Gear transmission system vibration response rapid prediction method based on system division model correction

Abstract

The invention relates to the technical field of gear transmission system vibration response prediction, solves the technical problems that prediction of a traditional method is difficult to meet timeliness requirements and measurement point arrangement is limited by space and equipment, and particularly relates to a gear transmission system vibration response rapid prediction method based on system division model correction. The method comprises the following steps: dividing subsystems and establishing a finite element model; correcting the finite element model; establishing a multi-body dynamic model and performing simulation to obtain vibration response data under multiple groups of working conditions; and constructing a sample data set, and training and evaluating the vibration response prediction model. According to the invention, a reliable basis can be provided for state monitoring of the gear transmission system, the operation state of the system can be effectively evaluated, and sufficient preparation is provided for fault early warning and shutdown maintenance of the gear transmission system, so that supplementary data is provided for equipment state evaluation, a monitoring blind area is avoided, and monitoring comprehensiveness and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of gear transmission system vibration response prediction, and in particular to a gear transmission system vibration response rapid prediction method based on system partition model correction. Background Art

[0002] Gear transmission is one of the most important and widely used transmission forms in mechanical transmission. It has the advantages of high transmission efficiency, stable transmission ratio, and reliable operation. It is widely used in modern mechanical engineering fields such as aerospace, automobiles, and ships. However, during the operation of the gear transmission system, complex vibration responses will be generated due to factors such as gear meshing excitation, processing errors, and operating conditions. These response signals contain important information about the system's operating status. By analyzing the vibration response, potential faults can be discovered in a timely manner and design parameters can be optimized. Therefore, vibration response prediction is of great significance for gear transmission systems.

[0003] As gear transmission systems develop towards high speed and heavy load, their application scope continues to expand, and the requirements for system operation stability and vibration response are also increasing. Under these high load and high speed conditions, the vibration problem of gear transmission systems is particularly prominent. If the vibration response cannot be accurately predicted, it will not only affect the system's operating reliability, but may also cause equipment failure or even major safety accidents.

[0004] In the existing prediction of the vibration response of gear transmission systems, traditional methods based on numerical calculation or simulation models have played an important role. At present, they mainly include finite element method and dynamic modeling method. The finite element method is to discretize a continuous object into a finite number of units, and determine the dynamic characteristics of the entire system by solving the interaction force between the units. By using parametric programming language and combining the boundary conditions between various components, a finite element equivalent model of the gear transmission system is established to study its dynamic characteristics. The dynamic modeling method mainly describes the vibration response of the system by establishing the dynamic equation of the gear and solving the dynamic equation. For example, the lumped parameter method is a relatively common dynamic modeling method. The lumped parameter method regards the system as a set of concentrated mass points, which are connected by springs or damping units, and the dynamic characteristics of the system are described by the connection relationship between the mass points. The dynamic model of the gear transmission system is established by the lumped parameter method, and the meshing error of the gear and the excitation of the time-varying stiffness are comprehensively considered to solve the inherent characteristics of the system. The normal gear and the faulty gear are modeled and their dynamic characteristics are studied respectively, and the influence of gear cracks and other faults on the vibration response characteristics of the gear transmission system is analyzed.

[0005] In addition, relying on multi-body dynamics simulation software to establish a dynamic model of the gear transmission system and perform simulation solutions is also an important method for solving vibration response. However, this type of method relies on the accuracy of system parameters and complex mathematical models. The complexity of model construction and solution makes the prediction process time-consuming, which is difficult to meet the timeliness requirements in engineering application scenarios that require rapid prediction of vibration response. Therefore, although numerical calculations or simulation models can provide relatively accurate prediction results, their application is subject to certain timeliness limitations.

[0006] Of course, it is also possible to install sensors to monitor the gear transmission system in real time. However, although the measured data can obtain the vibration response signal, it often requires a high monitoring cost in the actual data collection process, and the measurement point layout is often subject to space limitations and equipment constraints. Especially in the monitoring of rotating machinery, it is difficult to arrange sensors at certain key points, resulting in the inability to fully and accurately capture the vibration response characteristics of the system. In addition, the measured data is also easily interfered by factors such as the test environment, sensor installation status, and data transmission process, affecting the accuracy and reliability of the test results. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention provides a method for quickly predicting the vibration response of a gear transmission system based on the correction of the system partition model, which solves the technical problems that the prediction of traditional methods is difficult to meet the timeliness requirements and the measurement point layout is subject to space limitations and equipment constraints.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for quickly predicting the vibration response of a gear transmission system based on the correction of the system partition model, the method comprising the following steps: S1. Divide the gear transmission system into different subsystems according to the contact mode and connection relationship between the transmission structures in the gear transmission system, and establish finite element models of each subsystem and the gear transmission system; S2. Modify the finite element models of each subsystem and the gear transmission system to obtain modified system model parameters; S3. Use multi-body dynamics analysis method to establish a multi-body dynamics model of rigid-flexible coupling of the gear transmission system, substitute the system model parameters into the multi-body dynamics model and perform simulation to obtain vibration response data under multiple working conditions; S4. constructing a sample data set based on vibration response data under multiple groups of working conditions, and using the sample data set to train and evaluate a vibration response prediction model based on a BP neural network; S5. The speed, load and normalized time ID of the gear transmission system are used as inputs of the vibration response prediction model, and the output is the vibration acceleration response value at the corresponding time point, so as to realize rapid prediction of vibration signals under different working conditions.

[0009] Furthermore, the subsystem includes a pinion shaft subsystem, a large gear shaft subsystem, a housing and housing cover connection system, a housing and bearing end cover connection system, a housing and input shaft support system, and a housing and output shaft support system.

[0010] Furthermore, in step S1, the specific process includes the following steps: S11. Divide the gear transmission system into different subsystems according to the contact mode and connection relationship between them, and establish geometric models of different subsystems using 3D modeling software; S12. Import the geometric model into the finite element analysis software ANSYS, and mesh the gear transmission system. Modeling and simulation are performed separately for the connection and contact of different components to simplify the overall geometric structure. Modeling and simulation to simplify the geometric structure include: The connection between the gear and the gear shaft is simplified by using the thin layer element method; Thin layer elements are used to simulate the connection between the box body and the box cover, and the connection between the bearing end cover and the box body; For the meshing contact modeling between gears, the Combin14 unit in the finite element analysis software ANSYS is used for simulation; For the simulation of bearings, the bearing unit of finite element analysis software ANSYS is used to simulate its radial support, and the spring unit is used to simulate its axial support; S13. Establish finite element models of each subsystem and gear transmission system according to the simplified modeling simulation scheme.

[0011] Furthermore, in step S2, the specific process includes the following steps: S21, performing modal knocking tests and operating modal analysis on each subsystem and gear transmission system to obtain modal parameters including natural frequencies and modal vibration shapes; S22, selecting correction parameters corresponding to each subsystem and the gear transmission system, wherein in each subsystem, the correction parameters include the elastic modulus of the material, the elastic modulus of the thin layer unit, and the bearing stiffness; in the gear transmission system, the correction parameters include the meshing stiffness of the gear and the three-way support stiffness of the workbench; S23. Correct the correction parameters based on the response surface model to obtain more accurate system model parameters.

[0012] Furthermore, in step S21, the specific process includes the following steps: S211. Importing a finite element model of any subsystem into the finite element analysis software ANSYS, setting the initial elastic modulus of the material and the initial elastic modulus of the thin layer unit, and solving the modal information of the subsystem; S212, extracting a group of nodes that can fully reflect its modal vibration shape from the modal information, combining the nodes as the measurement points of the modal test and constructing the required geometric model in LMS Test.lab; S213, using the mobile hammer method, sticking the sensor on the end face of the geometric model, and using the hammer to stimulate all measuring points in turn, hitting each measuring point at least 3 times and taking the average value to reduce the error; S214. After the tapping is completed, the test results are processed to obtain the modal parameters of the subsystem including the natural frequency and the modal vibration shape.

[0013] Furthermore, in step S23, the specific process includes the following steps: S231, construct response surface model based on Kriging model; S232. The objective function of the response surface model is constructed according to the natural frequency measured by the modal knocking test. The expression of the objective function is: ; In the formula, is the parameter value to be corrected, is the lower limit of the value range of the corresponding parameter; is the upper limit of the value range; is the test frequency value; The response frequency values ​​calculated for the response surface; is the number of parameters to be corrected; is the number of objective functions; S233. Based on the objective function, iterative optimization is performed through a multi-objective genetic algorithm to seek the input variable combination that best meets the target result as the system model parameters.

[0014] Furthermore, in step S231, the specific process includes the following steps: S2311, based on any set of input data and output response Establish the Kriging model, the expression is: ; In the formula, is a polynomial function; is the coefficient vector corresponding to the polynomial; is a random process with mean zero and variance Normal distribution of S2312, determine the random process The covariance function of , the expression is: ; In the formula, is the spatial correlation function used to describe the sampling points and The correlation between is a key parameter used to adjust the correlation between sample points; S2313, use the maximum likelihood estimation method to solve the coefficient vector and variance The predicted value of , the calculation formula is: ; ; In the formula, is the number of parameters to be corrected; To output the response data set; is a polynomial function The matrix composed of S2314, according to the spatial function and variance To solve the key parameters , the calculation formula is: ; S2315, determine the correlation vector between the point to be measured and the known sampling point , the expression is: ; S2316, the relevant vector , key parameters , coefficient vector , spatial function and variance Substituting into the Kriging model, we get the response surface model used to correct the correction parameters, and the expression is: ; In the formula, The point to be tested The predicted value of the response; is a polynomial function The matrix composed of.

[0015] Furthermore, in step S3, the specific process includes the following steps: S31. Import the geometric model of the gear transmission system into ADAMS in the STEP neutral format, apply corresponding constraints between different components according to their connection relationships, and simulate the gear meshing transmission and the bearing and workbench support; S32, establishing a rigid body dynamics model of the gear transmission system including a rigid body according to the simulation of the gear meshing transmission and the simulation of the bearing and the worktable support; S33, generate an MNF file of the flexible box through finite element software, import the MNF file into ADAMS to replace the original rigid body, and realize the creation of the flexible body by checking the center of mass position, mass and moment of inertia conditions; S34, coupling the degrees of freedom of the rigid body and the flexible body by connecting them in a sleeve force manner, and obtaining a rigid-flexible coupled multi-body dynamics model that considers the flexible behavior of the box body components; S35, substituting the corrected system model parameters into the multi-body dynamics model as corresponding parameter values; S36. Build a vibration response test bench and set test conditions, apply rotation speed and load to perform dynamic simulation, and obtain vibration response data under multiple groups of conditions.

[0016] By means of the above technical solution, the present invention provides a method for quickly predicting the vibration response of a gear transmission system based on the system partition model correction, which has at least the following beneficial effects: 1. The present invention can provide a reliable basis for the condition monitoring of the gear transmission system. By comparing the difference between the actual vibration response and the predicted vibration response and formulating appropriate condition judgment indicators, the operating status of the system can be effectively evaluated, and sufficient preparations can be provided for fault warning and shutdown maintenance of the gear transmission system. In addition, it can also help obtain the vibration response of key positions in the gear transmission system that are difficult to monitor, thereby providing supplementary data for equipment condition evaluation, avoiding monitoring blind spots, and improving the comprehensiveness and accuracy of monitoring.

[0017] 2. The present invention comprehensively considers the deviation between the model and the actual structure to improve its accuracy, and divides the gear transmission system into subsystems. The divided subsystems can effectively reduce the parameter coupling in the correction process, ensure the subsequent transmission system model correction process, thereby improving the correction accuracy and greatly improving the timeliness and accuracy of vibration response prediction.

[0018] 3. The present invention improves the simulation efficiency by constructing a rigid-flexible coupling dynamic model, and can also accurately simulate the interaction between the various components of the system, avoiding the loss of precision. At the same time, based on the rigid-flexible coupling multi-body dynamic model of the gear transmission system, the system model parameters obtained by correcting the finite element model are substituted into the dynamic model to ensure accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a schematic diagram of dividing the gear transmission system of the present invention into subsystems; Figure 2It is a flow chart of model correction based on response surface methodology in the present invention; Figure 3 is a schematic diagram of the multi-body dynamics model of the present invention; Figure 4 It is a comparison diagram of the simulation signal and the filtering test signal in the present invention; Figure 5 It is a curve diagram of vibration acceleration data under multiple working conditions in the present invention; Figure 6 A neural network structure diagram of the vibration response prediction model in the present invention; Figure 7 It is a fitting effect diagram of the vibration response prediction model in the present invention on the training set; Figure 8 This is a fitting effect diagram of the vibration response prediction model in the present invention on the test set; Fig. 9 It is a comparison chart of the prediction results and the simulation results in the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0021] Accurate prediction of vibration response is of great significance for the optimal design and condition monitoring of gear transmission systems. However, traditional numerical calculation or simulation models rely on the accuracy of system parameters and complex mathematical models. The complexity of model construction and solution makes the prediction process time-consuming and difficult to meet timeliness requirements. The actual measurement of vibration response often requires a high monitoring cost, and the arrangement of measurement points is often subject to space limitations and equipment constraints. Especially in the monitoring of rotating machinery, it is difficult to arrange sensors at certain key points, resulting in the inability to fully and accurately capture the vibration response characteristics of the system. In addition, the measured data is also easily disturbed by factors such as the test environment, sensor installation status, and data transmission process, affecting the accuracy and reliability of the test results. Therefore, the existing technology still needs to be further developed and improved in terms of vibration response prediction, especially how to improve the accuracy of vibration response prediction and the rapid prediction of vibration response under multiple working conditions.

[0022] To quickly predict the vibration response of the gear transmission system under different working conditions, please refer to Figure 1-Figure 9This embodiment proposes a method for quickly predicting the vibration response of a gear transmission system based on system partition model correction. The method first divides the subsystem to reduce parameter coupling, uses finite element model correction technology to correct material elastic modulus and connection characteristic parameters, and builds a high-fidelity multi-body dynamics model based on multi-body dynamics analysis technology. Finally, the BP neural network is used to achieve rapid prediction of the system vibration response under different working conditions. It is hoped that the problems existing in the prior art will be overcome, the timeliness and accuracy of the prediction will be improved, an effective way will be provided for the status monitoring of the gear transmission system, and its engineering application value will be enhanced. The method includes the following steps: S1. Divide the gear transmission system into different subsystems according to the contact mode and connection relationship between the transmission structures, and establish the finite element model of each subsystem and the gear transmission system. Figure 1 As shown, the subsystems after division include a pinion shaft subsystem, a large gear shaft subsystem, a housing and housing cover connection system, a housing and bearing end cover connection system, a housing and input shaft support system, and a housing and output shaft support system. The specific process includes the following steps: S11. Divide the gear transmission system into different subsystems according to the contact mode and connection relationship between them, and use 3D modeling software to establish geometric models of different subsystems, such as SolidWorks, PROE, UG, etc. At the same time, appropriately simplify the overall geometric structure, ignore details such as screw connections and chamfers, and complete the assembly process of the overall model.

[0023] S12. Import the geometric model into the finite element analysis software ANSYS, and mesh the gear transmission system. Modeling and simulation are performed separately for the connection and contact of different components to simplify the overall geometric structure. Specific and feasible simplified modeling methods are given for the connection and contact parts.

[0024] S13. Establish finite element models of each subsystem and gear transmission system according to the simplified modeling simulation scheme. Specifically, for the connection between the gear and the gear shaft, it is simplified by the thin layer unit method. The thin layer unit method introduces thin layer units in the connection area and simulates the connection stiffness of the contact part with the elastic modulus of the thin layer unit. Its advantage is accurate simulation and can consider nonlinear behaviors such as contact and friction. Thin layer units are used to simulate the connection between the box body and the box cover, and the connection between the bearing end cover and the box body. For the meshing contact modeling between gears, Combin14 units in the finite element analysis software ANSYS are used for simulation. By arranging multiple Combin14 units in the gear contact area along the tooth width direction, the simulation of gear meshing is realized, which reduces the complexity of the model and effectively improves the efficiency of simulation calculation, avoiding the time cost and parameter errors that may be introduced by the traditional nonlinear contact modeling method. For the simulation of the bearing, the bearing unit of the finite element analysis software ANSYS is used to simulate its radial support, and the spring unit is used to simulate its axial support. Finally, the finite element model of each subsystem and the entire gear transmission system is established.

[0025] The design of gear transmission system often requires high precision and high reliability. Its structure is usually composed of multiple interacting subsystems, relying on the coordinated work of different components to achieve complex motion and load transfer. These subsystems of the gear transmission system each have different functions, and through the transmission of each other's motion and force, they jointly build the integrity and functionality of the system. The gear transmission system is divided into multiple subsystems through the contact mode and connection relationship to reduce the interference caused by the parameter coupling between the subsystems and ensure the subsequent transmission system model correction process.

[0026] S2. Correct the finite element models of each subsystem and the gear transmission system to obtain the corrected system model parameters. This step is based on the model correction method of system division. The gear transmission system is first divided into multiple subsystems according to the connection method, contact relationship, etc., and then modal knocking tests and operational modal analysis are performed on each subsystem and the system as a whole to obtain its modal parameters. The response surface method is used to correct parameters such as material elastic modulus, support stiffness, meshing stiffness, etc. to obtain more accurate system model parameters. The specific process includes the following steps: S21, perform modal knocking test and operation modal analysis on each subsystem and gear transmission system to obtain modal parameters including natural frequency and modal vibration shape. Among them, the operation modal analysis of the gear transmission system to obtain its modal parameters can be directly implemented by existing technical means. As a further technical innovation, this embodiment proposes a modal knocking test analysis method to obtain the modal parameters of each subsystem. The specific process includes the following steps: S211. Importing a finite element model of any subsystem into the finite element analysis software ANSYS, setting the initial elastic modulus of the material and the initial elastic modulus of the thin layer unit, and solving the modal information of the subsystem; S212, extracting a group of nodes that can fully reflect its modal vibration shape from the modal information, combining the nodes as the measurement points of the modal test and constructing the required geometric model in LMS Test.lab; S213, using the mobile hammer method, sticking the sensor on the end face of the geometric model, and using the hammer to stimulate all measuring points in turn, hitting each measuring point at least 3 times and taking the average value to reduce the error; S214. After the tapping is completed, the test results are processed to obtain the modal parameters of the subsystem including the natural frequency and the modal vibration shape.

[0027] This embodiment takes the pinion shaft subsystem as an example. The finite element model of the pinion and the pinion shaft is imported into ANSYS, and the modal analysis is carried out on the initial finite element model. The initial elastic modulus of the material and thin layer unit is set to solve the modal information of the pinion shaft subsystem. And according to the modal information, a group of nodes that can fully reflect its modal vibration shape are extracted from it, and this node combination is used as the measurement point of the modal test. Then, the required geometric model is constructed in LMS Test.lab, and a simplified geometric structure is constructed through the point-line-surface modeling method to carry out the modal knocking test.

[0028] For the experimental modal analysis, the moving hammer method is used. The sensor is pasted on the end face of the gear shaft. The hammer stimulates all the measuring points in turn. Each measuring point is struck 3 times and the average is taken to reduce the error. After the striking is completed, the test results are processed to obtain the experimental modal parameters such as the natural frequency and modal vibration shape of the pinion shaft subsystem. The vibration shape matching between the experimental vibration shape and the simulation vibration shape is performed according to the Modal Assurance Criteria (MAC), which uses the MAC value to represent the correlation between the two modal vibration shapes. The calculation method is: ; (1) In the formula, The matrix Line Elements of a column; For the test Order vibration mode; For the simulation Order vibration mode; Indicates transpose.

[0029] S22. Select correction parameters corresponding to each subsystem and gear transmission system. In each subsystem, the correction parameters include the elastic modulus of the material, the elastic modulus of the thin layer unit and the support stiffness of the bearing; in the gear transmission system, the correction parameters include the meshing stiffness of the gear and the three-way support stiffness of the workbench.

[0030] Next, the finite element model of the pinion shaft subsystem is modified. Considering the sensitivity of each modal parameter to each order of natural frequency, the elastic modulus E1 of the pinion, the elastic modulus E2 of the thin layer unit and the elastic modulus E3 of the pinion shaft are selected as correction parameters. The Kriging response surface model is selected to modify the finite element model of the pinion shaft subsystem. The Kriging response surface is an interpolation method based on spatial statistics. Its core idea is to estimate the response surface by considering the correlation between spatial positions and samples. The Kriging response surface not only interpolates through existing experimental data, but also provides error estimates, so it has significant advantages in optimization and simulation.

[0031] S23, based on the response surface model, the correction parameters are corrected to obtain more accurate system model parameters, and the specific process includes the following steps: S231. Constructing a response surface model based on the Kriging model. The specific process includes the following steps: S2311, based on any set of input data and output response Establish the Kriging model, the expression is: ; (2) In the formula, is a polynomial function; is the coefficient vector corresponding to the polynomial; is a random process with mean zero and variance Normal distribution of S2312, determine the random process The covariance function of , the expression is: ; (3) In the formula, is the spatial correlation function used to describe the sampling points and The correlation between is a key parameter used to adjust the correlation between sample points; S2313, use the maximum likelihood estimation method to solve the coefficient vector and variance The predicted value of , due to the spatial correlation function The general form is as follows: ; (4) In the formula, is the number of variables; and The sample points are and No. components, the most commonly used Gaussian correlation function form is: ; (5) According to the maximum likelihood estimation method, we can obtain: ; (6) ; (7) In the formula, is the number of parameters to be corrected; To output the response data set; is a polynomial function The matrix composed of is the correlation matrix, that is, the spatial function, and its specific expression is as follows: ; (8) ; (9) From equations (5), (6) and (7), we can see that , and All depends on key parameters , based on the maximum likelihood estimation theory, we can get value.

[0032] S2314, according to the spatial function and variance To solve the key parameters , the calculation formula is: ; (10) S2315, determine the correlation vector between the point to be measured and the known sampling point , the expression is: ; (11) S2316, the relevant vector , key parameters , coefficient vector , spatial function and variance Substituting into the Kriging model, we get the response surface model used to correct the correction parameters, and the expression is: ; (12) In the formula, The point to be tested The predicted value of the response; is a polynomial function The matrix composed of.

[0033] S232. The objective function of the response surface model is constructed according to the natural frequency measured by the modal knocking test. The expression of the objective function is: ; (13) In the formula, is the parameter value to be corrected, is the lower limit of the value range of the corresponding parameter; is the upper limit of the value range; is the test frequency value; The response frequency values ​​calculated for the response surface; is the number of parameters to be corrected; is the number of objective functions.

[0034] S233, based on the objective function, iterative optimization is performed through a multi-objective genetic algorithm to seek the input variable combination that best meets the objective result as the system model parameter. During the optimization process, the iterative convergence criterion is set as the error of the objective function meets a certain accuracy requirement, that is, the correction is completed if it reaches the set error range.

[0035] This embodiment greatly improves the timeliness and accuracy of vibration response prediction. The model correction proposal comprehensively considers the deviation between the model and the actual structure to improve its accuracy, and divides the gear transmission system into subsystems. The divided subsystems can effectively reduce the parameter coupling in the correction process, thereby improving the correction accuracy. At the same time, based on the powerful nonlinear fitting ability of the neural network, a vibration response prediction model based on the BP neural network is constructed to realize the rapid prediction of vibration response under different working conditions.

[0036] S3. Use multi-body dynamics analysis method to establish a multi-body dynamics model of the rigid-flexible coupling of the gear transmission system, substitute the system model parameters into the multi-body dynamics model and perform simulation to obtain the vibration response data under multiple working conditions.

[0037] Since it is difficult for the finite element method to take into account both simulation accuracy and efficiency in dynamic analysis, reducing the number of grids and simplifying modeling can improve solution efficiency, but this will cause the system's degrees of freedom to differ too much from the actual situation, making the solution results unreliable. Directly using nonlinear contact and other methods to model and simulate will result in excessive solution time costs, and the solution efficiency is difficult to meet the requirements of engineering applications. Therefore, multi-body dynamics analysis technology is used to realize the dynamic simulation of the gear transmission system. By constructing a rigid-flexible coupled multi-body dynamic model, the simulation efficiency is improved, and the interaction between the various components of the system can be accurately simulated to avoid loss of accuracy. At the same time, based on the rigid-flexible coupled multi-body dynamic model of the gear transmission system, the system model parameters obtained by correcting the finite element model are substituted into the multi-body dynamic model to ensure the accuracy of the model. The specific process includes the following steps: S31. Import the geometric model of the gear transmission system into ADAMS in the neutral format of STEP, apply corresponding constraints between different components according to their connection relationships, and simulate the gear meshing transmission and the bearing and workbench support. Among them, the collision function method is used to simulate the gear meshing transmission. The collision function method calculates the contact force between components based on the IMPACT function, and the gear meshing contact force is converted into two parts: the elastic force caused by the mutual penetration when the gear teeth mesh and the damping force caused by the relative speed. The specific calculation method is: ; (14) In the formula, is the contact stiffness coefficient; is the contact penetration; is the maximum permissible penetration depth; is the maximum contact damping at maximum penetration depth; is the nonlinear spring force exponent.

[0038] In ADAMS The function definition is as follows: ; (15) In the formula, is the independent variable, .

[0039] The simulation of bearings and table supports can be achieved through the bushing force tool. The bushing force model is a commonly used simplified modeling method to simulate the bearing force and damping effect on the rotor or shaft. This model equates the complex dynamic behavior of the bearing to a linear spring-damper system, mainly describing the radial and axial stiffness and damping characteristics of the bearing. The gear meshing stiffness, bearing stiffness, and table support stiffness are substituted with the model correction results.

[0040] S32. A rigid body dynamics model of the gear transmission system including a rigid body is established based on the simulation of the gear meshing transmission and the simulation of the bearing and the worktable support. At the same time, in order to achieve a more accurate vibration response simulation of the gear transmission system, a rigid-flexible coupling multi-body dynamics model is constructed considering the flexible behavior of the box components.

[0041] S33, generate an MNF file of the flexible box through finite element software, import the MNF file into ADAMS to replace the original rigid body, and realize the creation of the flexible body by checking the center of mass position, mass and moment of inertia conditions; S34. After the flexible body is created, the degrees of freedom of the rigid body and the flexible body need to be coupled by connecting the sleeve force between them to obtain a multi-body dynamics model that takes into account the flexible behavior of the box components and is rigid-flexible coupled. For example, a sleeve force is applied between the rigid area of ​​the bolt hole of the flexible box and the ground, and the stiffness value of the sleeve force is set to the corrected three-way support stiffness value, thus realizing the rigid-flexible coupling of the multi-body dynamics model. Figure 3 shown.

[0042] S35, substituting the corrected system model parameters into the multi-body dynamics model as corresponding parameter values; S36, build a vibration response test bench and set test conditions, apply speed and load to perform dynamic simulation, and obtain vibration response data under multiple conditions. Specifically, on the constructed multi-body dynamics model, set test conditions, apply speed and load to perform dynamic simulation, and build a test bench to verify the accuracy of the multi-body dynamics model.

[0043] This embodiment uses multi-body dynamics analysis technology to realize the dynamic simulation of the gear transmission system. By constructing a rigid-flexible coupling dynamic model, the simulation efficiency is improved, and the interaction between the various components of the system can be accurately simulated to avoid the loss of accuracy. At the same time, based on the rigid-flexible coupling multi-body dynamic model of the gear transmission system, the system model parameters obtained by correcting the finite element model are substituted into the dynamic model to ensure accuracy.

[0044] S4. Construct a sample data set based on the vibration response data under multiple working conditions, and use the sample data set to train and evaluate the vibration response prediction model based on the BP neural network. In this embodiment, 20 groups of vibration response data under working conditions are sampled according to the optimal Latin hypercube sampling method, the original data is obtained through dynamic simulation, and the sample data set is constructed by data resampling and other processing. Figure 4 and Figure 5 shown.

[0045] This embodiment establishes a vibration response prediction model based on BP neural network to complete the following Figure 6The network structure design is shown in the figure. The activation function is selected as the ReLU function, the loss function is the Mean Squared Error (MSE) function, and the optimization algorithm is the Adam algorithm. Before the neural network training, the Z-score standardization method is selected to convert the original data into a standard normal distribution with a mean of 0 and a standard deviation of 1, so as to ensure that each feature contributes evenly to the model training. Then the vibration response prediction model is trained, and the MSE, MAE, RMSE, R 2 The model training results are evaluated on the training set and the test set as evaluation indicators, such as Figure 7 and Figure 8 The standardized formula is: ; (16) In the formula, is the data before standardization, is the sample mean, is the sample standard deviation, is the standardized data.

[0046] In this embodiment, the training set is a speed range of 800r / min to 2000r / min, a load torque range of 2 to 18Nm, and 20 groups of samples are selected. The 20 groups of operating parameters obtained by optimal Latin hypercube sampling are distributed more evenly in the sample space, so the constructed data set can better represent the entire sample space. During the training process, the data set contains a total of 4000 data, and the data set is divided into 80% training set and 20% test set. The initial learning rate is 0.001, and the number of training times is 500. The structure of the neural network is an input layer, two hidden layers and an output layer. The structure of the neural network is that the number of input layer nodes is 3, the number of two hidden layer nodes is 128, and the number of output layer nodes is 1. A set of working conditions outside the training set was selected to verify the training effect of the model. The speed was 1300r / min and the load torque was 7.5N·m. It was found that the MSE of the prediction results and the simulation results was 0.255, the RMSE was 0.505, and the MAE was 0.383. The prediction error was small, indicating that the prediction model can accurately predict the vibration response signal of the gear transmission system.

[0047] This embodiment is based on the vibration response prediction model construction method of the BP neural network, and proposes to construct a high-fidelity multi-body dynamics model of the gear transmission system through the modified system model parameters, and perform simulation to obtain vibration response data under multiple groups of working conditions. Finally, the vibration response prediction model of the gear transmission system is constructed in combination with the BP neural network to achieve rapid prediction of the vibration response under different working parameters.

[0048] S5. The speed, load and normalized time ID of the gear transmission system are used as inputs of the vibration response prediction model, and the output is the vibration acceleration response value at the corresponding time point, so as to realize rapid prediction of vibration signals under different working conditions.

[0049] The input of the vibration response prediction model is the speed, load and normalized time ID, and the output is the vibration acceleration response value at the corresponding time point. A set of data outside the training set and the test set is selected for verification. The prediction curve obtained by the vibration response prediction model is in good agreement with the dynamic simulation results. Fig. 9 As shown in the figure, the present invention has been applied and verified on a primary gear transmission system. The results of application and verification show that the prediction results obtained by the proposed method are compared with the dynamic simulation results. The prediction curve and the simulation curve have a high degree of consistency, and are close at the extreme values ​​of the vibration acceleration signal. At the same time, the corresponding curve change trends at different time points are basically consistent, which shows that the constructed vibration response prediction model can realize the rapid prediction of vibration signals under different working conditions.

[0050] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, so the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0051] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for rapid prediction of vibration response of a gear transmission system based on system partition model correction, characterized in that: The method comprises the following steps: S1. Divide the gear transmission system into different subsystems according to the contact mode and connection relationship between the transmission structures in the gear transmission system, and establish finite element models of each subsystem and the gear transmission system; S2. Modify the finite element models of each subsystem and the gear transmission system to obtain modified system model parameters; S3. Use multi-body dynamics analysis method to establish a multi-body dynamics model of rigid-flexible coupling of the gear transmission system, substitute the system model parameters into the multi-body dynamics model and perform simulation to obtain vibration response data under multiple working conditions; S4. constructing a sample data set based on vibration response data under multiple groups of working conditions, and using the sample data set to train and evaluate a vibration response prediction model based on a BP neural network; S5. The speed, load and normalized time ID of the gear transmission system are used as inputs of the vibration response prediction model, and the output is the vibration acceleration response value at the corresponding time point, so as to realize rapid prediction of vibration signals under different working conditions.

2. The method for rapid prediction of vibration response of a gear transmission system according to claim 1, characterized in that: The subsystems include a pinion shaft subsystem, a large gear shaft subsystem, a box body and box cover connection system, a box body and bearing end cover connection system, a box body and input shaft support system, and a box body and output shaft support system.

3. The method for rapid prediction of vibration response of a gear transmission system according to claim 1, characterized in that: In step S1, the specific process includes the following steps: S11. Divide the gear transmission system into different subsystems according to the contact mode and connection relationship between them, and establish geometric models of different subsystems using 3D modeling software; S12. Import the geometric model into the finite element analysis software ANSYS, and mesh the gear transmission system. Modeling and simulation are performed separately for the connection and contact of different components to simplify the overall geometric structure. Modeling and simulation to simplify the overall geometric structure include: The connection between the gear and the gear shaft is simplified by using the thin layer element method; Thin layer elements are used to simulate the connection between the box body and the box cover, and the connection between the bearing end cover and the box body; For the meshing contact modeling between gears, the Combin14 unit in the finite element analysis software ANSYS is used for simulation; For the simulation of bearings, the bearing unit of finite element analysis software ANSYS is used to simulate its radial support, and the spring unit is used to simulate its axial support; S13. Establish finite element models of each subsystem and gear transmission system according to the simplified modeling simulation scheme.

4. The method for rapid prediction of vibration response of a gear transmission system according to claim 1, characterized in that: In step S2, the specific process includes the following steps: S21, performing modal knocking tests and operating modal analysis on each subsystem and gear transmission system to obtain modal parameters including natural frequencies and modal vibration shapes; S22, selecting correction parameters corresponding to each subsystem and the gear transmission system, wherein in each subsystem, the correction parameters include the elastic modulus of the material, the elastic modulus of the thin layer unit, and the bearing stiffness; in the gear transmission system, the correction parameters include the meshing stiffness of the gear and the three-way support stiffness of the workbench; S23. Correct the correction parameters based on the response surface model to obtain more accurate system model parameters.

5. The method for rapid prediction of vibration response of a gear transmission system according to claim 4, characterized in that: In step S21, the specific process includes the following steps: S211. Importing a finite element model of any subsystem into the finite element analysis software ANSYS, setting the initial elastic modulus of the material and the initial elastic modulus of the thin layer unit, and solving the modal information of the subsystem; S212, extracting a group of nodes that can fully reflect its modal vibration shape from the modal information, combining the nodes as the measurement points of the modal test and constructing the required geometric model in LMS Test.lab; S213, using the mobile hammer method, sticking the sensor on the end face of the geometric model, and using the hammer to stimulate all measuring points in turn, hitting each measuring point at least 3 times and taking the average value to reduce the error; S214. After the tapping is completed, the test results are processed to obtain the modal parameters of the subsystem including the natural frequency and the modal vibration shape.

6. The method for rapid prediction of vibration response of a gear transmission system according to claim 4, characterized in that: In step S23, the specific process includes the following steps: S231, construct response surface model based on Kriging model; S232. The objective function of the response surface model is constructed according to the natural frequency measured by the modal knocking test. The expression of the objective function is: ; In the formula, is the parameter value to be corrected, is the lower limit of the value range of the corresponding parameter; is the upper limit of the value range; is the test frequency value; The response frequency values ​​calculated for the response surface; is the number of parameters to be corrected; is the number of objective functions; S233. Based on the objective function, iterative optimization is performed through a multi-objective genetic algorithm to seek the input variable combination that best meets the target result as the system model parameters.

7. The method for rapid prediction of vibration response of a gear transmission system according to claim 6, characterized in that: In step S231, the specific process includes the following steps: S2311, based on any set of input data and output response Establish the Kriging model, the expression is: ; In the formula, is a polynomial function; is the coefficient vector corresponding to the polynomial; is a random process with mean zero and variance Normal distribution of S2312, determine the random process The covariance function of , the expression is: ; In the formula, is the spatial correlation function used to describe the sampling points and The correlation between is a key parameter used to adjust the correlation between sample points; S2313, use the maximum likelihood estimation method to solve the coefficient vector and variance The predicted value of , the calculation formula is: ; ; In the formula, is the number of parameters to be corrected; To output the response data set; is a polynomial function The matrix composed of S2314, according to the spatial function and variance To solve the key parameters , the calculation formula is: ; S2315, determine the correlation vector between the point to be measured and the known sampling point , the expression is: ; S2316, the relevant vector , key parameters , coefficient vector , spatial function and variance Substituting into the Kriging model, we get the response surface model used to correct the correction parameters, and the expression is: ; In the formula, The point to be tested The predicted value of the response; is a polynomial function The matrix composed of.

8. The method for rapid prediction of vibration response of a gear transmission system according to claim 1, characterized in that: In step S3, the specific process includes the following steps: S31. Import the geometric model of the gear transmission system into ADAMS in the STEP neutral format, apply corresponding constraints between different components according to their connection relationships, and simulate the gear meshing transmission and the bearing and workbench support; S32, establishing a rigid body dynamics model of the gear transmission system including a rigid body according to the simulation of the gear meshing transmission and the simulation of the bearing and the worktable support; S33, generate an MNF file of the flexible box through finite element software, import the MNF file into ADAMS to replace the original rigid body, and realize the creation of the flexible body by checking the center of mass position, mass and moment of inertia conditions; S34, coupling the degrees of freedom of the rigid body and the flexible body by connecting them in a sleeve force manner, and obtaining a rigid-flexible coupled multi-body dynamics model that considers the flexible behavior of the box body components; S35, substituting the corrected system model parameters into the multi-body dynamics model as corresponding parameter values; S36. Build a vibration response test bench and set test conditions, apply rotation speed and load to perform dynamic simulation, and obtain vibration response data under multiple groups of conditions.

Images