Parameter determination method and device, equipment and storage medium

Abstract

The invention relates to a parameter determination method and device, equipment and a storage medium, and relates to the technical field of vehicles. The method comprises the following steps: determining a value range, an objective function and a constraint condition of a plurality of to-be-optimized parameters of the instrument board; the minimum mass, the maximum modal frequency and the minimum head collision acceleration of the instrument board serve as objective functions, the stress threshold value, the deformation threshold value and the modal frequency threshold value of the instrument board under the rigidity and strength working condition serve as constraint conditions, and one to-be-optimized parameter is used for representing one to-be-optimized part parameter or one to-be-optimized area parameter. And determining a target value of each to-be-optimized parameter according to the value range of the plurality of to-be-optimized parameters, the trained neural network model, the target function and the constraint condition. Therefore, the efficiency of determining the parameters of the instrument board is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, in particular to the field of instrument panel technology, and specifically to a parameter determination method, device, equipment and storage medium. Background Art

[0002] With the development of automobile technology, higher requirements are placed on the safety, functionality and comfort of dashboards. Sufficient rigidity and strength can ensure that the dashboard maintains a stable shape under various working conditions and avoids deformation or damage due to vehicle vibration, impact and other factors. Good performance can reduce noise and vibration in the car, creating a quiet and comfortable environment for drivers and passengers. At the same time, with the development of the automobile industry and the improvement of environmental protection requirements, automobile dashboards need to meet lightweight requirements. Lightweighting can not only reduce the overall weight of the vehicle, improve fuel economy, reduce exhaust emissions, and comply with the concept of sustainable development, but also a lighter dashboard can help improve vehicle handling and acceleration performance.

[0003] At present, in the design of automobile instrument panels, in order to ensure the performance of rigidity, modality and safety, the calculation conditions are built according to the performance requirements by using the finite element simulation model, and finally the weak links and potential problems in the instrument panel structure are identified by analyzing the finite element simulation results, and optimization measures are taken, such as adjusting the material distribution, changing the structural shape, adding reinforcement ribs, etc. for optimization and iteration. However, due to the large number of instrument panel parameters and the low simulation efficiency of the finite element simulation model, the efficiency of determining the parameters of the automobile instrument panel using the finite element simulation model is low. Summary of the invention

[0004] The present application provides a parameter determination method, device, equipment and storage medium to improve the efficiency of determining instrument panel parameters. The technical solution of the present application is as follows:

[0005] According to the first aspect provided by the present application, a parameter determination method is provided, the method comprising: determining the value ranges, objective functions and constraints of multiple configuration parameters of the instrument panel. The objective functions are to minimize the mass, maximize the modal frequency and minimize the head-impact acceleration of the instrument panel, and the stress threshold, deformation threshold and modal frequency threshold of the instrument panel under the rigidity and strength conditions are used as constraints. A configuration parameter is used to characterize a part parameter to be optimized or a region parameter to be optimized. According to the value ranges of multiple configuration parameters, the trained neural network model, the objective function and the constraints, the target value of each configuration parameter is determined.

[0006] According to the above technical means, the target value of each configuration parameter is determined according to the value ranges of multiple configuration parameters, the trained neural network model, the objective function and the constraints. In this way, the simulation results of the dashboard are simulated by the neural network model. Since the neural network model can quickly obtain the simulation results, the target value can be quickly obtained from the value range, thereby improving the efficiency of determining the parameters of the dashboard.

[0007] In one possible way, the target value of each configuration parameter is determined according to the value ranges of multiple configuration parameters, the trained neural network model, the objective function and the constraints, including: inputting the candidate value of each configuration parameter into the trained neural network model to obtain simulation data. The simulation data includes modal frequency, head impact acceleration and deformation value of the instrument panel under stiffness and strength conditions. The candidate value of each configuration parameter is any value in the value range of each configuration parameter. The target value of each configuration parameter is determined according to the simulation data, the objective function, the constraints and the non-dominated sorting genetic algorithm.

[0008] According to the above technical means, the target value is determined by a non-dominated sorting genetic algorithm. Since the non-dominated sorting genetic algorithm can quickly find the target value, the computing power of the electronic device can be saved.

[0009] In one possible manner, determining the value ranges of multiple configuration parameters of the dashboard includes: simulating initial data of the dashboard according to a finite element pre-processing model to obtain simulation results, determining multiple configuration parameters according to the simulation results, and determining the value range of each configuration parameter in response to a configuration operation on each configuration parameter.

[0010] According to the above technical means, the finite element pre-processing model is used for simulation, the simulation results are obtained, and multiple configuration parameters are determined according to the simulation results. In this way, the area to be optimized and the value range of the configuration parameters of the area to be optimized can be accurately determined.

[0011] In one possible manner, the plurality of configuration parameters include parameters of the region to be optimized, and the plurality of configuration parameters are determined according to the simulation results, including: determining the region to be optimized according to the simulation results, and using the parameters of the region to be optimized as the configuration parameters. The region to be optimized includes a first region whose variable energy density is greater than or equal to a density threshold, a second region whose deformation value is greater than or equal to a deformation threshold, or a third region whose corresponding acceleration is greater than or equal to an acceleration threshold.

[0012] In a possible manner, the method further includes: obtaining a training sample data set according to the value ranges of the multiple configuration parameters and the finite element pre-processing model, and training the initial neural network model according to the training sample data set to obtain a trained neural network model.

[0013] In one possible manner, a training sample data set is obtained according to the value ranges of multiple configuration parameters and a finite element pre-processing model, including: sampling the value range of each configuration parameter according to Latin hypercube sampling to obtain multiple data combinations, and inputting each data combination in the multiple data combinations into the finite element pre-processing model to obtain simulation data of each data combination. Each data combination and the simulation data corresponding to each data combination are used as a training sample to obtain a training sample data set.

[0014] According to the above technical means, a Latin hypercube sampling algorithm is used to sample the value range of each configuration parameter to obtain multiple data combinations, so that the data combinations of multiple configuration parameters can be quickly determined.

[0015] In one possible approach, the plurality of configuration parameters include the coordinates of the center of mass of the display screen in the instrument panel, its mass, and the thickness of a bracket connected to the instrument panel.

[0016] According to the second aspect provided by the present application, a parameter determination device (60) is provided, and the parameter determination device (60) includes: a determination unit (601). The determination unit (601) is used to determine the value ranges, objective functions and constraints of multiple configuration parameters of the instrument panel. Taking the minimum mass, maximum modal frequency and minimum head impact acceleration of the instrument panel as the objective function, and taking the stress threshold, deformation threshold and modal frequency threshold of the instrument panel under the rigidity and strength conditions as the constraints, a configuration parameter is used to characterize a part parameter to be optimized or a region parameter to be optimized. The determination unit (601) is also used to determine the target value of each configuration parameter based on the value ranges of multiple configuration parameters, the trained neural network model, the objective function and the constraints.

[0017] In one possible manner, the determination unit (601) is specifically used to: input the candidate value of each configuration parameter into the trained neural network model to obtain simulation data. The simulation data includes modal frequency, head impact acceleration, and deformation value of the instrument panel under stiffness and strength conditions. The candidate value of each configuration parameter is any value in the value range of each configuration parameter. According to the simulation data, the objective function, the constraint conditions, and the non-dominated sorting genetic algorithm, the target value of each configuration parameter is determined.

[0018] In one possible manner, the determination unit (601) is specifically configured to: simulate the initial data of the dashboard according to the finite element pre-processing model to obtain simulation results, determine multiple configuration parameters according to the simulation results, and determine the value range of each configuration parameter in response to the configuration operation on each configuration parameter.

[0019] In one possible manner, the plurality of configuration parameters include parameters of a region to be optimized, and the determination unit (601) is used to: determine the region to be optimized according to the simulation result, and use the parameters of the region to be optimized as the configuration parameters. The region to be optimized includes a first region whose variable energy density is greater than or equal to a density threshold, a second region whose deformation value is greater than or equal to a deformation threshold, or a third region whose corresponding acceleration is greater than or equal to an acceleration threshold.

[0020] In a possible manner, the parameter determination device (60) further includes: a processing unit (602). The processing unit (602) is used to obtain a training sample data set according to the value ranges of the multiple configuration parameters and the finite element pre-processing model. The processing unit (602) is also used to train the initial neural network model according to the training sample data set to obtain a trained neural network model.

[0021] In one possible manner, the processing unit (602) is specifically configured to: sample the value range of each configuration parameter according to Latin hypercube sampling to obtain multiple data combinations, and input each data combination of the multiple data combinations into a finite element pre-processing model to obtain simulation data of each data combination. Each data combination and the simulation data corresponding to each data combination are used as a training sample to obtain a training sample data set.

[0022] In one possible approach, the plurality of configuration parameters include the coordinates of the center of mass of the display screen in the instrument panel, its mass, and the thickness of a bracket connected to the instrument panel.

[0023] According to a third aspect provided by the present application, an electronic device is provided, comprising: a memory (702) and a processor (701); the memory (702) and the processor (701) are coupled. The memory (702) is used to store computer program code, and the computer program code includes computer instructions. When the processor (701) executes the computer instructions, the electronic device executes the method in the first aspect and any possible implementation method thereof.

[0024] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of a processing device, the processing device is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0025] According to the fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on a processing device, the processing device executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0026] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0027] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0029] Figure 1 is a structural schematic diagram of a parameter determination system according to an exemplary embodiment;

[0030] Figure 2 is one of the flowchart diagrams of a parameter determination method according to an exemplary embodiment;

[0031] Figure 3 is a second flow chart of a parameter determination method according to an exemplary embodiment;

[0032] Figure 4 is a third flow chart of a parameter determination method according to an exemplary embodiment;

[0033] Figure 5 is a block diagram of a parameter determination device according to an exemplary embodiment;

[0034] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0035] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0037] As described in the background technology, in the design of the instrument panel, a finite element simulation model is established based on the three-dimensional data of the instrument panel, and a calculation condition is established according to the performance requirements of the instrument panel. Further, by analyzing the finite element simulation results, the weak links and potential problems in the structure of the instrument panel are determined, and optimization measures are taken, such as adjusting the material distribution, changing the structural shape, adding reinforcement ribs, etc. for optimization and iteration. However, due to the numerous calculation conditions through the finite element simulation model, the complex structure of the parts, and the numerous optimization parameters, the efficiency of determining the parameters of the automobile instrument panel using the finite element simulation model is low. In order to solve the above technical problems, the present application provides a parameter determination method, the method comprising: determining the value range, objective function and constraint conditions of multiple configuration parameters of the instrument panel; taking the minimum mass, maximum modal frequency and minimum head impact acceleration of the instrument panel as the objective function, taking the stress threshold, deformation threshold and modal frequency threshold of the instrument panel under the rigidity and strength condition as the constraint condition, and a configuration parameter is used to characterize a part parameter to be optimized or a region parameter to be optimized. According to the value range of multiple configuration parameters, the trained neural network model, the objective function and the constraint conditions, the target value of each configuration parameter is determined.

[0038] In this way, the target value of each configuration parameter is determined according to the value range of multiple configuration parameters, the trained neural network model, the objective function and the constraint conditions. In this way, the simulation results of the dashboard are simulated by the neural network model. Since the neural network model can quickly obtain the simulation results, the target value can be quickly obtained from the value range, thereby improving the efficiency of parameter determination of the dashboard.

[0039] like Figure 1 As shown, Figure 1 A parameter determination system 100 is provided in an embodiment of the present application. The parameter determination method system 100 may include an electronic device 101 and a parameter determination device 102 .

[0040] The electronic device 101 is used to determine the value ranges, objective functions and constraints of multiple configuration parameters of the instrument panel. The objective functions are to minimize the mass, maximize the modal frequency and minimize the head-impact acceleration of the instrument panel, and the stress threshold, deformation threshold and modal frequency threshold of the instrument panel under the rigidity and strength conditions are used as constraints. A configuration parameter is used to characterize a part parameter to be optimized or a region parameter to be optimized. The electronic device 101 is used to determine the target value of each configuration parameter based on the value ranges of multiple configuration parameters, the trained neural network model, the objective function and the constraints.

[0041] It should be noted that the electronic device 101 and the parameter determination device 102 in the embodiment of the present application may be the same device or different devices, and the embodiment of the present application does not limit this.

[0042] For ease of understanding, the parameter determination method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0043] Figure 2 According to an exemplary embodiment, a flow chart of a parameter determination method is shown as follows: Figure 2 As shown, the parameter determination method includes: S201-S202.

[0044] S201. Determine value ranges, objective functions, and constraints of multiple configuration parameters of the dashboard.

[0045] Among them, the objective function is to minimize the mass of the dashboard, maximize the modal frequency, and minimize the head impact acceleration. The stress threshold, deformation threshold, and modal frequency threshold of the dashboard under the stiffness and strength conditions are used as constraints. A configuration parameter is used to characterize a part parameter to be optimized or a region parameter to be optimized.

[0046] In some embodiments, the electronic device determines the value ranges of the multiple configuration parameters in response to the user's configuration of the multiple configuration parameters. Further, the electronic device determines the objective function of the dashboard in response to the configuration operation of the objective function, and determines the constraint conditions of the dashboard in response to the configuration operation of the constraint conditions.

[0047] In some embodiments, the plurality of configuration parameters include parameters of the plurality of regions and parameters of the part.

[0048] For example, a configuration parameter may be the height, thickness or distance of the region to be optimized. For another example, a configuration parameter may be the mass or thickness of the part to be optimized.

[0049] Exemplarily, the electronic device determines multiple areas to be optimized and parts to be optimized, and obtains the value range of the thickness of the area to be optimized in response to the configuration parameters of the value range of the thickness of each area to be optimized, and obtains the value range of the mass of the part to be optimized in response to the configuration parameters of the value range of the mass of the part to be optimized. Specifically, multiple areas are areas to be optimized. Determine the area to be optimized: In the case of modal analysis of the instrument panel assembly, since the area with higher strain energy density plays an important role in the dynamic response of the instrument panel structure, the area with higher strain energy density is determined as the first area to be optimized. Rigidity and head impact conditions are determined according to stress and strain conditions: in the rigidity analysis, the stress concentration area and the area with deformation greater than the preset deformation threshold are taken as the second area to be optimized; in the head impact condition analysis, the acceleration response is greater than the speed threshold and the area that may affect the safety of the occupants is taken as the third area to be optimized. Subsequently, the parameters of the first area to be optimized, the parameters of the second area to be optimized, and the parameters of the third area to be optimized are added to the multiple configuration parameters.

[0050] In the embodiments of the present application, strain energy density may also be referred to as deformation energy density, which is used to characterize the deformation energy contained in a unit volume after the elastic body is deformed.

[0051] For example, in the upper and lower bodies of the instrument panel, the first area to be optimized, the second area to be optimized, and the third area to be optimized are selected respectively, and the rib features in the areas to be optimized are analyzed. The distance (density) d, height h, and thickness t of the ribs are respectively used as configuration parameters using finite element pre-processing software (such as the Morph mesh deformation technology of the automatic net-generation for structural analysis (ANSA)). On the instrument panel crossbeam, the thickness of the bracket connecting the instrument panel body tC1~14 is used as a configuration parameter. The value range of the configuration parameters can be: d1, d2, and d3∈[5mm,15mm], h1, h2, and h3∈[0mm,5mm], t1, t2, and t3∈[0mm,1.5mm], tC1-14∈[1mm,3mm]. Among them, 1-3, is the first area to be optimized to the third area to be optimized. tC1-14 represent 14 brackets connected to the instrument panel body, such as: tC1 is the first bracket, tC12 is the twelfth bracket, and tC14 is the fourteenth bracket.

[0052] In addition, according to the displacement cloud diagram of the first-order mode vibration shape of the instrument panel, the display screen has a greater influence on the mode of the instrument panel assembly. Therefore, in the calculation model, the display screen adopts a simplified model and adds mass points for modeling. Therefore, the center of mass coordinates and mass of the display screen are also used as configuration parameters. The value range of the configuration parameters can be: the center of mass coordinates are in the xz plane 20mm 2 The display quality fluctuation value is within the range of dx∈[-10mm,10mm] and dy∈[-10mm,10mm], and the display quality fluctuation value is dm∈[-0.3kg,0.3kg]. Among them, dx is the value of the center of mass coordinate x, and dy is the value of the center of mass coordinate y. dm is the display quality fluctuation value. For example, if the initial value of the display is M, the quality of the display is m∈[M-0.3,M+0.3].

[0053] At the same time, according to the stress / displacement cloud diagram results of head impact and stiffness, the thickness of the upper and lower bodies of the instrument panel is considered as a configuration parameter, and the value range of the configuration parameter can be: tA∈[2mm,3mm], tB∈[2mm,3mm]. Among them, tA can be the thickness of the lower body of the instrument panel, and tB can be the thickness of the upper body of the instrument panel.

[0054] S202: Determine a target value for each configuration parameter according to the value ranges of the multiple configuration parameters, the trained neural network model, the objective function, and the constraints.

[0055] In some embodiments, the electronic device takes a value for each configuration parameter according to the value range of each configuration parameter to obtain a candidate value for each configuration parameter, and inputs the candidate value for each configuration parameter into a trained neural network model to obtain a simulation result. Further, the electronic device determines a target simulation result according to multiple simulation results, an objective function, and constraints, and determines the candidate value corresponding to the target simulation result as the target value.

[0056] In some embodiments, the electronic device inputs the candidate value of each configuration parameter into a trained neural network model to obtain simulation data; the simulation data includes modal frequency, head impact acceleration, and deformation value of the instrument panel under rigidity conditions; the candidate value of each configuration parameter is any value in the value range of each configuration parameter. Further, the electronic device determines the target value of each configuration parameter based on the simulation data, the objective function, the constraint conditions, and the non-dominated sorting genetic algorithm.

[0057] Subsequently, the electronic device outputs the target value after determining the target value of each configuration parameter to instruct the developer to configure the dashboard according to the target value.

[0058] It should be noted that the neural network model in the embodiments of the present application may be a convolutional neural network model, a deep learning model, a recurrent neural network model or a BP (back propagation) neural network model, and the embodiments of the present application do not make any specific limitations on this.

[0059] In one possible design, the above S202 includes: S2021-S2022.

[0060] S2021. Input the candidate numerical value of each configuration parameter into the trained neural network model to obtain simulation data.

[0061] The simulation data include modal frequency, head impact acceleration and deformation value of the instrument panel under stiffness and strength conditions; the candidate value of each configuration parameter is any value within the value range of each configuration parameter.

[0062] S2022. Determine the target value of each configuration parameter according to the simulation data, the objective function, the constraints and the non-dominated sorting genetic algorithm.

[0063] Specifically, according to the trained neural network model, a multi-objective optimization solution is performed with the minimum mass of the instrument panel assembly, the rigidity and strength performance, and the acceleration requirements of the head-impact working condition as the optimization objective function.

[0064] On the basis that the accuracy of the prediction model meets the requirements, the optimization objective function is to minimize the mass of the instrument panel assembly, maximize the first-order modal frequency, and minimize the 3ms acceleration of the head impact. The maximum stress, maximum deformation and first-order frequency under the stiffness and strength conditions are used as constraints, and the design variables determined in step three are used as optimization parameter design variables.

[0065] In the embodiment of the present application, a non-dominated sorting genetic algorithm (NSGA) with an elite strategy is used to solve the model, obtain the Pareto frontier of lightweight design, and select the optimal solution as the design optimization combination, such as Figure 3 As shown, including: S301-S310.

[0066] S301. Randomly initialize the population.

[0067] In some embodiments, a combination of initial configuration parameters is used as an initial population P0 of the algorithm to perform non-dominated sorting of individuals in the population.

[0068] S302: Calculate the congestion degree.

[0069] In some embodiments, the crowding degree of each non-dominated layer individual is calculated and ranked.

[0070] S303: Generate a progeny population.

[0071] In some embodiments, selection, crossover and mutation operations are performed on the initial population P0 to obtain a first-generation subpopulation Q0.

[0072] In some embodiments, the elite retention strategy is implemented at the beginning of the second generation, the initialized parent population P0 and the child population Q0 are merged to form a new population R0, and all individuals in R0 are non-dominated. Further, the crowding degree of each non-dominated layer individual is calculated and arranged, and the best N individuals are retained as the new parent population PN+1.

[0073] S304: Update the number of iterations.

[0074] In some embodiments, the iteration number is updated. For example, the iteration number Gen = gen + 1. Gen is the current calculation number, and Gen is the updated technical number.

[0075] S305, selection, crossover and mutation.

[0076] In some embodiments, selection, crossover, and mutation operations are performed on the best parent population PN+1.

[0077] S306, merge the father and son generations.

[0078] In some embodiments, the parent population and the child population are merged to form a new population.

[0079] S307, fast non-dominated sort.

[0080] In some embodiments, a non-dominated sort is performed on all individuals in the new population.

[0081] S308: Determine the congestion degree.

[0082] In some embodiments, the crowding degree of each non-dominated layer individual is calculated and ranked.

[0083] S309: Determine whether the number of iterations is greater than or equal to a threshold number.

[0084] If yes, then execute S310. If no, then execute S304.

[0085] It should be noted that the number threshold is pre-set in the electronic device by the operation and maintenance personnel, and the embodiment of the present application does not specifically limit the number threshold.

[0086] S310: Determine a target value for each configuration parameter.

[0087] For example, when the number of iterations Gen reaches the set maximum value Genmax, the calculation is terminated and the current configuration parameters are used as the target values.

[0088] In another case, the electronic device calculates the asymptotically dominated number of the individual xai in the a-th generation population Ra while determining the objective function and constraints. Furthermore, the population Ra is sorted according to whether the asymptotically dominated number is zero; individuals are selected from the sorted population as the parent population of the next generation; the objective function of each individual in the next generation population Ra+1 generated by the next generation parent population is calculated, and is used to output a new parent population until the iteration termination condition is met, and the final population is output to obtain the optimization result. Wherein, a is a natural number greater than 0. The numerical value in the objective function is obtained according to the trained neural network model.

[0089] In one possible design, the above S201 includes: S2011-S2013.

[0090] S2011. Simulate the initial data of the dashboard according to the finite element pre-processing model to obtain simulation results.

[0091] In this embodiment, based on the assembly data of the instrument panel, the finite element pre-processing model ANSA is used to perform geometric cleaning on the three-dimensional entity of the instrument panel and extract the mid-surface of the thin-walled parts. For example, the mesh is divided into shell units, the average mesh size is 5 mm, the total number of model units is 642987, the total number of nodes is 590512, the number of shell units is 577810, and the number of rigid units is 1194. In addition, the proportion of failed units such as warping angle, distortion, and Jacobi in the mesh model is less than 0.5%. In addition, according to the preset material model, the elastic modulus, density, Poisson's ratio, plastic segment curve, etc. of each material are set; the instrument panel can be installed with bolts and the car body. At the installation position in the model of the instrument panel, the first target constraint DOF1-6 is added, and at the front end area of ​​the instrument panel body, at the bayonet connection position with the front panel metal, the second target constraint DOF3-5 is added, and the constraint is applied to the main node of the RBE2 unit of the finite element pre-processing software.

[0092] For the modal condition of the instrument panel, the Nastran solver of the finite element pre-processing model was used for calculation, and the EIGRL card was set to extract the first 10 modal frequencies;

[0093] For the rigidity and strength conditions, the Abaqus solver of the finite element pre-processing model is used for calculation. Specifically, the dashboard is divided into easy-to-touch areas, general touch areas, and difficult-to-touch areas, and different sizes of indenters are established to load 50N / 100N two conditions. The loading direction can be normal, and the deformation and stress cloud diagrams of different areas are set to output.

[0094] For head-on collision conditions, for example, a 6.8 kg rigid pendulum model is established, and the impact speed is set to 24.1 km / h (km / h), the direction is the pendulum impact direction, and the collision point is selected in the head-impactable area of ​​the driver and co-driver. The Ls-dyna solver of the finite element pre-processing model is used for calculation to obtain the acceleration curve of the pendulum, and the 3ms acceleration value is further obtained through the post-processing tool (satisfying the maximum acceleration threshold of the continuous curve segment with a duration equal to 3ms).

[0095] Subsequently, the calculated simulation results, such as the first-order modal frequency, displacement, and 3ms acceleration value, are compared with the test results of the trial-produced parts to calculate the relative error: relative error = |simulation result - test result| / test result × 100%.

[0096] If the relative error is less than 10%, the simulation model is considered to meet the accuracy requirements. Otherwise, the parameters of the finite element pre-processing model need to be corrected, such as mesh refinement, adjustment of material parameters, etc.

[0097] S2012. Determine multiple configuration parameters according to the simulation results.

[0098] In some embodiments, a region to be optimized is determined according to simulation results, and parameters of the region to be optimized are used as configuration parameters.

[0099] S2013. In response to the configuration operation on each configuration parameter, determine a value range of each configuration parameter.

[0100] In a possible design, the multiple configuration parameters include parameters of the area to be optimized, and the above S2012 includes: S401-S402.

[0101] S401. Determine the area to be optimized according to the simulation results.

[0102] The area to be optimized includes a first area whose variable energy density is greater than or equal to a density threshold, a second area whose deformation value is greater than or equal to a deformation threshold, or a third area whose corresponding acceleration is greater than or equal to an acceleration threshold.

[0103] S402: Use the parameters of the area to be optimized as configuration parameters.

[0104] In some embodiments, when the area to be optimized is determined, in response to a parameter configuration operation on the area to be optimized, the parameters of the area to be optimized are determined, and the parameters of the area to be optimized are used as configuration parameters.

[0105] Exemplarily, in response to a user input operation on the electronic device for parameters of the area to be optimized, the configuration parameters of the area to be optimized are determined according to the parameters input by the user.

[0106] Specifically, the configuration parameters of the area to be optimized may be detailed in the above S201.

[0107] In a possible design, the parameter confirmation method provided in the embodiment of the present application further includes: S203-S204.

[0108] S203: Obtain a training sample data set according to the value ranges of multiple configuration parameters and a finite element pre-processing model.

[0109] S204: Train the initial neural network model according to the training sample data set to obtain a trained neural network model.

[0110] In some embodiments, the training sample data set is processed using a minimum-maximum normalization method, such as the following formula 1.

[0111]

[0112] Among them, X normalizedis the normalized data, X is the original data, Xmax and Xmin are the maximum and minimum values ​​in the data respectively.

[0113] In some embodiments, the normalized training sample data set is divided into a training data set and a test data set according to a preset ratio. For example, 80% of the data is used as training data and 20% of the data is used as test data; or 76% of the data is used as training data and 34% of the data is used as test data.

[0114] In addition, according to the selected design variables, the input layer nodes are determined to be 28, and the number of hidden layer nodes and the number of layers are determined by an empirical formula. For example, the empirical formula is shown in the following formula 2.

[0115]

[0116] Among them, n input is the number of nodes in the input layer, n output is the number of nodes in the output layer, n hidden is the number of hidden layer nodes.

[0117] The initial learning rate of the neural network model is a preset learning rate (such as 0.2), and the sigmoid function is used as the excitation function of the neurons of the neural network model. The excitation function is shown in the following formula three.

[0118]

[0119] Among them, f(x) is the output value and x is the input value.

[0120] Finally, the training data set is used to train the initial neural network model, and the root mean square error (RMSE) is used to test the accuracy of the neural network model to obtain a trained neural network model. The closer the RSME value is to 0, the higher the model accuracy.

[0121] After the accuracy of the trained neural network model is tested, if the accuracy of the simulation result meets the preset accuracy, the subsequent structural lightweight design is carried out according to this model. Among them, the RSME value is less than or equal to the preset threshold, which determines that the accuracy of the simulation result meets the requirements.

[0122] In one possible design, the above S203 includes: S2031-S2033.

[0123] S2031. Sample the value range of each configuration parameter according to Latin hypercube sampling to obtain multiple data combinations.

[0124] S2032. Input each data combination among the multiple data combinations into a finite element pre-processing model to obtain simulation data of each data combination.

[0125] S2033. Take each data combination and the simulation data corresponding to each data combination as a training sample to obtain a training sample data set.

[0126] In some embodiments, the electronic device determines the 28 design variables, each parameter takes a 3-digit series, uses Latin hypercube and uses the algorithm library pyDOE to perform stratified sampling to determine the variable combination. For the design variable combination corresponding to each sampling point, the finite element model is assigned parameters and the calculation is submitted. After the calculation is completed, according to the calculation results of each working condition, a post-processing script is written to batch read the results, including the first-order modal frequency, stiffness results, and 3ms acceleration of the head impact, to establish a design variable-simulation result database.

[0127] In one design, in order to better understand the parameter determination method provided in the embodiment of the present application, as Figure 4 As shown, a flow chart of a parameter determination method is shown, including: S501-S508.

[0128] S501. Establish a finite element pre-processing model of the instrument panel.

[0129] S502, obtaining simulation results according to the finite element pre-processing model calculation.

[0130] In some embodiments, the simulation results may be modal values, stiffness values, and head impact test values.

[0131] Exemplarily, the modal value may be a first-order modal frequency, the stiffness value may be a displacement, and the head impact test value may be a 3 ms acceleration value.

[0132] S503: Determine whether the relative error between the simulation result and the test result is less than or equal to an error threshold.

[0133] In some embodiments, when the simulation result is obtained, the relative error between the simulation result and the test result is calculated, and it is determined whether the relative error between the simulation result and the test result is less than or equal to the error threshold. This step is detailed in S2011.

[0134] If yes, then S504 is executed. If no, then the parameters of the finite element pre-processing model are adjusted, and the simulation result is calculated again according to the finite element pre-processing model.

[0135] It should be noted that the error threshold is pre-set by the operation and maintenance personnel, and the error threshold may be 10% or 11%, and this embodiment of the present application does not make any specific limitation on this.

[0136] S504: Determine value ranges of multiple configuration parameters of the dashboard according to the simulation results.

[0137] This step is detailed in S201 and S2011-S2013 above.

[0138] S505: Configure the parameters of the initial neural network model.

[0139] S506: Generate a training data set.

[0140] This step is detailed in S203 and S2031-S2033 and will not be repeated here.

[0141] S507: Train the initial neural network model according to the training data set to obtain a trained neural network model.

[0142] S508 . Determine a target value for each configuration parameter based on a non-dominated sorting genetic algorithm and a trained neural network model.

[0143] This step is detailed in S2021-S2022 and will not be repeated here.

[0144] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the regulating device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0145] Figure 5 is a parameter determination device according to an exemplary embodiment. Figure 5 , the parameter determination device 60 includes: a determination unit 601.

[0146] The determination unit 601 is used to determine the value ranges, objective functions and constraints of multiple configuration parameters of the instrument panel. The minimum mass, maximum modal frequency and minimum head impact acceleration of the instrument panel are used as the objective functions, and the stress threshold, deformation threshold and modal frequency threshold of the instrument panel under the rigidity and strength conditions are used as the constraints. A configuration parameter is used to characterize a part parameter to be optimized or a region parameter to be optimized. The determination unit is also used to determine the target value of each configuration parameter based on the value ranges of multiple configuration parameters, the trained neural network model, the objective function and the constraints.

[0147] In one possible manner, the determination unit 601 is specifically used to: input the candidate value of each configuration parameter into the trained neural network model to obtain simulation data. The simulation data includes modal frequency, head impact acceleration, and deformation value of the instrument panel under stiffness and strength conditions. The candidate value of each configuration parameter is any value in the value range of each configuration parameter. According to the simulation data, the objective function, the constraint conditions, and the non-dominated sorting genetic algorithm, the target value of each configuration parameter is determined.

[0148] In one possible manner, the determination unit 601 is specifically configured to: simulate the initial data of the dashboard according to the finite element pre-processing model to obtain simulation results, determine multiple configuration parameters according to the simulation results, and determine the value range of each configuration parameter in response to the configuration operation on each configuration parameter.

[0149] In one possible manner, the plurality of configuration parameters include parameters of the region to be optimized, and the determination unit 601 is used to: determine the region to be optimized according to the simulation results, and use the parameters of the region to be optimized as the configuration parameters. The region to be optimized includes a first region whose variable energy density is greater than or equal to a density threshold, a second region whose deformation value is greater than or equal to a deformation threshold, or a third region whose corresponding acceleration is greater than or equal to an acceleration threshold.

[0150] One possible approach is Figure 5 As shown, the parameter determination device 60 also includes: a processing unit 602. The processing unit 602 is used to obtain a training sample data set according to the value ranges of multiple configuration parameters and the finite element pre-processing model. The processing unit is also used to train the initial neural network model according to the training sample data set to obtain a trained neural network model.

[0151] In one possible manner, the processing unit 602 is specifically configured to: sample the value range of each configuration parameter according to Latin hypercube sampling to obtain multiple data combinations, and input each data combination in the multiple data combinations into the finite element pre-processing model to obtain simulation data of each data combination. Each data combination and the simulation data corresponding to each data combination are used as a training sample to obtain a training sample data set.

[0152] In one possible approach, the plurality of configuration parameters include the coordinates of the center of mass of the display screen in the instrument panel, its mass, and the thickness of a bracket connected to the instrument panel.

[0153] Figure 6 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 6 As shown, the electronic device includes but is not limited to: a processor 701 and a memory 702 .

[0154] The memory 702 is coupled to the processor 701. The memory 702 is used to store computer program codes, and the computer program codes include computer instructions. When the processor 701 executes the computer instructions, the electronic device executes the parameter determination method of the embodiment of the present application.

[0155] It should be noted that those skilled in the art can understand that Figure 6 The processing device structure shown in the figure does not constitute a limitation on the processing device, and the processing device may include Figure 6 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0156] The processor 701 is the control center of the processing device. It uses various interfaces and lines to connect various parts of the entire processing device. By running or executing software programs and / or modules stored in the memory 702, and calling data stored in the memory 702, it performs various functions of the processing device and processes data, thereby monitoring the processing device as a whole. The processor 701 may include one or more processing units. Optionally, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701.

[0157] The memory 702 may be used to store software programs and various data. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0158] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 702 including instructions, and the above instructions can be executed by a processor 701 of a processing device to implement the method in the above embodiment.

[0159] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0160] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 701 of the processing device to complete the method in the above embodiment.

[0161] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the processing device, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0162] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0163] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0164] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0165] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0166] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0167] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A parameter determination method, characterized in that: The method comprises: Determine the value ranges, objective functions and constraints of multiple configuration parameters of the instrument panel; take the minimum mass, maximum modal frequency and minimum head impact acceleration of the instrument panel as the objective function, take the stress threshold, deformation threshold and modal frequency threshold of the instrument panel under the rigidity and strength conditions as the constraints, and a parameter to be optimized is used to characterize a part parameter to be optimized or a region parameter to be optimized; The target value of each configuration parameter is determined according to the value ranges of the multiple configuration parameters, the trained neural network model, the objective function and the constraint conditions; the trained neural network model is used to determine the operating parameters of the dashboard.

2. The method according to claim 1, characterized in that: Determining a target value of each configuration parameter according to the value ranges of the multiple configuration parameters, the trained neural network model, the objective function, and the constraint conditions includes: Inputting the candidate value of each configuration parameter into the trained neural network model to obtain simulation data; the simulation data includes modal frequency, head impact acceleration and deformation value of the instrument panel under stiffness and strength conditions; the candidate value of each configuration parameter is any value in the value range of each configuration parameter; A target value of each configuration parameter is determined according to the simulation data, the objective function, the constraint conditions and the non-dominated sorting genetic algorithm.

3. The method according to claim 1, characterized in that: Determining the value ranges of the multiple configuration parameters of the dashboard includes: Simulating the initial data of the instrument panel according to the finite element pre-processing model to obtain simulation results; The plurality of configuration parameters are determined according to the simulation result, and in response to a configuration operation on each configuration parameter, a value range of each configuration parameter is determined.

4. The method according to claim 3, characterized in that: The multiple configuration parameters include parameters of the area to be optimized, and determining the multiple configuration parameters according to the simulation result includes: According to the simulation results, the area to be optimized is determined, and the parameters of the area to be optimized are used as configuration parameters; the area to be optimized includes a first area whose variable energy density is greater than or equal to a density threshold, a second area whose deformation value is greater than or equal to a deformation threshold, or a third area whose corresponding acceleration is greater than or equal to an acceleration threshold.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Obtaining a training sample data set according to the value ranges of the multiple configuration parameters and a finite element pre-processing model; The initial neural network model is trained according to the training sample data set to obtain the trained neural network model.

6. The method according to claim 5, characterized in that: The step of obtaining a training sample data set according to the value ranges of the multiple configuration parameters and the finite element pre-processing model comprises: Sampling the value range of each configuration parameter according to Latin hypercube sampling to obtain multiple data combinations, and inputting each data combination of the multiple data combinations into the finite element pre-processing model to obtain simulation data of each data combination; Each data combination and the simulation data corresponding to each data combination are taken as a training sample to obtain the training sample data set.

7. The method according to any one of claims 1 to 4, characterized in that: The plurality of configuration parameters include coordinates of the center of mass of the display screen in the instrument panel, the mass, and the thickness of a bracket connecting the instrument panel.

8. A parameter determination device (60), characterized in that: The parameter determination device (60) comprises: a determination unit (601); The determination unit (601) is used to determine the value ranges, objective functions and constraints of multiple configuration parameters of the instrument panel; the objective function is to minimize the mass, maximize the modal frequency and minimize the head impact acceleration of the instrument panel; the stress threshold, deformation threshold and modal frequency threshold of the instrument panel under the rigidity and strength working conditions are used as the constraints; a configuration parameter is used to characterize a part parameter to be optimized or a region parameter to be optimized; The determination unit (601) is further used to determine the target value of each configuration parameter according to the value ranges of the multiple configuration parameters, the trained neural network model, the objective function and the constraint conditions.

9. The device (60) according to claim 8, characterized in that The determining unit (601) is specifically configured to: Inputting the candidate value of each configuration parameter into the trained neural network model to obtain simulation data; the simulation data includes modal frequency, head impact acceleration and deformation value of the instrument panel under stiffness and strength conditions; the candidate value of each configuration parameter is any value in the value range of each configuration parameter; A target value of each configuration parameter is determined according to the simulation data, the objective function, the constraint conditions and the non-dominated sorting genetic algorithm.

10. The device (60) according to claim 8, characterized in that The determining unit (601) is specifically configured to: Simulating the initial data of the instrument panel according to the finite element pre-processing model to obtain simulation results; The plurality of configuration parameters are determined according to the simulation result, and in response to a configuration operation on each configuration parameter, a value range of each configuration parameter is determined.

11. An electronic device, characterized in that: comprising a memory (702) and a processor (701); The memory (702) is coupled to the processor (701); The memory (702) is used to store computer program code, wherein the computer program code includes computer instructions; When the processor (701) executes the computer instructions, the electronic device performs the determination method as described in any one of claims 1-7.

12. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of a processing device, the processing device can perform the determination method according to any one of claims 1 to 7.

Images