Method for constructing mathematical model of oil stirring loss of gear with cover of vehicle transmission system

Abstract

The invention discloses a mathematical model construction method for oil stirring loss of a gear with a cover of a vehicle transmission system, and relates to the technical field of gear transmission. The method comprises the following steps: constructing an oil stirring test bed, and configuring a plurality of shield structures with different design parameters; collecting oil stirring resistance moments of the gear with the cover under different shield structures at different rotating speeds; constructing an oil stirring loss basic model of the gear with the cover, and describing a mathematical relationship between the oil stirring loss influence factors and the structural parameters of the gear with the cover by adopting a plurality of undetermined parameters; constructing a mathematical relational expression between each parameter to be determined and the rotating speed of the gear by adopting a plurality of coefficients to be determined; and substituting the optimal solution of each to-be-determined coefficient into the mathematical relationship, and substituting the relationship between each to-be-determined parameter and the gear rotating speed into the basic model to obtain an oil stirring loss mathematical model of the gear with the cover. Through the method, the model of the oil stirring loss of the gear with the cover can be constructed, and an effective tool is provided for evaluating and optimizing the oil stirring loss of the gear with the cover.

Description

Technical Field

[0001] The invention relates to the technical field of gear transmission, and in particular to a method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system. Background Art

[0002] As the global demand for environmental protection and sustainable development continues to increase, the performance and sales of new energy products (especially electric drive technology) in the passenger car, commercial vehicle and construction machinery industries have achieved significant progress. The widespread use of these new energy vehicles not only marks a milestone in technological progress, but also has a profound impact on the transformation of the energy structure of the economy and society. Their widespread use has significantly reduced the economy and society's dependence on non-renewable resources such as oil and natural gas, providing important support for promoting the sustainable and healthy development of the green economy and society.

[0003] In electric drive transmission systems, gear systems have become an indispensable key component due to their superior performance such as high transmission efficiency, long life, and wide speed ratio variation range. In order to further optimize the efficiency of the transmission system, especially in high-power gearbox systems, an oil baffle structure is often set around the gears. This oil baffle structure is designed to reduce the energy loss caused by the oil stirring effect during the rotation of the gears, thereby improving the overall operating efficiency of the system. The actual performance of the oil baffle in the operation of the gears and its inhibitory effect on the oil stirring loss have become one of the important factors affecting the efficiency of the transmission system. How to accurately predict the energy loss of the covered gears and their surrounding components during the lubrication process has become a key technical challenge in the design of efficient electric drive transmission systems. At present, the research on the mathematical model of the oil stirring loss behavior of the covered gears is still in its preliminary stage, and there is still a lack of a theoretical framework that can comprehensively and accurately describe this complex phenomenon. Therefore, evaluating the oil stirring loss of the covered gears through a more economical and reliable strategy has become one of the core tasks of the lubrication design of the electric drive transmission system, which is of great significance to the development of future efficient electric drive technology. Summary of the invention

[0004] The object of the present invention is to provide a method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system, so as to realize the construction of a model of oil churning loss of a covered gear.

[0005] To achieve the above object, the present invention adopts the following technical solutions: According to one aspect of the present invention, a method for constructing a mathematical model of oil stirring loss of a covered gear in a vehicle transmission system is provided, comprising: constructing an oil stirring test bench including a gear and a shield, and configuring a plurality of shield structures with different design parameters; based on the constructed oil stirring test bench, collecting the oil stirring resistance torque of the covered gear at different speeds under different shield structures, and calculating the oil stirring loss influencing factors of different shield structures; constructing a basic model of oil stirring loss of the covered gear, wherein the independent variables of the model are the structural parameters of the covered gear, and the dependent variables are the oil stirring loss influencing factors, and a plurality of undetermined parameters are used to describe the mathematical relationship between the oil stirring loss influencing factors and the structural parameters of the covered gear; and calculating the different shield structures obtained. The oil stirring loss influencing factor of the structure and the corresponding structural parameters of the covered gear are substituted into the basic model for solution to obtain the values ​​of each undetermined parameter at different speeds; a mathematical relationship between each undetermined parameter and the gear speed is constructed using multiple undetermined coefficients, and the mathematical relationship is fitted according to the obtained values ​​of each undetermined parameter at different speeds and the corresponding gear speeds to solve the optimal solution of each undetermined coefficient; the optimal solution of each undetermined coefficient is substituted into the mathematical relationship to obtain the relationship between each undetermined parameter and the gear speed, and then the relationship between each undetermined parameter and the gear speed is substituted into the basic model to obtain the mathematical model of oil stirring loss of covered gear.

[0006] Optionally, the design parameters of the shroud structure in the oil stirring test bench include tooth top clearance, axial clearance, and radial clearance; the structural parameters of the covered gear in the basic model of oil stirring loss of covered gear include tooth top clearance, axial clearance, radial clearance, gear pitch circle radius, gear module, and tooth width.

[0007] Optionally, the collecting of the oil stirring resistance torque of the covered gear under different shroud structures at different speeds and the calculation of the oil stirring loss influence factor of the different shroud structures include: for each speed, collecting the first oil stirring resistance torque of the gear without a shroud, and collecting the second oil stirring resistance torque of the covered gear under each shroud structure; for each shroud structure and each speed, the ratio of the second oil stirring resistance torque to the first oil stirring resistance torque is the oil stirring loss influence factor of the corresponding shroud structure at the speed.

[0008] Optionally, the basic model includes four undetermined parameters, which are the first undetermined parameters , the second undetermined parameter 、The third undetermined parameter 、The fourth undetermined parameter , the mathematical relationship expression of the basic model is as follows: ; In the formula, represents the influencing factor of churning loss; is the tooth top clearance; is the axial clearance; is the radial clearance; is the gear pitch circle radius; is the gear module; is the tooth width.

[0009] Optionally, using a plurality of undetermined coefficients to construct a mathematical relationship between each undetermined parameter and the gear speed includes: using a first undetermined coefficient and the second unknown coefficient Establish the first pending parameter Speed ​​of gear with cover n The power function relationship between ; Using the third unknown coefficient Establish the second pending parameter Speed ​​of gear with cover n The constant function relationship between ; Using the fourth unknown coefficient and the fifth undetermined coefficient Establish the third pending parameter Speed ​​of gear with cover n The logarithmic function relationship between ; Use the sixth undetermined coefficient and the seventh undetermined coefficient Establish the fourth pending parameter Speed ​​of gear with cover n The logarithmic function relationship between .

[0010] Optionally, fitting the mathematical relationship according to the obtained values ​​of each unknown parameter at different speeds and the corresponding gear speeds, solving the optimal solution for each unknown coefficient includes: using a curve fitting strategy driven by the least squares method to fit the mathematical relationship between each unknown parameter and the gear speed, when the sum of the squares of the vertical distances between the actual data points and the fitted curve is the smallest, determining it as the best fitting curve, and obtaining the values ​​of each unknown coefficient according to the equation of the fitted best fitting curve.

[0011] Optionally, after obtaining the mathematical model of oil stirring loss of covered gear, the method further includes: using BP neural network and particle swarm optimization algorithm to construct an intelligent prediction model, and introducing NSGA-Ⅲ algorithm to construct a multi-objective optimization framework to optimize the intelligent prediction model, wherein the intelligent prediction model is used to solve the influencing factor of oil stirring loss of covered gear, the particle swarm optimization is used to improve the versatility of the prediction model, and the NSGA-Ⅲ algorithm is used to simultaneously seek the comprehensive minimum oil stirring loss influencing factor under different cover configurations.

[0012] The present invention systematically constructs a mathematical model of the oil churning loss of the covered gear of a vehicle transmission system by building a test bench, collecting data, constructing a basic model, establishing mathematical relationships, solving model parameters, etc., providing an effective tool for evaluating and optimizing the oil churning loss of the covered gear.

[0013] The present invention constructs a mathematical model of the oil churning loss of covered gears taking into account the near-wall turbulence effect, collects and fits data through cover structures with various design parameters, establishes a general calculation formula for the oil churning loss factor of the covered gear model, and transforms the engineering problem of high-speed gear oil churning loss into a mathematical problem through simple mathematical configuration, thereby obtaining a mathematical model of oil churning loss suitable for different cover structures. The model can accurately reflect the oil churning loss of covered gears under different cover structures and rotational speeds, and achieves high-precision prediction of the oil churning loss of covered gears. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 It is a flow chart of a method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] In this embodiment, a method for constructing a mathematical model of oil churning losses of a covered gear in a vehicle transmission system is provided.

[0018] Reference Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps: Step 1, build an oil stirring test bench including gears and shields, and configure shield structures with various design parameters; In order to evaluate the oil churning loss of covered gears, this embodiment builds an oil churning test bench including gears and shields, and establishes four shield configurations with different tooth top clearance, radial clearance, and axial clearance to carry out oil churning tests. The influence of different shield clearances on the oil churning loss is studied through the four shield configurations, and data is provided for mathematical modeling to obtain a more universal mathematical modeling model of the oil churning loss of covered gears.

[0019] Among them, the tooth top clearance refers to the clearance between the gear tooth top and the inner wall of the shield; the radial clearance refers to the clearance between the gear shaft and the shield side plate in the direction perpendicular to the gear axis. The axial clearance refers to the clearance between the gear end face and the shield side plate in the direction along the gear axis.

[0020] Take shield configuration 1 with specific tooth top clearance, axial clearance and radial clearance as the basic configuration. On the basis of configuration 1, change the tooth top clearance to obtain shield configuration 2, change the axial clearance to obtain shield configuration 3, and change the radial clearance to obtain shield configuration 4. Specific configuration data can be selected according to experimental requirements or actual conditions.

[0021] Step 2, based on the constructed oil stirring test bench, collect the oil stirring resistance torque of the covered gear under different shroud structures at different speeds, and calculate the oil stirring loss influence factor of different shroud structures; The oil stirring loss influencing factor refers to the ratio of the oil stirring loss of the gear with a guard to the oil stirring loss of the gear without a guard, which reflects the degree to which the guard structure reduces the gear oil stirring resistance, that is, the relative size of the oil stirring loss.

[0022] The splash lubrication behavior test of covered gears was carried out using the oil stirring test bench built in step 1. The oil stirring resistance torque under four shield configurations was collected at different speeds, and the oil stirring resistance torque when no shield was configured at the corresponding speed was collected. The oil stirring loss influencing factor of different shield structures was calculated based on the ratio of the oil stirring resistance torque when the shield was configured to the oil stirring resistance torque when the shield was not configured, so as to study the relationship between the oil stirring loss and the shield design parameters, so as to better optimize the efficiency of the gear system.

[0023] Specifically, for each speed, the first oil stirring resistance torque of the gear without a shield is collected, and the second oil stirring resistance torque of the gear with a shield under each shield structure is collected; for each shield structure and each speed, the ratio of the second oil stirring resistance torque to the first oil stirring resistance torque is the oil stirring loss influence factor of the corresponding shield structure at this speed. The formula is expressed as: ; In the formula, represents the influencing factor of churning loss; T ch is the oil stirring resistance moment of the model with shroud, in N·m; T ref It is the oil stirring resistance torque of the gear model without a guard at the same speed, in N·m.

[0024] In one example, the speed range is set from 100rpm to 5000rpm, and data is recorded every 100rpm, recording 50 sets of data (50 speed points). The torque sensor is used to measure the oil stirring resistance torque at each speed, and data are collected for four shroud configurations respectively, obtaining a total of 200 sets of data (4 configurations × 50 sets of data). Data is also collected for gears without shrouds, obtaining 50 sets of data. The collected oil stirring resistance torque data are sorted and analyzed, and the changing trends of the oil stirring resistance torque with speed and design parameters (tooth top clearance, axial clearance, radial clearance) are observed. The oil stirring loss under different shroud configurations is compared, and the oil stirring loss influencing factors of different shroud structures are obtained.

[0025] Step 3, constructing a basic model of oil churning loss of a covered gear, wherein the independent variables of the model are the structural parameters of the covered gear, the dependent variables are the oil churning loss influencing factors, and multiple undetermined parameters are used to describe the mathematical relationship between the oil churning loss influencing factors and the structural parameters of the covered gear; The commonly used expression for gear churning loss is: ; In the formula, Indicates gear churning loss, unit: w, Indicates the circumferential friction resistance of the gear, in N. Indicates the friction resistance of the gear tooth surface, unit N, Indicates the rotation speed in rad / s. The value is the gear pitch circle radius, that is, Dp / 2 (Dp is the gear pitch circle diameter), Indicates oil density in kg / m 3 , Indicates the gear oil immersion depth, unit: m. is the dimensionless torque; The basic model of oil churning loss of the shrouded gear in the embodiment of the present invention is based on the mathematical model of oil churning loss of the gear with flange or baffle developed by Changenet et al., as follows: ; In the formula, is the gear oil churning loss, unit is W; It represents the oil churning loss of the shroud model, in W; , are the gear pitch circle radius and diameter respectively, in m; is the outer arc diameter of the shield, in m; is the axial clearance between the side plate and the tooth end, in m; Indicates the gear speed, unit is rad / s; Indicates the kinematic viscosity of lubricating oil, unit: m 3 / s; is the gear module (which can be calculated by gear pitch diameter / number of teeth, or tooth pitch / pi); is the tooth width, unit: m.

[0026] Since the above mathematical model cannot characterize the oil churning loss of the covered gear, in order to describe the oil churning loss of the covered gear, the embodiment of the present invention fully considers the influence of the shield in all directions on the oil flow around the gear, and establishes a general basic model of the oil churning loss factor of the covered gear model based on the Vaschy-Buckingham theory. The model calculation formula is as follows: ; In the formula, represents the influencing factor of churning loss; is the tooth top clearance; is the axial clearance; is the radial clearance; is the gear pitch circle radius; is the gear module; is the tooth width.

[0027] In this formula, the structural parameters of the gear and the shield ( , , , , , ) is the independent variable, and the influencing factor of oil churning loss ( ) is the dependent variable, ~ These are the undetermined parameters, which are the constant terms of the formula and are determined through subsequent data fitting, optimization algorithms, etc.

[0028] This formula introduces the shield configuration parameters and can be applied to different shield configurations. In the embodiment of the present invention, the oil stirring test bench is equipped with four shield configurations S1~S4. Substituting into the above basic model, the following equation group can be obtained: ; In the formula, ~ The influence factors of oil churning loss corresponding to the four shroud configurations are shown; ~ Indicates the tooth top clearance corresponding to the four guard configurations; ~ Indicates the axial clearance corresponding to the four shield configurations; ~ Indicates the radial clearances corresponding to the four shield configurations.

[0029] Step 4, substituting the obtained oil stirring loss influencing factors of different shroud structures and the corresponding shrouded gear structural parameters into the basic model to solve and obtain the values ​​of each unknown parameter at different speeds; Substitute the oil stirring loss influencing factors of the four different shroud structures determined based on the test data in step 1 and the corresponding shrouded gear structure parameters into the equation group of step 3 above, and solve the corresponding undetermined parameters at each speed using the built-in solver of MATLAB. ~ The value of .

[0030] Step 5, using multiple undetermined coefficients to construct a mathematical relationship between each undetermined parameter and the gear speed, fitting the mathematical relationship according to the values ​​of each undetermined parameter at different speeds and the corresponding gear speeds, and solving to obtain the optimal solution of each undetermined coefficient; According to the evolution trend of the four unknown parameters with the gear speed, after multiple tests, the embodiment of the present invention uses power function, constant function and logarithmic function to track the evolution of the parameters with the speed, and proposes ~ Seven undetermined coefficients are used to fit the mathematical expression between each undetermined parameter and the speed of the covered gear, as follows: ; ; ; ; Using the first undetermined coefficient and the second unknown coefficient Establish the first pending parameter Speed ​​of gear with cover n The power function relationship between them; using the third unknown coefficient Establish the second pending parameter Speed ​​of gear with cover n The constant function relationship between them; using the fourth unknown coefficient and the fifth undetermined coefficient Establish the third pending parameter Speed ​​of gear with cover n The logarithmic function relationship between and the seventh undetermined coefficient Establish the fourth pending parameter Speed ​​of gear with cover n The logarithmic function relationship between them. n is the gear speed, unit is r / min.

[0031] The corresponding undetermined parameters at each speed obtained in step 4 are ~ The values ​​of and the corresponding speeds are fitted to the above four mathematical relationships to obtain the various unknown coefficients. ~ The optimal solution of .

[0032] The optimal solution of each undetermined coefficient is obtained by fitting the mathematical relationship between each undetermined parameter and the gear speed using a least squares method driven curve fitting strategy, assuming that The relevant data sets have random errors and satisfy independent and identically distributed normal distributions. When the sum of the squares of the vertical distances between the actual data points and the fitting curve is the smallest, the best fitting curve is determined. The values ​​of each unknown coefficient are obtained based on the equation of the fitted best fitting curve.

[0033] The goal of the least squares method is to minimize the error function: ; In the formula, N is the number of sample points in the data set, i is the index of the dataset sample; l It is known that a Parameterized speed n The function consists of the minimum number of coefficients. a Contains several undetermined coefficients ( ~ ), once the parameter set a Knowing that, we can uniquely determine the function l . for l The measured value of l ( , a ) determines its value ( Speed n Measured value of ).

[0034] Fitting the function by using the least squares method l To the data set, by minimizing the error function s(a) , we can get the parameter set a The optimal solution is to find the parameter set that minimizes the sum of the squares of the vertical distances between the actual data points and the fitted curve. a .

[0035] The accuracy of the curve fitting can be measured using R 2 The determination coefficient R 2 It represents the ratio of the regression sum of squares to the total sample sum of squares; ; in, P and Q are the fitted data and the actual data, respectively, R 2 The closer the value is to 1, the better the fitting effect is.

[0036] Step 6, substitute the optimal solution of each unknown coefficient into the mathematical relationship to obtain the relationship between each unknown parameter and the gear speed, and then substitute the relationship between each unknown parameter and the gear speed into the basic model to obtain the mathematical model of oil stirring loss of covered gear.

[0037] The mathematical model of oil stirring loss of the covered gear is used to reflect the oil stirring loss of the covered gear under different cover structures and speeds. The optimal solution of each undetermined coefficient obtained in step 5 is substituted into step 5. ~ In the mathematical relationship of ~ With gear speed n Then, substitute these relationships into the basic model constructed in step 3 In the formula, a complete mathematical model of oil churning loss for covered gears is obtained. This model can be used to predict the influencing factors of oil churning loss under different cover structures and speeds, providing a theoretical basis for the design and optimization of gear systems.

[0038] In addition, the embodiment of the present invention also uses BP neural network and particle swarm optimization algorithm (PSO) to build an intelligent prediction model, and introduces NSGA-Ⅲ algorithm to build a multi-objective optimization framework. The PSO-BP and NSGA-Ⅲ algorithms are run in MATLAB 2021 version.

[0039] By using the 7 characteristic variables in the mathematical model and combining the error back propagation algorithm, an intelligent prediction model of the oil churning loss influence coefficient based on BP neural network was established. In order to improve the generalization ability of the proposed mathematical model, the NSGA-Ⅲ algorithm was introduced to reduce the error of the mathematical model.

[0040] Among them, the stirring loss influence coefficient prediction model based on BP neural network consists of an input layer, a hidden layer and an output layer. The input layer receives the sample matrix obtained by the experimental design (including parameters such as gear speed, tooth top clearance, axial clearance, radial clearance, gear pitch radius, gear module and tooth width), passes it to the internal information processing layer, and then to the output layer (the stirring loss influence coefficient error corresponding to each shield), and finally completes the forward propagation process. The input layer transmits the data to the internal information processing layer, and then to the output layer (the stirring loss influence coefficient error corresponding to different shields). Finally, the forward propagation process is completed. If the influence coefficient of the stirring loss is different from the expected value, the deviation will move in the opposite direction of the previous forward learning, and the gradient descent method will be used to correct the weight to minimize the deviation. The output of the neural network is shown in the following formula: ; In the formula, is the output value of the jth neuron in the output layer; is the input of the jth neuron; For input signal The connection weights between the output layer and the is the threshold of the kth neuron, where k represents the layer number in the neural network.

[0041] Update the weights according to the strategy shown below: ; ; In the formula, is the learning rate; is the weight between the i-th input and the j-th neuron; x ( i ) is the input value of BP neural network; is the number of nodes in the output layer; is the error term; The thresholds are updated as follows: ; is the threshold of the jth neuron.

[0042] Particle swarm optimization is an optimization strategy inspired by the predatory behavior of birds. The entire group realizes the movement transformation from disordered state to ordered state in the solution space through information sharing between individuals. The particle swarm algorithm is based on this principle to obtain the optimal solution, which has the characteristics of fast search speed and high accuracy. In the particle swarm algorithm, the particle swarm random solution is first initialized, and then iterated until the optimal solution is found.

[0043] NSGA (Non-dominated Sorting Genetic Algorithms) is a genetic algorithm based on the concept of Pareto Optimality. The NSGA-III algorithm is an improved version of the NSGA-II algorithm, which mainly optimizes the survival selection mechanism. NSGA-III uses widely distributed and adaptively updated reference points to maintain the diversity among population members. The goal optimized by the NSGA-III algorithm is to simultaneously seek the minimum comprehensive churning loss coefficient under four shield configurations. Based on NSGA-III, a set of equally important solutions are generated, called Pareto (non-dominated) solutions. These solutions represent the optimization objectives under the four shield configurations, ensuring a comprehensive solution for space exploration.

[0044] The steps in the above-mentioned embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The technical features can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the embodiment are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present invention.

[0045] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system, characterized in that: include: Build an oil stirring test bench including gears and shields, and configure shield structures with various design parameters; Based on the constructed oil stirring test bench, the oil stirring resistance torque of the covered gear under different shroud structures at different speeds was collected, and the oil stirring loss influencing factors of different shroud structures were calculated. A basic model of oil churning loss of covered gears is constructed. The independent variables of the model are the structural parameters of the covered gears, and the dependent variables are the influencing factors of oil churning loss. Multiple undetermined parameters are used to describe the mathematical relationship between the influencing factors of oil churning loss and the structural parameters of covered gears. Substituting the obtained oil stirring loss influencing factors of different shroud structures and the corresponding shrouded gear structural parameters into the basic model for solution, the values ​​of the unknown parameters at different speeds are obtained; A mathematical relationship between each undetermined parameter and the gear speed is constructed using multiple undetermined coefficients, and the mathematical relationship is fitted according to the values ​​of each undetermined parameter at different speeds and the corresponding gear speeds to obtain the optimal solution of each undetermined coefficient; Substitute the optimal solution of each unknown coefficient into the mathematical relationship to obtain the relationship between each unknown parameter and the gear speed, and then substitute the relationship between each unknown parameter and the gear speed into the basic model to obtain the mathematical model of oil stirring loss of covered gear.

2. The method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to claim 1, characterized in that: The design parameters of the shield structure in the oil stirring test bench include tooth top clearance, axial clearance, and radial clearance; The structural parameters of the covered gear in the basic model of oil churning loss of the covered gear include tooth top clearance, axial clearance, radial clearance, gear pitch circle radius, gear module, and tooth width.

3. The method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to claim 1, characterized in that: The oil stirring resistance torque of the covered gear under different shroud structures at different speeds is collected, and the oil stirring loss influencing factors of different shroud structures are calculated, including: For each speed, the first oil stirring resistance torque of the gear without a shield is collected, and the second oil stirring resistance torque of the gear with a shield under each shield structure is collected; For each shroud structure and each rotation speed, the ratio of the second oil stirring resistance torque to the first oil stirring resistance torque is the oil stirring loss influence factor of the corresponding shroud structure at the rotation speed.

4. The method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to claim 1, characterized in that: The basic model includes four undetermined parameters, namely, the first undetermined parameter , the second undetermined parameter 、The third undetermined parameter 、The fourth undetermined parameter , the mathematical relationship expression of the basic model is as follows: ； In the formula, represents the influencing factor of churning loss; is the tooth top clearance; is the axial clearance; is the radial clearance; is the gear pitch circle radius; is the gear module; is the tooth width.

5. The method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to claim 4, characterized in that: The mathematical relationship between each undetermined parameter and the gear speed is constructed using multiple undetermined coefficients, including: Using the first undetermined coefficient and the second unknown coefficient Establish the first pending parameter Speed ​​of gear with cover n The power function relationship between ; Using the third unknown coefficient Establish the second pending parameter Speed ​​of gear with cover n The constant function relationship between ; Using the fourth unknown coefficient and the fifth undetermined coefficient Establish the third pending parameter Speed ​​of gear with cover n The logarithmic function relationship between ; Using the sixth undetermined coefficient and the seventh undetermined coefficient Establish the fourth pending parameter Speed ​​of gear with cover n The logarithmic function relationship between .

6. The method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to claim 5, characterized in that: According to the values ​​of the unknown parameters at different speeds and the corresponding gear speeds, the mathematical relationship is fitted to obtain the optimal solutions of the unknown coefficients, including: The curve fitting strategy driven by the least squares method is used to fit the mathematical relationship between each unknown parameter and the gear speed. When the sum of the squares of the vertical distances between the actual data points and the fitting curve is the smallest, the best fitting curve is determined. The values ​​of each unknown coefficient are obtained according to the equation of the fitted best fitting curve.

7. The method for constructing a mathematical model of oil churning loss of a covered gear in a vehicle transmission system according to claim 6, characterized in that: After obtaining the mathematical model of oil churning loss of the covered gear, the method further comprises: The BP neural network and particle swarm optimization algorithm are used to construct an intelligent prediction model, and the NSGA-Ⅲ algorithm is introduced to construct a multi-objective optimization framework to optimize the intelligent prediction model. The intelligent prediction model is used to solve the influencing factor of oil churning loss of covered gears, the particle swarm optimization is used to improve the versatility of the prediction model, and the NSGA-Ⅲ algorithm is used to simultaneously seek the comprehensive minimum influencing factor of oil churning loss under different cover configurations.

Images