Generation method of suspension two-force rod, electronic equipment and storage medium

Abstract

The invention relates to the technical field of structural design, and provides a generation method of a suspension two-force rod, electronic equipment and a storage medium. The method comprises the following steps: acquiring a target parameter range, a target performance index and a target quality index of the two-force rod of the suspension; taking the target performance index and the target quality index as constraint conditions, and calling a trained calculation model to perform data calculation in a target parameter range based on an optimization algorithm; wherein the calculation model is used for calculating structural data meeting performance indexes and quality indexes in a parameter range of the two-force rod structure; and generating a three-dimensional model of the two-force rod of the suspension according to a data calculation result. By the adoption of the method, multiple rounds of structure optimization and simulation analysis processes are not needed, and time consumed for designing the suspension two-force rod structure can be effectively shortened.

Description

Technical Field

[0001] The present application relates to the technical field of structural design, and in particular to a method for generating a suspension two-force rod, an electronic device and a storage medium. Background Art

[0002] The chassis suspension is the main load-bearing unit of the vehicle. The suspension two-force rod provided on it is an important connecting component, which directly affects the movement performance of the chassis suspension in terms of performance indicators such as strength, stiffness and buckling force. At present, when designing the structure of the suspension two-force rod, the initial two-force rod structure is usually designed according to the vehicle model parameters, and then the finite element analysis software is used to simulate and analyze the relevant performance of the two-force rod structure to determine whether its performance indicators meet the requirements. If it does not meet the requirements, CAE software is used to perform multiple rounds of meshing and load loading calculations, and the key parameters affecting the performance are found according to the calculation results of each time, and the two-force rod structure is continuously optimized through trial and error until its performance indicators meet the requirements. However, this structural design method requires multiple rounds of structural optimization and simulation analysis, which is time-consuming. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a method for generating a two-force rod of a suspension, an electronic device, and a storage medium, which can reduce the time consumption in designing a two-force rod structure of a suspension.

[0004] A first aspect of an embodiment of the present application provides a method for generating a suspension two-force rod, comprising:

[0005] Obtaining target parameter range, target performance index and target quality index of the suspension two-force rod;

[0006] Taking the target performance index and the target quality index as constraints, the trained calculation model is called based on the optimization algorithm to perform data calculation within the target parameter range; wherein the calculation model is used to calculate the structural data that meets the performance index and the quality index within the parameter range of the two-force rod structure;

[0007] According to the results of data calculation, a three-dimensional model of the suspension two-force rod is generated.

[0008] In the technical solution of the embodiment of the present application, a calculation model is pre-trained for calculating structural data that meets performance indicators and quality indicators within the parameter range of the two-force bar structure. After determining the target parameter range, target performance indicators and target quality indicators of the suspension two-force bar to be created, the target performance indicators and target quality indicators are used as constraints, and the calculation model is called based on the optimization algorithm to perform data calculation within the target parameter range. In this way, the two-force bar structure data that meets the target performance indicators and target quality indicators and is within the target parameter range can be obtained, thereby generating a three-dimensional model of the suspension two-force bar and completing the structural design. This method does not require multiple rounds of structural optimization and simulation analysis processes, so it can effectively reduce the time spent on designing the suspension two-force bar structure.

[0009] In one implementation of the embodiment of the present application, the training process of the computing model includes:

[0010] Construct a two-force bar finite element model;

[0011] Generate structural sample points according to the set parameter range of the two-force bar structure and the two-force bar finite element model;

[0012] Based on the structural sample points, the computational model is trained.

[0013] In one implementation of the embodiment of the present application, constructing a two-force bar finite element model includes:

[0014] Obtain a three-dimensional model of the sample two-force rod;

[0015] Extracting model parameters of the three-dimensional model of the sample two-force rod;

[0016] According to the model parameters, a two-force bar finite element model is constructed.

[0017] In one implementation of the embodiment of the present application, a computing model is trained based on the structural sample points, including:

[0018] Based on structural sample points, a computational model that meets the computational accuracy requirements is trained using machine learning or optimization algorithms.

[0019] In one implementation of the embodiment of the present application, the structural sample points include multiple groups of test samples; based on the structural sample points, a computing model that meets the computing accuracy requirements is trained by machine learning or optimization algorithm, including:

[0020] Obtaining a set number of target test samples from multiple groups of test samples;

[0021] Based on the target test samples, use machine learning or optimization algorithms to train the initial model;

[0022] Under the condition of determining the set performance index and the set quality index, obtaining the sample structure data calculated by the initial model;

[0023] Determine whether the sample structure data meets the set performance index and the set quality index according to the structure simulation result of the sample structure data;

[0024] If the sample structure data meets the set performance index and the set quality index, the initial model is determined as the calculation model.

[0025] In one implementation of the embodiment of the present application, obtaining a target parameter range, a target performance index, and a target quality index of a suspension two-force rod includes:

[0026] Obtain vehicle model parameters corresponding to the suspension two-force rod;

[0027] According to the vehicle model parameters, determine the target parameter range, target performance indicators and target quality indicators.

[0028] In one implementation of the embodiment of the present application, the target parameter range, target performance index and target quality index are determined according to the vehicle model parameters, including:

[0029] According to the vehicle model parameters, determine the space size and hard point position of the vehicle chassis suspension to which the suspension two-force rod belongs;

[0030] According to the spatial dimensions and hard point positions, the target parameter range, target performance indicators and target quality indicators are determined.

[0031] In one implementation of the embodiment of the present application, after determining the target parameter range, the target performance index and the target quality index according to the space size and the hard point position, it also includes:

[0032] Determine the age of the vehicle to which the suspension strut belongs;

[0033] According to the service life, the target parameter range, target performance indicators and target quality indicators are adjusted.

[0034] A second aspect of an embodiment of the present application provides a device for generating a suspension two-force rod, comprising:

[0035] A parameter acquisition module, used to obtain a target parameter range, target performance index and target quality index of a suspension two-force rod;

[0036] A data calculation module is used to use the target performance index and the target quality index as constraints, and to call the trained calculation model based on the optimization algorithm to perform data calculation within the target parameter range; wherein the calculation model is used to calculate the structural data that meets the performance index and the quality index within the parameter range of the two-force rod structure;

[0037] The structure generation module is used to generate a three-dimensional model of the suspension two-force rod according to the results of data calculation.

[0038] In one implementation of the embodiment of the present application, the device for generating the two-force rod of the suspension further includes:

[0039] Finite element model building module, used to build a two-force bar finite element model;

[0040] A sample point generation module is used to generate structural sample points according to a set parameter range of the two-force bar structure and a two-force bar finite element model;

[0041] The model training module is used to train the computational model based on the structural sample points.

[0042] In one implementation of the embodiment of the present application, the finite element model building module includes:

[0043] A structural model acquisition unit, used to acquire a three-dimensional model of a sample two-force rod;

[0044] A model parameter extraction unit, used to extract model parameters of the three-dimensional model of the sample two-force rod;

[0045] The finite element model building unit is used to build a two-force bar finite element model according to model parameters.

[0046] In one implementation of the embodiment of the present application, the model training module includes:

[0047] The model training unit is used to train a computing model that meets the computing accuracy requirements based on structural sample points by using machine learning or optimization algorithms.

[0048] In one implementation of the embodiment of the present application, the structure sample points include multiple groups of test samples; and the model training unit includes:

[0049] A test sample acquisition subunit, used to acquire a set number of target test samples from multiple groups of test samples;

[0050] The initial model training subunit is used to train the initial model based on the target test sample by using machine learning or optimization algorithm;

[0051] A sample structure acquisition subunit, used to acquire sample structure data calculated by an initial model under the condition of determining a set performance index and a set quality index;

[0052] The performance evaluation subunit is used to determine whether the sample structure data meets the set performance index and the set quality index according to the structure simulation result of the sample structure data;

[0053] The model determination subunit is used to determine the initial model as the calculation model if the sample structure data meets the set performance index and the set quality index.

[0054] In one implementation of the embodiment of the present application, the parameter acquisition module includes:

[0055] A vehicle model parameter acquisition unit, used to acquire vehicle model parameters corresponding to the suspension two-force rod;

[0056] The parameter determination unit is used to determine the target parameter range, target performance index and target quality index according to the vehicle model parameters.

[0057] In one implementation of the embodiment of the present application, the parameter determination unit includes:

[0058] The suspension determination subunit is used to determine the space size and hard point position of the vehicle chassis suspension to which the suspension two-force rod belongs according to the vehicle model parameters;

[0059] The parameter determination subunit is used to determine the target parameter range, target performance index and target quality index according to the spatial size and hard point position.

[0060] In one implementation of the embodiment of the present application, the parameter determination unit further includes:

[0061] A service life determination subunit, used to determine the service life of the vehicle to which the suspension two-force rod belongs;

[0062] The parameter adjustment subunit is used to adjust the target parameter range, target performance index and target quality index according to the service life.

[0063] A third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for generating a suspension two-force rod as provided in the first aspect of the embodiment of the present application is implemented.

[0064] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating a suspension two-force rod as provided in the first aspect of the embodiment of the present application is implemented.

[0065] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0067] Figure 1 It is a flow chart of a method for generating a suspension two-force rod provided in an embodiment of the present application;

[0068] Figure 2 It is a schematic diagram of a training process of a computing model provided in an embodiment of the present application;

[0069] Figure 3 It is a schematic diagram of an operation flow of generating a two-force rod structure of a suspension using a calculation model provided by an embodiment of the present application;

[0070] Figure 4 It is a structural schematic diagram of a device for generating a two-force rod of a suspension provided in an embodiment of the present application;

[0071] Figure 5 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures, technologies, etc. are proposed, so as to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed description of well-known systems, devices, circuits and methods is omitted to prevent unnecessary details from hindering the description of the present application. In addition, in the description of the present application specification and the attached claims, the terms "first", "second", "third" etc. are only used to distinguish the description, and cannot be interpreted as indicating or suggesting relative importance.

[0073] A two-force bar refers to a rigid body that is in equilibrium under the action of two forces. The two-force bar of the suspension is an important connecting component in the chassis suspension of the vehicle. At present, when performing structural design on the two-force bar of the suspension, it is usually necessary to use finite element analysis software and CAE software to perform multiple rounds of structural optimization and simulation analysis, which is time-consuming.

[0074] In view of the above problems, the embodiments of the present application provide a method for generating a suspension two-force bar, an electronic device, and a storage medium. The performance index and quality index of the suspension two-force bar are used as constraints, and the trained calculation model is called based on the optimization algorithm to perform data calculation within the parameter range of the suspension two-force bar, thereby generating a three-dimensional model of the suspension two-force bar structure. This method does not require multiple rounds of structural optimization and simulation analysis processes, and can effectively reduce the time spent on designing the suspension two-force bar structure. For more specific technical implementation details of the embodiments of the present application, please refer to the various method embodiments described below.

[0075] It should be understood that the execution subjects of the various method embodiments of the present application are various types of electronic devices, such as mobile phones, tablet computers, wearable devices, vehicle-mounted terminals, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiments of the present application do not impose any restrictions on the specific types of the electronic devices.

[0076] See also Figure 1 , shows a method for generating a suspension two-force rod provided in an embodiment of the present application, comprising:

[0077] 101. Obtain the target parameter range, target performance index and target quality index of the suspension two-force rod;

[0078] First, the target parameter range, target performance index and target quality index of the suspension two-force bar are obtained, wherein the suspension two-force bar refers to the two-force bar structure to be designed; the target parameter range refers to the value range of various parameter variables of the suspension two-force bar, and these parameter variables may include but are not limited to: rod diameter, length, thickness, cross-sectional size and material, etc.; the target performance index refers to the performance index that the suspension two-force bar needs to achieve, such as structural stiffness, strength, fatigue and buckling force; the target quality index refers to the quality requirement that the suspension two-force bar needs to achieve, such as how many kg the mass of the suspension two-force bar should reach.

[0079] In actual operation, the target parameter range, target performance index and target quality index can be obtained by manual input. For example, designers usually know the design parameters such as the parameter variable size of the suspension two-force rod to be designed, the performance index and quality index to be achieved, so they can easily input these design parameters.

[0080] Considering that the suspension two-force rod is a connecting component in the vehicle chassis suspension, and the structural dimensions and performance requirements of the chassis suspension of different models are different, it can be inferred that different models have different design parameter requirements for the suspension two-force rod.

[0081] In one implementation of the embodiment of the present application, obtaining a target parameter range, a target performance index, and a target quality index of a suspension two-force rod includes:

[0082] (1) Obtaining vehicle model parameters corresponding to the suspension two-force rod;

[0083] (2) Based on the vehicle model parameters, determine the target parameter range, target performance indicators, and target quality indicators.

[0084] When designing a suspension two-force bar structure, the vehicle model to which it is applied is usually known, that is, the vehicle model parameters corresponding to the suspension two-force bar can be obtained. Therefore, the parameter range, performance index and quality index of the two-force bar structure corresponding to each different vehicle model parameter can be collected and stored in advance, so that after obtaining the vehicle model parameters corresponding to the suspension two-force bar, the parameter range, performance index and quality index of the corresponding two-force bar structure can be found based on the vehicle model parameters, and the target parameter range, target performance index and target quality index can be determined respectively. For example, if the vehicle model parameters corresponding to the suspension two-force bar are model A, the parameter range, performance index and quality index of the two-force bar structure corresponding to model A are found, and they are used as the target parameter range, target performance index and target quality index respectively; if the vehicle model parameters corresponding to the suspension two-force bar are model B, the parameter range, performance index and quality index of the two-force bar structure corresponding to model B are found, and they are used as the target parameter range, target performance index and target quality index respectively, and so on. Through such a setting, the corresponding suspension two-force bar structure design parameters can be automatically found according to the vehicle model parameters, and the operation of the user inputting the structure design parameters is omitted.

[0085] In one implementation of the embodiment of the present application, the target parameter range, target performance index and target quality index are determined according to the vehicle model parameters, including:

[0086] (1) Determine the spatial dimensions and hard point position of the vehicle chassis suspension to which the suspension two-force rod belongs based on the vehicle model parameters;

[0087] (2) Determine the target parameter range, target performance index, and target quality index based on the spatial dimensions and hard point locations.

[0088] In the process of determining the target parameter range, target performance index and target quality index according to the vehicle model parameters, the spatial dimensions and hard point positions of the vehicle chassis suspension to which the suspension two-force rod belongs can be determined according to the vehicle model parameters, and then, according to the spatial dimensions and hard point positions, the parameter range, performance index and quality index of the adapted two-force rod structure can be determined as the target parameter range, target performance index and target quality index respectively. For example, when the spatial dimensions and hard point positions of the vehicle chassis suspension are known, the value range of the parameter variables such as the length and thickness of the two-force rod that meet the spatial dimensions can be defined, and the requirements of the strength, stiffness, buckling force or quality of the two-force rod that needs to be achieved can be defined according to the hard point arrangement.

[0089] In one implementation of the embodiment of the present application, after determining the target parameter range, the target performance index and the target quality index according to the space size and the hard point position, it also includes:

[0090] (1) Determine the age of the vehicle to which the suspension arm belongs;

[0091] (2) Adjust the target parameter range, target performance indicators and target quality indicators based on the service life.

[0092] Considering that when the service life of a vehicle is high, its chassis suspension may age and cause changes in structural performance. At this time, the performance and quality requirements of the two-force bar structure adapted to the chassis suspension will also change. Therefore, after determining the target parameter range, target performance index and target quality index according to the spatial size and hard point position of the chassis suspension, the service life of the vehicle to which the suspension two-force bar belongs can also be obtained, and the performance changes that may occur in the chassis suspension can be evaluated according to the service life, and then the performance and quality requirements that need to be adjusted for the two-force bar structure adapted to it can be inferred. Finally, the target parameter range, target performance index and target quality index are adjusted accordingly according to the requirements. For example, if the service life of the vehicle exceeds 10 years, its chassis suspension may age, which will put higher requirements on the stiffness and quality of the two-force bar structure, so the target performance index and target quality index can be improved accordingly. Through such a setting, a suspension two-force bar structure that better meets the requirements of the actual vehicle can be designed.

[0093] 102. Taking the target performance index and target quality index as constraints, the trained calculation model is called based on the optimization algorithm to perform data calculation within the target parameter range;

[0094] After obtaining the target parameter range, target performance index and target quality index, the trained calculation model is called based on the optimization algorithm to perform data calculation within the target parameter range with the target performance index and target quality index as constraints, so that the two-force bar structure data that meets the requirements of the target performance index and target quality index and is within the target parameter range can be obtained. Among them, the calculation model is used to calculate the structural data that meets the performance index and quality index within the parameter range of the two-force bar structure. The training principle of the calculation model is first explained below.

[0095] In one implementation of the embodiment of the present application, the training process of the computing model includes:

[0096] (1) Construct a two-bar finite element model;

[0097] (2) generating structural sample points according to the set parameter range of the two-force bar structure and the two-force bar finite element model;

[0098] (3) Based on the structural sample points, the computational model is trained.

[0099] When training the computational model, a two-force bar finite element model is first constructed, and then the set parameter range of the two-force bar structure and the two-force bar finite element model are analyzed to generate corresponding structural sample points, and finally the computational model can be trained based on the generated structural sample points. Among them, the two-force bar finite element model can be constructed by a parameterized model of the two-force bar, and using the parameter analysis results of the two-force bar finite element model, many groups of structural sample points whose structural parameters are within the set parameter range can be generated. Each group of structural sample points can be called a group of test samples, which are used to represent a two-force bar structure. After obtaining multiple groups of structural sample points, machine learning or optimization algorithm software can be used to train a computational model involving the parameter range of the two-force bar structure, the calculation relationship between performance indicators and quality indicators based on these structural sample points.

[0100] In one implementation of the embodiment of the present application, constructing a two-force bar finite element model includes:

[0101] (1) Obtain a three-dimensional model of the sample two-force rod;

[0102] (2) extracting model parameters of the three-dimensional model of the sample two-force rod;

[0103] (3) Construct a two-force bar finite element model based on the model parameters.

[0104] The two-force bar finite element model is constructed through the parameterized model of the two-force bar. Specifically, a three-dimensional model of a designed sample two-force bar can be obtained first, and then the three-dimensional model can be parameterized, that is, various model parameters of the three-dimensional model can be extracted, such as the coordinates of each position point in the two-force bar structure and the model size and other parameters. After obtaining these model parameters, the two-force bar finite element model can be constructed by referring to the basic construction method of the finite element model. The finite element model is a group of unit combinations that are connected only at the nodes, transmit forces only at the nodes, and are constrained only at the nodes. It is the result of the discretization of the mechanical model and is essentially a digital model for numerical calculation. After obtaining the two-force bar finite element model, various finite element analysis methods can be used to calculate the stress, strain and other parameters of each unit. When the volume of each unit is small enough, the unit combination can represent the real parameter conditions at each position in the two-force bar structure.

[0105] In one implementation of the embodiment of the present application, a computing model is trained based on the structural sample points, including:

[0106] Based on structural sample points, a computational model that meets the computational accuracy requirements is trained using machine learning or optimization algorithms.

[0107] Based on the structural sample points, a computational model can be trained to calculate the structural data that meets the performance index and quality index within the parameter range of the two-force rod structure by using machine learning or optimization algorithms. Moreover, by using multiple groups of different structural sample points for iterative optimization training, the computational accuracy of the computational model can be improved, and finally a computational model that meets the computational accuracy requirements can be obtained.

[0108] As an example, the structural sample points may be DOE sample points. DOE is an experimental design method that constructs parameter variables such as geometry or material of a two-force bar structure to perform a combination of experimental variables. Each combination may be regarded as a set of DOE sample points. The embodiment of the present application may also use a Latin hypercube sampling method to optimize the obtained DOE sample point results. The steps of extracting DOE sample points using the Latin hypercube sampling method include:

[0109] (1) Assuming that m samples are to be extracted from an n-dimensional vector space, each dimension of the space is divided into m non-overlapping intervals so that each interval has the same probability;

[0110] (2) Randomly select a sample point in each interval in each dimension. These sample points constitute the population of the Latin hypercube, with a total of m^n points;

[0111] (3) Randomly extract sample points from the population in each dimension and organize them into vectors. The technique used in Latin hypercube sampling is "sampling without replacement". Once a sample point is extracted from a stratum, this stratum will no longer be sampled. Ultimately, one sample point is extracted from each stratum.

[0112] It should be noted that Latin hypercube sampling requires that the number of partitions m for each variable is the same, but does not require that the number of samples m also increase when the variable increases. This process can capture representative sample points from a large number of sample points. Subsequently, only the representative sample points need to be optimized and calculated, thereby effectively reducing the computational cost.

[0113] When training the calculation model based on the structural sample points, the optimization platform software can be used to build the performance and target optimization process of the two-force bar structure, and realize the automation of pre-processing boundary definition and post-processing result output. The set variables are used to drive the parametric model, generate the corresponding structural sample points, and then submit the structural sample points to the server for solution calculation, and automatically extract the results, so that a data table can be obtained. The input of the data table is the set variables, and the output is the performance and target of the response. Based on the data table, AI algorithms, such as the radial basis function algorithm, can automatically learn the relationship between variables and responses, thereby establishing a corresponding calculation model.

[0114] In one implementation of the embodiment of the present application, the structural sample points include multiple groups of test samples; based on the structural sample points, a computing model that meets the computing accuracy requirements is trained by machine learning or optimization algorithm, including:

[0115] (1) obtaining a set number of target test samples from multiple groups of test samples;

[0116] (2) Based on the target test samples, train the initial model using machine learning or optimization algorithms;

[0117] (3) obtaining sample structure data calculated by the initial model when the set performance index and the set quality index are determined;

[0118] (4) determining whether the sample structure data meets the set performance index and the set quality index according to the structure simulation result of the sample structure data;

[0119] (5) If the sample structure data meets the set performance index and the set quality index, the initial model is determined as the calculation model.

[0120] When training the calculation model, a certain number of test samples can be first obtained as target test samples, for example, more than 10 groups of test samples can be obtained. Then, based on the target test samples, an initial model is trained by machine learning or optimization algorithm. When the set performance index and the set quality index are determined, the initial model is used for calculation to obtain the corresponding sample structure data. In addition, the sample structure data is subjected to structural simulation processing, for example, it can be simulated by finite element analysis software or CAE software to obtain the structural simulation result of the sample structure data. According to the structural simulation result, it can be evaluated whether the sample structure data meets the set performance index and the set quality index. If the set performance index and the set quality index are met, it means that the calculation accuracy of the initial model has met the requirements, and the initial model can be determined as the training completed calculation model for saving. If the set performance index and the set quality index are not met, it means that the calculation accuracy of the initial model does not meet the requirements, and at this time, the step of obtaining the target test sample can be returned to obtain another plurality of test samples, and the initial model is optimized and trained in the same way, and its calculation accuracy is continuously improved until it meets the requirements.

[0121] As an example, Figure 2 Schematic diagram of a training process of a computing model provided in an embodiment of the present application. Figure 2 In the method, firstly, the designed two-force bar parametric model is obtained, and a two-force bar finite element model is constructed according to the two-force bar parametric model; then, the corresponding DOE sample points are generated according to the set parameter range of the two-force bar structure and the two-force bar finite element model; then, multiple groups of test samples are obtained from the DOE sample points, and the initial model is trained by machine learning or optimization algorithm based on the obtained test samples; the sample structure data can be obtained by calculation using the initial model; then, the sample structure data is subjected to structural simulation processing, and according to the structural simulation results, it is judged whether the sample structure data meets the requirements of performance indicators and quality indicators; if the requirements are met, it means that the calculation accuracy of the initial model is sufficient, and its output is saved as a calculation model; if the requirements are not met, it returns to the step of obtaining multiple groups of test samples from the DOE sample points, and selects new test samples to optimize the initial model for training, and continues to improve its calculation accuracy. After the calculation model is obtained by training in the above manner, the structural design of the suspension two-force bar can be easily completed by simply calling the calculation model for calculation. Specifically, with the target performance index and the target quality index as constraints, the calculation model is called based on the optimization algorithm such as the response surface to perform data calculation within the target parameter range, so as to obtain the optimal two-force rod structure data that meets the target performance index and the target quality index and is within the target parameter range.

[0122] As an example, the GRSM global response search method can be used to complete the optimization. The global response search method is an optimization technique that can be used to solve multi-objective optimization problems of complex systems. The global response search method approximates the behavior of the actual system by constructing a global response surface model, so that efficient exploration and optimization can be performed in the design space. The core of the global response search method is to use a mathematical model to describe the relationship between the design variables and the objective function, and to find the optimal design parameters through the optimization algorithm to achieve the preset performance goals. For the scenario of two-force bar structure design, the geometric parameters or materials of the suspension two-force bar can be used as variables, and performance indicators such as torsional stiffness, bending stiffness and strength can be used as constraints. The minimum mass is set as the goal, and the GRSM optimization algorithm is started to continuously perform optimization calculations. Through the combination of finite element analysis and global response surface method, the optimal structural design parameters can be obtained, that is, the optimal two-force bar structure data that meets the target performance indicators and target quality indicators and is within the target parameter range.

[0123] 103. Based on the results of data calculation, generate a three-dimensional model of the suspension two-force rod.

[0124] The data calculation result of the calculation model is the structural data of the two-force bar. By integrating these structural data, a three-dimensional model of the suspension two-force bar can be generated, thereby completing the structural design of the suspension two-force bar. After obtaining the three-dimensional model of the suspension two-force bar, the three-dimensional model can be further rendered or manually fine-tuned to obtain a more accurate and more beautiful suspension two-force bar structural design result. In addition, a simulation analysis can be performed on the obtained suspension two-force bar structure to determine whether it meets the requirements of the target performance index and the target quality index. If the requirements are met, it means that the calculation accuracy of the calculation model is up to standard, and the suspension two-force bar structural design result can be output at this time. If the requirements are not met, it means that the calculation accuracy of the calculation model is not up to standard. At this time, more two-force bar structure sample points can be obtained, and the calculation model can continue to be optimized and trained until the calculation accuracy of the calculation model meets the standard.

[0125] As an example, Figure 3 This is a schematic diagram of an operation flow of generating a two-force rod structure of a suspension using a calculation model provided by an embodiment of the present application. Figure 3 In the method, the parameter range, performance index and quality index of the suspension two-force bar are first defined according to the spatial dimensions and hard point arrangement of the vehicle chassis suspension; then, with the defined performance index and quality index as constraints, the calculation model is called based on the optimization algorithm to perform data calculation within the defined parameter range, and the optimal suspension two-force bar structure design scheme can be output.

[0126] In the technical solution of the embodiment of the present application, a calculation model is pre-trained for calculating structural data that meets performance indicators and quality indicators within the parameter range of the two-force bar structure. After determining the target parameter range, target performance indicators and target quality indicators of the suspension two-force bar to be created, the target performance indicators and target quality indicators are used as constraints, and the calculation model is called based on the optimization algorithm to perform data calculation within the target parameter range. In this way, the two-force bar structure data that meets the target performance indicators and target quality indicators and is within the target parameter range can be obtained, thereby generating a three-dimensional model of the suspension two-force bar and completing the structural design. This method does not require multiple rounds of structural optimization and simulation analysis processes, so it can effectively reduce the time spent on designing the suspension two-force bar structure.

[0127] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0128] A method for generating a two-force rod of a suspension is mainly described above, and a device for generating a two-force rod of a suspension will be described below.

[0129] See also Figure 4 , shows a device for generating a suspension two-force rod provided in an embodiment of the present application, comprising:

[0130] The parameter acquisition module 401 is used to acquire the target parameter range, target performance index and target quality index of the suspension two-force rod;

[0131] The data calculation module 402 is used to use the target performance index and the target quality index as constraints, and to call the trained calculation model based on the optimization algorithm to perform data calculation within the target parameter range; wherein the calculation model is used to calculate the structural data that meets the performance index and the quality index within the parameter range of the two-force rod structure;

[0132] The structure generation module 403 is used to generate a three-dimensional model of the suspension two-force rod according to the result of data calculation.

[0133] In one implementation of the embodiment of the present application, the device for generating the two-force rod of the suspension further includes:

[0134] Finite element model building module, used to build a two-force bar finite element model;

[0135] A sample point generation module is used to generate structural sample points according to a set parameter range of the two-force bar structure and a two-force bar finite element model;

[0136] The model training module is used to train the computational model based on the structural sample points.

[0137] In one implementation of the embodiment of the present application, the finite element model building module includes:

[0138] A structural model acquisition unit, used to acquire a three-dimensional model of a sample two-force rod;

[0139] A model parameter extraction unit, used to extract model parameters of the three-dimensional model of the sample two-force rod;

[0140] The finite element model building unit is used to build a two-force bar finite element model according to model parameters.

[0141] In one implementation of the embodiment of the present application, the model training module includes:

[0142] The model training unit is used to train a computing model that meets the computing accuracy requirements based on structural sample points by using machine learning or optimization algorithms.

[0143] In one implementation of the embodiment of the present application, the structure sample points include multiple groups of test samples; and the model training unit includes:

[0144] A test sample acquisition subunit, used to acquire a set number of target test samples from multiple groups of test samples;

[0145] The initial model training subunit is used to train the initial model based on the target test sample by using machine learning or optimization algorithm;

[0146] A sample structure acquisition subunit, used to acquire sample structure data calculated by an initial model under the condition of determining a set performance index and a set quality index;

[0147] The performance evaluation subunit is used to determine whether the sample structure data meets the set performance index and the set quality index according to the structure simulation result of the sample structure data;

[0148] The model determination subunit is used to determine the initial model as the calculation model if the sample structure data meets the set performance index and the set quality index.

[0149] In one implementation of the embodiment of the present application, the parameter acquisition module includes:

[0150] A vehicle model parameter acquisition unit, used to acquire vehicle model parameters corresponding to the suspension two-force rod;

[0151] The parameter determination unit is used to determine the target parameter range, target performance index and target quality index according to the vehicle model parameters.

[0152] In one implementation of the embodiment of the present application, the parameter determination unit includes:

[0153] The suspension determination subunit is used to determine the space size and hard point position of the vehicle chassis suspension to which the suspension two-force rod belongs according to the vehicle model parameters;

[0154] The parameter determination subunit is used to determine the target parameter range, target performance index and target quality index according to the spatial size and hard point position.

[0155] In one implementation of the embodiment of the present application, the parameter determination unit further includes:

[0156] A service life determination subunit, used to determine the service life of the vehicle to which the suspension two-force rod belongs;

[0157] The parameter adjustment subunit is used to adjust the target parameter range, target performance index and target quality index according to the service life.

[0158] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating a suspension two-force rod as represented in any of the above embodiments is implemented.

[0159] Figure 5 is a schematic diagram of an electronic device provided by an embodiment of the present application. Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. When the processor 50 executes the computer program 52, the steps in the above-mentioned embodiments of the method for generating the two-force rod of the suspension are implemented, for example Figure 1 Alternatively, when the processor 50 executes the computer program 52, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 4 Modules 401 to 403 of the device shown.

[0160] The computer program 52 may be divided into one or more modules / units, which are stored in the memory 51 and executed by the processor 50 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 52 in the electronic device 5.

[0161] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0162] The memory 51 may be an internal storage unit of the electronic device 5, such as a hard disk or memory of the electronic device 5. The memory 51 may also be an external storage device of the electronic device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the electronic device 5. The memory 51 is used to store the computer program and other programs and data required by the electronic device. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0163] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0164] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0165] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0166] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software 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 be beyond the scope of this application.

[0167] In the 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 system embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0169] 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.

[0170] 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 computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0171] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for generating a suspension two-force rod, characterized in that: include: Obtaining target parameter range, target performance index and target quality index of the suspension two-force rod; Taking the target performance index and the target quality index as constraints, the trained calculation model is called based on the optimization algorithm to perform data calculation within the target parameter range; wherein the calculation model is used to calculate the structural data that meets the performance index and the quality index within the parameter range of the two-force rod structure; A three-dimensional model of the suspension two-force rod is generated according to the result of the data calculation.

2. The method according to claim 1, characterized in that The training process of the computing model includes: Construct a two-force bar finite element model; Generating structural sample points according to a set parameter range of the two-force bar structure and the two-force bar finite element model; The calculation model is obtained by training based on the structural sample points.

3. The method according to claim 2, characterized in that The construction of the two-force bar finite element model comprises: Obtain a three-dimensional model of the sample two-force rod; Extracting model parameters of the three-dimensional model of the sample two-force rod; According to the model parameters, the two-force bar finite element model is constructed.

4. The method according to claim 2, characterized in that The step of training the calculation model based on the structural sample points includes: Based on the structural sample points, the calculation model that meets the calculation accuracy requirements is trained by using machine learning or optimization algorithms.

5. The method according to claim 4, characterized in that The structural sample points include multiple groups of test samples; the calculation model that meets the calculation accuracy requirement is trained based on the structural sample points by using machine learning or optimization algorithms, including: Acquire a set number of target test samples from the multiple groups of test samples; Based on the target test sample, train the initial model by using machine learning or optimization algorithm; When the set performance index and the set quality index are determined, obtaining sample structure data calculated by the initial model; Determining whether the sample structure data meets the set performance index and the set quality index according to the structure simulation result of the sample structure data; If the sample structure data meets the set performance index and the set quality index, the initial model is determined as the calculation model.

6. The method according to any one of claims 1 to 5, characterized in that: The method of obtaining the target parameter range, target performance index and target quality index of the suspension two-force rod includes: Obtaining vehicle model parameters corresponding to the suspension two-force rod; According to the vehicle model parameters, the target parameter range, the target performance index and the target quality index are determined.

7. The method according to claim 6, characterized in that The step of determining the target parameter range, the target performance index and the target quality index according to the vehicle model parameters includes: Determining the spatial dimensions and hard point positions of the vehicle chassis suspension to which the suspension two-force rod belongs according to the vehicle model parameters; The target parameter range, the target performance index and the target quality index are determined according to the spatial size and the hard point position.

8. The method according to claim 7, characterized in that After determining the target parameter range, the target performance index and the target quality index according to the space size and the hard point position, the method further includes: Determining the age of the vehicle to which the suspension lever belongs; According to the service life, the target parameter range, the target performance index and the target quality index are adjusted.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for generating a suspension two-force rod according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for generating a suspension dual-force rod according to any one of claims 1 to 8 is implemented.

Images