High-precision machining method and machining equipment for internal spline of planetary gear

Abstract

The invention relates to the technical field of internal spline machining, in particular to an internal spline high-precision machining method and device suitable for a planetary gear, and the method comprises the steps that periodicity measurement and a trend line function are obtained; obtaining a cutting force fluctuation coefficient and a cutting influence coefficient of each time of internal spline machining; and on the basis of the cutting influence coefficient, obtaining the particle weight of each particle in the particle swarm optimization algorithm and the updated inertia weight of each iteration, and performing high-precision machining on the internal spline of the planetary gear. The machining precision of the internal spline of the planetary gear is improved.

Description

Technical Field

[0001] The present application relates to the technical field of internal spline processing, and in particular to a high-precision processing method and processing equipment for internal splines suitable for planetary gears. Background Art

[0002] RV reducers are high-precision speed reduction devices widely used in industrial machinery. They offer advantages such as compact structure, high torque, and high transmission efficiency. They are widely used in machine tools, robotics, and automation equipment. Planetary gears are a key component in RV reducers, and their precision is crucial to ensuring their quality. The internal spline is a key component of planetary gears. Due to the high machining precision requirements and the complexity of machining, ensuring high-precision machining of the internal spline is a key concern in planetary gear machining. To ensure this accuracy, it is necessary to control variables, conduct repeated experiments, and repeatedly adjust the broaching parameters to ultimately determine the optimal parameters.

[0003] With the gradual introduction of computer technology into the machinery industry, existing technologies often use optimization algorithms to iteratively obtain the optimal solution in order to improve efficiency and reduce the number of experiments. However, when using optimization algorithms, the weights of different processing data are the same. This requires that the processing parameters of different particles be sufficiently uniform to ensure good global and local search capabilities. However, when actually processing internal splines, experimental conditions are often set based on experience, resulting in a high degree of similarity in the processing parameters of different particles. This similarity results in poor global search capabilities when iterating the optimal processing parameters using optimization algorithms, making it easy to fall into local optimality. The resulting optimal parameters are not accurate enough, which in turn affects the processing accuracy of the internal splines. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a high-precision processing method and processing equipment for the internal splines of planetary gears. The technical solutions adopted are as follows: In a first aspect, an embodiment of the present application provides a high-precision machining method for an internal spline of a planetary gear, the method comprising the following steps: Collect the vibration sequence, temperature sequence, tangential force sequence, radial force sequence, axial force sequence of the tool cutting during each planetary gear internal spline processing, and the cutting speed of the tool cutting at each collection moment; The tangential force sequence is segmented according to the change of cutting speed to obtain the cutting preparation sequence, cutting sequence and cutting completion sequence; Obtaining a periodicity measure of the cutting sequence based on the autocorrelation of the cutting sequence; Get trend line function based on cutting sequence; Based on the mutation of the cutting preparation sequence and the cutting completion sequence, the periodicity measurement of the cutting sequence, the slope of the trend line function, and the average of the elements in the tangential force sequence, radial force sequence, and axial force sequence, the cutting force fluctuation coefficient of each internal spline machining is obtained; The cutting influence coefficient of each internal spline machining is obtained based on the cutting force fluctuation coefficient, the discrete degree of the vibration sequence and the temperature sequence, the correlation between the tangential force sequence and the vibration sequence, and the difference between adjacent elements in the tangential force sequence and the temperature sequence. Obtain the particle weight of each particle in the particle swarm optimization algorithm based on the cutting influence coefficient; The updated inertia weight of each iteration in the particle swarm optimization algorithm is obtained based on the particle weight, and the internal splines of the planetary gear are processed with high precision.

[0005] Furthermore, the method for obtaining the cutting preparation sequence, cutting sequence and cutting completion sequence is: For the cutting speed at each acquisition moment, the time period from the moment the internal spline starts to be machined to the acquisition moment when the cutting speed first reaches the preset normal cutting speed is taken as the cutting start time period; the time period from the acquisition moment when the cutting speed first reaches the preset normal cutting speed to the acquisition moment when the cutting speed last reaches the preset normal cutting speed is taken as the cutting stabilization time period; the time period from the acquisition moment when the cutting speed last reaches the preset normal cutting speed to the moment when the internal spline stops machining is taken as the cutting end time period; For the tangential force sequence, the tangential force sequence in the cutting start time period is regarded as the cutting preparation sequence, the tangential force sequence in the cutting stable time period is regarded as the cutting sequence, and the tangential force sequence in the cutting end time period is regarded as the cutting completion sequence.

[0006] Furthermore, the method for obtaining the periodic metric is: Using the autocorrelation function to obtain the respective correlation coefficients and lags of the autocorrelation coefficients of the cutting sequences, constructing an autocorrelation function graph with the autocorrelation coefficient as the ordinate and the lags of the autocorrelation coefficient as the abscissa, using a peak detection algorithm to obtain peaks in the autocorrelation function graph, and taking peaks greater than a preset correlation threshold as significant peaks; The order of each significant peak in all peaks of the autocorrelation function diagram is used as the abscissa, and the hysteresis of the significant peak is used as the ordinate to perform straight line fitting to obtain the hysteresis fitting line; The goodness of fit of the hysteresis fitting line multiplied by the mean of all significant peaks in the autocorrelation function graph was used as a measure of the periodicity of the cutting sequence.

[0007] Furthermore, obtaining a trend line function according to the cutting sequence includes: The cutting sequence is used as the input of the time series decomposition algorithm to output the trend sequence; the trend line function of the trend sequence is obtained using the straight line fitting algorithm.

[0008] Furthermore, the method for obtaining the cutting force fluctuation coefficient is: Obtain a first-order difference sequence of the cutting preparation sequence, then use the mean of all elements in the first-order difference sequence of the cutting preparation sequence as a first mutation threshold, and use elements in the first-order difference sequence that are greater than the first mutation threshold as mutation points of the first-order difference sequence of the cutting preparation sequence; obtain a first-order difference sequence of the cutting completion sequence, then use the mean of all elements in the first-order difference sequence of the cutting completion sequence as a second mutation threshold, and use elements in the first-order difference sequence of the cutting completion sequence that are less than the second mutation threshold as mutation points of the first-order difference sequence of the cutting completion sequence; The ratio of the number of mutation points in the first-order difference sequence of the cutting preparation sequence to the number of all elements in the first-order difference sequence of the cutting preparation sequence is calculated as the first mutation ratio; the first-order difference sequence of the cutting completion sequence is processed using the same method as that used to obtain the first mutation ratio, to obtain the second mutation ratio; The calculation formula of the cutting force fluctuation coefficient is: Where, is the cutting force fluctuation coefficient of each internal spline processing, 、 They are the first mutation threshold and the second mutation threshold, is the sum of the first mutation ratio and the second mutation ratio, is a measure of the periodicity of the cutting sequence, is the slope of the trendline function, is the mean of all elements in the tangential force series and radial force series, is the mean of all elements in the axial force series.

[0009] Furthermore, the calculation formula of the cutting influence coefficient is: Where, is the cutting influence coefficient of each internal spline processing; is the cutting force fluctuation coefficient of internal spline machining, 、 are the variances of all elements in the vibration sequence and the variances of all elements in the temperature sequence, is the Pearson correlation coefficient between the tangential force series and the vibration series, is the mean of the absolute values ​​of the differences between all adjacent elements in the tangential force sequence, is the mean of the absolute values ​​of the differences between all adjacent elements in the temperature series.

[0010] Furthermore, the particle weight is obtained as follows: Each internal spline machining process is regarded as each particle in the particle swarm optimization algorithm, and the particle weight of each particle is calculated as follows: Where, It is The particle weight of each particle, 、 It is Second internal spline processing process, Cutting influence coefficient of secondary internal spline machining process, is the total number of internal spline machining times.

[0011] Furthermore, the method for obtaining the updated inertia weight is: The particle swarm optimization algorithm is used to iterate all particles in combination with the particle weight of each particle. For each iteration process, the sum of the particle weights of all particles within the preset neighborhood radius of the optimal solution particle during the iteration process and the preset initial inertia weight are calculated as the updated inertia weight of each iteration process.

[0012] Furthermore, the high-precision processing of the internal splines of the planetary gear includes: According to the updated inertia weight of each iteration process, the particle swarm optimization algorithm is used to iterate all particles to obtain the optimal solution particle. The preset machining parameters of the tool for the internal spline machining process corresponding to the optimal solution particle are used as the optimal machining parameters, and the internal spline of the planetary gear is machined with high precision using the optimal machining parameters.

[0013] In the second aspect, an embodiment of the present application also provides a high-precision processing device for internal splines of planetary gears, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0014] This application has at least the following beneficial effects: The present application calculates the cutting force fluctuation coefficient according to the changing trend and characteristics of the cutting force during the internal spline machining process, which helps to identify the advantages and disadvantages of the machining parameters and quantifies the stability and reliability of the machining process; then, the vibration and temperature fluctuations during the machining process are combined to calculate the cutting influence coefficient, which more comprehensively evaluates the advantages and disadvantages of the machining parameters, helps to identify the influence of the vibration and temperature changes caused by the cutting force on the machining accuracy, and quantifies the influence of the machining parameters on the machining quality; finally, the particle weights are calculated using the cutting influence coefficients, and the optimization iteration is performed to obtain the optimal machining parameters. In this way, according to the influence of the machining parameters on the cutting force, stability and temperature during the internal spline machining process, the advantages and disadvantages of the machining parameters are quantified by the fluctuation of the data during the machining process, and then each particle is weighted according to the quantified results, thereby improving the sensitivity of particle difference identification, and then making it possible to adaptively construct the corresponding inertia weights according to the differences between the particles when performing the subsequent optimization algorithm, thereby improving the globality of the optimization algorithm, reducing the probability of falling into the local optimum, ensuring the accuracy of the optimal solution, helping to obtain the optimal machining parameters, and thus improving the machining accuracy of the internal spline machining of the planetary gear. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 A flowchart of a method for high-precision machining of internal splines of planetary gears according to an embodiment of the present application; Figure 2 A flowchart for obtaining particle weights is provided for one embodiment of the present application. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effectiveness of this application's implementation of the intended invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the high-precision machining method and apparatus for internal splines of planetary gears, including their specific implementation, structure, features, and effectiveness. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0019] The specific scheme of the high-precision machining method and machining equipment for the internal splines of planetary gears provided in this application is described in detail below with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flowchart of a high-precision machining method for an internal spline of a planetary gear provided by an embodiment of the present application, the method comprising the following steps: Step S1 , collecting the vibration sequence, temperature sequence, tangential force sequence, radial force sequence, axial force sequence and cutting speed of the tool at each collection moment during each planetary gear internal spline machining process.

[0021] During each planetary gear internal spline machining process, the tool's preset machining parameters are set and the internal splines are machined. An accelerometer mounted on the tool shank collects vibration data during cutting. A temperature sensor on the tool monitors temperature changes during cutting. A triaxial force sensor on the tool shank monitors cutting forces in the tangential, radial, and axial directions. All data is collected at a frequency of 1kHz, and the cutting speed at each point in the process is measured.

[0022] According to the above analysis, for each type of data collected during the internal spline machining process of each planetary gear, the data at all collection moments are respectively constructed into corresponding data sequences in chronological order, namely vibration sequence, temperature sequence, tangential force sequence, radial force sequence and axial force sequence.

[0023] Step S2, segmenting the tangential force sequence according to the change of cutting speed to obtain the cutting preparation sequence, cutting sequence and cutting completion sequence; obtaining the periodicity measurement of the cutting sequence based on the autocorrelation of the cutting sequence; obtaining the trend line function according to the cutting sequence; obtaining the cutting force fluctuation coefficient of each internal spline processing based on the mutation of the cutting preparation sequence and the cutting completion sequence, the periodicity measurement of the cutting sequence, the slope of the trend line function and the average of the elements in the tangential force sequence, the radial force sequence and the axial force sequence.

[0024] In the broaching process of internal splines, tools are needed to cut and grind the workpiece. The cutting speed, feed rate and number of teeth of the tool will affect the processing quality of the internal splines. Therefore, how to choose the optimal cutting speed, feed rate and number of teeth becomes the key to high-precision processing of internal splines.

[0025] In order to improve production efficiency, optimization algorithms (such as particle swarm optimization) are often used to iteratively obtain the optimal processing parameters. However, since the approximate range of processing parameters is often determined based on experience during internal spline broaching, the processing parameters between particles in the particle swarm optimization algorithm are relatively close. In traditional particle swarm optimization algorithms, the weights of particles are the same, which makes particles have a greater influence on the acquisition of the optimal solution. At the same time, they are prone to falling into local optimality and have weak global search capabilities, which in turn affects the accuracy of the optimal solution.

[0026] Since the cutting speed, feed rate and number of teeth will affect the changes in vibration data, temperature data and cutting force during the internal spline processing, and it is precisely because of the changes in these data that the processing process and the tool are affected, and ultimately the accuracy of the internal spline processing is affected, the pros and cons of the corresponding processing parameters can be determined by monitoring the changes in these data.

[0027] During the internal spline machining process, under normal circumstances, there are cutting forces in three directions: tangential, radial, and axial. The tangential force is the force along the cutting direction, and the radial force is the force perpendicular to the cutting direction. These two directions of force are the main cutting forces that ensure the cutting efficiency of the tool. The axial force is the force along the axial direction of the workpiece. Its main function is to maintain the stability of the workpiece in the axial direction and reduce vibration and deformation. The order of the forces in the three directions is tangential force is the largest, radial force is the second largest, and axial force is the smallest. Therefore, in order to ensure the machining efficiency of the internal spline, it is necessary to control the tangential and radial forces so that they are not too small. In order to ensure the stability of the workpiece, a smaller axial force is required. Therefore, the better the machining parameters during the internal spline machining process, the more accurate the machining accuracy of the internal spline can be guaranteed, and the greater the difference between the tangential force, radial force, and axial force.

[0028] Secondly, during internal spline processing, as the teeth of the tool enter the workpiece in sequence, friction is generated with the workpiece, resulting in a gradual increase in the broaching load and a corresponding increase in the cutting force. Therefore, when the tool starts to work, the cutting force shows a step-by-step increasing trend; as the tool penetrates the workpiece, the number of working teeth of the tool reaches a maximum, and the tool begins to gradually speed up to the preset normal cutting speed. The tool enters a stable working state at the normal cutting speed, and the cutting force shows a periodic fluctuation trend with the cycle of the teeth on the tool. In addition, since the friction is large at the beginning of rough processing, the broaching load is large and the cutting force is also large. As the processing progresses, it gradually enters the finishing stage, whereby the friction decreases, resulting in a gradual decrease in the cutting force. That is, when the tool is in the stable working state at the normal cutting speed, the cutting force shows a periodic change and an overall decreasing trend. Finally, at the end of cutting, the cutting speed gradually decreases, and the tool teeth exit the workpiece in sequence, so that the cutting force shows a step-by-step decreasing trend.

[0029] Furthermore, for the cutting speed at each collected moment, the period from the moment the internal spline machining begins to the moment the cutting speed first reaches the preset normal cutting speed is defined as the cutting start period; the period from the moment the cutting speed first reaches the preset normal cutting speed to the moment the cutting speed last reaches the preset normal cutting speed is defined as the cutting stabilization period; and the period from the moment the cutting speed last reaches the preset normal cutting speed to the moment the internal spline machining stops is defined as the cutting end period. In this embodiment, the preset normal cutting speed is 45 m / min; implementers may select other values ​​based on actual circumstances.

[0030] For the tangential force sequence, the tangential force sequence in the cutting start time period is regarded as the cutting preparation sequence, the tangential force sequence in the cutting stable time period is regarded as the cutting sequence, and the tangential force sequence in the cutting end time period is regarded as the cutting completion sequence.

[0031] The cutting sequence is taken as input, STL decomposition is used to output the trend sequence, and then linear fitting is used to obtain the fitting straight line function of the trend sequence, which is called the trend line function.

[0032] Furthermore, the cutting sequence is used as the input of the autocorrelation function, and the respective correlation coefficients of the cutting sequences are output. Each autocorrelation coefficient corresponds to a different lag, and the difference between adjacent lags is 1. In this embodiment, the lag range is [1,500], and the implementer can select other values ​​according to actual conditions.

[0033] An autocorrelation function graph is constructed based on all autocorrelation coefficients of the cutting sequence and the lag of the autocorrelation coefficient. The horizontal axis of the autocorrelation function graph represents the lag and the vertical axis represents the autocorrelation coefficient. A peak detection algorithm is used to obtain peaks in the autocorrelation function graph, and peaks greater than a preset correlation threshold are considered significant peaks. In this embodiment, the preset correlation threshold is 0.7; implementers may select other values ​​based on actual conditions.

[0034] Furthermore, a linear fit is performed using the position order of each significant peak in the autocorrelation function graph among all peaks as the abscissa and the hysteresis of the significant peak as the ordinate to obtain a hysteresis fitting line. STL decomposition, autocorrelation function, and linear fitting are well-known techniques, and the specific process is not repeated here.

[0035] Furthermore, the first-order difference sequence of the cutting preparation sequence is obtained, and then the mean of all elements in the first-order difference sequence of the cutting preparation sequence is used as the first mutation threshold, and the elements in the first-order difference sequence that are greater than the first mutation threshold are used as the mutation points of the first-order difference sequence of the cutting preparation sequence; similarly, the first-order difference sequence of the cutting completion sequence is obtained, and the mean of all elements in the first-order difference sequence of the cutting completion sequence is used as the second mutation threshold, and the elements in the first-order difference sequence of the cutting completion sequence that are less than the second mutation threshold are used as the mutation points of the first-order difference sequence of the cutting completion sequence.

[0036] The first mutation ratio is calculated as the ratio of the number of mutation points in the first-order difference sequence of the cutting preparation sequence to the number of all elements in the first-order difference sequence of the cutting preparation sequence. The first-order difference sequence of the cutting completion sequence is processed using the same method as the first-order difference sequence of the cutting preparation sequence to obtain the second mutation ratio. Furthermore, the goodness of fit of the lag fitting line is multiplied by the mean of all significant peaks in the autocorrelation function graph as a measure of the periodicity of the cutting sequence.

[0037] Based on the above analysis, in order to measure the temporal variation trend of the cutting force during the internal spline machining process, the cutting force fluctuation coefficient is calculated. The calculation formula is: Where, is the cutting force fluctuation coefficient of each internal spline processing, 、 They are the first mutation threshold and the second mutation threshold, is the sum of the first mutation ratio and the second mutation ratio, is a measure of the periodicity of the cutting sequence, is the slope of the trendline function, is the mean of all elements in the tangential force series and radial force series, is the mean of all elements in the axial force series.

[0038] It should be noted that when the cutting parameters are optimal during internal spline machining, the tangential and radial cutting forces are greater than the axial cutting force, and the greater the difference, the better. The greater the tangential and radial cutting forces, although it can ensure higher machining efficiency, it will also lead to increased vibration, thereby affecting the accuracy of the internal spline. Therefore, the tangential and radial cutting forces cannot be too large, that is, Secondly, in the cutting preparation and cutting completion stages, the corresponding cutting forces change in a step-by-step manner, so there are fewer mutation points in the corresponding first-order difference sequence, and the mutation threshold in the cutting preparation stage is smaller, while the mutation threshold in the cutting completion stage is larger, that is, 、 Smaller, Large; the cutting force in the cutting stage shows periodic changes, and the overall trend is decreasing, thus Large, and the value of periodic measurement is large; so when the cutting parameters are better during internal spline machining, the cutting force fluctuation coefficient On the contrary, when the cutting parameters are worse, the change of cutting force in the process of machining will be more serious, which will make the possibility and degree of deviation from the normal state greater, thus the cutting force fluctuation coefficient Larger.

[0039] Step S3, based on the cutting force fluctuation coefficient, the discrete degree of the vibration sequence and the temperature sequence, the correlation between the tangential force sequence and the vibration sequence, and the difference between adjacent elements in the tangential force sequence and the temperature sequence, obtain the cutting influence coefficient of each internal spline processing; based on the cutting influence coefficient, obtain the particle weight of each particle in the particle swarm optimization algorithm.

[0040] The cutting force fluctuation coefficient only measures the change of cutting force, and the effect of cutting force on the machining accuracy of internal splines is relatively small. It is mainly the vibration and temperature changes caused by cutting force during the machining process that ultimately affect the machining accuracy of the internal splines or cause deformation. Therefore, only considering the change of cutting force has certain limitations. Only when the cutting force causes vibration and temperature changes can the impact of cutting force on machining accuracy be accurately judged.

[0041] Under normal circumstances, when the internal spline machining parameters are optimal, as the cutting force changes, the vibration and temperature also change accordingly, and the change frequencies are relatively close. At the same time, the fluctuations in vibration and temperature are small, resulting in a higher final internal spline precision. However, when the internal spline machining parameters are poor, as the cutting force changes, the instantaneous changes in vibration and temperature are more drastic, resulting in a significant difference in the change frequencies. At the same time, the fluctuations in vibration and temperature are large, resulting in a lower final internal spline precision.

[0042] Based on the above analysis, in order to improve the accuracy of data change feature measurement during internal spline machining, the cutting influence coefficient is calculated using the following formula: Where, is the cutting influence coefficient of each internal spline processing; is the cutting force fluctuation coefficient of internal spline machining, 、 are the variances of all elements in the vibration sequence and the variances of all elements in the temperature sequence, is the Pearson correlation coefficient between the tangential force series and the vibration series, is the mean of the absolute values ​​of the differences between all adjacent elements in the tangential force sequence, is the mean of the absolute values ​​of the differences between all adjacent elements in the temperature series.

[0043] It should be noted that when the internal spline machining parameters are optimal, the cutting force fluctuation coefficient is small, and the change of cutting force causes the change of vibration and temperature, and the change frequencies are relatively close, so there is a high correlation between the tangential force sequence and the vibration sequence, that is, Secondly, the change of cutting force will cause the fluctuation of instantaneous temperature. When the processing parameters are better, the changes of the two are closer and the difference between the change rates is relatively small, that is, Small; vibration and temperature fluctuations are small, that is 、 Small; so when the internal spline processing parameters are better, the cutting influence coefficient On the contrary, when the internal spline processing parameters are poor, it will cause drastic changes in vibration and temperature, which will increase the difference between the changes in cutting force and the cutting influence coefficient. Larger.

[0044] When using the original particle swarm optimization algorithm to iterate internal spline machining parameters, each particle has the same weight, resulting in a high risk of the final optimal solution falling into a local optimum. To avoid this problem, based on the characteristics of the internal spline machining process, by analyzing the changes in various monitoring data during the internal spline machining process, the cutting influence coefficient is calculated to measure the quality of the corresponding internal spline machining parameters. This weight is then assigned to each particle, enhancing the global search capability of the optimization algorithm and improving the accuracy of the optimal machining parameters.

[0045] According to the above analysis, each internal spline machining process is regarded as a particle. Furthermore, in order to reflect the machining parameters of the tool in each internal spline machining process, the particle weight of each particle is obtained based on the cutting influence coefficient. The calculation formula is: Where, It is The particle weight of each particle, 、 It is Second internal spline processing process, Cutting influence coefficient of secondary internal spline machining process, Is the total number of internal spline processing. In this embodiment, the value of n is 100, and the implementer can select other values ​​according to actual conditions. Among them, the particle weight acquisition flow chart is as follows Figure 2 shown.

[0046] It should be noted that for the i-th internal spline machining process, when the tool machining parameters are poor, Larger, so that the particle weight When the particle swarm optimization is performed later, the weight is used to construct a larger inertia weight, which helps to enhance the global search capability and avoid falling into the local optimum, thereby improving the accuracy of the optimal solution. On the contrary, when the processing parameters of the tool are good, the particle weight The smaller the θ, the smaller the inertia weight of subsequent constructions, which helps to increase the iteration speed while maintaining a good iteration effect.

[0047] Step S4: obtaining the updated inertia weight of each iteration in the particle swarm optimization algorithm based on the particle weight, and performing high-precision processing on the internal spline of the planetary gear.

[0048] The set of parameter settings for each internal spline machining is considered as a particle. (In this embodiment ), particle dimensions (In this embodiment , respectively cutting speed, feed rate, number of teeth), the maximum number of iterations of the system (In this embodiment ), preset initial inertia weight , learning factor , preset neighborhood radius (In this embodiment ) as input, the particle swarm optimization algorithm is used to output the optimal solution. In this process, each time an iteration is completed, the inertia weight needs to be updated according to the optimal solution obtained by the iteration. Specifically, when the After the iteration is completed, according to the position of the current optimal solution, Particles within the neighborhood radius are then updated with inertia weights. Based on the above analysis, the calculation formula for updating inertia weights is: Where, It is After the iteration is completed, the inertia weight is updated. is the preset initial inertia weight, It is The sum of the particle weights of all particles within the preset neighborhood radius of the optimal solution particle at the iteration.

[0049] When The optimal solution of the iteration If the processing parameters of particles within the neighborhood radius are poor, Larger, thus increasing the inertia weight , which helps to jump out of the current local area, enhance the global search capability, and enhance the ability to obtain the global optimal solution in subsequent iterations. Conversely, if the processing parameters of the particles around the current optimal solution are good, reduce the inertia weight to improve the search efficiency.

[0050] After the optimal solution is finally iterated, the processing parameters are set according to the optimal solution to achieve high-precision machining of the internal spline. In this way, each particle is assigned a weight based on the data changes during the internal spline machining process, which is then used to adjust the inertia weight, allowing the optimization algorithm to maintain good global search capabilities and high search efficiency. At the same time, even if the processing parameters of the particles vary relatively little, this method enhances the sensitivity of identifying small differences, thereby improving the accuracy of obtaining the optimal processing parameters.

[0051] Based on the same inventive concept as the above method, an embodiment of the present application also provides a high-precision processing device for internal splines of planetary gears, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned high-precision processing methods for internal splines of planetary gears.

[0052] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0053] The various embodiments in this application are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0054] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A high-precision machining method for the internal splines of planetary gears, characterized in that: The method comprises the following steps: Collect the vibration sequence, temperature sequence, tangential force sequence, radial force sequence, axial force sequence of the tool cutting during each planetary gear internal spline processing, and the cutting speed of the tool cutting at each collection moment; The tangential force sequence is segmented according to the change of cutting speed to obtain the cutting preparation sequence, cutting sequence and cutting completion sequence; Obtaining a periodicity measure of the cutting sequence based on the autocorrelation of the cutting sequence; Get trend line function based on cutting sequence; Based on the mutation of the cutting preparation sequence and the cutting completion sequence, the periodicity measurement of the cutting sequence, the slope of the trend line function, and the average of the elements in the tangential force sequence, radial force sequence, and axial force sequence, the cutting force fluctuation coefficient of each internal spline machining is obtained; The cutting influence coefficient of each internal spline machining is obtained based on the cutting force fluctuation coefficient, the discrete degree of the vibration sequence and the temperature sequence, the correlation between the tangential force sequence and the vibration sequence, and the difference between adjacent elements in the tangential force sequence and the temperature sequence. Obtain the particle weight of each particle in the particle swarm optimization algorithm based on the cutting influence coefficient; The updated inertia weight of each iteration in the particle swarm optimization algorithm is obtained based on the particle weight, and the internal splines of the planetary gear are processed with high precision.

2. The high-precision machining method for internal splines of planetary gears according to claim 1, characterized in that: The method for obtaining the cutting preparation sequence, cutting sequence and cutting completion sequence is as follows: For the cutting speed at each acquisition moment, the time period from the moment the internal spline starts to be machined to the acquisition moment when the cutting speed first reaches the preset normal cutting speed is taken as the cutting start time period; the time period from the acquisition moment when the cutting speed first reaches the preset normal cutting speed to the acquisition moment when the cutting speed last reaches the preset normal cutting speed is taken as the cutting stabilization time period; the time period from the acquisition moment when the cutting speed last reaches the preset normal cutting speed to the moment when the internal spline stops machining is taken as the cutting end time period; For the tangential force sequence, the tangential force sequence in the cutting start time period is regarded as the cutting preparation sequence, the tangential force sequence in the cutting stable time period is regarded as the cutting sequence, and the tangential force sequence in the cutting end time period is regarded as the cutting completion sequence.

3. The high-precision machining method for internal splines of planetary gears according to claim 1, characterized in that: The method for obtaining the periodic metric is: Using the autocorrelation function to obtain the respective correlation coefficients and lags of the autocorrelation coefficients of the cutting sequences, constructing an autocorrelation function graph with the autocorrelation coefficient as the ordinate and the lags of the autocorrelation coefficient as the abscissa, using a peak detection algorithm to obtain peaks in the autocorrelation function graph, and taking peaks greater than a preset correlation threshold as significant peaks; The order of each significant peak in all peaks of the autocorrelation function diagram is used as the abscissa, and the hysteresis of the significant peak is used as the ordinate to perform straight line fitting to obtain the hysteresis fitting line; The goodness of fit of the hysteresis fitting line multiplied by the mean of all significant peaks in the autocorrelation function graph was used as a measure of the periodicity of the cutting sequence.

4. The high-precision machining method for internal splines of planetary gears according to claim 1, characterized in that: The step of obtaining a trend line function according to a cutting sequence includes: The cutting sequence is used as the input of the time series decomposition algorithm to output the trend sequence; the trend line function of the trend sequence is obtained using the straight line fitting algorithm.

5. The high-precision machining method for internal splines of planetary gears according to claim 1, characterized in that: The method for obtaining the cutting force fluctuation coefficient is: Obtain a first-order difference sequence of the cutting preparation sequence, then use the mean of all elements in the first-order difference sequence of the cutting preparation sequence as a first mutation threshold, and use elements in the first-order difference sequence that are greater than the first mutation threshold as mutation points of the first-order difference sequence of the cutting preparation sequence; obtain a first-order difference sequence of the cutting completion sequence, then use the mean of all elements in the first-order difference sequence of the cutting completion sequence as a second mutation threshold, and use elements in the first-order difference sequence of the cutting completion sequence that are less than the second mutation threshold as mutation points of the first-order difference sequence of the cutting completion sequence; The ratio of the number of mutation points in the first-order difference sequence of the cutting preparation sequence to the number of all elements in the first-order difference sequence of the cutting preparation sequence is calculated as the first mutation ratio; the first-order difference sequence of the cutting completion sequence is processed using the same method as that used to obtain the first mutation ratio, to obtain the second mutation ratio; The calculation formula of the cutting force fluctuation coefficient is: Where, is the cutting force fluctuation coefficient of each internal spline processing, 、 They are the first mutation threshold and the second mutation threshold, is the sum of the first mutation ratio and the second mutation ratio, is a measure of the periodicity of the cutting sequence, is the slope of the trendline function, is the mean of all elements in the tangential force series and radial force series, is the mean of all elements in the axial force series.

6. The high-precision machining method for internal splines of planetary gears according to claim 1, characterized in that: The calculation formula of the cutting influence coefficient is: Where, is the cutting influence coefficient of each internal spline processing; is the cutting force fluctuation coefficient of internal spline machining, 、 are the variances of all elements in the vibration sequence and the variances of all elements in the temperature sequence, is the Pearson correlation coefficient between the tangential force series and the vibration series, is the mean of the absolute values ​​of the differences between all adjacent elements in the tangential force sequence, is the mean of the absolute values ​​of the differences between all adjacent elements in the temperature series.

7. The high-precision machining method for internal splines of planetary gears according to claim 1, characterized in that: The method for obtaining the particle weight is: Each internal spline machining process is regarded as each particle in the particle swarm optimization algorithm, and the particle weight of each particle is calculated as follows: Where, It is The particle weight of each particle, 、 It is Second internal spline processing process, Cutting influence coefficient of secondary internal spline machining process, is the total number of internal spline machining times.

8. The high-precision machining method for internal splines of planetary gears according to claim 7, characterized in that: The method for obtaining the updated inertia weight is: The particle swarm optimization algorithm is used to iterate all particles in combination with the particle weight of each particle. For each iteration process, the sum of the particle weights of all particles within the preset neighborhood radius of the optimal solution particle during the iteration process and the preset initial inertia weight are calculated as the updated inertia weight of each iteration process.

9. The high-precision machining method for internal splines of planetary gears according to claim 8, characterized in that: The high-precision processing of the internal splines of the planetary gear includes: According to the updated inertia weight of each iteration process, the particle swarm optimization algorithm is used to iterate all particles to obtain the optimal solution particle. The preset machining parameters of the tool for the internal spline machining process corresponding to the optimal solution particle are used as the optimal machining parameters, and the internal spline of the planetary gear is machined with high precision using the optimal machining parameters.

10. A high-precision machining device for internal splines of planetary gears, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the high-precision machining method for internal splines of planetary gears according to any one of claims 1 to 9 are implemented.

Images