Method, device, storage medium and vehicle for producing a vehicle transmission

Abstract

The application discloses a production method and device of a vehicle transmission part, a storage medium and a vehicle. The method comprises the following steps: obtaining vehicle driving data, a target service life and gear design parameters, wherein the vehicle driving data is used to represent data generated by the vehicle in a driving process under a target scene, the target service life is used to represent a service life to be achieved by the vehicle transmission part, and the gear design parameters are used to represent design parameters of gears in the vehicle transmission part; a neural network model is used to predict process parameters of the vehicle transmission part based on the vehicle driving data, the target service life and the gear design parameters, to obtain a prediction result, wherein the process parameters are used to represent at least one parameter that needs to be controlled or adjusted in a machining process of the vehicle transmission part; and the vehicle transmission part is produced based on the prediction result and the gear design parameters. The application solves the technical problem of low service life of the vehicle transmission part in the related art.

Description

Technical Field

[0001] This invention relates to the field of vehicle manufacturing, and more specifically, to a method, apparatus, storage medium, and vehicle for producing vehicle transmission components. Background Technology

[0002] Currently, methods for optimizing the lifespan of vehicle transmission components can be broadly categorized as follows: structural design optimization; adding wear-resistant coatings to the gear surface to increase service life; and improving material properties by altering the gear body material, thereby enhancing gear fatigue life. However, these traditional lifespan optimization methods consider only one aspect of the factors and cannot take all influencing factors into account, thus limiting the effectiveness of improving gear lifespan.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, storage medium, and vehicle for producing vehicle transmission components, thereby at least addressing the technical problem of low lifespan of vehicle transmission components in related technologies.

[0005] According to one aspect of the present invention, a method for manufacturing a vehicle transmission component is provided, comprising: acquiring vehicle driving data, a target lifespan, and gear design parameters, wherein the vehicle driving data represents data generated by the vehicle during driving in a target scenario, the target lifespan represents the expected service life of the vehicle transmission component, and the gear design parameters represent the design parameters of the gears in the vehicle transmission component; using a neural network model to predict process parameters of the vehicle transmission component based on the vehicle driving data, the target lifespan, and the gear design parameters, and obtaining prediction results, wherein the process parameters represent at least one parameter of the vehicle transmission component that needs to be controlled or adjusted during processing; and manufacturing the vehicle transmission component based on the prediction results and the gear design parameters.

[0006] Optionally, producing vehicle transmission components based on prediction results and gear design parameters includes: determining production parameters for the vehicle transmission components based on prediction results, wherein the production parameters include at least one of the following: gear machining parameters, gear position parameters, gear material parameters, and lubricating oil parameters; and producing vehicle transmission components based on production parameters and gear design parameters.

[0007] Optionally, the neural network model is trained based on the sample lifetime of vehicle transmission components, sample vehicle driving data, and sample process parameters under different conditions. The sample lifetime of vehicle transmission components under different conditions is obtained based on the sample vehicle driving data, wherein the sample vehicle driving data is used to represent the data generated by the vehicle during driving in different scenarios.

[0008] Optionally, the sample life of the transmission component under different conditions is obtained by bench testing the target vehicle's driving data. The target vehicle's driving data is obtained by converting the rainflow count results to equal damage. The rainflow count results are obtained by performing fatigue analysis on the sample vehicle's driving data using the rainflow count algorithm.

[0009] Optionally, a simulation experimental environment for vehicle transmission components is constructed based on the target scenario; fatigue experiments are conducted on the vehicle transmission components in the simulation experimental environment to obtain the actual lifespan of the vehicle transmission components; and the model parameters of the neural network model are adjusted based on the target lifespan and the actual lifespan.

[0010] Optionally, fatigue tests are conducted on vehicle transmission components in a simulation experimental environment to obtain the actual lifespan of the vehicle transmission components, including: obtaining process parameters and gear design parameters of the vehicle transmission components; and conducting fatigue tests on the vehicle transmission components in a simulation experimental environment based on the process parameters and gear design parameters to obtain the actual lifespan of the vehicle transmission components.

[0011] Optionally, the model parameters of the neural network model are adjusted based on the target lifetime and the actual lifetime, including: constructing a loss function based on the target lifetime and the actual lifetime; and adjusting the model parameters of the neural network model using the loss function.

[0012] According to another aspect of the present invention, a production apparatus for a vehicle transmission component is also provided, comprising: an acquisition module for acquiring vehicle driving data, a target lifespan, and gear design parameters, wherein the vehicle driving data represents data generated by the vehicle during driving in a target scenario, the target lifespan represents the expected service life of the vehicle transmission component, and the gear design parameters represent the design parameters of the gears in the vehicle transmission component; a prediction module for using a neural network model to predict process parameters of the vehicle transmission component based on the vehicle driving data, the target lifespan, and the gear design parameters, and obtaining prediction results, wherein the process parameters represent at least one parameter of the vehicle transmission component that needs to be controlled or adjusted during processing; and a generation module for producing the vehicle transmission component based on the prediction results and the gear design parameters.

[0013] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, the above-described method for producing a vehicle transmission component is executed in a processor of the device.

[0014] According to another aspect of the present invention, a vehicle is also provided, along with one or more processors; a storage device for storing one or more programs; and when one or more programs are executed by one or more processors, causing the one or more processors to perform the above-described method for producing a vehicle transmission component.

[0015] In this embodiment of the invention, vehicle driving data, target lifespan, and gear design parameters are acquired. Vehicle driving data represents data generated during vehicle operation in a target scenario. Target lifespan represents the expected service life of the vehicle transmission component. Gear design parameters represent the design parameters of the gears within the vehicle transmission component. A neural network model is used to predict the process parameters of the vehicle transmission component based on the vehicle driving data, target lifespan, and gear design parameters, yielding prediction results. Process parameters represent at least one parameter that needs to be controlled or adjusted during the manufacturing process of the vehicle transmission component. The vehicle transmission component is then manufactured based on the prediction results and gear design parameters, thus realizing the design and production of the vehicle transmission component. It is noteworthy that using a neural network model to predict the process parameters of the vehicle transmission component based on vehicle driving data, target lifespan, and gear design parameters comprehensively considers the aforementioned influencing factors during the design and production stages of the vehicle transmission component, effectively improving the service life of the vehicle transmission component and thus solving the technical problem of low service life of vehicle transmission components in related technologies. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a method for producing a vehicle transmission component according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of a neural network model of a vehicle transmission component manufacturing method according to an embodiment of the present invention;

[0019] Figure 3 This is a flowchart illustrating the output of process parameters via a neural network model according to an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of a production apparatus for a vehicle transmission component according to an embodiment of this application. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] Example 1

[0024] According to an embodiment of the present invention, an embodiment of a method for producing vehicle transmission components is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0025] Figure 1 This is a flowchart of a method for producing a vehicle transmission component according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0026] Step S102: Obtain vehicle driving data, target lifespan, and gear design parameters.

[0027] Among them, vehicle driving data is used to represent the data generated by the vehicle during driving in the target scenario, target life is used to represent the lifespan to be achieved by the vehicle transmission components, and gear design parameters are used to represent the design parameters of the gears in the vehicle transmission components.

[0028] The aforementioned vehicle driving data can refer to various data information generated during vehicle operation, including but not limited to vehicle position, speed, acceleration, distance traveled, travel time, turning data, gear data, driving mode, input torque of the drive axle, input speed and time, etc. Vehicle driving data can be used to characterize the user's driving habits.

[0029] The aforementioned vehicle transmission components can refer to parts in the power system of an automobile, used to transmit power and torque and convert the energy of the engine into the motion of the wheels. These components may include, but are not limited to, gears, bearings, drive shafts, drive shafts, differentials, and other devices.

[0030] The aforementioned target lifespan can be used to represent the required lifespan of vehicle transmission components. The target lifespan can be set by the user based on factors such as the type of vehicle transmission component, usage conditions, and operating environment.

[0031] The gear design parameters mentioned above refer to the parameters obtained by the user in designing the gears in the vehicle transmission components, which may include, but are not limited to, gear module, number of teeth, pressure angle, gear width, gear material, gear precision grade, gear transmission ratio, gear lubrication, gear axial force, gear transmission efficiency, etc.

[0032] In one optional embodiment, vehicle driving data generated when a user drives the vehicle can be obtained through various sensors and on-board equipment mounted on the vehicle, or historical vehicle driving data can be used, or other methods can be used to obtain vehicle driving data, which are not limited here.

[0033] By performing the above step S102, various factors affecting the lifespan of vehicle transmission components during the design and production stages are obtained, which facilitates the comprehensive consideration of these various influencing factors in subsequent steps during the design and production stages of vehicle transmission components.

[0034] Step S104: Using a neural network model, the process parameters of the vehicle transmission components are predicted based on vehicle driving data, target life, and gear design parameters to obtain the prediction results.

[0035] Among them, process parameters are used to represent at least one parameter that needs to be controlled or adjusted during the processing of vehicle transmission components.

[0036] The aforementioned neural network model can be a computational model consisting of an input layer, a hidden layer, and an output layer. The input layer can receive vehicle driving data, target lifespan, and gear design parameters. The hidden layer performs calculations and processing, and the output layer outputs the process parameters of the vehicle transmission components.

[0037] The aforementioned process parameters can be at least one parameter that needs to be controlled or adjusted during the manufacturing process of the transmission component. These parameters may include, but are not limited to, tooth surface parameters, machining parameters, gear materials, contact area distribution, offset distance, lubricating oil parameters, and lubrication methods that may affect gear life. Specifically, tooth surface parameters and machining parameters may include parameters such as gear helix angle, tooth surface roughness, surface hardness, core hardness, and hardened layer depth. Gear materials can refer to various materials used in gear manufacturing. Contact area distribution may include positions such as the middle end, the smaller end of the middle, and the larger end of the middle of the gear. Lubricating oil parameters may include data such as the viscosity, density, and content of major trace elements in the lubricating oil. Lubrication methods may include active lubrication, splash lubrication, etc.

[0038] In one alternative embodiment, factors affecting the lifespan of transmission components, such as vehicle driving data, target lifespan, and gear design parameters, can be input into the neural network model. The neural network is then used to calculate and transmit these factors, outputting predicted results of the process parameters of the vehicle transmission components.

[0039] By performing step S104 above, a neural network model is used to comprehensively utilize various influencing factors affecting the lifespan of transmission components, and prediction results of process parameters of vehicle transmission components are obtained. This facilitates subsequent steps in producing vehicle transmission components based on the prediction results and gear design parameters.

[0040] Step S106: Produce vehicle transmission components based on the prediction results and gear design parameters.

[0041] In one alternative embodiment, prediction results can be obtained by analyzing process parameters during the production of vehicle transmission components, and vehicle transmission components can be produced based on the gear design parameters required for production and the prediction results.

[0042] By performing the above step S106, vehicle transmission components are produced based on the prediction results and gear design parameters. This achieves comprehensive consideration of various factors affecting the lifespan of transmission components during the design and production stages of vehicle transmission components, effectively improving the service life of transmission components.

[0043] In this embodiment of the invention, vehicle driving data, target lifespan, and gear design parameters are acquired. Vehicle driving data represents data generated during vehicle operation in a target scenario. Target lifespan represents the expected service life of the vehicle transmission component. Gear design parameters represent the design parameters of the gears within the vehicle transmission component. A neural network model is used to predict the process parameters of the vehicle transmission component based on the vehicle driving data, target lifespan, and gear design parameters, yielding prediction results. Process parameters represent at least one parameter of the vehicle transmission component that needs to be controlled or adjusted during manufacturing. The vehicle transmission component is then produced based on the prediction results and gear design parameters, thus realizing the design and production of the transmission component. It is noteworthy that using a neural network model to predict the process parameters of the vehicle transmission component based on vehicle driving data, target lifespan, and gear design parameters comprehensively considers various influencing factors during the design and production stages of the transmission component, effectively improving the service life of the transmission component and thus solving the technical problem of low service life of vehicle transmission components in related technologies.

[0044] Optionally, producing vehicle transmission components based on prediction results and gear design parameters includes: determining production parameters for the vehicle transmission components based on prediction results, wherein the production parameters include at least one of the following: gear machining parameters, gear position parameters, gear material parameters, and lubricating oil parameters; and producing vehicle transmission components based on production parameters and gear design parameters.

[0045] The aforementioned production parameters refer to various parameters and indicators used to describe the gear manufacturing process during gear production. These parameters may include, but are not limited to, gear module, number of teeth, pressure angle, gear tooth profile modification, gear precision grade, gear hardness, and gear surface roughness. These parameters are key elements in gear manufacturing and can affect the quality, performance, and reliability of gears.

[0046] In one optional embodiment, parameters such as the type, module, number of teeth, tooth width, and material of the gear to be produced can be determined based on the prediction results. Based on these gear parameters, the gear tooth profile is designed and the gear manufacturing process is determined. Finally, the gear production parameters are calculated based on the gear manufacturing process and gear parameters. The process of producing vehicle transmission components based on production parameters and gear design parameters may include, but is not limited to, steps such as designing gears, determining gear materials, determining gear processing technology, gear processing, heat treatment, gear inspection, assembly, and quality control.

[0047] Optionally, the neural network model is trained based on the sample lifetime of vehicle transmission components, sample vehicle driving data, and sample process parameters under different conditions. The sample lifetime of vehicle transmission components under different conditions is obtained based on the sample vehicle driving data, wherein the sample vehicle driving data is used to represent the data generated by the vehicle during driving in different scenarios.

[0048] The sample lifespan of the vehicle transmission components mentioned above can refer to the historical lifespan of the vehicle transmission components. The sample lifespan of vehicle transmission components is affected by a variety of factors such as vehicle driving conditions, user driving habits, vehicle maintenance and repair, and vehicle parking environment.

[0049] The aforementioned sample lifespan of vehicle transmission components can refer to the lifespan of sample vehicle transmission components used as the training and testing sets in a neural network model, and can be used to train and test the neural network model.

[0050] The aforementioned sample vehicle driving data can refer to vehicle driving data used as the training and testing sets in a neural network model, which can be used to train and test the neural network model.

[0051] The aforementioned sample process parameters can refer to the process parameters of the sample vehicle transmission components used as the training and testing sets in the neural network model, and can be used to train and test the neural network model.

[0052] In one optional embodiment, a certain number of sample lifespans of vehicle transmission components, sample vehicle driving data, and sample process parameters can be used as a training set. The training set is input into the neural network model for training, and the model parameters are continuously adjusted to improve the model's accuracy and generalization ability. Then, a portion of the sample lifespans of vehicle transmission components, sample vehicle driving data, and sample process parameters are used as a test set. The trained model is tested using the test set to evaluate the accuracy of the generated vehicle transmission component process parameters, thereby obtaining the neural network model.

[0053] Optionally, the sample life of the transmission component under different conditions is obtained by bench testing the target vehicle's driving data. The target vehicle's driving data is obtained by converting the rainflow count results to equal damage. The rainflow count results are obtained by performing fatigue analysis on the sample vehicle's driving data using the rainflow count algorithm.

[0054] The rainflow counting algorithm described above can be used as a method for fatigue life prediction and vibration signal analysis. The rainflow counting algorithm can decompose the vibration signal into a series of combinations of amplitude and stress cycle number, and then count these cycles. Based on the characteristics of the vibration signal, the cumulative damage is calculated, thereby predicting the fatigue life of the transmission component.

[0055] The fatigue analysis described above refers to the analysis and evaluation of the fatigue behavior of materials, structures, or systems during long-term use. Fatigue, in this context, refers to the failure phenomenon that occurs when a material or structure is subjected to alternating loads and undergoes a certain number of cyclic loading cycles. The purpose of fatigue analysis is to determine the fatigue life of a material or structure to ensure that it does not fail due to fatigue within its service life.

[0056] The aforementioned damage transformation refers to the process of converting damage in a material into an observable signal or extracting useful information. Damage typically refers to defects or changes in the material, such as cracks, fatigue, wear, and corrosion. The purpose of damage transformation is to predict material lifespan, performance degradation, or failure in advance through monitoring and assessing material damage, and to take corresponding repair, replacement, or improvement measures to ensure the safety and reliability of materials and structures.

[0057] The aforementioned bench testing refers to establishing a bench facility in a laboratory or factory that simulates the actual working environment for testing and verifying a certain device, system, or product. Bench testing can help verify the performance, reliability, and safety of the device, system, or product, identify potential problems, and make improvements and optimizations.

[0058] In one optional embodiment, fatigue analysis can be performed on sample vehicle driving data that characterizes user driving habits to obtain rainflow count results. The rainflow count results can be converted to equal damage to obtain target vehicle driving data. Finally, bench tests can be performed on the target vehicle driving data to obtain the sample life of transmission components under different conditions.

[0059] Optionally, a simulation experimental environment for vehicle transmission components is constructed based on the target scenario; fatigue experiments are conducted on the vehicle transmission components in the simulation experimental environment to obtain the actual lifespan of the vehicle transmission components; and the model parameters of the neural network model are adjusted based on the target lifespan and the actual lifespan.

[0060] The target scenarios mentioned above can be used to represent different driving scenarios in which simulated users are in, and data representing users' driving habits under different conditions can be obtained through different driving scenarios.

[0061] The aforementioned simulation environment can be an experimental environment that simulates the operation of a vehicle transmission system. By simulating the movement and interaction of various components of the vehicle transmission system, as well as the influence of the external environment, the performance and reliability of the vehicle transmission components can be evaluated.

[0062] The aforementioned fatigue test can refer to the process of testing the fatigue performance of components in a vehicle transmission system. This is used to evaluate the durability and lifespan of transmission components during long-term use and to determine their safety performance under actual working conditions.

[0063] In one alternative embodiment, fatigue tests can be conducted on the vehicle transmission components under different usage conditions in an experimental environment simulating the operation of the vehicle transmission components to obtain the actual lifespan of the vehicle transmission components. Finally, the parameters of the neural network model are adjusted based on the target lifespan of the vehicle transmission components and the actual lifespan of the vehicle transmission components under different usage conditions to improve the accuracy and generalization ability of the model.

[0064] Optionally, fatigue tests are conducted on vehicle transmission components in a simulation experimental environment to obtain the actual lifespan of the vehicle transmission components, including: obtaining process parameters and gear design parameters of the vehicle transmission components; and conducting fatigue tests on the vehicle transmission components in a simulation experimental environment based on the process parameters and gear design parameters to obtain the actual lifespan of the vehicle transmission components.

[0065] In one optional embodiment, fatigue tests can be conducted by setting different process parameters and gear design parameters in the experiment, and the failure time of the transmission components can be recorded to obtain the lifespan of the transmission components under different parameters. The experimental data can be statistically analyzed to obtain the lifespan distribution curve of the transmission components, thereby evaluating the reliability and lifespan prediction of the transmission components. Based on this experimental data, the design of the transmission components can be optimized and improved to enhance their lifespan and reliability.

[0066] Optionally, the model parameters of the neural network model are adjusted based on the target lifetime and the actual lifetime, including: constructing a loss function based on the target lifetime and the actual lifetime; and adjusting the model parameters of the neural network model using the loss function.

[0067] The loss function mentioned above can be used to measure the difference between the model's prediction and the actual result. The smaller the value of the loss function, the closer the model's prediction is to the actual result, and the better the model's performance. During training, the model uses optimization algorithms, such as gradient descent, to minimize the loss function in order to improve the model's prediction accuracy.

[0068] In an alternative embodiment, a loss function can be constructed to measure the difference between the target and the actual life. The design of the loss function can be determined according to specific needs and circumstances. For example, a possible loss function can be designed as follows: Loss function = Actual life - Target life. In this loss function, the actual life refers to the actual service life of the vehicle transmission component, while the target life is a pre-set expected life. By calculating the value of the loss function, the degree of difference between the target life and the actual life can be evaluated.

[0069] In one alternative embodiment, the model parameters of the neural network model can be adjusted using a loss function via backpropagation. In practice, various loss functions can be used to adjust the model parameters, such as the squared error loss function and the cross-entropy loss function. The specific loss function chosen depends on the characteristics and requirements of the problem. Simultaneously, regularization methods can also be used to adjust the model parameters to prevent overfitting.

[0070] In one alternative embodiment, this application proposes an optimization method based on the target life of transmission components. Taking gears as an example, after designers determine the gear design parameters, they typically use simulation software to verify the fatigue life at the simulation level. Then, they apply a strengthening load spectrum and combine this with bench tests to verify the fatigue life of the transmission components. This is a traditional forward development approach. There are two problems here: First, each time, the tooth surface machining parameters and gear materials can only be determined based on experience, often through inherent judgments and understandings. It's impossible to fully consider all the factors involved, and the design boundary depends on the limits of the designer's cognition, potentially leading to design redundancy. Second, without a development database, verification must be done through simulation or bench tests, limiting the time-sharing potential. If a reverse development approach is established, by creating a process parameter database, based on the completed gear design parameters and the understanding of user driving habits, and using the target life as input, the model can output process parameters, significantly shortening the development verification cycle and obtaining the optimal design parameters that meet the requirements.

[0071] In one alternative embodiment, Figure 2 This is a schematic diagram of a neural network model of an optional vehicle transmission component manufacturing method according to an embodiment of the present invention, such as... Figure 2 As shown, the neural network model consists of an input layer that receives raw data, several hidden layers in the middle for extracting and transforming features, and an output layer that produces the final prediction result. The input layer contains the target life, typical load spectrum, and gear design parameters; the output layer contains tooth surface parameters and machining parameters, gear material, contact area distribution, offset distance, lubricant parameters, and lubrication method.

[0072] In one optional embodiment, the overall scheme of this embodiment is based on target life requirements and gear design parameters, guiding the selection of process parameters. Process parameters refer to all factors that may affect lifespan, including tooth surface parameters and gear machining parameters, gear material, contact area distribution, offset distance, lubricant parameters, and the choice of lubrication method. Tooth surface parameters and gear machining parameters include helix angle, tooth surface roughness, surface hardness, core hardness, and hardened layer depth. Gear materials include a range of possible gear materials. Contact area distribution includes the middle end, the smaller end of the middle, and the larger end of the middle. Lubricant parameters include information such as lubricant viscosity, density, and the content of major trace elements. Lubrication methods include active lubrication and splash lubrication. The method guiding the selection of process parameters is a neural network.

[0073] In one alternative embodiment, Figure 3 This is a flowchart illustrating the output of process parameters using a neural network model according to an embodiment of the present invention, such as... Figure 3 As shown, load spectrum data characterizing user driving habits, i.e., sample vehicle driving data, is collected. Typical user driving habit data is not limited to the input torque and input speed time history of the drive axle. On one hand, this data serves as the first input to the subsequent neural network. On the other hand, this data undergoes rainflow counting and damage conversion to generate a reinforced load spectrum for bench testing. Using this load spectrum, i.e., the target vehicle driving data, bench testing is conducted to verify the data and obtain the total number of cycles / life under different conditions, i.e., the sample life of the transmission component under different conditions. The obtained total number of cycles / life under different conditions is used as the second input to the model. When designers complete the preliminary design of gear parameters, the factory parameters of the gears are used as the third input to the model. The process parameters are used as the output to construct a neural network model, which is then trained. When user driving habits change, or new requirements are placed on the target life, or the gear parameters are optimized, the optimal process parameters can be obtained based on this network.

[0074] This method utilizes load spectrum data derived from user driving habits, ensuring the accuracy and representativeness of the entire prediction method. Furthermore, the approach of using the target life as input, combined with gear design parameters to derive a series of process parameters, is unique and lacks in many current methods. Neural networks further enhance the speed and intelligence of the prediction process.

[0075] Example 2

[0076] According to another aspect of the present invention, a vehicle transmission component production apparatus is also provided. This apparatus can execute the vehicle transmission component production method of the above embodiments. The specific implementation method and preferred application scenarios are the same as those of the above embodiments, and will not be repeated here.

[0077] Figure 4 This is a schematic diagram of a production apparatus for a vehicle transmission component according to an embodiment of this application, as shown below. Figure 4 As shown, the device includes the following: an acquisition module 402, a prediction module 404, and a generation module 406.

[0078] The acquisition module 402 is used to acquire vehicle driving data, target lifespan, and gear design parameters. The vehicle driving data represents the data generated by the vehicle during driving in the target scenario. The target lifespan represents the expected service life of the vehicle transmission component. The gear design parameters represent the design parameters of the gears in the vehicle transmission component. The prediction module 404 is used to predict the process parameters of the vehicle transmission component based on the vehicle driving data, target lifespan, and gear design parameters using a neural network model to obtain prediction results. The process parameters represent at least one parameter of the vehicle transmission component that needs to be controlled or adjusted during the manufacturing process. The generation module 406 is used to produce the vehicle transmission component based on the prediction results and gear design parameters.

[0079] In the above embodiments of this application, the generation module includes: a determination unit and a production unit.

[0080] The determining unit is used to determine the production parameters of the vehicle transmission component based on the prediction results. The production parameters include at least one of the following: gear machining parameters, gear position parameters, gear material parameters, and lubricating oil parameters. The production unit is used to produce the vehicle transmission component based on the production parameters and gear design parameters.

[0081] The prediction module includes a neural network model trained on sample lifespan of vehicle transmission components under different conditions, sample vehicle driving data, and sample process parameters. The sample lifespan of vehicle transmission components under different conditions is obtained based on sample vehicle driving data, which represents the data generated by the vehicle during driving in different scenarios.

[0082] The prediction module includes the sample life of transmission components under different conditions, which is obtained by bench testing the target vehicle's driving data. The target vehicle's driving data is obtained by converting the rain flow count results into equal damage. The rain flow count results are obtained by fatigue analysis of the sample vehicle's driving data using the rain flow count algorithm.

[0083] In the above embodiments of this application, the prediction module includes: a construction unit, an experimental unit, and an adjustment unit.

[0084] The construction unit is used to build a simulation experimental environment for vehicle transmission components based on the target scenario; the experimental unit is used to conduct fatigue experiments on vehicle transmission components in the simulation experimental environment to obtain the actual life of vehicle transmission components; and the adjustment unit is used to adjust the model parameters of the neural network model based on the target life and the actual life.

[0085] In the above embodiments of this application, the experimental unit includes: an acquisition subunit and an experimental subunit.

[0086] The acquisition subunit is used to acquire process parameters and gear design parameters of vehicle transmission components; the experiment subunit is used to conduct fatigue tests on vehicle transmission components in a simulation environment based on process parameters and gear design parameters to obtain the actual life of vehicle transmission components.

[0087] In the above embodiments of this application, the adjustment unit includes: a construction subunit and an adjustment subunit.

[0088] The construction subunit is used to construct a loss function based on the target lifetime and the actual lifetime; the adjustment subunit is used to adjust the model parameters of the neural network model using the loss function.

[0089] Example 3

[0090] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, the above-described method for producing a vehicle transmission component is executed in a processor of the device.

[0091] The computer storage medium mentioned in the above steps can be a medium used in computer memory to store certain discontinuous physical quantities. Computer storage media mainly include semiconductors, magnetic cores, magnetic drums, magnetic tapes, and laser discs. Computer-readable storage media includes stored programs, which can be a set of instructions that a computer can recognize and execute, running on an electronic computer to meet certain human needs—an information tool.

[0092] Example 4

[0093] According to another aspect of the present invention, a vehicle is also provided, along with one or more processors; a storage device for storing one or more programs; and when one or more programs are executed by one or more processors, causing the one or more processors to perform the above-described method for producing a vehicle transmission component.

[0094] The storage device in the above steps can be a type of sequential logic circuit, a memory component used to store data and instructions, mainly used to store programs and data; the processor can be a functional unit that interprets and executes instructions, and it has a unique set of operation commands, which can be called the processor's instruction set, such as store, load, etc.; the storage device stores computer programs, which can be a set of instructions that a computer can recognize and execute, running on an electronic computer, and is an information tool that meets people's certain needs.

[0095] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0097] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0099] If the integrated unit is implemented as 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 technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0100] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for producing a vehicle transmission component, characterized in that, include: Acquire vehicle driving data, target lifespan, and gear design parameters, wherein the vehicle driving data represents the data generated by the vehicle during driving in a target scenario, the target lifespan represents the expected service life of the vehicle transmission component, and the gear design parameters represent the design parameters of the gears in the vehicle transmission component. The process parameters of the vehicle transmission component are predicted using a neural network model based on the vehicle driving data, the target life, and the gear design parameters, and the prediction results are obtained. The process parameters are used to represent at least one parameter of the vehicle transmission component that needs to be controlled or adjusted during the processing. The vehicle transmission component is produced based on the predicted results and the gear design parameters.

2. The method for producing vehicle transmission components according to claim 1, characterized in that, Based on the prediction results and the gear design parameters, the vehicle transmission component is manufactured, including: Based on the prediction results, the production parameters of the vehicle transmission component are determined, wherein the production parameters include at least one of the following: gear machining parameters, gear position parameters, gear material parameters, and lubricating oil parameters; The vehicle transmission component is manufactured based on the production parameters and the gear design parameters.

3. The method for producing vehicle transmission components according to claim 1, characterized in that, The neural network model is trained based on the sample lifetime of the vehicle transmission component under different conditions, sample vehicle driving data, and sample process parameters. The sample lifetime of the vehicle transmission component under different conditions is obtained based on the sample vehicle driving data, wherein the sample vehicle driving data is used to represent the data generated by the vehicle during driving in different scenarios.

4. The method for producing vehicle transmission components according to claim 3, characterized in that, The sample lifespan of the transmission components under different conditions was obtained by bench testing the target vehicle's driving data. The target vehicle's driving data was obtained by converting the rainflow count results to equal damage. The rainflow count results were obtained by performing fatigue analysis on the sample vehicle's driving data using the rainflow count algorithm.

5. The method for producing a vehicle transmission component according to claim 3, characterized in that, The method further includes: A simulation experimental environment for the vehicle transmission components is constructed based on the target scenario; In the simulation test environment, fatigue tests were conducted on the vehicle transmission components to obtain their actual lifespan. The model parameters of the neural network model are adjusted based on the target lifetime and the actual lifetime.

6. The method for producing a vehicle transmission component according to claim 5, characterized in that, Fatigue tests were conducted on the vehicle transmission component in the simulation experimental environment to obtain the actual lifespan of the vehicle transmission component, including: Obtain the process parameters and gear design parameters of the vehicle transmission component; In the simulation environment, fatigue tests are conducted on the vehicle transmission component based on the process parameters and the gear design parameters to obtain the actual lifespan of the vehicle transmission component.

7. The method for producing a vehicle transmission component according to claim 5, characterized in that, The model parameters of the neural network model are adjusted based on the target lifetime and the actual lifetime, including: A loss function is constructed based on the target lifetime and the actual lifetime; The model parameters of the neural network model are adjusted using the loss function.

8. A production apparatus for vehicle transmission components, characterized in that, include: The acquisition module is used to acquire vehicle driving data, target lifespan, and gear design parameters. The vehicle driving data represents the data generated by the vehicle during driving in the target scenario. The target lifespan represents the service life to be achieved by the vehicle transmission component. The gear design parameters represent the design parameters of the gears in the vehicle transmission component. The prediction module is used to predict the process parameters of the vehicle transmission component based on the vehicle driving data, the target life and the gear design parameters using a neural network model, and to obtain the prediction result. The process parameters are used to represent at least one parameter of the vehicle transmission component that needs to be controlled or adjusted during the processing. A generation module is used to produce the vehicle transmission component based on the prediction results and the gear design parameters.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the execution of the method for producing a vehicle transmission component according to any one of claims 1 to 7 in the processor of the device.

10. A vehicle, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the method for producing a vehicle transmission component as described in any one of claims 1 to 7.

Images