Methods and systems for improving the system behavior of a technical entity

Abstract

The invention relates to a method for improving the system behavior of a technical entity (10) in a scenario, such as in particular a vehicle in a driving situation, comprising: - Generating a simulation model (350) to simulate the system behavior of the technical entity (10) in a simulation scenario and training it with training data sets; - Providing input data (240) via a user interface (220) or from a database (290), wherein the input data (240) parameters (p i ), parameter values ​​and / or properties (e i ) of the entity (10) include; - Performing a simulation using the input data (240) and the trained simulation model (450) from a simulation module (400) for the simulation task; - Generating simulation results (340); - Passing the simulation results (340) to a learning enhancement module (400); - Calculating modeled values ​​for the parameters (p i ), parameter values ​​and / or properties (e i ) of the entity (10) from the simulation results (340) to achieve improved system behavior of the entity (10); - Generating and outputting output data (550) by an output module (500), wherein the output data (550) are optimized results, in particular in the form of the modeled values ​​for the parameters (p i ), parameter values ​​and / or properties (e i ) of entity (10).

Description

[0001] The invention relates to a method, a system and a computer program product for improving the system behavior of a technical entity in a scenario, such as in particular a vehicle in a driving situation.

[0002] Passive vehicle safety refers to technologies and features of a vehicle that help protect occupants and minimize injuries in the event of a crash. These include airbags, seat belts, head restraints, and reinforced passenger compartments. In contrast, active vehicle safety refers to technologies that help prevent or mitigate accidents, such as anti-lock braking systems (ABS) and electronic stability control (ESC).

[0003] Crash simulation is used to predict the behavior of a structure or technical component or system, e.g., a vehicle with a dummy inside, during an impact or crash. This involves creating a computer model of the structure or component, specifying the properties of the materials used in the design, and simulating the effects of an impact on the model. Crash simulation is therefore an important tool for product development in various industries, including the automotive and aerospace industries. In the automotive industry, crash simulation is used to evaluate and optimize the safety of vehicle designs. In aerospace, for example, crash simulation is used to evaluate the strength and durability of aircraft components.

[0004] The results of crash simulation make it possible to identify potential weak points and improve the performance of structures or technical systems before they are built and tested under real-world conditions. This saves costs and time and, above all, increases the safety of occupants and users.

[0005] The finite element method (FEM), in particular, is used in crash simulation to model and predict the behavior of components, structures, and systems during an impact. FEM software can calculate the behavior of materials under various stress and deformation conditions and analyze the resulting forces and accelerations in the structure. The advantage of applying the finite element method in crash simulation is the ability to simulate the behavior and reactions of components or structures under various crash scenarios. This can help identify flaws and weaknesses in existing designs and improve new developments.

[0006] The finite element method (FEM) is a method for the numerical solution of partial differential equations in mechanics. It is used to calculate the stresses and deformations of components under static or dynamic loading. In FEM simulation, the system or component to be analyzed is discretized into a finite number of elements, each represented by a set of equations based on its geometry, material properties, and boundary conditions.

[0007] To simulate a vehicle impact with a dummy, the user enters the crash test scenario parameters, such as speed and impact angle, and starts the simulation. The software generates a digital animation of the impact, showing how the vehicle and dummy behave during the collision. The simulation can also provide detailed data on the forces and loads acting on the dummy, which can be used to evaluate vehicle safety and improve vehicle design.

[0008] However, conducting crash simulations based on FEM simulation requires considerable experience and expertise. Furthermore, all relevant parameters—from vehicle geometry and the type of impact load to material data—must be taken into account. Furthermore, FEM simulations are only as accurate as the assumptions and data used in the analysis. Simulations for the same technical system or component can therefore lead to different results. Furthermore, an impact involves complex and nonlinear system behavior, meaning there is no proportional relationship between the forces acting and the effects. This means that a small change in an impact scenario can have a major impact on the system's behavior.

[0009] Repeatedly running simulations to determine optimal parameters, e.g., for a vehicle restraint system, is therefore very time-consuming and computationally intensive. Since the parameter changes are typically entered by an engineer, it can take a very long time to find an optimal parameter configuration due to the complex system behavior and the highly nonlinear dependencies of the parameters.

[0010] Therefore, it is desirable to perform structural optimization to improve the structure of a system, especially a vehicle, so that the desired safety properties are achieved more quickly. However, the application of well-known optimization algorithms such as gradient methods, evolutionary algorithms, annealing methods, or particle swarm optimization often leads to unsuitable or inaccurate results because the number of parameters is too large and the dependency behavior of the parameters cannot be accurately represented.

[0011] US Pat. No. 6,850,821 B1 describes a method for cascading system-level objectives to component-level design objectives using machine learning and design synthesis techniques. Surrogate models are created from simulation results, test results, or benchmarking data.

[0012] DE 10 202020 128 881 A1 discloses improved component dimensioning by inputting histograms of operating parameters and environmental data of the test vehicle into a machine learning program, which outputs a classification that is in turn used by a predictive component model.

[0013] EP 4 060 443 A1 discloses a method for producing a composite structure in which neural networks are used to classify inconsistencies.

[0014] The invention is based on the object of demonstrating possibilities for improving the system behavior of an entity such as a technical system or a component in a scenario, in particular for a restraint system in a vehicle in a driving situation, and thus creating the prerequisite for an improved structural optimization of the entity.

[0015] The present invention enables parameters, parameter values ​​and / or properties of an entity, such as a restraint system in a vehicle, to be optimized with regard to system behavior in a specific scenario, such as a collision situation. By coupling a pre-trained simulation model with a learning reinforcement module, optimized values ​​for parameters, parameter values ​​and / or properties of the entity can be calculated without having to carry out a large number of simulations, each with modified simulation data. Since, for example, the system behavior of a vehicle with a dummy in the interior is complex and highly non-linear, it is difficult for an engineer to decide which parameters, parameter values ​​and / or properties should be changed and to what extent in order to achieve acceptable system behavior of the entity, e.g. the vehicle.

[0016] The invention therefore enables the determination of an optimal configuration of parameters, parameter values, and / or properties of an entity for system behavior in a specific scenario, so that only fine-tuning of the parameters, parameter values, and / or properties is required in subsequent simulations. This reduces the need for a large number of simulations, saving computing time and thus costs and energy. In particular, a pre-trained simulation model can be used to implement finite element methods directly in a learning reinforcement module. The invention can thus contribute to increasing and improving the safety and performance of an entity.

[0017] This object is achieved according to the invention with respect to a method by the features of patent claim 1, with respect to a system by the features of patent claim 11, and with respect to a computer program product by the features of patent claim 15. The further claims relate to preferred embodiments of the invention.

[0018] According to a first aspect, the invention provides a method for improving the system behavior of a technical entity in a scenario, such as, in particular, a vehicle in a driving situation. The method comprises the following method steps: - Creating a simulation model to simulate the system behavior of the technical entity in a simulation scenario and training the simulation model with training data sets, wherein the training data sets contain measurement signals from sensors; - Providing input data via a user interface or from a database, wherein the input data comprises in particular parameters, parameter values ​​and / or properties of the entity for a specific simulation task with regard to the system behavior in a specific scenario; - Performing a simulation using the input data and the trained simulation model from a simulation module for the simulation task; - Generating simulation results, wherein the simulation results reflect the system behavior of the entity in the simulation scenario; - Passing the simulation results to a learning reinforcement module; - Calculating modeled values ​​for the parameters, parameter values ​​and / or properties of the entity from the simulation results to achieve improved system behavior of the entity in the simulation scenario; - Generating and outputting output data by an output module, wherein the output data contains optimized results, in particular in the form of the modeled values ​​for the parameters, parameter values ​​and / or properties of the entity.

[0019] In an advantageous embodiment, it is provided that the training data for the simulation model represent input and / or output data of a FEM simulation such as, in particular, parameters, time series data and finite element attributes, wherein finite element attributes are node positions of finite elements in 3-dimensional space.

[0020] In a further development, it is planned that in the case of inconsistent data formats of the input and output data of the FEM simulation, an adjustment is carried out by a transformation into a uniform voxel grid.

[0021] In a further development, it is provided that the learning reinforcement module comprises at least one learning reinforcement agent, an action module, an environment module, a state module and a reward module.

[0022] In an advantageous embodiment, it is provided that a state of the entity is determined by the state module, wherein a state is determined by parameters and / or parameter values ​​and / or a property of the entity.

[0023] In a further embodiment, it is provided that the simulation model uses at least one neural network, in particular recurrent neural networks or convolutional neural networks, or gradient tree boosting as algorithm.

[0024] In particular, the reinforcement learning algorithm of the learning reinforcement module is designed as a Markov decision process or as Temporal Difference Learning (TD-Learning) or as Q-Learning or as SARSA or as Monte Carlo simulation or as Actor-Critic or as Proximal Policy Optimization.

[0025] Advantageously, at least one parameter and / or a parameter value and / or a property entity represents a position, a dimension, a material, a shape, a characteristic value, a measured value, a safety factor, a speed, an acceleration, a force, a torque, a rotational speed, a state of charge, a specific fuel consumption, a thermal resistance, an electrical resistance, a conductivity, a strength, a fracture behavior, a density, a plastic deformation, a stress, pressure, bending resistance, a material property or a surface property.

[0026] In a further embodiment, it is provided that a calculation function and / or an action is selected based on a policy for the state for modifying at least one parameter and / or a parameter value and / or a property of the entity by the learning reinforcement agent; wherein a new state is calculated by the environment module based on the modified value for the parameter and / or the parameter value and / or the property; wherein the new state is compared with a target state and a deviation for a comparison result is calculated in the state module; wherein a reward is determined by the reward module for the comparison result; and wherein the states and / or actions are changed until the target state is reached.

[0027] In particular, it is intended that the output data contain design plans, images and graphics, video sequences, acoustic sequences, holograms, key figures, diagrams, mathematical formulas and / or Power Point presentations, etc.

[0028] In a further development, it is provided that the environment module includes a software application for simulating the system behavior of the entity using a finite element method and that the results of the FEM simulation are forwarded directly to the state module.

[0029] In a further embodiment, the learning reinforcement module performs a multifunctional geometry optimization through a plurality of iterations.

[0030] According to a second aspect, the invention provides a system for improving the system behavior of a technical entity in a scenario, such as, in particular, a vehicle in a driving situation. The system comprises an input module, a simulation module, a learning reinforcement module, and an output module. The simulation model is designed to generate a simulation model for simulating the system behavior of the technical entity in a simulation scenario by training with training data sets, wherein the data of the training data sets contain measurement signals from sensors. The input module is designed to provide input data via a user interface or from a database, wherein the input data in particular comprise parameters, parameter values, and / or properties of the entity for a specific simulation task, such as the system behavior in a specific scenario.The simulation module is further configured to perform a simulation using the input data and the trained simulation model for the simulation task and to generate simulation results, wherein the simulation results reflect the system behavior of the entity in the simulation scenario. The learning reinforcement module is configured to calculate modeled values ​​for the parameters, parameter values, and / or properties of the entity from the simulation results in order to achieve improved system behavior of the entity in the simulation scenario. The output module is configured to generate and output output data, wherein the output data contains optimized results, in particular in the form of the modeled values ​​for the parameters, parameter values, and / or properties of the entity.

[0031] In a further development, it is provided that the learning reinforcement module comprises at least one learning reinforcement agent, an action module, an environment module, a state module and a reward module.

[0032] In a further embodiment, it is provided that the environment module comprises a software application for simulating the system behavior of the entity using a finite element method and the results of the FEM simulation are forwarded directly to the state module.

[0033] Advantageously, the simulation model uses at least one neural network as algorithm, in particular recurrent neural networks or convolutional neural networks, or gradient tree boosting.

[0034] In particular, at least one parameter and / or a parameter value and / or a property of the entity represents a position, a dimension, a material, a shape, a characteristic value, a measured value, a safety factor, a speed, an acceleration, a force, a torque, a rotational speed, a state of charge, a specific fuel consumption, a thermal resistance, an electrical resistance, a conductivity, a strength, a fracture behavior, a density, a plastic deformation, a stress, pressure, bending resistance, a material property or a surface property.

[0035] According to a third aspect, the invention provides a computer program product comprising executable program code configured to carry out the method according to the first aspect when executed.

[0036] The invention is explained in more detail below with reference to embodiments shown in the drawing.

[0037] It shows: Fig. 1 is a block diagram illustrating an embodiment of a system according to the invention; Fig. 2 a representation of a learning reinforcement module; Fig. 3 a flow chart to explain the individual method steps of a method according to the invention; Fig. 4 is a block diagram of a computer program product according to an embodiment of the third aspect of the invention.

[0038] Additional features, aspects and advantages of the invention or embodiments thereof will become apparent from the detailed description taken in conjunction with the claims.

[0039] A restraint system in automotive engineering is a safety mechanism designed to protect occupants in the event of an accident or sudden braking. It typically includes seat belts, airbags, and head restraints, which help keep occupants in the vehicle and minimize injuries. A high-performance restraint system is an important part of the safety equipment of every modern vehicle. To simulate the behavior of the human body in an accident or other collision, dummies are typically used in the testing of vehicle restraint systems. They are specifically designed to measure the forces and loads to which the body is subjected during an accident and provide valuable data. The dummies are equipped with sensors attached to the entire body that measure the forces and loads occurring during an accident.The sensors in a crash test dummy collect data about the dummy's movements and the forces acting on it during an accident. This data is then evaluated to assess the safety of the tested vehicle. The data is used to improve the vehicle's design or safety features.

[0040] A computer simulation using a crash test dummy in a vehicle is a virtual model of a crash test created using computer software, often based on the finite element method. The simulation typically includes a digital representation of a vehicle, a crash test dummy, and other objects and environmental factors relevant to the test scenario. The simulation makes it possible to analyze the behavior of the vehicle and dummy during an impact without having to conduct a physical test. The simulation software is typically designed to recreate the physics of a real impact as accurately as possible. It takes into account factors such as the speed, weight, and dimensions of the vehicle, as well as the properties of the crash test dummy and any other objects in the simulation.The software contains algorithms that simulate the forces and loads to which the dummy is exposed during impact.

[0041] To perform the simulation, the user enters the crash test scenario parameters, such as speed and impact angle, and starts the simulation. The software generates a digital animation of the impact, showing how the vehicle and dummy behave during the impact. However, repeatedly running simulations to determine optimal parameters, e.g., for a vehicle restraint system, is very time-consuming and computationally intensive. Since the parameter changes are typically entered by an engineer, it can take a very long time to find an optimal parameter configuration due to the complex system behavior and the highly nonlinear dependencies of the parameters.

[0042] The system 100 according to the invention is based on reinforcement learning methods and is Fig. 1. The system 100 comprises an input module 200, a simulation module 300, a learning reinforcement module 400, and an output module 500. The simulation module 300 comprises a simulation model 350 with software for performing a simulation of the system behavior of a technical entity 10. The entity 10 can be a part, a component, or a technical system. In particular, the entity 10 can be a vehicle with a dummy in the interior, so that, for example, to analyze the restraint system, a simulated crash test is carried out with the vehicle and the crash test dummy. The technical entity 10 can also be an aircraft, a drone, a motorcycle, a bicycle, a household appliance, an electric motor, a solar system, a wind turbine, a production plant, etc.

[0043] Entity 10 can be defined by parameter p i and / or parameter values ​​and / or properties e i be described. For a parameter p i and / or a parameter value and / or a property e i It can be a position, a dimension, a material, a shape, a characteristic value, a measured value, a safety factor, a speed, an acceleration, a force, a torque, a speed, a state of charge, a specific fuel consumption, a thermal resistance, an electrical resistance, a conductivity, a strength, a fracture behavior, a density, a plastic deformation, a stress, pressure, bending resistance, a material property or a surface property.

[0044] The input module 200, the simulation module 300, the learning reinforcement module 400, and the output module 500 can be implemented as standalone computing units or as a cloud-based solution. In particular, they can each be provided with a processor and / or a memory unit.

[0045] In the context of the invention, a “processor” can be understood to mean, for example, a machine or an electronic circuit. A processor can in particular be a main processor (Central Processing Unit, CPU), a microprocessor or a microcontroller, e.g. an application-specific integrated circuit or a digital signal processor, optionally in combination with a memory unit for storing program instructions, etc. A processor can also be a virtualized processor, a virtual machine or a soft CPU. It can also be, for example, a programmable processor that is equipped with configuration steps for carrying out the aforementioned method according to the invention or is configured with configuration steps such that the programmable processor implements the inventive features of the method, the entity, the modules or other aspects and / or sub-aspects of the invention.In particular, the processor can contain highly parallel computing units and powerful graphics modules.

[0046] In the context of the invention, a "storage unit" or "storage module" and the like can be understood to mean, for example, a volatile memory in the form of random access memory (RAM), a permanent memory such as a hard disk or a data storage device, or, for example, a removable storage module. The storage module can also be a cloud-based storage solution.

[0047] In the context of the invention, a "module" can be understood, for example, as a processor and / or a memory unit for storing program instructions. For example, the processor is specifically configured to execute the program instructions in such a way that the processor and / or the control unit performs functions to execute or implement the method according to the invention or a step of the method according to the invention.

[0048] The simulation model 350 is designed to simulate the system behavior of the entity 10 in a scenario based on input data. A scenario is a specific situation or a temporal development in which forces act on the entity 10 that trigger a specific system behavior of the entity 10, such as an impact situation in a vehicle. For example, the behavior of a crash test dummy in a vehicle during an impact can be predicted based on the parameters of a restraint system, such as an airbag. For an airbag, the thresholds for the deployment mechanism, the number of deploying airbags, and the inflation speed of the airbags can be varied. Furthermore, sensors and / or algorithms can be used to determine the necessity and exact time of deployment and enable customized deployment behavior.These sensors and algorithms are then also used as digital models in the simulation.

[0049] The simulation model 350 specifically includes neural networks trained with suitable training datasets. However, other algorithms such as gradient tree boosting can also be used to make predictions about a system's behavior.

[0050] A neural network consists of neurons arranged in several layers and connected to each other in various ways. A neuron is able to receive information at its input from outside or from another neuron, evaluate this information in a specific way, and pass it on in a modified form at the neuron's output to another neuron or output it as the final result. Hidden neurons are located between the input neurons and the output neurons. Depending on the type of network, there can be several layers of hidden neurons. They ensure the forwarding and processing of information. Output neurons finally provide a result and pass it on to the outside world. The arrangement and interconnection of the neurons gives rise to different types of neural networks, such as feed-forward networks, recurrent networks, or convolutional neural networks.The networks can be trained through unsupervised or supervised learning.

[0051] The convolutional neural network (CNN) is a special form of artificial neural network. It has multiple convolutional layers and is ideally suited for machine learning and artificial intelligence (AI) applications in the field of pattern recognition. The individual layers of the CNN are the convolutional layer, the pooling layer, and the fully connected layer. The convolutional layer is the actual convolutional layer and is capable of detecting and extracting individual features from the input data. In pattern and image recognition, these can be features such as lines, edges, or specific shapes. The input data is processed in the form of tensors such as a matrix or vectors. The pooling layer, also called the subsampling layer, condenses and reduces the resolution of the detected features using suitable filter functions. The reduced data volume increases the computing speed.Because the CNN is divided into several local, partially connected layers, it requires significantly less memory than fully connected neural networks. The training time of the convolutional neural network is also significantly shorter. By using modern graphics processors, CNNs can be trained very efficiently.

[0052] Gradient Tree Boosting (GBT) is a machine learning algorithm that combines the concepts of gradient boosting and decision trees. It is a powerful technique for solving regression and classification problems. In gradient tree boosting, the algorithm iteratively generates a set of decision trees. Each tree is constructed to correct the errors of the preceding trees in the ensemble. This minimizes a loss function by adjusting the model's predictions based on the gradient of the loss function.

[0053] For reliable prediction, regression analysis, in particular, is an important aspect of the simulation model 350. It is a procedure for estimating an unknown function from data in order to make predictions or identify patterns in the data. Regression analysis is a statistical method for finding a function that describes the relationship between a dependent variable and one or more independent variables. It is mainly used to understand and predict the value of a continuous target variable based on the values ​​of other variables. In regression analysis, the dependent variable, also called the response variable or target variable, is the variable of interest whose behavior is to be predicted.The independent variables, also called predictor variables or characteristics, are the variables that are believed to be related to the dependent variable and that can help in prediction.

[0054] The goal of regression analysis is to estimate the parameters of the regression model that best describe the relationship between the dependent variable and the independent variables. The parameters are the coefficients or weights assigned to each independent variable, which indicate the strength and direction of its influence on the dependent variable. There are different types of regression analysis, notably simple linear regression with a single independent variable, multiple linear regression with several independent variables, and polynomial regression, which accounts for nonlinear relationships.

[0055] In regression analysis, the parameters of the regression model are estimated using various statistical methods, such as ordinary least squares (OLS) or maximum likelihood estimation. Once the model is trained, it can be used to predict new input data.

[0056] The input module 200 can be integrated into a computer, a tablet, a smartphone, etc., and has a user interface 220 for entering input data 240, such as, for example, airbag parameters. The user interface 220 is designed, in particular, as a touchscreen, via which numerical values, a drawing or a diagram, and other inputs can be entered. The input module 200 can additionally have a keyboard, a microphone, and / or a camera. The touchscreen is designed, in particular, as a resistive, capacitive, or inductive system. However, other technologies can also be used. In particular, the input module 200 has an input software application 250 for entering the input data 240 for performing a simulation with the simulation model 350.

[0057] Furthermore, the input module 200 can be connected to sensors 280, which transmit measurement signals as input data 240 from a system, such as a vehicle with a dummy, to the input module 200. The sensors 280 can be configured, in particular, as pressure sensors, piezo sensors, torque sensors, rotational speed sensors, acceleration sensors, speed sensors, capacitive sensors, inductive sensors, temperature sensors, image-capturing cameras, and / or optical distance and speed measuring systems. The measurement data recorded by the sensors are images and / or data about physical or chemical processes.

[0058] Furthermore, the input module 200 and / or the simulation module 300 can be connected to at least one database 290. The term "database" refers to both a storage algorithm and the hardware in the form of a storage unit. In particular, the database 290 can be implemented as a cloud computing infrastructure.

[0059] In particular, historical data in the form of images, graphics, time series, parameters, etc. are stored in the database 290. For example, target and target values ​​that define a safety standard can be stored in the database 290. Furthermore, a digital twin of a system component of the entity 10, e.g., a pillar in a vehicle or an airbag, can be stored in the database 290. A digital twin represents a digital model in the virtual world and contains simulations and algorithms that describe the properties and behavior of an object. Additionally, simulation results from component or system simulations can be stored in the database 290.The simulations are, in particular, crash simulations with a vehicle and a dummy located in the interior, whereby simulation parameters such as the vehicle speed, the properties of the obstacle, the seating position of the dummy, the seating construction, installations in the vehicle interior, safety devices such as airbags and seat belts can vary.

[0060] The input data 240 can be further processed by the input module 200 or passed directly to the simulation module 300. In particular, coding of the input data can be provided to enable better processing of the input data 240 by the simulation module 300. For example, the input module 200 can have a transformer module with an encoder and a decoder to translate the input data into another character string. The encoder and decoder use artificial intelligence algorithms such as deep learning and machine image analysis to enable, for example, the extraction and classification of features relevant to the simulation. Deep neural networks and / or recurrent neural networks and / or convolutional neural networks are used as algorithms.In particular, attention algorithms that mimic cognitive attention and utilize convolutional neural networks are used. The transformer module is trained accordingly using training data.

[0061] If the input module 200 and the simulation module 300 are not integrated into the same computing unit, communication connections such as a CAN bus system (Controller Area Network) or wireless connections can be provided for the transmission of the input data 240. A wireless communication connection is particularly designed as a mobile radio connection and / or near-field communication connection such as Bluetooth®, Ethernet, NFC (near field communication), or Wi-Fi®.

[0062] It may be planned to equip the input module 200 with cellular modules of the 5G or 6G standard. 5G is the fifth-generation cellular standard and is characterized by higher data rates of up to 10 Gbit / sec compared to the 4G cellular standard, with higher data rates of up to 10 Gbit / sec, the use of higher frequency ranges such as 2100, 2600, or 3600 MHz, higher frequency capacity, and thus higher data throughput. Latency times are very short, ranging from a few milliseconds to less than 1 ms, enabling real-time transmission of data and calculation results.

[0063] The high data transmission speed is advantageous when cloud-based solutions are used for data processing. Cloud-based solutions offer the advantage of high and thus fast computing power. If the simulation module 300 and / or the learning reinforcement module 400 are integrated into the cloud computing infrastructure 700, the input data 240 transmitted by the input module 200 can be sent to the simulation module 300 in real time. The simulation can then be performed in the cloud computing infrastructure using the simulation model 350.

[0064] To protect communication with the cloud computing infrastructure via a mobile radio connection, cryptographic encryption methods may be provided. In particular, cryptographic encryption methods are provided for the connection between the input module 200 and the simulation module 300 and / or for the connection between the learning reinforcement module 400 and the output module 500.

[0065] The input data 240 may, at least in part, include voxel grid data formats. A voxel grid is a three-dimensional grid composed of voxels (volume elements). Each voxel represents a small portion of 3D space and contains information such as the color, material, or texture of the object located at that grid cell in space. Voxel grids are frequently used in computer graphics to calculate or simulate complex 3D scenes.

[0066] While in the finite element method (FEM), the geometry is decomposed into a mesh of finite elements, and these elements are typically represented as triangles or tetrahedra in 2D or 3D analyses, voxel grids are commonly used in voxel-based modeling and simulation techniques such as voxel-based finite difference methods or voxel-based finite volume methods. In these methods, the region of interest is discretized into a regular grid of cubic cells, called voxels. Voxel-based methods are particularly suitable for modeling complex geometries. A voxel-based approach is therefore particularly interesting for the topology optimization of the entire vehicle, as the entire geometry can be represented very homogeneously.

[0067] Although voxel-based modeling and FEM share some similarities, such as discretization and numerical analysis, they are distinct methods with distinct applications. FEM is more commonly associated with traditional network-based approaches, while voxel-based techniques are often used in areas where dynamic processes are studied, such as the analysis of flows in porous media. However, the voxel grid can be converted into a finite element mesh using various techniques to enable finite element analysis.

[0068] The simulation module 300 calculates simulation results 340 using the simulation model 350, which include a prediction of the system behavior of the entity 10 in a scenario, such as the movement of the dummy during the impact and the deformation of the vehicle in an impact situation.

[0069] According to the invention, the input data 240 and the calculated simulation results 340 are transferred to the learning reinforcement module 400. As in Fig. 2, the reinforcement learning module 400 includes a reinforcement learning agent (RV) 410, an action module 420, an environment module 430, a state module 440, and a reward module 450.

[0070] In the learning reinforcement module 400, the learning reinforcement agent 410 selects a particular state s i ∈ S from a set of available states for at least one action a i ∈ 4 from a set of available actions. For the actions a i According to the invention, the parameters p i of the input data 240. For the selected action a i the LV agent 410 receives a reward that can be positive, neutral, or negative. The states s i receives the LV agent 410 from the state module 440, which stores the states si derived from the simulation results 340. A state s i ∈ S is determined by the selection of certain parameters p i , parameter values ​​and / or properties e i of the entity 10. In addition, further data from the various sensors 280 and / or the database 290 can be processed. This processed data is assigned states s i which the LV agent 410 can access.

[0071] The choice of the selected action a i is based on a strategy or policy. For the selected action a i the agent 410 receives a reward r i ∈ ℝ from the reward module 450. The strategy, in turn, changes because it is based on the received rewards r i The strategy determines which action a i ∈ A from the set of available actions for a given state s i∈ S is to be selected from the set of available states. This creates a new state s i+1 generated, for which the LV agent 410 receives a reward r i A strategy thus defines the assignment between a state s i and an action a i and thus specifies which action to be performed a i for a state s i The goal of the LV agent 410 is to collect the achieved rewards r i to maximize.

[0072] In the action module 420, the actions selected by the LV agent 410 are i executed. By an action a i an adjustment of a parameter p i and / or a parameter value and / or a property e i of entity 10. Preferably, an action a iis one of the three actions A(+), A(0), and A(-). A positive action A(+) refers to an action that changes the value for a parameter p i increased, a neutral action A(0) is an action where the value of the parameter p i remains the same, and with a negative action A(-) the value of the parameter p i reduced.

[0073] The environment module 430 calculates based on the selected action a i and taking into account the requirements and constraints defined by the simulation results 340, the states s i . Furthermore, it may be provided that further boundary conditions, for example, regarding cost structure, energy costs, environmental impact, availability, or the delivery situation, are taken into account. These boundary conditions can be transmitted separately to the learning reinforcement module 400.

[0074] In the reward module 450, the degree of deviation Δ between the calculated value for the state s i and the target value of a target state s t a reward r i Since the degree of deviation Δ from the selection of the respective action a i depends, preferably in a matrix or a database the reward r i for the selected action a i saved. A reward r i preferably has the values ​​+1 and -1, whereby a small or positive deviation Δ between the calculated state s i and the target state s t is rewarded with +1 and thus reinforced, while a significant negative deviation Δ is rewarded with -1 and thus negatively evaluated. However, it is also conceivable that values ​​> 1 and values ​​< 1 are used. The result state is reached when the calculated states s i equal to or greater than the target state st are.

[0075] Preferably, a Markov decision process is used as the algorithm for the LV agent 410. However, it may also be provided to use a Temporal Difference Learning (TD-Learning) algorithm. The LV agent 410 with a TD-Learning algorithm adapts the actions to i not only when he receives the reward, but after each action a i based on an estimated expected reward. Furthermore, algorithms such as Q-Learning and SARSA, as well as Actor-Critic or Monte Carlo simulations, are also conceivable, allowing for dynamic programming and strategy adaptation through iterative procedures.

[0076] In addition, the LV agent 410 and / or the action module 420 and / or the environment module 430 and / or the state module 440 and / or the reward module 450 contain calculation methods and algorithms for ifor mathematical regression methods or physical model calculations that require a correlation between selected parameters p i and a target state s t describe. For the mathematical functions f i These can be statistical methods such as mean values, minimum and maximum values, lookup tables, models of expected values, linear regression methods or Gaussian processes, fast Fourier transforms, integral and differential calculus, Markov methods, probability methods such as Monte Carlo methods, temporal difference learning, but also extended Kalman filters, radial basis functions, data fields, convergent neural networks, deep neural networks, and / or feedback neural networks. Based on the actions a i and the rewards r ithe LV agent 410 and / or the action module 420 and / or the environment module 430 and / or the state module 440 and / or the bypass module 430 selects / selects for a state s i one or more of these calculation functions f i out of.

[0077] Now a second cycle begins to optimize the parameters p i and / or parameter values ​​and / or properties e i of the entity 10. Here, the LV agent 410 can perform another action i+1 and / or another calculation function f i+1 and / or another parameter p i+1 select according to the specified strategy or policy. The result is again fed to the state module 440, and the result of the comparison is evaluated in the reward module 450. The LV agent 410 repeats the optimization process for all planned actions a i , calculation functions f i and parameter p i, until the greatest possible agreement between a calculated state s i and a target state s t is reached. Preferably, the result state of the optimization of entity 10 is reached when the deviation Δ is in the range of + / - 5%. The LV agent 410 thus optimizes its behavior and thus the strategy with which an action a i is selected until the calculated states s i converge. The optimized result of the design of entity 10 by modified parameters p i and / or parameter values ​​and / or properties e i is output in the form of output data 550 by the output module 500.

[0078] In the optimized result state, the optimized values ​​for the parameters p i and / or parameter values ​​and / or properties e iof entity 10 are defined, with which a specific behavior of entity 10, such as a specific safety criterion in the event of a collision between a vehicle and a dummy, can be achieved. If, for example, the simulation of the simulation model 350 has shown that the acceleration acting on a dummy head in the event of an impact is too great, the parameters p i and / or parameter values ​​and / or properties e i of the entity 10 is modified and adjusted by the learning reinforcement module 400 until an acceptable acceleration value is reached.

[0079] In a further development, it can be provided that the simulation module 300 is used only for pre-training the learning reinforcement module 400. In this case, the environment module 430 of the learning reinforcement module 400 has simulation software 435, which is particularly designed for conducting finite element simulations. The results of the finite element simulation are then fed directly to the state module 440, which uses them to determine the corresponding states. i which the learning reinforcement agent 410 can access.

[0080] The pre-trained learning reinforcement module 400 is thus used according to the invention to solve similar optimization tasks. For example, the weight of a dummy can be varied. If the learning reinforcement module 400 was trained with a dummy with a body weight of 90 kg, the restraint system can now be optimized for a dummy with a body weight of 55 kg without the need to calculate simulation results 340 by the simulation module 300. In this case, the suggestions of the RV agent 410 are recalculated directly by the simulation software 435 of the environment module 430 to determine new states s i .

[0081] The output module 500 is configured to output the optimized results in the form of output data 550. The output module 500 can also be integrated into a hardware device such as a computer, a tablet, a smartphone, etc., wherein, in particular, the hardware device for the input module 200 and the hardware device for the output module 500 can be identical.

[0082] The optimized results in the form of output data 550 can be output directly by the output module 500. However, it can also be provided that the output module 500 has an output transformer module that translates the optimized results calculated by the learning reinforcement agent 400 into a user-accessible data format. The data formats can be, for example, design plans, images and graphics, video sequences, acoustic sequences, holograms, key figures, diagrams, mathematical formulas, PowerPoint presentations, etc. For this purpose, the output transformer module can also have at least one encoder and one decoder, or encoders and decoders connected in series.

[0083] In particular, it can be provided that the calculation results are stored in the form of states, actions, rewards, and strategies in the cloud computing infrastructure and are each available via the Internet. The LV agent 410, the action module 420, the environment module 430, the state module 440, and the reward module 450 have the necessary technical interfaces and protocols for accessing the cloud computing infrastructure. This can increase computing efficiency because the access options and speeds to previously calculated states, actions, rewards, and strategies are simplified.

[0084] Since a fast calculation result is often desired, the computing speed is crucial for the numerous computing operations in the simulation module 300 and the learning reinforcement module 400. To enable the computing operations to be performed in real time, the use of cloud computing infrastructure is advantageous, as this ensures fast calculation.

[0085] In a further development, the system 100 according to the invention can also be used for multifunctional geometry optimization, in particular of a vehicle. For example, different geometric stiffness requirements arise for a side impact than for a frontal impact or a rear impact. Through mutual optimization, an optimal solution can be found with the aid of the learning reinforcement algorithm 410, which covers a large number of scenarios in such a way that an optimal holistic result is found. It is also possible to weight the probabilities of the various impact scenarios, e.g., using key performance indices (KPIs), and to take this weighting into account when calculating the optimization parameters by the learning reinforcement agent 410.

[0086] For multifunctional geometry optimization, standardized data formats based on finite elements, in particular voxel grids or parameters, are used as input data 240 for the environment module 430. In addition, the environment module 430 comprises at least one neural network for processing the standardized data formats based on finite elements, in particular voxel grids or parameters, since this network is particularly suitable for learning relationships in high-dimensional data.

[0087] In Fig. 3 shows the method steps for improving the system behavior of a technical entity 10 in a scenario, such as in particular a vehicle in a driving situation.

[0088] In a step S10, a simulation model 350 is used to simulate the system behavior of the technical entity 10 in a simulation scenario and to train the simulation model 350 with training data sets, wherein the data of the training data sets contain measurement signals from sensors 280.

[0089] In a step S20, input data 240 are provided via a user interface 220 or from a database 290, wherein the input data 240 contains parameters p i , parameter values ​​and / or properties e i of entity 10 for a specific simulation task such as the system behavior in a specific scenario.

[0090] In a step S30, a simulation is performed using the input data 240 and the trained simulation model 450 by a simulation module 400 for the simulation task.

[0091] In a step S40, simulation results 340 are generated, wherein the simulation results 340 reflect the system behavior of the entity 10 in the simulation scenario.

[0092] In a step S50, the simulation results 340 are passed on to a learning reinforcement module 400.

[0093] In a step S60, modeled values ​​for the parameters p i , parameter values ​​and / or properties e i of the entity from the simulation results to achieve an improved system behavior of the entity 10 in the simulation scenario.

[0094] In a step S70, output data 550 are generated and output by an output module 500, wherein the output data 550 contains optimized results, in particular in the form of the modeled values ​​for the parameters p i , parameter values ​​and / or properties e i of entity 10.

[0095] Fig.4 schematically illustrates a computer program product 900 comprising executable program code 950 configured to perform the method according to the first aspect of the present invention.

[0096] The invention enables parameters, parameter values, and / or properties of an entity, such as a restraint system in a vehicle, to be optimized with regard to system behavior in a specific scenario, such as a collision situation. By coupling a pre-trained simulation model with a learning reinforcement module, optimized values ​​for parameters, parameter values, and / or properties of the entity can be calculated without having to run numerous simulations, each with modified simulation data. Since, for example, the system behavior of a vehicle with a dummy in the interior is complex and highly non-linear, it is difficult for an engineer to decide which parameters, parameter values, and / or properties should be changed, and to what extent, in order to achieve acceptable system behavior of the entity, such as the vehicle.

[0097] The invention therefore enables the determination of an optimal configuration of parameters, parameter values, and / or properties of an entity for system behavior in a specific scenario, so that only fine-tuning of the parameters, parameter values, and / or properties is required in subsequent simulations. This reduces the need for a large number of simulations, saving computing time and thus costs and energy. In particular, a pre-trained simulation model can be used to implement finite element methods directly in a learning reinforcement module. The invention can thus contribute to increasing and improving the safety and performance of an entity. Reference symbol 10 Entity 100 systems 200 input module 220 User Interface 240 input data 250 input software application 280 sensors 290 database 300 simulation module 340 simulation results 350 simulation model 400 Learning Reinforcement Module 410 Learning reinforcement agent 420 Action Module 430 Environment module 435 Software application 440 State module 450 Reward Module 500 output module 550 output data 900 Computer program product 950 program code QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] US 6 850 821 B1

[0011] DE 10 202020 128 881 A1

[0012] EP 4 060 443 A1

[0013]

Claims

[1] Method for improving the system behavior of a technical entity (10) in a scenario, such as in particular a vehicle in a driving situation, comprising: - generating (S10) a simulation model (350) for simulating the system behavior of the technical entity (10) in a simulation scenario and training the simulation model (350) with training data sets, wherein the training data sets contain measurement signals from sensors (280); - Providing (S20) input data (240) via a user interface (220) or from a database (290), wherein the input data (240) comprises parameters (p i ), parameter values ​​and / or properties (e i ) of the entity (10) for a specific simulation task such as the system behavior in a specific scenario; - performing (S30) a simulation using the input data (240) and the trained simulation model (450) from a simulation module (400) for the simulation task; - generating (S40) simulation results (340), wherein the simulation results (340) reflect the system behavior of the entity (10) in the simulation scenario; - passing (S50) the simulation results (340) to a learning reinforcement module (400); - Calculate (S60) modeled values ​​for the parameters (p i ), parameter values ​​and / or properties (e i ) of the entity (10) from the simulation results (340) to achieve an improved system behavior of the entity (10) in the simulation scenario; - generating and outputting (S70) output data (550) by an output module (500), wherein the output data (550) contain optimized results, in particular in the form of the modeled values ​​for the parameters (p i), parameter values ​​and / or properties (e i ) of the entity (10). [2] The method of claim 1, wherein the learning reinforcement module (400) comprises at least one learning reinforcement agent (410), an action module (420), an environment module (430), a state module (440), and a reward module (450). [3] Method according to claim 1 or 2, wherein a state (s i ) of the entity (10) is determined by the state module (440), wherein a state (s i ) by parameter (p i ) and / or parameter values ​​and / or a property (e i ) of the entity (10) is determined. [4] Method according to one of claims 1 to 3, wherein the simulation model (350) uses at least one neural network, in particular recurrent neural networks or convolutional neural networks or gradient tree boosting, as algorithm. [5] Method according to one of claims 1 to 4, wherein the reinforcement learning algorithm of the learning reinforcement module (400) is designed as a Markov decision process or as Temporal Difference Learning (TD-Learning) or as Q-Learning or as SARSA or as Monte Carlo simulation or as Actor-Critic or as Proximal Policy Optimization. [6] Method according to one of claims 1 to 5, wherein at least one parameter (p i ) and / or a parameter value and / or a property (e i) of the entity (10) represents a position, a dimension, a material, a shape, a characteristic value, a measured value, a safety factor, a speed, an acceleration, a force, a torque, a speed, a state of charge, a specific fuel consumption, a thermal resistance, an electrical resistance, a conductivity, a strength, a fracture behavior, a density, a plastic deformation, a stress, pressure, bending resistance, a material property or a surface property. [7] Method according to one of claims 2 to 6, wherein a calculation function (f i ) and / or an action (̇a i ) based on a policy for the condition (s i ) is selected for the modification of at least one parameter (p i ) and / or a parameter value and / or a property (e i) of the entity (10) from the learning reinforcement agent (410); wherein a new state (s i+1 ) from the environment module (430) based on the modified value for the parameter (p i ) and / or the parameter value and / or the property (e i ) is calculated; where the new state (s i+1 ) with a target state (s t ) and a deviation (Δ) for a comparison result is calculated in the state module (440); wherein a reward (r i ) is determined by the reward module (450) for the comparison result; and wherein the states (s i ) and / or actions (a i ) until the target state (s t ) is reached. [8] Method according to one of claims 1 to 7, wherein the output data (550) contain design plans, images and graphics, video sequences, acoustic sequences, holograms, key figures, diagrams, mathematical formulas and / or Power Point presentations, etc. [9] Method according to one of claims 2 to 8, wherein the environment module (430) comprises a software application (435) for simulating the system behavior of the entity (10) by means of a finite element method and the results of the FEM simulation are forwarded directly to the state module (440). [10] The method according to any one of claims 1 to 9, wherein the learning reinforcement module (400) performs a multifunctional geometry optimization through a plurality of iterations. [11] System (100) for improving the system behavior of a technical entity (10) in a scenario, such as in particular a vehicle in a driving situation, comprising an input module (200), a simulation module (300), a learning reinforcement module (400) and an output module (500), wherein the simulation module (300) is designed to generate a simulation model (350) for simulating the system behavior of the technical entity (10) in a simulation scenario by training with training data sets, wherein the data of the training data sets contain measurement signals from sensors (280); wherein the input module (200) is designed to provide input data (240) via a user interface (220) or from a database (290), wherein the input data (240) in particular contain parameters (p i ), parameter values ​​and / or properties (e i) of the entity (10) for a specific simulation task, such as the system behavior in a specific scenario; wherein the simulation module (300) is designed to perform a simulation using the input data (240) and the trained simulation model (450) for the simulation task and to generate simulation results (340), wherein the simulation results (340) reflect the system behavior of the entity (10) in the simulation scenario; wherein the learning reinforcement module (400) is designed to derive modeled values ​​for the parameters (p i ), parameter values ​​and / or properties (e i) of the entity (10) to achieve an improved system behavior of the entity (10) in the simulation scenario; wherein the output module (500) is designed to generate and output output data (550), wherein the output data (550) contain optimized results, in particular in the form of the modeled values ​​for the parameters (p i ), parameter values ​​and / or properties (e i ) of the entity (10). [12] System (100) according to claim 11, wherein the learning reinforcement module (400) comprises at least one learning reinforcement agent (410), an action module (420), an environment module (430), a state module (440) and a reward module (450), and wherein the environment module (430) comprises a software application (435) for simulating the system behavior of the entity (10) by means of a finite element method and the results of the FEM simulation are forwarded directly to the state module (440). [13] System (100) according to claim 11 or 12, wherein the simulation model (350) uses at least one neural network, in particular recurrent neural networks or convolutional neural networks, or gradient tree boosting as algorithm. [14] System (100) according to one of claims 11 to 13, wherein at least one parameter (p i ) and / or a parameter value and / or a property (e i) of the entity (10) represents a position, a dimension, a material, a shape, a characteristic value, a measured value, a safety factor, a speed, an acceleration, a force, a torque, a speed, a state of charge, a specific fuel consumption, a thermal resistance, an electrical resistance, a conductivity, a strength, a fracture behavior, a density, a plastic deformation, a stress, pressure, bending resistance, a material property or a surface property. [15] A computer program product (900) comprising an executable program code (950) configured to carry out the method according to any one of claims 1 to 10 when executed.

Images