# US 2023/0056513 A1 · Method and system for automated support of a design of a technical system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0056513 A1 - Document ID: US20230056513A1 - Status: Published application - Kind: A1 - Application number: 17/885,961 - Filed: 2022-08-11 - Published: 2023-02-23 - Earliest claimed: 2021-08-19 - Assignees: Siemens Aktiengesellschaft - Applicants: Siemens Aktiengesellschaft - Inventors: Mitchell Joblin; Serghei Mogoreanu - Web page: https://patentgrep.com/patent/US20230056513A1 ## CPC - G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model - G06F 30/12: characterised by design entry means specially adapted for CAD, e.g. graphical user interfaces [GUI] specially adapted for CAD - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/092: Reinforcement learning - G06N 5/02: Knowledge representation; Symbolic representation - G06F 2119/02: Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA] - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 3/045: Combinations of networks - G06N 3/047: Probabilistic or stochastic networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract 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. ## Claims ### Claim 1 A computer implemented method for automated support of a design of a technical system, comprising the following operations, wherein the operations are performed by modules, and wherein the modules are software modules executed by one or more processors and/or hardware modules: receiving, by a machine learning model, a current partial design of a technical system and a candidate component for a next design step of designing the technical system; computing, by the machine learning model; a probability distribution, which is a probability distribution over changes of a design key performance indicator if the candidate component is added to the current partial design, with the design key performance indicator describing a property of the technical system; and/or a predicted impact value predicting an absolute value of the design key performance indicator or a change of the design key performance indicator if the candidate component is added to the current partial design; and outputting, by the machine learning model and/or a user interface, the probability distribution and/or the predicted impact value. ### Claim 2 (depends on 1) The method according to claim 1, wherein the current partial design is a graph-based representation; and the machine learning model is graph-based. ### Claim 3 (depends on 1) The method according to claim 1, wherein the machine learning model contains at least one graph neural network; at least one graph convolutional neural network; and/or at least one Bayesian neural network. ### Claim 4 (depends on 1) The method according to claim 1, wherein the machine learning model computes individual probability distributions and/or predicted impact values for several next component options; and wherein the user interface outputs the individual probability distribution and/or predicted impact value for each next component option. ### Claim 5 (depends on 4) The method according to claim 4, with the additional operations of: detecting, by the user interface, a user interaction selecting one of the next component options; and completing, by a processor, the current partial design with the selected next component option, thereby producing a completed design. ### Claim 6 (depends on 5) The method according to claim 5, with the additional operation of: automatically manufacturing, by an automated plant, the completed design, thereby producing the technical system. ### Claim 7 (depends on 1) The method according to claim 1, with the initial operation of training, by a training module, the machine learning model with training examples, with each training example comprising: a partial design; a candidate next component; and a best value for the design key performance indicator computed by a simulation environment for a completed design, wherein the completed design is reachable and feasible when adding the candidate next component to the partial design. ### Claim 8 (depends on 7) The method according to claim 7, wherein the training examples are initially prepared with the following operations: generating, by a processor executing a SAT solver, the training examples by taking partial designs and candidate next components as input and sampling with feasibility constraints in order to produce expanded designs, with the expanded designs consisting of samples of a design space that are each reachable and feasible given a set of component compatibility constraints when combining a partial design with one of the candidate next components; iterating the generating operation, using the expanded designs as partial designs, until completed designs are reached; and simulating, by the simulation environment, each completed design in order to compute its value for the design key performance indicator. ### Claim 9 A system for automated support of a design of a technical system, comprising: a machine learning model, configured for receiving a current partial design of a technical system and a candidate component for a next design step of designing the technical system; and computing a probability distribution, which is a probability distribution over changes of a design key performance indicator if the candidate component is added to the current partial design, with the design key performance indicator describing a property of the technical system; and/or a predicted impact value predicting an absolute value of the design key performance indicator or a change of the design key performance indicator if the candidate component is added to the current partial design; and a user interface with a display, configured for outputting the probability distribution and/or the predicted impact value. ### Claim 10 (depends on 1) A computer program configured to be executed by one or more processors of a computer system and to perform the method according to claim 1. ### Claim 11 (depends on 1) A computer program product, comprising a computer readable hardware storage device having computer readable program code stored therein, said program code executable by a processor of a computer system to implement the method according to claim 1. ### Claim 12 (depends on 1) A computer-readable storage media having stored thereon: instructions executable by one or more processors of a computer system, wherein execution of the instructions causes the computer system to perform the method according to claim 1.