Machining method and system for gear shaping in bearing

Abstract

The invention discloses a bearing internal gear shaping machining method and system, and relates to the technical field of data analysis, and the method comprises the steps: building a target finite element model based on a structure model of a to-be-machined bearing; performing equipment state detection on the gear shaping equipment, and performing machining deviation prediction based on equipment state information in combination with the relative position relationship between the to-be-machined bearing and the gear shaping equipment; analyzing initial feed amount data, initial stroke speed and initial cutting depth data of the to-be-processed bearing in each gear shaping processing stage based on the processing deviation prediction information and the target finite element model; the initial feed amount data, the initial stroke speed and the initial cutting depth data are optimized based on an analogue simulation result of bearing gear shaping machining; and gear shaping machining equipment is controlled to conduct gear shaping machining on the to-be-machined bearing based on the optimized feeding amount data, the optimized stroke speed and the optimized cutting depth data. The bearing gear shaping machining precision can be improved, and the high quality of bearing gear shaping machining is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, and particularly relates to a bearing inner spline machining method and system. BACKGROUND

[0002] The bearing is the core basic component of the mechanical system, which ensures the efficient, safe and stable operation of the equipment by reducing friction, supporting load and maintaining rotation accuracy, and the spline machining is the key process for improving the accuracy and performance of the bearing. At present, the spline machining parameters of the bearing are mainly analyzed by technical personnel according to theory and experience, but this method is too dependent on the professional accomplishment of the relevant personnel, and it is difficult to guarantee the accuracy of the spline machining parameter analysis, and with the increasing amount of data, this method gradually cannot meet the current analysis efficiency. And the state change of the spline machining equipment is usually not considered in the current spline machining parameter analysis, and with the long-term use of the spline machining equipment, its performance state will also change, and due to the state change of the spline machining equipment, there will be a certain machining deviation in the operation process, and if the state detection of the equipment is not considered, the reliability of the machining parameters will be insufficient, which will affect the quality of the bearing inner spline machining. SUMMARY

[0003] The purpose of the present application is to overcome the shortcomings of the prior art, and the present application provides a bearing inner spline machining method and system, which can improve the accuracy of the bearing spline machining and guarantee the high quality of the bearing spline machining.

[0004] In order to solve the above technical problems, the present application provides a bearing inner spline machining method, which comprises: Obtaining the structure model of the bearing to be machined, and constructing the target finite element model of the bearing to be machined based on the structure model; Performing equipment state detection on the spline machining equipment to obtain equipment state information, and based on the equipment state information, the relative position relationship between the bearing to be machined and the spline machining equipment is combined to predict the machining deviation, and the machining deviation prediction information is obtained; Based on the machining deviation prediction information and the target finite element model, the initial feed amount data, the initial stroke speed and the initial cutting depth data of the bearing to be machined at each spline machining stage are analyzed; Based on the initial feed amount data, the initial stroke speed and the initial cutting depth data, the simulation of the spline machining of the bearing is carried out, the simulation results are obtained, and based on the simulation results, the initial feed amount data, the initial stroke speed and the initial cutting depth data are optimized, and the optimized feed amount data, the optimized stroke speed and the optimized cutting depth data are obtained; Based on the optimized feed amount data, the optimized stroke speed and the optimized cutting depth data, the spline machining equipment is controlled to perform spline machining processing on the bearing to be machined.

[0005] Optionally, the structure model of the bearing to be machined is acquired, and a target finite element model of the bearing to be machined is constructed based on the structure model, including: The material physical parameters and point cloud data of the bearing to be machined are acquired, and a structure model of the bearing to be machined is constructed based on the point cloud data; The material physical parameters are used to divide and refine the grid of the structure model based on a local encryption method and stress analysis, to obtain an initial finite element model; The mechanical boundary condition and the thermal boundary condition are determined, and the initial finite element model is adjusted based on the mechanical boundary condition and the thermal boundary condition, to obtain a target finite element model of the bearing to be machined.

[0006] Optionally, the structure model of the bearing to be machined is constructed based on the point cloud data, including: The point cloud data is subjected to noise reduction processing to obtain noise-reduced point cloud data; The noise-reduced point cloud data is subjected to dense sampling processing to obtain dense-sampled point cloud data, and a spatial triangular mesh model is constructed based on the dense-sampled point cloud data; The model of the bearing to be machined is constructed based on the spatial triangular mesh model in combination with a three-dimensional reconstruction technology, to obtain a structure model of the bearing to be machined.

[0007] Optionally, the device state detection is performed on the gear shaping machine tool to obtain device state information, and the machining deviation prediction is performed based on the device state information in combination with the relative position relationship between the bearing to be machined and the gear shaping machine tool, to obtain machining deviation prediction information, including: The historical state data of the gear shaping machine tool is acquired, and change trend analysis is performed based on the historical state data to obtain change trend data; The wear characteristic data of a plurality of time steps is constructed based on the historical state data; The precision retention capability data of the gear shaping machine tool is analyzed based on the historical state data by using a Bayesian algorithm, and the device state detection is performed based on the change trend data, the wear characteristic data and the precision retention capability data by using an attention network, to obtain device state information; The first position information of the bearing to be machined and the second position information of the gear shaping machine tool in the machining process are acquired, and the relative position relationship between the bearing to be machined and the gear shaping machine tool is generated based on the first position information and the second position information; The running data of the gear shaping machine tool running according to the preset process information is collected, and the machining deviation prediction is performed based on the running data, the relative position relationship and the device state information by using a prediction model, to obtain machining deviation prediction information.

[0008] Optionally, the processing deviation prediction is performed based on the running data, relative position relationship and device state information by using a prediction model to obtain processing deviation prediction information, comprising: The historical running data of the gear shaping processing device is acquired, the geometric error function fitting is performed based on the historical state data and historical running data to obtain a target geometric error function, and the prediction model is constructed based on the geometric error function; The running data, relative position relationship and device state information are input into the prediction model to perform processing deviation prediction and obtain processing deviation prediction information.

[0009] Optionally, the initial feed amount data, initial stroke speed and initial cutting depth data of the bearing to be processed in each gear shaping processing stage are analyzed based on the processing deviation prediction information and the target finite element model, comprising: The initial adjustment amount of the preset process information in each gear shaping processing stage is analyzed based on the processing deviation prediction information and the target finite element model; The processing process energy consumption data corresponding to each initial adjustment amount is determined, and the power data corresponding to each initial adjustment amount is analyzed; The instantaneous characteristic analysis of power change is performed based on the processing process energy consumption data to obtain instantaneous characteristic data, and the cumulative energy consumption analysis is performed based on the processing process energy consumption data to obtain cumulative energy consumption data; The quality constraint function is constructed, the target adjustment amount is determined based on the instantaneous characteristic data, cumulative energy consumption data and power data in combination with the quality constraint function, and the initial feed amount data, initial stroke speed and initial cutting depth data of the bearing to be processed in each gear shaping processing stage are determined based on the target adjustment amount.

[0010] Optionally, the processing process energy consumption data corresponding to each initial adjustment amount is determined, and the power data corresponding to each initial adjustment amount is analyzed, comprising: The processing auxiliary material consumption data and device energy consumption data corresponding to each initial adjustment amount are matched, and the corresponding processing process energy consumption data is determined based on the processing auxiliary material consumption data and device energy consumption data; The load power analysis and no-load power analysis are performed based on the initial adjustment amount to obtain load power data and no-load power data, and the corresponding power data is determined based on the load power data and no-load power data.

[0011] Optionally, the initial feed amount data, initial stroke speed and initial cutting depth data are optimized based on the simulation result to obtain optimized feed amount data, optimized stroke speed and optimized cutting depth data, comprising: extract feedback data based on the simulation result, and optimize the initial feed amount data, initial stroke speed and initial cutting depth data based on the feedback data to obtain optimized feed amount data, optimized stroke speed and optimized cutting depth data.

[0012] Optionally, the control of the gear shaping machining equipment to perform gear shaping machining on the bearing to be machined based on the optimized feed amount data, optimized stroke speed and optimized cutting depth data comprises: generating control instructions based on the optimized feed amount data, optimized stroke speed and optimized cutting depth data; controlling the gear shaping machining equipment to perform gear shaping machining on the bearing to be machined in each stage based on the control instructions, and controlling the pouring equipment to perform cooling oil pouring processing on the bearing during the gear shaping machining processing.

[0013] In addition, the application further provides a bearing gear shaping machining system, which comprises: a model construction module configured to acquire a structure model of a bearing to be machined, and construct a target finite element model of the bearing to be machined based on the structure model; a deviation prediction module configured to detect a device state of a gear shaping machining equipment to obtain device state information, and predict a machining deviation based on the device state information in combination with a relative position relationship between the bearing to be machined and the gear shaping machining equipment to obtain machining deviation prediction information; a parameter analysis module configured to analyze initial feed amount data, initial stroke speed and initial cutting depth data of the bearing to be machined in each gear shaping machining stage based on the machining deviation prediction information and the target finite element model; a parameter optimization module configured to perform simulation of gear shaping machining of the bearing based on the initial feed amount data, initial stroke speed and initial cutting depth data to obtain a simulation result, and optimize the initial feed amount data, initial stroke speed and initial cutting depth data based on the simulation result to obtain optimized feed amount data, optimized stroke speed and optimized cutting depth data; a gear shaping machining module configured to control the gear shaping machining equipment to perform gear shaping machining on the bearing to be machined based on the optimized feed amount data, optimized stroke speed and optimized cutting depth data.

[0014] In the embodiment of the present application, the structural model of the bearing to be machined is acquired, and the target finite element model of the bearing to be machined is constructed based on the structural model. The finite element model can provide more reliable data support for subsequent gear shaping machining parameter analysis. The equipment state of the gear shaping machining equipment is detected, and the machining deviation is predicted based on the equipment state information and the relative position relationship between the bearing to be machined and the gear shaping machining equipment. The state change of the gear shaping machining equipment is more clearly understood, and the accuracy of the machining deviation prediction is improved. The initial feed amount data, the initial stroke speed and the initial cutting depth data of the bearing to be machined at each gear shaping machining stage are analyzed based on the machining deviation prediction information and the target finite element model, which greatly reduces the dependence on manual work and improves the reliability and efficiency of the gear shaping machining parameter analysis. The initial feed amount data, the initial stroke speed and the initial cutting depth data are optimized through simulation of the bearing gear shaping machining according to the initial feed amount data, the initial stroke speed and the initial cutting depth data. The gear shaping machining equipment is controlled based on the optimized feed amount data, the optimized stroke speed and the optimized cutting depth data to perform gear shaping machining on the bearing to be machined, which can further improve the precision of the bearing gear shaping machining and ensure the high quality of the bearing gear shaping machining. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0016] Figure 1 is a flowchart of the bearing internal gear shaping machining method in the embodiment of the present application; Figure 2 is a flowchart of the bearing internal gear shaping machining method in another embodiment of the present application; Figure 3 is a structural composition diagram of the bearing internal gear shaping machining system in the embodiment of the present application. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0018] Embodiment one Please refer to Figure 1 , Figure 1is a flowchart of a bearing internal spline machining method in an embodiment of the application, the method comprising: S11: obtaining a structure model of a bearing to be machined, and constructing a target finite element model of the bearing to be machined based on the structure model; In the specific implementation of the application, the material physical parameters and point cloud data of the bearing to be machined are obtained, the structure model of the bearing to be machined is constructed based on the point cloud data, the material physical parameters are used to perform grid division and grid refinement on the structure model based on the local encryption method and stress analysis, and an initial finite element model is obtained; the mechanical boundary condition and the thermal boundary condition are determined, the initial finite element model is adjusted based on the mechanical boundary condition and the thermal boundary condition, and a target finite element model of the bearing to be machined is obtained, which can obtain a more accurate finite element model and provide more reliable data support for subsequent spline machining parameter analysis.

[0019] S12: performing equipment state detection on the spline machining equipment to obtain equipment state information, and performing machining deviation prediction based on the equipment state information in combination with the relative position relationship between the bearing to be machined and the spline machining equipment to obtain machining deviation prediction information; In the specific implementation of the application, the change trend of the historical state data of the spline machining equipment is analyzed; a plurality of time step wear characteristic data are constructed based on the historical state data; the precision retention capability data of the spline machining equipment are analyzed based on the historical state using the Bayesian algorithm, and the equipment state information is obtained by performing equipment state detection using the attention network based on the change trend data, the wear characteristic data and the precision retention capability data; the relative position relationship between the bearing to be machined and the spline machining equipment is generated based on the first position information of the bearing to be machined and the second position information of the spline machining equipment during the machining process; the running data of the spline machining equipment running according to the preset process information is collected, and the machining deviation prediction is performed using the prediction model based on the running data, the relative position relationship and the equipment state information, which can accurately reflect the state of the spline machining equipment and make the obtained machining deviation prediction information more close to the actual situation.

[0020] S13: analyzing the initial feed amount data, the initial stroke speed and the initial cutting depth data of the bearing to be machined at each spline machining stage based on the machining deviation prediction information and the target finite element model; In the specific implementation of the present application, based on the machining deviation prediction information and the target finite element model, a plurality of initial adjustment amounts of preset process information in each gear shaping machining stage are analyzed; the machining process energy consumption data corresponding to each initial adjustment amount is determined, and the power data corresponding to each initial adjustment amount is analyzed; the instantaneous characteristic analysis of power change is carried out based on the machining process energy consumption data, the instantaneous characteristic data is obtained, the cumulative energy consumption analysis is carried out based on the machining process energy consumption data, and the cumulative energy consumption data is obtained; the quality constraint function is constructed, the target adjustment amount is determined based on the instantaneous characteristic data, the cumulative energy consumption data and the power data combined with the quality constraint function, the initial feed amount data, the initial stroke speed and the initial cutting depth data of the bearing to be machined in each gear shaping machining stage are determined based on the target adjustment amount, and the influence of the gear shaping equipment state on the machining parameters is considered. At the same time, the consideration of machining energy consumption is introduced, so that the analyzed initial feed amount data, initial stroke speed and initial cutting depth data are more reliable.

[0021] S14: Simulation of bearing gear shaping is carried out based on the initial feed amount data, initial stroke speed and initial cutting depth data, simulation results are obtained, and the initial feed amount data, initial stroke speed and initial cutting depth data are optimized based on the simulation results, to obtain optimized feed amount data, optimized stroke speed and optimized cutting depth data. In the specific implementation of the present application, simulation of bearing gear shaping is carried out based on the initial feed amount data, initial stroke speed and initial cutting depth data, feedback data is extracted based on the simulation results, and the initial feed amount data, initial stroke speed and initial cutting depth data are optimized based on the feedback data, to further improve the accuracy of the gear shaping parameters. At the same time, a large amount of manpower and material resources can be saved through simulation.

[0022] S15: The gear shaping equipment is controlled based on the optimized feed amount data, optimized stroke speed and optimized cutting depth data to carry out gear shaping processing on the bearing to be machined.

[0023] In the specific implementation of the present application, control instructions are generated based on the optimized feed amount data, optimized stroke speed and optimized cutting depth data, the gear shaping equipment is controlled based on the control instructions to carry out gear shaping processing on the bearing to be machined in each stage, and the pouring equipment is controlled to carry out cooling oil pouring processing on the bearing in the gear shaping processing process. Through the optimized feed amount data, optimized stroke speed and optimized cutting depth data, the quality of bearing gear shaping can be effectively improved, and the obtained machining finished product is more in line with the ideal situation.

[0024] In the embodiment of the present application, the structure model of the bearing to be machined is acquired, and a target finite element model of the bearing to be machined is constructed based on the structure model. The finite element model can provide more reliable data support for subsequent gear shaping machining parameter analysis. The state of the gear shaping machining equipment is detected, and the machining deviation is predicted based on the state information of the equipment in combination with the relative position relationship between the bearing to be machined and the gear shaping machining equipment. The state change of the gear shaping machining equipment is more clearly understood, and the accuracy of the machining deviation prediction is improved. The initial feed amount data, the initial stroke speed and the initial cutting depth data of the bearing to be machined at each gear shaping machining stage are analyzed based on the machining deviation prediction information and the target finite element model. The artificial dependence is greatly reduced, and the reliability and efficiency of the gear shaping machining parameter analysis are improved. The initial feed amount data, the initial stroke speed and the initial cutting depth data are optimized through simulation of bearing gear shaping machining according to the initial feed amount data, the initial stroke speed and the initial cutting depth data. The gear shaping machining equipment is controlled based on the optimized feed amount data, the optimized stroke speed and the optimized cutting depth data to perform gear shaping machining on the bearing to be machined. The precision of the bearing gear shaping machining is further improved, and the high quality of the bearing gear shaping machining is ensured.

[0025] Embodiment two Please refer to Figure 2 , Figure 2 is a flowchart of a bearing gear shaping machining method in another embodiment of the present application. The method comprises the following steps: S201: acquiring a structure model of a bearing to be machined, and constructing a target finite element model of the bearing to be machined based on the structure model; In the specific implementation process of the present application, the structure model of the bearing to be machined is acquired, and a target finite element model of the bearing to be machined is constructed based on the structure model. Specifically, the material physical parameters and point cloud data of the bearing to be machined are acquired, and a structure model of the bearing to be machined is constructed based on the point cloud data. The material physical parameters are used to perform grid division and grid refinement on the structure model based on local encryption method and stress analysis, to obtain an initial finite element model. The mechanical boundary conditions and thermal boundary conditions are determined, and the initial finite element model is adjusted based on the mechanical boundary conditions and the thermal boundary conditions, to obtain the target finite element model of the bearing to be machined.

[0026] Specifically, the material physical parameters and point cloud data of the bearing to be machined are acquired. The material physical parameters include elastic modulus, density, thermal expansion coefficient, thermal conductivity and specific heat capacity, etc. The structure model of the bearing to be machined is constructed based on the point cloud data. The point cloud data can be subjected to noise reduction and dense sampling processing, and the structure model is constructed according to the processed point cloud data.

[0027] Based on the local refinement method and stress analysis, the structural model is meshed and refined using the material physical parameters. Finite element mesh models with different mesh sizes are constructed according to the structural model. The stress corresponding to the finite element mesh models with different mesh sizes is analyzed. The mesh size of the finite element mesh model corresponding to the maximum stress is adjusted. If the stress of the finite element mesh model no longer increases with the decrease of size, such as the size gradually decreasing from 10 mm to 1 mm, then this size is used as the mesh size. The structural model is meshed according to the mesh size. At the same time, the mesh of the joint of the bearing to be machined is refined using the local refinement method. The joint is the area where the parts of the mechanical structure come into contact with each other and the load is transferred between them, such as the contact area between the ball and the raceway. The local refinement method can adopt the circular local refinement method, which refines the mesh with the contact point as the center. The corresponding material physical parameters are assigned to each mesh that is divided and refined to obtain the initial finite element model.

[0028] Mechanical and thermal boundary conditions are determined. Mechanical boundary conditions include displacement constraints, the application of external forces and external stresses, etc. Thermal boundary conditions are temperature boundary conditions and boundary conditions for heat flow in the finite element model. Based on the mechanical and thermal boundary conditions, the initial finite element model is adjusted to obtain the target finite element model of the bearing to be processed. That is, mechanical and thermal boundary conditions are applied to the initial finite element model to make the obtained target finite element model more comprehensive and accurate.

[0029] Furthermore, the step of constructing a structural model of the bearing to be processed based on the point cloud data includes: performing noise reduction processing on the point cloud data to obtain noise-reduced point cloud data; performing dense sampling processing on the noise-reduced point cloud data to obtain densely sampled point cloud data, and constructing a spatial triangular mesh model based on the densely sampled point cloud data; and constructing a model of the bearing to be processed based on the spatial triangular mesh model combined with three-dimensional reconstruction technology to obtain a structural model of the bearing to be processed.

[0030] Specifically, the point cloud data is denoised to obtain denoised point cloud data. The denoising process can employ filtering algorithms. Dense sampling is then performed on the denoised point cloud data to obtain densely sampled point cloud data. Multiple triangular facets are obtained from the denoised point cloud data. Random sampling is performed based on the vertex coordinates of each triangular facet to obtain multiple random sampling points. Upsampling is then performed on the point cloud data based on these random sampling points to obtain densely sampled point cloud data. Dense sampling increases the density of the original point cloud to a higher level by generating additional sampling points, smoothing the surface of the point cloud, reducing noise and irregularities in the shape, and ensuring that the point cloud data is at a uniformly dense state across all positions on the curved surface.

[0031] A spatial triangular mesh model is constructed based on the densely sampled point cloud data. Corresponding contour segments are generated from the densely sampled point cloud data, and cross-sectional geometric contours are generated from the contour segments. Triangulation is performed by combining the Delaunay growth algorithm with the cross-sectional geometric contours to construct a triangular mesh, thereby obtaining the spatial triangular mesh model.

[0032] The model of the bearing to be processed is constructed based on the spatial triangular mesh model combined with 3D reconstruction technology. The 3D reconstruction technology can use convolutional neural networks to extract the features of the spatial triangular mesh model to construct the 3D structure of the object, that is, to obtain the structural model of the bearing to be processed, so that the obtained structural model is more accurate and can reduce the error of processing parameter analysis.

[0033] S202: Obtain historical status data of the gear hobbing equipment, and perform trend analysis based on the historical status data to obtain trend data; In the specific implementation of this invention, historical status data of the gear shaping equipment is obtained. The gear shaping equipment is a gear shaping cutter with a rotating base and high-speed movement. The historical status data includes wear data, abnormal occurrence data, and performance degradation data of the gear shaping equipment in various historical time periods. Based on the historical status data, trend analysis is performed to obtain trend data, that is, to analyze the numerical trend of the historical status data, such as the trend of wear data.

[0034] S203: Construct wear characteristic data for several time steps based on the historical state data; In the specific implementation of this invention, wear data for each historical time period is extracted based on historical state data. The wear data is divided into several different time steps, and feature extraction is performed on the wear data of each time step to obtain wear feature data for several time steps, such as mechanical vibration and cutting force signals of the equipment.

[0035] S204: Based on the historical state data, the accuracy retention capability data of the gear hobbing equipment is analyzed using a Bayesian algorithm, and based on the change trend data, wear characteristic data, and accuracy retention capability data, an attention network is used to detect the equipment status and obtain equipment status information. In the specific implementation of this invention, historical state data is input into a deep learning model employing Naive Bayes to analyze the accuracy retention capability of the gear hobbing equipment, thereby obtaining accuracy retention capability data. The trend data, wear characteristic data, and accuracy retention capability data are then input into an attention network for equipment state detection. This attention network is a neural network employing an attention mechanism. Through this attention network, equipment state information is obtained, describing the current state of the gear hobbing equipment, such as high wear levels and poor accuracy retention capability.

[0036] S205: Obtain the first position information of the bearing to be processed and the second position information of the gear hobbing equipment during the processing, and generate the relative positional relationship between the bearing to be processed and the gear hobbing equipment based on the first position information and the second position information; In the specific implementation of this invention, the first position information of the bearing to be processed and the second position information of the gear hobbing equipment are obtained during the gear hobbing process. Based on the first and second position information, the relative positional relationship between the bearing to be processed and the gear hobbing equipment is generated. The first and second position information are input into the analysis software to obtain the relative positional relationship between the bearing to be processed and the gear hobbing equipment. The analysis software is equipped with a function to analyze the relative positional changes of the bearing and the gear hobbing equipment.

[0037] S206: Collect the operating data of the gear hobbing equipment according to the preset process information, and use the prediction model to predict the processing deviation based on the operating data, relative position relationship and equipment status information to obtain processing deviation prediction information; In a specific implementation of this invention, the step of using a prediction model to predict processing deviations based on the operating data, relative positional relationships, and equipment status information to obtain processing deviation prediction information includes: acquiring historical operating data of the gear hobbing equipment; fitting a geometric error function based on the historical status data and historical operating data to obtain a target geometric error function; and constructing a prediction model based on the geometric error function; inputting the operating data, relative positional relationships, and equipment status information into the prediction model to predict processing deviations and obtain processing deviation prediction information.

[0038] Specifically, the operation data of the gear hobbing equipment is collected when it operates according to the preset process information. That is, when the gear hobbing equipment is running in simulation according to the preset process information, its operation data at each time point is collected, such as feed rate and cutting speed. The preset process information is the processing process parameters of each processing stage set in advance according to the specifications of the bearing to be processed, including feed rate data, stroke speed and cutting depth.

[0039] Historical operating data of the gear hobbing equipment is obtained. Geometric error function fitting is performed based on the historical state data and historical operating data. Equipment error data for historical time periods is analyzed based on the historical operating data and historical state data. Polynomial fitting is performed based on the equipment error data to obtain the target geometric error function. Data points (x, y) of the equipment error data are obtained. The order n and coefficient vector a of the fitting polynomial are determined, and a polynomial function is constructed. The expression of the polynomial function can be: A prediction model is constructed based on the geometric error function, that is, a prediction model is constructed using a deep learning algorithm based on the geometric error function. The operating data, relative positional relationships, and equipment status information are input into the prediction model to predict machining deviations, thereby obtaining machining deviation prediction information. This machining deviation prediction information predicts various deviations that may exist in the machining of bearings by the gear hobbing equipment under the current state, such as deviations in cutting depth and speed.

[0040] S207: Based on the machining deviation prediction information and the target finite element model, analyze the initial feed rate, initial stroke speed and initial cutting depth data of the bearing to be machined in each gear hobbing stage; In the specific implementation of this invention, the step of analyzing the initial feed rate, initial stroke speed, and initial cutting depth data of the bearing to be processed in each gear shaping stage based on the machining deviation prediction information and the target finite element model includes: analyzing several initial adjustment amounts of preset process information in each gear shaping stage based on the machining deviation prediction information and the target finite element model; determining the machining process energy consumption data corresponding to each initial adjustment amount, and analyzing the power data corresponding to each initial adjustment amount; performing instantaneous feature analysis of power change based on the machining process energy consumption data to obtain instantaneous feature data, and performing cumulative energy consumption analysis based on the machining process energy consumption data to obtain cumulative energy consumption data; constructing a mass constraint function, determining the target adjustment amount based on the instantaneous feature data, cumulative energy consumption data, and power data combined with the mass constraint function, and determining the initial feed rate, initial stroke speed, and initial cutting depth data of the bearing to be processed in each gear shaping stage based on the target adjustment amount.

[0041] Specifically, based on the machining deviation prediction information and the target finite element model analysis, several initial adjustment quantities of the preset process information are obtained in each gear hobbing stage. The stiffness data and stress field data of the bearing to be processed are extracted according to the target finite element model. The machining deviation prediction information, stiffness data and stress field data are input into the adjustment quantity analysis model to obtain several initial adjustment quantities of the preset process information of the bearing to be processed in each gear hobbing stage, which are the adjustment quantities of the preset feed rate data, preset stroke speed and preset cutting depth. The adjustment quantity analysis model is a convergent model obtained by inputting the sample dataset into a deep neural network for training.

[0042] Determine the processing energy consumption data corresponding to each initial adjustment amount. The processing energy consumption data includes processing auxiliary material consumption data and equipment energy consumption data. Analyze the power data corresponding to each initial adjustment amount, including load power data and no-load power data.

[0043] Instantaneous characteristic analysis of power changes is performed based on the energy consumption data of the processing process to obtain instantaneous characteristic data. The maximum energy consumption, minimum energy consumption, standard deviation of energy consumption, and average energy consumption are analyzed based on the energy consumption data. Instantaneous characteristic data is determined based on these parameters, reflecting the pattern of power changes. Cumulative energy consumption analysis is then performed based on the energy consumption data of the processing process. Energy utilization rate, total processing energy consumption, and energy efficiency are analyzed based on the energy consumption data. Cumulative energy consumption data is generated based on these parameters, describing the overall energy consumption and energy efficiency of the processing process.

[0044] A quality constraint function is constructed, using the expected surface roughness C and expected cutting accuracy Q as quality constraints. The expression for the quality constraint function F can be: F = [min(C), max(Q)]. Based on the instantaneous feature data, cumulative energy consumption data, and power data, combined with the quality constraint function, the target adjustment amount is determined. The instantaneous feature data and cumulative energy consumption data are fused to obtain fused data. Based on the fused data and power data, combined with the quality constraint function, an optimization model is used to determine the final target adjustment amount from several initial adjustment amounts. The optimization model can be a deep learning model employing an optimization algorithm, such as a genetic algorithm. The algorithm employs particle swarm optimization and other methods to determine the initial feed rate, initial stroke speed, and initial depth of cut data for the bearing to be machined at each gear shaping stage based on the target adjustment amount. Specifically, it adjusts the preset feed rate, preset stroke speed, and preset depth of cut according to the target adjustment amount to obtain the initial feed rate, initial stroke speed, and initial depth of cut data for the bearing to be machined at each gear shaping stage. The feed rate data includes radial feed and circumferential feed. The gear shaping stage may include five stages; for example, the radial feed in the first gear shaping stage can be set to 0.0200 mm / Str, and the circumferential feed can be set to 0.200 mm / Str. The initial feed rate can be set to 0.547 mm / Str, the stroke speed can be set to 205 Str / min, and the depth of cut can be set to 0.547 mm. In the second stage, the radial feed rate can be set to 0.0200 mm / Str, the circumferential feed rate can be set to 0.200 mm / Str, the stroke speed can be set to 250 Str / min, and the depth of cut can be set to 0.500 mm. The different gear shaping parameters in different stages make the obtained initial feed rate data, initial stroke speed, and initial depth of cut data more accurate, while also reducing machining energy consumption.

[0045] Furthermore, determining the processing energy consumption data corresponding to each initial adjustment amount and analyzing the power data corresponding to each initial adjustment amount includes: matching the processing auxiliary material consumption data and equipment energy consumption data corresponding to each initial adjustment amount, and determining the corresponding processing energy consumption data based on the processing auxiliary material consumption data and equipment energy consumption data; performing load power analysis and no-load power analysis based on the initial adjustment amount to obtain load power data and no-load power data, and determining the corresponding power data based on the load power data and no-load power data.

[0046] Specifically, the data on the consumption of auxiliary processing materials and the energy consumption of equipment are matched with the data on the consumption of auxiliary materials that are effective in terms of energy consumption, such as the amount of cooling oil consumed in a certain processing stage. The data on the energy consumption of equipment is the energy consumption and processing time of the gear hobbing equipment under the initial adjustment. Based on the data on the consumption of auxiliary processing materials and the energy consumption of equipment, the corresponding energy consumption data of the processing process is determined.

[0047] Based on the initial adjustment amount, load power analysis and no-load power analysis are performed. The corresponding load power coefficient and no-load power coefficient are matched according to the initial adjustment amount. The load power is analyzed based on the load power coefficient, and the no-load power is analyzed based on the no-load power coefficient. That is, load power data and no-load power data are obtained. Based on the load power data and no-load power data, the corresponding power data is determined. The power data obtained in this way is more comprehensive and can provide more specific data support for the analysis of gear hobbing parameters.

[0048] S208: Simulate the bearing gear shaping process based on the initial feed rate data, initial stroke speed and initial cutting depth data, obtain simulation results, and optimize the initial feed rate data, initial stroke speed and initial cutting depth data based on the simulation results to obtain optimized feed rate data, optimized stroke speed and optimized cutting depth data. In the specific implementation of this invention, the step of optimizing the initial feed rate data, initial stroke speed, and initial depth of cut data based on the simulation results to obtain optimized feed rate data, optimized stroke speed, and optimized depth of cut data includes: extracting feedback data based on the simulation results, and optimizing the initial feed rate data, initial stroke speed, and initial depth of cut data based on the feedback data to obtain optimized feed rate data, optimized stroke speed, and optimized depth of cut data.

[0049] Specifically, the initial feed rate, initial stroke speed, and initial depth of cut data are input into simulation software to simulate bearing gear shaping, obtaining simulation results. Feedback data is extracted based on the simulation results, and the results are compared with the expected machining effect to analyze the deviation. Based on this feedback data, the initial feed rate, initial stroke speed, and initial depth of cut data are optimized. Corresponding optimization values ​​can be matched according to the feedback data; for example, the optimization value for radial feed can be 0.0050 mm / Str, and the optimization value for circumferential feed can be 0.050 mm / Str. Based on these optimization values, the relevant data are optimized to obtain optimized feed rate, optimized stroke speed, and optimized depth of cut data, further improving the reliability of the gear shaping machining parameters.

[0050] S209: Based on the optimized feed rate data, optimized stroke speed and optimized cutting depth data, control the gear shaping equipment to perform gear shaping on the bearing to be processed.

[0051] In a specific implementation of this invention, controlling the gear shaping equipment to perform gear shaping on the bearing to be processed based on the optimized feed rate data, optimized stroke speed, and optimized cutting depth data includes: generating control commands based on the optimized feed rate data, optimized stroke speed, and optimized cutting depth data; controlling the gear shaping equipment to perform gear shaping processing on the bearing to be processed at each stage based on the control commands; and controlling the casting equipment to perform cooling oil casting on the bearing during the gear shaping process.

[0052] Specifically, control commands are generated based on the optimized feed rate, optimized stroke speed, and optimized depth of cut data. Based on these control commands, the gear shaping equipment is controlled to perform gear shaping processing on the bearing to be processed at each stage. The casting equipment is also controlled to pour cooling oil onto the bearing during the gear shaping process. The cooling oil pouring reduces friction during gear shaping and also washes away machining debris. By using this optimized feed rate, optimized stroke speed, and optimized depth of cut data for bearing gear shaping, both machining quality and energy consumption can be ensured to be reasonable.

[0053] In this embodiment of the invention, a structural model of the bearing to be processed is obtained, and a target finite element model of the bearing to be processed is constructed based on the structural model. This finite element model provides more reliable data support for subsequent gear shaping parameter analysis. Equipment status monitoring is performed on the gear shaping equipment. Based on the equipment status information and the relative positional relationship between the bearing to be processed and the gear shaping equipment, processing deviation prediction is performed, providing a clearer understanding of the equipment's status changes and improving the accuracy of processing deviation prediction. Based on the processing deviation prediction information and the target finite element model, the initial feed rate, initial stroke speed, and initial depth of cut data of the bearing to be processed at each gear shaping stage are analyzed, greatly reducing reliance on manual labor and improving the reliability and efficiency of gear shaping parameter analysis. Simulation of the bearing gear shaping process is performed based on the initial feed rate, initial stroke speed, and initial depth of cut data to optimize these data. Controlling the gear shaping equipment to process the bearing to be processed based on the optimized feed rate, optimized stroke speed, and optimized depth of cut data further improves the precision of the bearing gear shaping process and ensures high quality.

[0054] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of the structural composition of the bearing internal gear shaping system in an embodiment of the present invention. The system includes: Model building module 31: used to obtain the structural model of the bearing to be processed, and to build the target finite element model of the bearing to be processed based on the structural model; Deviation prediction module 32: used to detect the equipment status of the gear hobbing equipment, obtain equipment status information, and predict the processing deviation based on the equipment status information and the relative positional relationship between the bearing to be processed and the gear hobbing equipment, thereby obtaining processing deviation prediction information; Parameter analysis module 33: used to analyze the initial feed rate, initial stroke speed and initial cutting depth data of the bearing to be processed in each gear hobbing stage based on the machining deviation prediction information and the target finite element model; Parameter optimization module 34: used to perform simulation of bearing gear hobbing based on the initial feed rate data, initial stroke speed and initial cutting depth data, obtain simulation results, and optimize the initial feed rate data, initial stroke speed and initial cutting depth data based on the simulation results to obtain optimized feed rate data, optimized stroke speed and optimized cutting depth data; Gear shaping module 35: Used to control the gear shaping equipment to perform gear shaping on the bearing to be processed based on the optimized feed rate data, optimized stroke speed and optimized cutting depth data.

[0055] In the specific implementation of this invention, the specific implementation methods of the system items can be referred to the implementation methods of the above-mentioned method items, and will not be repeated here.

[0056] In this embodiment of the invention, a structural model of the bearing to be processed is obtained, and a target finite element model of the bearing to be processed is constructed based on the structural model. This finite element model provides more reliable data support for subsequent gear shaping parameter analysis. Equipment status monitoring is performed on the gear shaping equipment. Based on the equipment status information and the relative positional relationship between the bearing to be processed and the gear shaping equipment, processing deviation prediction is performed, providing a clearer understanding of the equipment's status changes and improving the accuracy of processing deviation prediction. Based on the processing deviation prediction information and the target finite element model, the initial feed rate, initial stroke speed, and initial depth of cut data of the bearing to be processed at each gear shaping stage are analyzed, greatly reducing reliance on manual labor and improving the reliability and efficiency of gear shaping parameter analysis. Simulation of the bearing gear shaping process is performed based on the initial feed rate, initial stroke speed, and initial depth of cut data to optimize these data. Controlling the gear shaping equipment to process the bearing to be processed based on the optimized feed rate, optimized stroke speed, and optimized depth of cut data further improves the precision of the bearing gear shaping process and ensures high quality.

[0057] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0058] Furthermore, the above provides a detailed description of a bearing internal gear cutting method and system provided by the embodiments of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for machining gears inside a bearing, characterized in that, The method includes: Obtain the structural model of the bearing to be processed, and construct the target finite element model of the bearing to be processed based on the structural model; The gear hobbing equipment is subjected to equipment status detection to obtain equipment status information. Based on the equipment status information and the relative positional relationship between the bearing to be processed and the gear hobbing equipment, the processing deviation is predicted to obtain processing deviation prediction information. Based on the machining deviation prediction information and the target finite element model, the initial feed rate, initial stroke speed and initial cutting depth data of the bearing to be machined in each gear hobbing stage are analyzed. Simulation of bearing gear shaping is performed based on the initial feed rate data, initial stroke speed and initial depth of cut data. Simulation results are obtained, and the initial feed rate data, initial stroke speed and initial depth of cut data are optimized based on the simulation results to obtain optimized feed rate data, optimized stroke speed and optimized depth of cut data. Based on the optimized feed rate data, optimized stroke speed, and optimized cutting depth data, the gear shaping equipment is controlled to perform gear shaping on the bearing to be machined.

2. The bearing internal gear cutting method according to claim 1, characterized in that, The process of obtaining the structural model of the bearing to be processed and constructing a target finite element model of the bearing to be processed based on the structural model includes: Obtain the material physical parameters and point cloud data of the bearing to be processed, and construct a structural model of the bearing to be processed based on the point cloud data; Based on the local densification method and stress analysis, the material physical parameters are used to perform mesh generation and mesh refinement on the structural model to obtain an initial finite element model; Determine the mechanical boundary conditions and thermal boundary conditions, and adjust the initial finite element model based on the mechanical boundary conditions and thermal boundary conditions to obtain the target finite element model of the bearing to be processed.

3. The bearing internal gear cutting method according to claim 2, characterized in that, The construction of the structural model of the bearing to be processed based on the point cloud data includes: The point cloud data is subjected to noise reduction processing to obtain noise-reduced point cloud data; Dense sampling processing is performed on the noise-reduced point cloud data to obtain densely sampled point cloud data, and a spatial triangular mesh model is constructed based on the densely sampled point cloud data. Based on the aforementioned spatial triangular mesh model and combined with 3D reconstruction technology, a model of the bearing to be processed is constructed to obtain the structural model of the bearing to be processed.

4. The bearing internal gear cutting method according to claim 1, characterized in that, The process involves monitoring the equipment status of the gear hobbing equipment to obtain equipment status information, and then predicting machining deviations based on this equipment status information and the relative positional relationship between the bearing to be processed and the gear hobbing equipment. This process yields machining deviation prediction information, including: Historical status data of the gear hobbing equipment is acquired, and trend analysis is performed based on the historical status data to obtain trend data. Based on the historical state data, wear characteristic data for several time steps are constructed; Based on the historical state data, the accuracy retention capability data of the gear hobbing equipment is analyzed using a Bayesian algorithm. Based on the change trend data, wear characteristic data, and accuracy retention capability data, an attention network is used to detect the equipment status and obtain equipment status information. The first position information of the bearing to be processed and the second position information of the gear shaping equipment are obtained during the processing, and the relative positional relationship between the bearing to be processed and the gear shaping equipment is generated based on the first position information and the second position information. The operating data of the gear hobbing equipment is collected according to the preset process information. Based on the operating data, relative positional relationship and equipment status information, a prediction model is used to predict the processing deviation and obtain the processing deviation prediction information.

5. The bearing internal gear cutting method according to claim 4, characterized in that, The process of predicting processing deviations using a prediction model based on the operational data, relative positional relationships, and equipment status information to obtain processing deviation prediction information includes: Historical operating data of the gear hobbing equipment is obtained, and a geometric error function is fitted based on the historical state data and historical operating data to obtain the target geometric error function. A prediction model is then constructed based on the geometric error function. The operating data, relative positional relationships, and equipment status information are input into the prediction model to predict processing deviations and obtain processing deviation prediction information.

6. The bearing internal gear cutting method according to claim 1, characterized in that, The analysis of the initial feed rate, initial stroke speed, and initial depth of cut data of the bearing to be machined at each gear shaping stage based on the machining deviation prediction information and the target finite element model includes: Based on machining deviation prediction information and target finite element model analysis, several initial adjustment values ​​of preset process information are determined in each gear hobbing stage. Determine the processing energy consumption data corresponding to each initial adjustment amount, and analyze the power data corresponding to each initial adjustment amount; Instantaneous characteristic analysis of power changes is performed based on the energy consumption data of the processing process to obtain instantaneous characteristic data, and cumulative energy consumption analysis is performed based on the energy consumption data of the processing process to obtain cumulative energy consumption data. A quality constraint function is constructed, and a target adjustment amount is determined based on the instantaneous feature data, cumulative energy consumption data, and power data combined with the quality constraint function. Based on the target adjustment amount, the initial feed rate, initial stroke speed, and initial depth of cut data of the bearing to be processed are determined at each gear hobbing stage.

7. The bearing internal gear cutting method according to claim 6, characterized in that, The determination of the processing energy consumption data corresponding to each initial adjustment amount, and the analysis of the power data corresponding to each initial adjustment amount, includes: Match the processing auxiliary material consumption data and equipment energy consumption data corresponding to each initial adjustment amount, and determine the corresponding processing energy consumption data based on the processing auxiliary material consumption data and equipment energy consumption data; Based on the initial adjustment amount, load power analysis and no-load power analysis are performed to obtain load power data and no-load power data, and the corresponding power data is determined based on the load power data and no-load power data.

8. The bearing internal gear cutting method according to claim 1, characterized in that, The optimization of the initial feed rate data, initial stroke speed, and initial depth of cut data based on the simulation results to obtain optimized feed rate data, optimized stroke speed, and optimized depth of cut data includes: Feedback data is extracted based on the simulation results, and the initial feed rate, initial stroke speed, and initial depth of cut data are optimized based on the feedback data to obtain optimized feed rate, optimized stroke speed, and optimized depth of cut data.

9. The bearing internal gear cutting method according to claim 1, characterized in that, The gear shaping equipment, controlled based on the optimized feed rate data, optimized stroke speed data, and optimized depth of cut data, performs gear shaping on the bearing to be machined, including: Control commands are generated based on the optimized feed rate data, optimized stroke speed data, and optimized depth of cut data. Based on the control commands, the gear hobbing equipment is controlled to perform gear hobbing processing on the bearing to be processed at each stage, and the casting equipment is controlled to perform cooling oil casting on the bearing during the gear hobbing process.

10. A bearing internal gear shaping system, characterized in that, The system includes: Model building module: used to obtain the structural model of the bearing to be processed, and to build the target finite element model of the bearing to be processed based on the structural model; Deviation prediction module: used to detect the equipment status of the gear hobbing equipment, obtain equipment status information, and predict the processing deviation based on the equipment status information and the relative positional relationship between the bearing to be processed and the gear hobbing equipment, thereby obtaining processing deviation prediction information; Parameter analysis module: used to analyze the initial feed rate, initial stroke speed and initial depth of cut data of the bearing to be processed in each gear hobbing stage based on the machining deviation prediction information and the target finite element model; Parameter optimization module: used to perform simulation of bearing gear shaping based on the initial feed rate data, initial stroke speed and initial depth of cut data, obtain simulation results, and optimize the initial feed rate data, initial stroke speed and initial depth of cut data based on the simulation results to obtain optimized feed rate data, optimized stroke speed and optimized depth of cut data; Gear shaping module: Used to control the gear shaping equipment to perform gear shaping on the bearing to be processed based on the optimized feed rate data, optimized stroke speed and optimized cutting depth data.

Images