mapped with the aid of a computer.
- a model for the technical system can thus be generated on the basis of a read-in text-based specification of the technical system.
- a model with a topology that corresponds to the topology of the corresponding real technical system is consequently generated from the model components.
- the method enables a reduction in the manual effort involved in creating a computer-readable model for a technical system, since the model generation and model parameterization can be carried out automatically. This enables, in particular, a constant quality of the models.
- This data-based approach is also more robust and flexible than, for example, a rule-based approach in which models are generated based on specified rules.
- the model components are selected based on specific model component identifiers and converted into the computer-readable model put together.
- the generated computer-readable model can be used, for example, to simulate and / or control and / or analyze the technical system.
- the method according to the invention can be used to plan a technical system, ie first to create a computer-readable model before the real technical system is constructed.
- Text-based specification data can, for example, be in the form of a textual requirement that a technical system should meet, e.g. a production goal of a plant. Text-based specification data can, for example, only include boundary conditions and / or basic requirements for the technical system. These can later be compared with the model data of the generated model.
- the text-based specification data for the technical system can be used to extract parameter values for parameters of the technical system and / or of components of the technical system and the generated computer-readable model depending on the extracted parameter values and using the first neural network are parameterized.
- the text-based specification data can include, for example, parameter values which can be taken into account when generating the computer-readable model.
- information can be obtained from the text-based specification data, for example by means of a method for processing text data and / or natural language, from which information can be derived from which parameter values can be derived.
- the first neural network can be trained by means of a second neural network and on the basis of training data, - where the training data can include at least text-based specification data of a technical system and / or model data from at least one computer-readable model of a technical system,
- the training of the first neural network by means of the second neural network comprises that by means of the first neural network on the basis of text-based specification data for a technical system, model components are selected from a large number of model components based on their model component identifiers, a computer-readable component from the selected model components Model is generated for the technical system and by means of the second neural network on the basis of the training data it is checked whether the model data of the computer-aided model generated by the first neural network meet the system condition specified in the text-based specification data.
- the first neural network can also be referred to as a generator network.
- the second neural network can also be referred to as a discriminator network. Together they describe a Generative Adversarial Network.
- both neural networks are trained together.
- Training data include, for example, data on a large number of technical systems, with both model data from computer-readable models and assigned text-based specification data being given for each technical system.
- the generator network is trained using the discriminator network.
- the model is generated from a large number of model components and based on their model component identifiers.
- model components are selected whose model component identifiers can be assigned to the text-based specification data.
- the generated computer-readable model is checked by the second neural network on the basis of further (training) model data that are assigned to the text-based specification data, whether the generated model meets the system condition specified in the text-based specification data.
- the trained generator network is finally provided, such as stored, for generating a computer-readable model for a technical system.
- a computer-aided model provided for the technical system can be validated by means of the second neural network.
- the discriminator network can in particular be used to validate a provided computer-readable model.
- the model data of the computer-readable model are checked by the trained second neural network and a test result is output. It can thus be checked in particular whether the topology of the computer-readable model and / or an output of a simulation based on the computer-readable model is sensible in comparison to the specified system conditions.
- specification data of the technical system can be recorded by means of a voice input unit, converted into text-based specification data by means of an evaluation unit and the text-based specification data provided.
- specification data can be transmitted orally by a user, recorded by means of a voice input unit and converted into text-based specification data for further use.
- the computer-readable model can be generated as a computer-aided simulation model for simulating the technical system.
- the creation of a computer-aided simulation model from the computer-readable model can preferably be done by means of a simulation tool - also referred to as a simulation tool. net - be carried out in a simulation unit which comprises at least one processor.
- the input of the simulation unit is preferably the output of the generative neural network.
- the computer-aided simulation model can be created from the simulation components provided.
- Simulation components are, for example, computer-aided images of the real components, which are preferably designed in such a way that physical and / or functional processes and / or properties of the real components can be simulated in a computer-aided manner.
- a computer-aided simulation model is, in particular, an executable model with which, for example, a temporal course of a process of a technical system can be simulated with a computer.
- the technical system and / or a process or a functionality of the technical system can be simulated with the aid of the computer-aided simulation model and / or the computer-aided simulation model can be output to control the technical system.
- the simulation model can be made available and executed with the aid of a computer in a simulation environment.
- the corresponding simulation data for controlling the real technical system can then be output.
- the computer-aided simulation can be used, for example, to validate a process and / or a functionality and / or a specification of the technical system.
- the invention relates to a device for generating a computer-readable model for a technical system, the device having at least one processor for performing the steps of a method according to the preceding claims.
- a processor can in particular be a main processor (Central Processing Unit, CPU), a microprocessor or a microcontroller, for example an application-specific integrated circuit or a digital signal processor, possibly in combination with a memory unit for storing program instructions , etc. act.
- a processor can, for example, also be an IC (integrated circuit) or a graphics processor GPU (graphics processing
- the processor can have one or more computing cores (multi-core).
- a processor can also be understood to be a virtualized processor or a soft CPU. It can also be a programmable processor, for example, which is equipped with configuration steps for executing the method according to the invention or is configured with configuration steps in such a way that the programmable processor implements the features of the method according to the invention or other aspects and partial aspects of the invention.
- the device can, for example, be coupled to a simulation unit or a simulation tool, so that a computer-aided simulation model for simulating the technical system can be generated and / or executed.
- the invention also relates to a computer program product which can be loaded directly into a programmable computer, comprising program code parts which are suitable for performing the steps of a computer-implemented method according to the invention.
- a computer program product such as a computer program means, for example, can be provided or delivered as a storage medium or data carrier such as a memory card, USB stick, CD-ROM, DVD or also in the form of a downloadable file from a server in a network be produced.
- a storage medium or data carrier such as a memory card, USB stick, CD-ROM, DVD or also in the form of a downloadable file from a server in a network be produced.
- FIG. 3 shows a schematic representation of a further exemplary embodiment of a method according to the invention.
- FIG. 4 shows a schematic representation of a device according to the invention in a block representation.
- Figure 1 shows a flow chart of a method according to the invention for generating a computer-readable model for a technical system, such as a factory plant.
- the method can be used to plan a system that does not yet exist on the computer.
- a text-based specification for the system to be modeled is provided and recorded as text-based specification data.
- text-based specification data can include, for example, requirements, boundary conditions, construction conditions, operating conditions, a production target, or the like for the factory.
- the text-based specification data can for example be provided by a user, i.e. e.g. formulated and / or entered and can be read in for further steps. Alternatively, the text-based specification data can be extracted from a file and / or read in.
- a computer-readable model is now to be created by means of the computer-implemented method which meets the system conditions for the factory specified in the text-based specification data. For example, a computer-readable model of a plant is to be generated which fulfills a specified production target for the plant.
- the method according to the invention is to be used to plan a system from components and to generate a model from corresponding model components so that the modeled system fulfills the specified production target.
- a computer-readable model can, for example, be a formalized engineering model which is available as computer-readable text data, e.g. saved in an XML file.
- a computer-readable model can also be a computer simulation model which can be read and executed by a computer.
- a computer readable model can be used as an abstract plant architecture, e.g. as a SysML or AutomationML file.
- model component th are preferably each assigned to real components, such as software and / or hardware, of a real technical system, so that a real component can be mapped or modeled and / or simulated by means of a model component.
- a model component can be assigned to a real component in advance, for example, by means of a trained machine learning method, the machine learning method being trained to assign a model component to real components of a technical system that has the functionality and / or physics of the real component from images.
- a respective model component is identified by a model component identifier.
- a model component identifier can be in the form of identifier data which, for example, can include a designation, identification, name, label, identification number, description, brief description or the like. Model component identifiers are preferably clearly assigned to a model component.
- the respective model components and / or their function can be described and / or identified on the basis of identification data. For example, on the basis of the text-based specification data, suitable model components can be selected using their model component IDs.
- a trained generative neural network is provided.
- the trained generative neural network is provided, for example, as a data structure, such as stored on a memory unit and read from there.
- the generative neural network is preferably first trained by means of a discriminator network, as shown for example in FIG.
- the generative neural network is trained in such a way that it selects certain model components on the basis of read-in text-based specification data for a technical system from a model component database on the basis of respective model component identifiers.
- a computer-readable model is generated from the selected model components.
- the generated computer-readable model is created in such a way that the model data meet at least one system condition specified in the imported text-based specification data.
- the model data of a generated model are compared with the specification data, for example.
- a system simulation can also be carried out using the generated model in order to test whether the model fulfills the specified system conditions.
- the production of a product can be simulated using the generated model in order to test whether a production target of a plant has been met.
- step S4 the recorded text-based specification data are transmitted and read into the trained generative neural network.
- the generative neural network On the basis of the imported text-based specification data, the generative neural network generates a computer-readable model from model components in a model component database.
- step S5 the generated computer-readable model is output.
- the generated computer-readable model is output as a data structure.
- the computer-readable model can be used, for example, for planning, design, computer-aided simulation and / or for controlling the factory.
- a factory can be planned and / or constructed and / or controlled using the computer-readable model that is output.
- FIG. 2 shows an exemplary embodiment of a method according to the invention for training a generative adversarial network, which is suitable for generating a computer-readable model for a technical system.
- Training of a neural network is generally understood to mean an optimization of a mapping of input parameters to one or more target parameters. This mapping is optimized according to predetermined criteria that have been learned and / or to be learned during a training phase.
- a training structure can include, for example, a network structure of neurons of a neural network and / or weights of connections between the neurons, which are formed by the training in such a way that the specified criteria are met as well as possible.
- the first neural network NN1 generates a computer-readable model M for a technical system on the basis of text-based specification data D_spec.
- the text-based specification data D_spec are read into the first neural network NN1.
- the first neural network NN1 is provided with a multiplicity of model components MK, each of which is assigned model component identifications MKK.
- the first neural network NN1 is coupled to a database or library in which model components MK are stored. From this, the first neural network NN1 selects certain model components MK for the computer-readable model M on the basis of the read-in text-based specification data D_spec and on the basis of the model component identifiers MKK.
- the specification data D_spec includes the requirement "Plant for the production of product X in time Y", where "X" and "Y” have a certain value.
- suitable model components can be selected, such as model components for machine tools, conveyor belts , etc ..
- a computer-readable model is generated from the selected model components MK.
- the generated computer-readable model M is output to the second neural network NN2 and read there.
- the second neural network NN2 checks the computer-readable model M on the basis of training data. For example, it is checked whether the generated computer-readable model M makes sense.
- model data MD * and the associated text-based specification data D_spec * from a large number of technical systems are made available as training data to the second neural network NN2.
- the training data comprise at least one pair of mutually assigned model data MD * and text-based specification data D_spec *.
- the text-based specification data D_spec * of the training data are preferably identical or similar to the originally read-in text-based specification data D_spec.
- the training data MD *, D_spec * are from other technical systems and / or similar technical systems as the technical system to be modeled, which have the same or similar system conditions.
- the second neural network NN2 can check whether the computer-readable model M generated by the first neural network NN1 fulfills the system condition specified in the text-based specification data D_spec.
- the model data MD of the computer-readable model M are compared with the training data MD *, D_spec *. For example, it can be checked whether the model data MD follow a statistical distribution of the training model data MD *.
- a new generation of a computer-readable model M can be triggered, FL if, for example, the model data MD does not meet the specified system condition D_spec.
- the training takes place preferably until a computer-readable model is generated that is checked by the second neural network NN2 as sensible or suitable, i.e. whose model data meet the specified system conditions at least within a specified tolerance range.
- the first and the second neural network NN1, NN2 can be output and provided as a data structure, for example.
- a predetermined computer-readable model of a technical system can be validated, ie it can be checked whether the model is designed in such a way that it meets a system condition.
- FIG. 3 shows a further embodiment of the inventive method.
- a trained first neural network NN1 is shown, which is designed as a generative neural network.
- the training of the first neural network NN1 can be carried out, for example, as shown with reference to FIG.
- the first neural network NN1 is coupled, for example, to a model component database which provides model components MK with associated model component identifications MKK.
- Text-based specification data D_spec are provided for a technical system and transferred to the first neural network NN1.
- the text-based specification data D_spec can, for example, be based on oral specification data that are recorded via a voice input unit and are output as text-based specification data D_spec.
- the neural network NN1 On the basis of the text-based specification data D_spec, the neural network NN1 generates a computer-readable model M from a large number of model components MK.
- the model components MK are selected based on their model component ideas MKK as a function of the text-based specification data D_spec and combined to form a computer-readable model M.
- parameter values for parameters of the technical system can be extracted and the generated computer-readable model M can be parameterized depending on the extracted parameter values and using the first neural network, i.e.
- Model M parameters are set.
- parameters can be physical quantities that describe the model components.
- the computer-readable model M can then be output, for example for planning the technical system.
- a computer-aided simulation model SM based on the computer-readable model M can be generated by means of a simulation tool if, for example, the computer-readable model M is only generated as a formalized engineering model and is to be implemented as an executable simulation model.
- a simulation tool can in particular have a programming interface (application programming interface, or API for short).
- the simulation model can be generated by the API of the simulation tool.
- the simulation tool or the internal functions of the tool can be accessed through the interface.
- the technical system and / or a process or functionality of the technical system can be simulated by means of the computer-aided simulation model.
- the computer-aided simulation model SM can be output to control the technical system.
- FIG. 4 shows a schematic block diagram of a device 100 according to the invention for generating a computer-readable model for a technical system, for example for planning the technical system.
- the device 100 comprises at least one processor 101 which is set up to carry out the steps of a method according to the invention, as shown for example with reference to one of FIGS. 1 to 3.
- the device 100 preferably comprises at least one storage unit 102 or is coupled to a storage unit or database.
- a large number of model components can be stored and provided on the storage unit 102.
- the storage unit 102 can store the trained first and / or second neural network and make it available for use as a data structure.
- the Generative Adversarial Networks can be trained in a training unit 103 using training data and transmitted to the memory unit 102 or to the processor 101.
- the device 100 can also comprise or with a simulation unit 104 be coupled to this, the simulation unit having, for example, a simulation tool in the form of software and being set up in such a way to create and output a simulation model that can be executed on a computer from simulation components.
- the simulation unit can also be set up to execute the simulation model.
- the individual units of the device 100 can be designed both as software and / or as hardware and are preferably advantageously coupled to one another.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP19170588.8A EP3731151A1 (de) | 2019-04-23 | 2019-04-23 | Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches system |
PCT/EP2020/058248 WO2020216553A1 (de) | 2019-04-23 | 2020-03-25 | Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches system |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3921780A1 true EP3921780A1 (de) | 2021-12-15 |
Family
ID=66248607
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP19170588.8A Withdrawn EP3731151A1 (de) | 2019-04-23 | 2019-04-23 | Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches system |
EP20718179.3A Pending EP3921780A1 (de) | 2019-04-23 | 2020-03-25 | Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches system |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP19170588.8A Withdrawn EP3731151A1 (de) | 2019-04-23 | 2019-04-23 | Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches system |
Country Status (4)
Country | Link |
---|---|
US (1) | US20220180153A1 (de) |
EP (2) | EP3731151A1 (de) |
CN (1) | CN113678145A (de) |
WO (1) | WO2020216553A1 (de) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11580375B2 (en) * | 2015-12-31 | 2023-02-14 | Kla-Tencor Corp. | Accelerated training of a machine learning based model for semiconductor applications |
EP3475778B1 (de) * | 2016-06-28 | 2024-07-10 | Cognata Ltd. | Realistische 3d-erstellung einer virtuellen welt und simulation zum trainieren automatisierter fahrsysteme |
US20180349526A1 (en) * | 2016-06-28 | 2018-12-06 | Cognata Ltd. | Method and system for creating and simulating a realistic 3d virtual world |
EP3410404B1 (de) * | 2017-05-29 | 2023-08-23 | Cognata Ltd. | Verfahren und system zur erzeugung und simulation einer realistischen virtuellen 3d-welt |
-
2019
- 2019-04-23 EP EP19170588.8A patent/EP3731151A1/de not_active Withdrawn
-
2020
- 2020-03-25 CN CN202080030761.5A patent/CN113678145A/zh active Pending
- 2020-03-25 US US17/601,278 patent/US20220180153A1/en active Pending
- 2020-03-25 EP EP20718179.3A patent/EP3921780A1/de active Pending
- 2020-03-25 WO PCT/EP2020/058248 patent/WO2020216553A1/de unknown
Also Published As
Publication number | Publication date |
---|---|
CN113678145A (zh) | 2021-11-19 |
WO2020216553A1 (de) | 2020-10-29 |
US20220180153A1 (en) | 2022-06-09 |
EP3731151A1 (de) | 2020-10-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2799983B1 (de) | Flexible Aufteilung der I/O Kanäle einer Hardware Komponente | |
DE69225527T2 (de) | Verfahren und System zur automatischen Bestimmung der logischen Funktion einer Schaltung | |
DE112020002961T5 (de) | Übersetzen einer abfrage in natürlicher sprache in eine formale datenabfrage | |
EP3082000A1 (de) | Verfahren und system zum testen eines mechatronischen systems | |
EP2442248B1 (de) | Kopplungsmethodik für nicht-iterative Co-Simulation | |
DE112020006021T5 (de) | Auf maschinelles lernen basierendes verfahren und vorrichtung für die berechnung und verifizierung von verzögerungen des entwurfs integrierter schaltungen | |
WO2017114883A1 (de) | Verfahren zum konfigurieren einer co-simulation für ein gesamtsystem | |
DE112020003050T5 (de) | Fehlerkompensation in analogen neuronalen netzen | |
DE112014003045T5 (de) | Verfahren und System zur Change-Evaluierung eines elektronischen Designs zur Verifizierungsbestätigung | |
EP3650970A1 (de) | Verfahren und vorrichtung zum computergestützten simulieren eines modularen technischen systems | |
DE112021002866T5 (de) | Modelltreueüberwachung und -neuerstellung zur entscheidungsunterstützung eines fertigungsverfahrens | |
EP3916493B1 (de) | Prognose eines systemzustands eines technischen systems | |
DE10324594A1 (de) | Verfahren zum Bereitstellen einer verbesserten Simulationsfähigkeit eines dynamischen Systems außerhalb der ursprünglichen Modellierungsumgebung | |
EP3921780A1 (de) | Verfahren und vorrichtung zum generieren eines computerlesbaren modells für ein technisches system | |
EP4179395B1 (de) | Steuerung eines technischen systems mit einer recheneinheit für künstliche intelligenz | |
WO2022022816A1 (de) | Steuern eines technischen systems mittels eines datenbasierten regelungsmodells | |
DE102017130842A1 (de) | Konfigurationssystem zur Konfiguration eines zum Testen eines elektronischen Steuergeräts geeigneten Testsystems | |
WO2020207728A1 (de) | Verfahren und vorrichtung zum generieren eines computergestützten simulationsmodells für ein technisches system | |
EP3771979A1 (de) | Verfahren und vorrichtung zur optimalen konfiguration eines geräts einer geräteklasse | |
EP3056994B1 (de) | Vorrichtung und verfahren zur erfassung, überprüfung und speicherung von prozessdaten aus mindestens zwei prozessschritten | |
DE102022133251B4 (de) | Neuronale Netzwerke zum Erzeugen von Roboteraufgabendemonstrationen | |
EP4016202A1 (de) | Verfahren zum nachbilden von rauschanteilen von verlustbehaftet aufgezeichneten betriebssignalen sowie steuereinrichtung | |
EP4293563A1 (de) | Anordnung und verfahren zum kalibrieren eines computergestützten simulationsmodells für ein technisches system sowie computerprogrammprodukt | |
DE112021007856T5 (de) | Vorrichtung für maschinelles Lernen, Vorrichtung zum Vorhersagen eines Schweregrades und Verfahren für maschinelles Lernen | |
WO2016146169A1 (de) | Ermitteln von verhaltensähnlichen komponenten für ein system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20210908 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20231025 |