Optimization method and device of automobile transmission system, electronic equipment and medium

Abstract

The embodiment of the invention discloses an optimization method and device of an automobile transmission system, electronic equipment and a medium. The method comprises the steps of generating a sample data set based on an original automobile transmission model of a to-be-optimized automobile transmission system, preset model input parameters and preset model output parameters; wherein the sample data set comprises input sample data corresponding to preset model input parameters and output sample data corresponding to preset model output parameters; the preset model input parameters are preset influence parameters of the to-be-optimized automobile transmission system, and the preset model output parameters are preset optimization indexes of the to-be-optimized automobile transmission system; and training a to-be-trained neural network model based on the input sample data and the output sample data to obtain a reduced-order model corresponding to the to-be-optimized automobile transmission system, determining a parameter value of a to-be-optimized parameter in the to-be-optimized automobile transmission system based on the reduced-order model, and optimizing the to-be-optimized automobile transmission system based on the parameter.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and in particular to an optimization method, device, electronic equipment and medium for an automobile transmission system. Background Art

[0002] The automobile transmission system is an important part of the automobile, which includes the engine, transmission, clutch, drive shaft, differential and transmission device. Usually, the automobile transmission model corresponding to the automobile transmission system is constructed to optimize the design of the automobile transmission system.

[0003] In the prior art, a vehicle transmission model corresponding to a vehicle transmission system is usually constructed using a mathematical formula. However, due to the cumbersome calculation of the mathematical model, in the process of optimizing the vehicle transmission model constructed by the data model, the number of iterations is large, the amount of calculation is large, and the optimization efficiency is slow. Summary of the invention

[0004] The embodiments of the present invention provide an optimization method, device, electronic equipment and medium for an automobile transmission system, so as to achieve the purpose of improving the optimization efficiency of the optimization process.

[0005] According to one aspect of the present invention, there is provided a method for optimizing an automobile transmission system, comprising:

[0006] Generate a sample data set based on an original automobile transmission model, preset model input parameters and preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are preset influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are preset optimization indicators of the automobile transmission system to be optimized;

[0007] Based on the input sample data and the output sample data, the neural network model to be trained is trained to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, so as to determine the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized based on the reduced-order model, and optimize the automobile transmission system to be optimized based on the parameters.

[0008] According to another aspect of the present invention, there is provided an optimization device for an automobile transmission system, the device comprising:

[0009] A sample data set generation module, used to generate a sample data set based on an original automobile transmission model, preset model input parameters and preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are preset influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are preset optimization indicators of the automobile transmission system to be optimized;

[0010] A reduced-order model generation module is used to train the neural network model to be trained based on the input sample data and the output sample data to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, so as to determine the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized based on the reduced-order model, and optimize the automobile transmission system to be optimized based on the parameters.

[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for optimizing the automobile transmission system described in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for optimizing the automobile transmission system described in any embodiment of the present invention when executed.

[0016] The technical solution of the embodiment of the present invention generates a sample data set based on the original automobile transmission model, preset model input parameters and preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are preset influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are preset optimization indicators of the automobile transmission system to be optimized; based on the input sample data and the output sample data, the neural network model to be trained is trained to obtain a reduced-order model corresponding to the automobile transmission system to be optimized. Since the degradation model is a neural network model, the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized are determined based on the reduced-order model, and when the automobile transmission system to be optimized is optimized based on the parameters, there is no need to perform multiple iterative calculations, the amount of calculation is small, and it is beneficial to improve the optimization efficiency of the optimization process.

[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a flow chart of an optimization method for an automobile transmission system provided according to an embodiment of the present invention;

[0020] Figure 2 is a flow chart of another method for optimizing an automobile transmission system provided according to an embodiment of the present invention;

[0021] Figure 3 is a schematic structural diagram of an optimization device for an automobile transmission system provided according to an embodiment of the present invention;

[0022] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the method for optimizing the automobile transmission system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "etc." and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] Figure 1 This is a flow chart of an optimization method for an automobile transmission system provided according to an embodiment of the present invention. This embodiment is applicable to the case where an automobile transmission system is optimized by determining parameter values ​​of parameters to be optimized. The method can be executed by an optimization device for an automobile transmission system, and the optimization device for an automobile transmission system can be implemented in the form of hardware and / or software.

[0026] like Figure 1 As shown, the method of this embodiment may specifically include:

[0027] S110, generating a sample data set based on the original vehicle transmission model, preset model input parameters, and preset model output parameters of the vehicle transmission system to be optimized.

[0028] The sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are the influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are the optimization indicators of the automobile transmission system to be optimized. The original automobile transmission model can be a model constructed based on a mathematical formula, such as a mathematical programming model or a differential equation group model.

[0029] Optionally, the influencing parameters include: at least one of transmission ratio, friction coefficient, material characteristic parameter, temperature, wheel parameter, tire parameter and weight. The optimization index includes at least one of the following: at least one of the power transmission efficiency index, acceleration performance index, fuel economy index, durability and reliability index, noise and vibration index, weight and compactness index, cost-effectiveness index and response speed index of the vehicle transmission system to be optimized.

[0030] In this embodiment, the power transmission efficiency index is used to maximize the efficiency of power transmission from the engine to the wheels and reduce energy loss. The acceleration performance index is used to improve the acceleration ability of the vehicle and shorten the time from rest to a specific speed. The fuel economy index is used to reduce fuel consumption and increase the cruising range. The durability and reliability index is used to ensure the long-term stable operation of the transmission system under various working conditions. The noise and vibration index is used to reduce noise and vibration during operation and improve driving comfort. The weight and compactness index is used to reduce the weight of the transmission system and improve the flexibility and maneuverability of the vehicle. The cost-effectiveness index is used to control production and maintenance costs. The response speed index is used to improve the control response during driving and enhance the driving experience.

[0031] In this embodiment, the parameter values ​​corresponding to the preset model input parameters can be input into the original automobile transmission model, and the parameter values ​​corresponding to the preset model output parameters can be output. The input values ​​of each preset model input parameter are used as input sample data, and the output values ​​of the preset model output parameters corresponding to the input values ​​of the preset model input parameters are used as output sample data. The input sample data and the output sample data constitute a sample data set.

[0032] S120. Based on the input sample data and the output sample data, the neural network model to be trained is trained to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, and based on the reduced-order model, parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized are determined, and the automobile transmission system to be optimized is optimized based on the parameters.

[0033] In a specific implementation, a neural network model may be pre-constructed, the pre-constructed neural network model may be trained by inputting sample data and outputting sample data, and the neural network model after training may be determined as a degradation model.

[0034] In order to make the generated reduced-order model match the original automobile transmission model to a high degree, a neural network model can be pre-built based on the correlation between the output data of the original automobile transmission model at different times. Specifically, before the neural network model to be trained is trained based on the input sample data and the output sample data to obtain the reduced-order model corresponding to the automobile transmission system to be optimized, it also includes: building a feedforward neural network model when the current output data corresponding to the original automobile transmission model has no correlation with the historical output data; building a recurrent neural network model when the current output data corresponding to the original automobile transmission model has no correlation with the historical output data and has a correlation with the current input data.

[0035] Among them, the current output data is the data output by the original automobile transmission model at the current moment; the historical output data is the data output by the original automobile transmission model at the moment before the current moment.

[0036] In a specific implementation, it can be determined whether the current output data is associated with the historical output data, that is, the current output data needs to be obtained based on the historical output data. If there is no association between the two, it means that the current output data is only obtained by relying on the current input data, and a feedforward neural network model can be constructed to generate a reduced-order model based on the feedforward neural network model. If there is an association between the two, that is, the current output data depends not only on the current input data but also on the historical output data, a recurrent neural network model can be constructed to generate a reduced-order model based on the recurrent neural network model.

[0037] This embodiment determines the type of neural network model to be constructed by determining whether there is a correlation between the current output data and the historical output data, so that the constructed neural network model can better meet the correlation requirements between the output data of the original automobile transmission model, which is conducive to generating a reduced-order model that better matches the original automobile transmission model.

[0038] In this embodiment, the neural network model to be trained is trained based on the input sample data and the output sample data to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, including: based on the input sample data and the output sample data, the neural network model to be trained is trained until the training is completed when the preset training conditions are met, and the neural network model after the training is obtained as the reduced-order model; wherein the preset training condition is the convergence of the loss function in the neural network model.

[0039] Specifically, the input sample data can be input into the neural network model to be trained to obtain the actual output data output by the neural network model. Based on the output sample data corresponding to the input sample data and the actual output data, the loss value of the neural network model to be trained is determined to correct the model parameters of the neural network model based on the loss value. The convergence of the loss function of the neural network model is used as the training goal, and the trained neural network model is used as the reduced-order model.

[0040] This embodiment provides a method for obtaining a reduced-order model by correcting the model parameters by determining the loss value of the neural network model and taking the convergence of the loss function as the training goal, thereby quickly and effectively completing the training process of the neural network model.

[0041] Optionally, determining parameter values ​​of parameters to be optimized in the automobile transmission system to be optimized based on the reduced-order model includes: determining parameter values ​​of parameters to be optimized in the automobile transmission system to be optimized based on a multi-objective particle swarm algorithm and the reduced-order model.

[0042] The parameters to be optimized are preset model input parameters that need to be optimized. One or more preset model input parameters can be set as the parameters to be optimized.

[0043] It should be noted that this embodiment uses a multi-objective particle swarm algorithm to introduce a parabolic solution for optimization and solution. The parabolic solution can consider multiple objectives at the same time, which is conducive to improving the accuracy of the parameters to be optimized. In the multi-objective particle swarm algorithm, the selection of the global optimal particle is a key link. When selecting the global optimal particle, it is mainly based on the density information of the particles in the created archive set. For the particles in the archive set, the lower the density value, the greater the probability of being selected; conversely, the smaller the probability of being selected. Finally, the method of generating random numbers is used to determine whether the particle is selected as the global optimal particle. Specifically, a target space can be created, and the entire target space can be divided into several grids, each of which has a unique number. The number of particles in each grid is calculated to determine the density value of the grid based on the particle data. The smaller the density value of the grid, the sparser the particles it contains, and vice versa. The density of each grid is normalized to obtain the selection probability of each grid, and the sum of the normalized probabilities is 1. Starting from the first grid, the selection probability of each grid is accumulated in sequence to obtain the cumulative probability. The cumulative probability represents the sum of the selection probabilities of all grids from the first grid to the current grid. Generate a random number between 0 and 1, and determine the grid with a cumulative probability greater than or equal to the random number as the selected grid. For example, if the cumulative probability of the first grid is 0.5, the cumulative probability of the second grid is 1, and the generated random number is 0.4; then the grids greater than or equal to the random number can be screened out, and the grid with the smallest difference between the cumulative probability and the random number can be found among the screened grids as the selected grid, that is, the first grid. Finally, a particle is randomly selected from the selected grid as the global optimal particle. It can be seen that the above process of determining the global optimal particle has a certain degree of randomness, and the quality of the determined global optimal particle is unstable.

[0044] Furthermore, a method for determining the global optimal particle is proposed as follows: for each particle in the archive set, the distance from the particle to the other particles is determined, and the minimum distance among all distances is used as the outlier distance of the particle. The example with the largest outlier distance is used as the global optimal particle.

[0045] In this embodiment, the multi-objective particle swarm algorithm can be used to determine the parameter values ​​of the optimization parameters in the reduced-order model when the preset optimization index of the automobile transmission system to be optimized is met.

[0046] This embodiment uses the example with the largest outlier distance as the global optimal particle, which can control the particles to search more space to the greatest extent, minimize the possibility of the result of the multi-objective particle swarm algorithm falling into the local optimum, and is conducive to improving the ability to find the global optimum.

[0047] The technical solution of the embodiment of the present invention generates a sample data set based on the original automobile transmission model, preset model input parameters and preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are preset influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are preset optimization indicators of the automobile transmission system to be optimized; based on the input sample data and the output sample data, the neural network model to be trained is trained to obtain a reduced-order model corresponding to the automobile transmission system to be optimized. Since the degradation model is a neural network model, the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized are determined based on the reduced-order model, and when the automobile transmission system to be optimized is optimized based on the parameters, there is no need to perform multiple iterative calculations, the amount of calculation is small, and it is beneficial to improve the optimization efficiency of the optimization process.

[0048] Figure 2 is a flowchart of another method for optimizing an automobile transmission system provided according to an embodiment of the present invention. Based on the above embodiment, this embodiment further includes: before generating a sample data set, determining the sensitivity value of the influencing parameter affecting the optimization index in the automobile transmission system to be optimized; determining the influencing parameter with a sensitivity value greater than a preset threshold as the parameter to be optimized for the optimization index of the automobile transmission system to be optimized. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 2 As shown, the method includes:

[0049] S210, determining the sensitivity value of the influencing parameter that affects the optimization index in the automobile transmission system to be optimized; determining the influencing parameter whose sensitivity value is greater than a preset threshold as the parameter to be optimized for the optimization index of the automobile transmission system to be optimized.

[0050] In a specific implementation, at least one preset model input parameter corresponding to the automobile transmission system to be optimized can be used as an influencing parameter affecting the optimization index, and the sensitivity value of each influencing parameter can be determined. The sensitivity value is used to reflect the degree of response of the value of the optimization index to the influencing parameter. The higher the sensitivity value, the faster the value of the optimization index responds to the influencing parameter; conversely, the slower the value of the optimization index responds to the influencing parameter.

[0051] In this embodiment, the method for determining the sensitivity value of the influencing parameter that affects the optimization index in the automobile transmission system to be optimized includes: for each influencing parameter, based on the preset value range of the influencing parameter and the original automobile transmission model, determining multiple groups of parameter sample data, and based on the multiple groups of parameter sample data, determining the sensitivity value of the influencing parameter.

[0052] Each set of parameter sample data includes a sample value of an influencing parameter and a sample optimization index value corresponding to the sample value. The sample optimization index value is the value corresponding to the optimization index when the value of the influencing parameter is the sample value.

[0053] In a specific implementation, multiple values ​​can be arbitrarily selected as sample values ​​within the preset value range of the influencing parameter, each sample value is input into the original vehicle transmission model, and the output value of the original vehicle transmission model is used as the sample optimization index value corresponding to the sample value. Based on each sample value and each sample optimization index value, the sensitivity value of the influencing parameter is determined.

[0054] In order to more clearly and explicitly show the process of determining the sensitivity value of the influencing parameter, any influencing parameter is used as an example for explanation below. For example, the influencing parameter for which the sensitivity value needs to be determined can be set to x1, and the remaining influencing parameters can be set to x2, ..., xn; wherein n represents the number of influencing parameters, which is a positive integer. The process of determining the sensitivity value of the influencing parameter x1 is as follows: k sample values ​​are collected in the preset value range of the influencing parameter x1 in a uniformly random manner, and the remaining influencing parameters adopt preset fixed values. For each sample value of the influencing parameter x1, the sample value and the remaining fixed values ​​of the influencing parameters are input into the original automobile transmission model, and the sample optimization index value corresponding to the sample value is output, and the partial derivative value of the sample optimization index value to the sample value is determined. The average value of the partial derivative values ​​corresponding to each sample value of the influencing parameter x1 is taken as the sensitivity value of the influencing parameter x1.

[0055] After determining the sensitivity value of each influencing parameter, in order to simplify the optimization calculation process and reduce the iteration time while ensuring the optimization effect of the automobile transmission system, the influencing parameters that have a greater impact on the numerical value of the optimization index can be screened out. Specifically, the influencing parameters whose sensitivity values ​​are greater than the preset threshold can be determined as the parameters to be optimized for the optimization index of the automobile transmission system to be optimized. It should be noted that those skilled in the art can determine the specific value of the preset threshold according to the actual application situation, and this embodiment does not limit this.

[0056] S220: Generate a sample data set based on the original vehicle transmission model, preset model input parameters, and preset model output parameters of the vehicle transmission system to be optimized.

[0057] S230. Based on the input sample data and the output sample data, the neural network model to be trained is trained to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, and based on the reduced-order model, parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized are determined, and the automobile transmission system to be optimized is optimized based on the parameters.

[0058] In this embodiment, after determining the sample data set, it can also include: generating at least one proxy model among the Kriging proxy model, the polynomial regression model and the support vector machine model based on the sample data set, and using the proxy model as a substitute for the original vehicle transmission model to simplify the iterative process during the optimization process.

[0059] In this embodiment, the influencing parameters whose sensitivity values ​​are greater than the preset threshold are used as the parameters to be optimized, thereby ensuring the optimization effect of the automobile transmission system while simplifying the optimization calculation process and reducing the iteration time.

[0060] Figure 3 1 is a schematic diagram of the structure of an optimization device for an automobile transmission system provided according to an embodiment of the present invention, and the device is used to execute the optimization method for an automobile transmission system provided by any of the above embodiments. The device and the optimization method for an automobile transmission system of the above embodiments belong to the same inventive concept, and the details not fully described in the embodiment of the optimization device for an automobile transmission system can refer to the embodiment of the optimization method for an automobile transmission system. Figure 3 As shown, the device comprises:

[0061] The sample data set generation module 10 is used to generate a sample data set based on the original automobile transmission model, the preset model input parameters and the preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are the influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are the optimization indicators of the automobile transmission system to be optimized;

[0062] The reduced-order model generation module 11 is used to train the neural network model to be trained based on the input sample data and the output sample data, to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, to determine the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized based on the reduced-order model, and to optimize the automobile transmission system to be optimized based on the parameters.

[0063] Based on any optional technical solution in the embodiments of the present invention, optionally, the device further includes:

[0064] A sensitivity value determination module, used to determine the sensitivity value of the influencing parameter affecting the optimization index in the automobile transmission system to be optimized before generating the sample data set;

[0065] The module for determining parameters to be optimized is used to determine the influencing parameters whose sensitivity values ​​are greater than a preset threshold as the parameters to be optimized for the optimization index of the automobile transmission system to be optimized.

[0066] Based on any optional technical solution in the embodiments of the present invention, optionally, the sensitivity value determination module includes:

[0067] A sensitivity value determination submodule is used to determine, for each influencing parameter, a plurality of groups of parameter sample data based on a preset value range of the influencing parameter and an original vehicle transmission model, and determine a sensitivity value of the influencing parameter based on the plurality of groups of parameter sample data;

[0068] Each set of parameter sample data includes a sample value affecting the parameter and a sample optimization index value corresponding to the sample value.

[0069] Based on any optional technical solution in the embodiments of the present invention, optionally, the reduced-order model generating module 11 includes:

[0070] The model training submodule is used to train the neural network model to be trained based on the input sample data and the output sample data until the training is completed when the preset training conditions are met, and obtain the neural network model after the training as a reduced-order model;

[0071] Among them, the preset training condition is the convergence of the loss function in the neural network model.

[0072] Based on any optional technical solution in the embodiments of the present invention, optionally, the reduced-order model generating module 11 includes:

[0073] The parameter value determination submodule is used to determine the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized based on the multi-objective particle swarm algorithm and the reduced-order model.

[0074] Based on any optional technical solution in the embodiments of the present invention, optionally, the method further includes:

[0075] A feedforward neural network model building module is used to train the neural network model to be trained based on the input sample data and the output sample data to obtain a reduced-order model corresponding to the vehicle transmission system to be optimized, and to build a feedforward neural network model when there is no correlation between the current output data and the historical output data corresponding to the original vehicle transmission model;

[0076] The recurrent neural network model building module is used to build a recurrent neural network model when the current output data corresponding to the original automobile transmission model has no correlation with the historical output data, but has a correlation with the current input data.

[0077] Based on any optional technical solution in the embodiments of the present invention, optionally, the influencing parameters include: at least one of: transmission ratio, friction coefficient, material characteristic parameters, temperature, wheel parameters, tire parameters and weight.

[0078] The technical solution of the embodiment of the present invention generates a sample data set based on the original automobile transmission model, preset model input parameters and preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are preset influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are preset optimization indicators of the automobile transmission system to be optimized; based on the input sample data and the output sample data, the neural network model to be trained is trained to obtain a reduced-order model corresponding to the automobile transmission system to be optimized. Since the degradation model is a neural network model, the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized are determined based on the reduced-order model, and when the automobile transmission system to be optimized is optimized based on the parameters, there is no need to perform multiple iterative calculations, the amount of calculation is small, and it is beneficial to improve the optimization efficiency of the optimization process.

[0079] It is worth noting that in the above-mentioned embodiment of the optimization device for the automobile transmission system, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0080] Figure 4 1 is a schematic diagram of the structure of an electronic device for implementing the optimization method of the automobile transmission system of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0081] like Figure 4As shown, the electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 21 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 23. In RAM23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, ROM22 and RAM23 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0082] A number of components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0083] The processor 21 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as an optimization method for an automobile transmission system.

[0084] In some embodiments, the optimization method of the automobile transmission system can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps of the optimization method of the automobile transmission system described above can be performed. Alternatively, in other embodiments, the processor 21 can be configured to execute the optimization method of the automobile transmission system by any other appropriate means (for example, by means of firmware).

[0085] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0087] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0088] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0089] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0090] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0091] This embodiment also provides a computer program product, including a computer program, which, when executed by a processor, implements the automobile transmission system optimization method provided in any embodiment of the present application.

[0092] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0093] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0094] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for optimizing an automobile transmission system, characterized in that: include: Generate a sample data set based on an original automobile transmission model, preset model input parameters and preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are preset influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are preset optimization indicators of the automobile transmission system to be optimized; Based on the input sample data and the output sample data, the neural network model to be trained is trained to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, so as to determine the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized based on the reduced-order model, and optimize the automobile transmission system to be optimized based on the parameters.

2. The method according to claim 1, characterized in that: Before generating the sample data set, the method further includes: Determine the sensitivity value of the influencing parameter affecting the optimization index in the automobile transmission system to be optimized; The influencing parameter whose sensitivity value is greater than a preset threshold is determined as the parameter to be optimized of the automobile transmission system to be optimized for the optimization index.

3. The method according to claim 2, characterized in that The step of determining the sensitivity value of the influencing parameter affecting the optimization index in the automobile transmission system to be optimized includes: For each influencing parameter, based on a preset value range of the influencing parameter and the original vehicle transmission model, multiple groups of parameter sample data are determined, and based on the multiple groups of parameter sample data, a sensitivity value of the influencing parameter is determined; Each group of the parameter sample data includes a sample value of the influencing parameter and a sample optimization index value corresponding to the sample value.

4. The method according to claim 1, characterized in that The step of training the neural network model to be trained based on the input sample data and the output sample data to obtain a reduced-order model corresponding to the automobile transmission system to be optimized includes: Based on the input sample data and the output sample data, the neural network model to be trained is trained until the training is completed when a preset training condition is met, and the neural network model after the training is obtained as the reduced-order model; Wherein, the preset training condition is the convergence of the loss function in the neural network model.

5. The method according to claim 1, characterized in that The step of determining the parameter value of the parameter to be optimized in the automobile transmission system to be optimized based on the reduced-order model comprises: Based on the multi-objective particle swarm algorithm and the reduced-order model, the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized are determined.

6. The method according to claim 1, characterized in that Before training the neural network model to be trained based on the input sample data and the output sample data to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, the method further includes: In the case where there is no correlation between the current output data and the historical output data corresponding to the original automobile transmission model, constructing a feedforward neural network model; When the current output data corresponding to the original automobile transmission model has no correlation with the historical output data but has a correlation with the current input data, a recurrent neural network model is constructed.

7. The method according to claim 1, characterized in that The influencing parameters include: at least one of: transmission ratio, friction coefficient, material characteristic parameters, temperature, wheel parameters, tire parameters and weight.

8. An optimization device for an automobile transmission system, characterized in that: include: A sample data set generation module, used to generate a sample data set based on an original automobile transmission model, preset model input parameters and preset model output parameters of the automobile transmission system to be optimized; wherein the sample data set includes input sample data corresponding to the preset model input parameters and output sample data corresponding to the preset model output parameters; the preset model input parameters are preset influencing parameters of the automobile transmission system to be optimized, and the preset model output parameters are preset optimization indicators of the automobile transmission system to be optimized; A reduced-order model generation module is used to train the neural network model to be trained based on the input sample data and the output sample data to obtain a reduced-order model corresponding to the automobile transmission system to be optimized, so as to determine the parameter values ​​of the parameters to be optimized in the automobile transmission system to be optimized based on the reduced-order model, and optimize the automobile transmission system to be optimized based on the parameters.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the automobile transmission system optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for optimizing the automobile transmission system according to any one of claims 1 to 7 when executed.

Images