A machine tool automation control optimization method based on sensor monitoring data

Abstract

The present invention relates to the field of automation control, and in particular to a machine tool automation control optimization method based on sensor monitoring data, the method comprising: obtaining a first distance optimization factor according to data feature information in a data window; optimizing the distance measurement between windows according to the first distance optimization factor to obtain a first optimized distance; performing secondary division on the window, and obtaining a local autocorrelation function of a time series data window according to all secondary divided windows; obtaining a second distance optimization factor according to the local autocorrelation function; optimizing the first optimized distance between time series data windows according to the second distance optimization factor to obtain a second optimized distance; performing distance measurement according to the second optimized distance to complete a clustering process to obtain a clustering result, optimizing a tool cutting force control parameter according to the clustering result, and performing tool cutting force control according to the optimized control parameter, thereby eliminating the influence of micro-vibration on tool cutting force control.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to a machine tool automatic control optimization method based on sensor data. Background Art

[0002] Precision control of automated machine tools is crucial to modern industrial manufacturing, and real-time monitoring of tool cutting forces is a key component. Changes in tool cutting forces directly reflect the interaction between the tool and the workpiece during machining. Monitoring data not only provides an important basis for optimizing machine tool control strategies but also enables diagnosis of tool wear and machining quality. To improve control system stability and responsiveness, PID control strategies are often employed to dynamically regulate cutting forces.

[0003] However, noise in the sensor data due to tool vibration can lead to misjudgment of key features such as cutting force fluctuations and acceleration changes, thus affecting the effectiveness of the PID control method. Therefore, effectively analyzing and processing the vibration in the cutting force sensor data has become an urgent problem to be solved. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a machine tool automation control optimization method based on sensor data to solve the problem of poor PID control effect caused by noise caused by tool micro-vibration in sensor monitoring data.

[0005] An embodiment of the present invention provides a method for optimizing machine tool automation control based on sensor data. The method comprises the following steps:

[0006] Data is collected from the tool cutting force sensor of the machine tool automation to obtain tool cutting force monitoring time series data; the tool cutting force monitoring time series data is divided into a first data window to obtain the first time series data window of all tool cutting force monitoring time series data; a first distance optimization factor is obtained by performing feature analysis on the first time series data window; the distance between the first time series data windows is optimized by the first distance optimization factor to obtain the first optimized distance between the first time series data windows; the first time series data window of the tool cutting force monitoring time series data is divided into a second data window to obtain the second time series data window of all tool cutting force monitoring time series data; the first time series data window is fitted and analyzed to obtain the first local autocorrelation function of a time series data window; obtaining a second distance optimization factor between first time series data windows through distribution distance analysis between the local autocorrelation functions; optimizing the first optimized distance between the first time series data windows of the tool cutting force monitoring time series data through the second distance optimization factor to obtain a second optimized distance; performing cluster analysis on the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data to obtain a clustering result of the first time series data window of the tool cutting force monitoring time series data; optimizing the tool cutting force control parameters through the clustering results to obtain the optimized tool cutting force control parameters, and performing automated machine tool tool cutting force control through the optimized tool cutting force control parameters.

[0007] The data collection of the tool cutting force sensor of the machine tool automation is performed to obtain the tool cutting force monitoring time series data, and the tool cutting force monitoring time series data is divided into a first data window to obtain the first time series data window of all the tool cutting force monitoring time series data, including:

[0008] Set the sampling frequency of the tool cutting force sensor and collect data on the tool cutting force values ​​in the automated machine tool according to the set sampling frequency to obtain tool cutting force monitoring time series data; set the tool cutting force monitoring time series data window length, and divide the tool cutting force monitoring time series data into windows according to the tool cutting force monitoring time series data window length to obtain the first time series data window of all tool cutting force monitoring time series data.

[0009] Preferably, the obtaining of the first distance optimization factor by performing feature analysis on the first time series data window includes:

[0010] Obtain the first time series data window of all tool cutting force monitoring time series data, and obtain the mean of the numerical means of all first time series data windows, the mean of the numerical standard deviations of all first time series data windows, the mean of the numerical skewness of all first time series data windows and the mean of the numerical kurtosis of all time series data windows according to all first time series data windows in the tool cutting force monitoring time series data; and add the mean of the numerical means of all first time series data windows, the mean of the numerical standard deviations of all first time series data windows, the mean of the numerical skewness of all first time series data windows and the mean of the numerical kurtosis of all time series data windows. The overall mean vector of all the time series data windows is formed according to the mean of the numerical kurtosis in the window; the Mahalanobis distance between the first time series data window of the tool cutting force monitoring time series data and the overall mean vector of all the first time series data windows is obtained according to the overall mean vector of all the first time series data windows; the constant 1 and the reciprocal of the sum of the Mahalanobis distances between the first time series data window of the tool cutting force monitoring time series data and the overall mean vector of all the first time series data windows are used as the first distance optimization factor of the first time series data window of the tool cutting force monitoring time series data.

[0011] Preferably, optimizing the distance between the first time series data windows by using the first distance optimization factor to obtain the first optimized distance between the first time series data windows includes:

[0012] Obtain the first time series data windows of any two of the tool cutting force monitoring time series data, multiply the first distance optimization factors of each of the any two first time series data windows as the optimization weight of the distance measurement between the any two first time series data windows; and use the calculation result of multiplying the optimization weight of the distance measurement between any two first time series data windows by the Euclidean distance between any two first time series data windows as the first optimized distance between the first time series data windows.

[0013] Preferably, the second data window division is performed on the first time series data window of the tool cutting force monitoring time series data to obtain a second time series data window of all tool cutting force monitoring time series data, and fitting analysis is performed on the second time series data window to obtain the local autocorrelation function of the first time series data window, including:

[0014] Obtain a set second data window length, divide the first time series data window of the tool cutting force monitoring time series data into two parts according to the second data window length, and obtain the second time series data window in the first time series data window of all the tool cutting force monitoring time series data; obtain a set autocorrelation lag parameter, and evaluate the local autocorrelation function corresponding to the first time series data window of the tool cutting force monitoring time series data for all the second time series data windows according to the set autocorrelation lag parameter to obtain the local autocorrelation function of the first time series data window.

[0015] Preferably, the obtaining of the second distance optimization factor between the first time series data windows by analyzing the distribution distance between the local autocorrelation functions includes:

[0016] Obtain the first time series data windows of any two of the tool cutting force monitoring time series data, obtain the distribution distance between the local autocorrelation functions corresponding to each of the any two first time series data windows, and use the constant 1 and the inverse of the sum of the distribution distances between the local autocorrelation functions corresponding to each of the any two first time series data windows as the second distance optimization factor between the first time series data windows.

[0017] Preferably, optimizing the first optimized distance between the first time series data windows of the tool cutting force monitoring time series data by using the second distance optimization factor to obtain the second optimized distance includes:

[0018] Obtain the first optimized distance between the first time series data windows and the second distance optimization factor between the first time series data windows, and use the result of multiplying the second distance optimization factor between the first time series data windows by the first optimized distance between the first time series data windows as the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data.

[0019] Preferably, performing cluster analysis based on the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data to obtain a clustering result of the first time series data windows of the tool cutting force monitoring time series data includes:

[0020] Obtain the set number of clusters, and use the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data as a distance metric to perform Clustering is performed to obtain the clustering result of the first time series data window of the tool cutting force monitoring time series data.

[0021] Preferably, optimizing the tool cutting force control parameters according to the clustering results to obtain optimized tool cutting force control parameters, and performing automated machine tool tool cutting force control according to the optimized tool cutting force control parameters, comprises:

[0022] Obtain the clustering result and the real-time tool cutting force monitoring time series data of the automatic machine tool, divide the real-time tool cutting force monitoring time series data of the automatic machine tool into a first time series data window, obtain the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool, perform cluster evaluation on the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool according to the clustering result, and obtain the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool belongs; optimize the tool cutting force control parameters of the automatic machine tool according to the cluster information of the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool, and output the optimized tool cutting force control parameter as a control signal to the machine tool actuator to achieve optimization of cutting force control.

[0023] Preferably, the cluster information of the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool is used to optimize the tool cutting force control parameters of the automatic machine tool, including:

[0024] Obtain the cutting force mean, standard deviation mean and average zero-crossing rate of the cluster center corresponding to each cluster in the clustering result of the first time series data window of the tool cutting force monitoring time series data; obtain the cluster information to which the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool belongs, and divide the cutting force mean corresponding to the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool by the cutting force mean of the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data belongs as the proportional gain adjustment factor; divide the cutting force standard deviation corresponding to the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool by the cutting force standard deviation of the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data belongs as the proportional gain adjustment factor. Integral gain adjustment factor; dividing the average zero-crossing rate of the cutting force corresponding to the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool by the average zero-crossing rate of the cutting force of the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data belongs as the differential gain adjustment factor; obtaining the real-time PID control parameter of the automatic machine tool; taking the product of the proportional gain adjustment factor and the proportional gain parameter of the real-time PID control of the automatic machine tool as the proportional gain optimization parameter; dividing the integral gain parameter of the real-time PID control of the automatic machine tool by the integral gain adjustment factor as the integral gain optimization parameter; taking the product of the differential gain adjustment factor and the differential gain parameter of the real-time PID control of the automatic machine tool as the differential gain optimization parameter.

[0025] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: the present invention collects data from the tool cutting force sensor of the machine tool automation to obtain the tool cutting force monitoring time series data; performs a first data window division on the tool cutting force monitoring time series data to obtain the first time series data window of all the tool cutting force monitoring time series data; obtains a first distance optimization factor by performing feature analysis on the first time series data window; optimizes the distance between the first time series data windows by using the first distance optimization factor to obtain the first optimized distance between the first time series data windows; performs a second data window division on the first time series data window of the tool cutting force monitoring time series data to obtain the second time series data window of all the tool cutting force monitoring time series data; performs feature analysis on the second time series data window to obtain the first distance optimization factor; optimizes the distance between the first time series data windows by using the first distance optimization factor to obtain the first optimized distance between the first time series data windows; performs a second data window division on the first time series data window of the tool cutting force monitoring time series data to obtain the second time series data window of all the tool cutting force monitoring time series data; A fitting analysis is performed to obtain the local autocorrelation function of the first time series data window; a distribution distance analysis between the local autocorrelation functions is performed to obtain a second distance optimization factor between the first time series data windows; the first optimized distance between the first time series data windows of the tool cutting force monitoring time series data is optimized by the second distance optimization factor to obtain a second optimized distance; a cluster analysis is performed on the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data to obtain a clustering result of the first time series data window of the tool cutting force monitoring time series data; the tool cutting force control parameters are optimized by the clustering result to obtain the optimized tool cutting force control parameters, and the optimized tool cutting force control parameters are used to perform tool cutting force control of an automated machine tool. Among them, by performing statistical feature extraction on all tool cutting force monitoring time series data windows, the overall feature vector of all time series data windows is obtained, and the first optimization factor is obtained according to the difference between the feature vector of each time series data window and the overall feature vector, thereby eliminating the influence of slight vibration data windows with large standard deviation, abnormal skewness or kurtosis in the distance measurement process, and on this basis, the second optimization factor is further obtained through the local autocorrelation information of the second window in the time series data window and further distance optimization is performed, so as to accurately evaluate the distance between data windows with different fluctuation modes, obtain accurate clustering results, and improve the optimization accuracy of PID control parameters through clustering results. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which constitute part of the present invention, are provided to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings:

[0027] Figure 1 A method flow chart of a machine tool automation control optimization method based on sensor data according to an embodiment of the present invention; DETAILED DESCRIPTION

[0028] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0029] It should be noted that the terms "first," "second," and the like in the specification and accompanying drawings of the present disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the data used in this toothpaste can be interchanged where appropriate so that the embodiments of the present disclosure described herein can be implemented in an unexpected order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with certain aspects of the present disclosure.

[0030] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0031] The specific scenario targeted by the present invention is: performing cutting force control optimization on the cutting force of a tool of an automated machine tool.

[0032] See also Figure 1 , is a method flow chart of a machine tool automation control optimization method based on sensor data provided by the first embodiment of the present invention, such as Figure 1 As shown, a machine tool automation control optimization method based on sensor data may include:

[0033] Step S101 : collecting tool cutting force monitoring time series data through a tool cutting force sensor of an automated machine tool and dividing the tool cutting force monitoring time series data into time series data windows.

[0034] For an automated machine tool with a tool cutting force sensor, the tool cutting force sensor can be used to collect data on the cutting force of the tool in the automated machine tool. The embodiment of the present invention collects tool cutting force monitoring time series data of all known tool cutting force sensors. Preferably, the sampling frequency of the tool cutting force sensor is set to 0.5 in the embodiment of the present invention. The tool cutting force value is collected once, and the tool cutting force monitoring time series data of the automated machine tool is obtained according to the set sampling frequency of the tool cutting force sensor.

[0035] Based on the above data acquisition method, the cutting force monitoring time series data of the tool in the automated machine tool is obtained. After obtaining the cutting force monitoring time series data of the tool in the automated machine tool, it is necessary to divide the cutting force monitoring time series data into windows according to the set window length. In the embodiment of the present invention, the window length is set to , the cutting force monitoring time series data of the tool in the automatic machine tool is divided into windows, and the cutting force monitoring time series data windows of all the tools in the automatic machine tool are obtained.

[0036] Step S102: Obtain the first distance optimization factor of the tool cutting force monitoring time series data window according to the data feature information in the tool cutting force monitoring time series data window, and optimize the distance measurement between the windows according to the first distance optimization factor of the tool cutting force monitoring time series data window to obtain the first optimized distance between the tool cutting force monitoring time series data windows.

[0037] After obtaining the monitoring time series data of the tool cutting force sensor, it is necessary to perform cluster analysis through the tool cutting force monitoring time series data window to divide the tool cutting force monitoring time series data into different clusters, and dynamically adjust the tool cutting force PID control parameters through the change information of the tool cutting force time series data window in the cluster. In the process of controlling the tool cutting force in the automatic machine tool through the PID control method, the PID control parameters are adjusted according to the different modes corresponding to the tool cutting force, so that the PID control process can more accurately adjust the cutting force of the tool in the automatic machine tool.

[0038] However, in the process of clustering the tool cutting force monitoring time series data windows in the automatic machine tool, the tool cutting force monitoring time series data windows are divided into different clusters by measuring the distance between the tool cutting force monitoring time series data windows. However, in the process of measuring the distance between the tool cutting force monitoring time series data windows, due to the existence of micro-vibration of the tool cutting force monitoring time series data, the distance measurement between the time series data windows will cause errors in the distance measurement between the two time series monitoring data windows. Therefore, in the distance measurement of the clustering process, it is necessary to optimize the distance measurement between the cutting force monitoring time series data windows to eliminate the influence of micro-vibration in the distance measurement between the cutting force monitoring time series data windows, thereby ensuring accurate clustering of the cutting force monitoring time series data windows.

[0039] Specifically, after obtaining the cutting force monitoring time series data window, the data points in the window will be affected by micro-vibration, causing the data points to show different statistical characteristics. For example, the standard deviation and peak value of the cutting force value in the data window with slight vibration will be larger than those in the data window with normal cutting. The clustering algorithm directly uses the Euclidean distance to calculate the distance between data windows, treats all data points equally, ignores the differences in the statistical characteristics of the data points, and makes the clustering results insensitive to micro-tremors.

[0040] To solve the micro-vibration problem, we first need to obtain the first distance optimization factor of the tool cutting force monitoring time series data window based on the data feature information in the tool cutting force monitoring time series data window, including:

[0041] Obtain all the time series data windows in the tool cutting force monitoring time series data, and obtain the mean of the numerical means in all the time series data windows, the mean of the numerical standard deviations in all the time series data windows, the mean of the numerical skewness in all the time series data windows, and the mean of the numerical kurtosis in all the time series data windows based on all the time series data windows in the tool cutting force monitoring time series data; form the overall mean vector of all the time series data windows with the mean of the numerical means in all the time series data windows, the mean of the numerical standard deviations in all the time series data windows, the mean of the numerical skewness in all the time series data windows, and the mean of the numerical kurtosis in all the time series data windows; obtain the Mahalanobis distance between the tool cutting force monitoring time series data window and the overall mean vector of all the time series data windows based on the overall mean vector of all the time series data windows; use the constant 1 and the reciprocal of the sum of the Mahalanobis distances between the tool cutting force monitoring time series data window and the overall mean vector of all the time series data windows as the first distance optimization factor of the tool cutting force monitoring time series data window.

[0042] In one embodiment, assuming that The mean eigenvector of the tool cutting force monitoring time series data window is , the overall mean vector of all time series data windows is , the covariance matrix of the statistical characteristics of all time series data windows is , then the calculation expression of the first distance optimization factor of the tool cutting force monitoring time series data window is:

[0043]

[0044] in, represents the first distance optimization factor of the tool cutting force monitoring time series data window; Indicates the The mean eigenvector of the tool cutting force monitoring time series data window; Represents the overall mean eigenvector of all time series data windows; Represents vector transpose; The inverse matrix of the covariance matrix representing the statistical characteristics of the entire time series data window; Represents a constant .

[0045] It should be noted that in the above formula The Mahalanobis distance is the mean eigenvector of the tool cutting force monitoring time series data window and the overall mean eigenvector of all time series data windows. The Mahalanobis distance weights each feature so that the correlation between different features is taken into account. For example, if the mean and standard deviation are positively correlated, then the Mahalanobis distance will be relatively small in the direction where the mean is large and the standard deviation is also large, because it considers this change to be "normal". For data points that deviate from this correlation (for example, the mean is large but the standard deviation is small, or the mean is small but the standard deviation is large), the Mahalanobis distance will be large. Convert the Mahalanobis distance to a range of When the statistical characteristics of a data window deviate far from the center of the data set (the Mahalanobis distance is large), its The value will be smaller; when the statistical characteristics of a data window are close to the center of the data set (the Mahalanobis distance is small), its The value will be close to .

[0046] After obtaining the first distance optimization factor of the tool cutting force monitoring time series data window, the distance metric between the windows can be optimized according to the first distance optimization factor of the tool cutting force monitoring time series data window to obtain the first optimized distance between the tool cutting force monitoring time series data windows, including:

[0047] Obtain any two of the tool cutting force monitoring time series data windows, multiply the first distance optimization factors of each of the any two tool cutting force monitoring time series data windows as the optimization weight of the distance measurement between the any two tool cutting force monitoring time series data windows; and use the calculation result of multiplying the optimization weight of the distance measurement between the any two tool cutting force monitoring time series data windows by the Euclidean distance between the any two tool cutting force monitoring time series data windows as the first optimized distance between the tool cutting force monitoring time series data windows.

[0048] In one embodiment, assuming that The tool cutting force monitoring time series data window is , No. The tool cutting force monitoring time series data window is , then the calculation expression of the first optimized distance between the tool cutting force monitoring time series data windows is:

[0049]

[0050] in, Indicates the The tool cutting force monitoring time series data window and the A first optimized distance between tool cutting force monitoring time series data windows; Indicates the The first distance optimization factor of a tool cutting force monitoring time series data window; Indicates the The first distance optimization factor of a tool cutting force monitoring time series data window; represents the mean eigenvector Features Indicates the The mean eigenvector of the tool cutting force monitoring time series data window is characteristic values; Indicates the The mean eigenvector of the tool cutting force monitoring time series data window characteristic values; Indicates the The tool cutting force monitoring time series data window and the The Euclidean distance between the tool cutting force monitoring time series data windows.

[0051] It should be noted that the optimization factor and It plays a weighted role. If two data windows and The statistical characteristics of the data set are far away from the center ( and are both smaller), then their distance Will be enlarged. If the two data windows and The statistical characteristics of the data are close to the center of the data set ( and are both large, close to 1), then their distance Close to the traditional Euclidean distance. If the statistical characteristics of one of the data windows deviate far from the center of the data set ( The statistical characteristics of the other data window are close to the center of the data set ( value is larger), then their distance It will be affected by data windows that deviate far away, and the distance will be magnified to a certain extent.

[0052] Step S103 , dividing the tool cutting force monitoring time series data window into a second data window, and obtaining a local autocorrelation function of the tool cutting force monitoring time series data window according to all second data windows in the tool cutting force monitoring time series data window.

[0053] After obtaining the first optimized distance between the tool cutting force monitoring time series data windows, although the first distance optimization factor The statistical characteristics of cutting force data within the data window (mean, standard deviation, skewness, kurtosis) are considered to enhance The algorithm is sensitive to differences in the overall data distribution. However, in actual cutting processes, different cutting states often correspond to different cutting force fluctuation patterns. For example, during normal cutting, the cutting force signal exhibits relatively random fluctuations; however, when slight chatter occurs, the cutting force signal typically exhibits a certain degree of periodicity or intermittency. This is because chatter, as a self-excited vibration, has a frequency that is related to the natural frequency of the machine tool-tool-workpiece system. Furthermore, factors such as tool wear and uneven workpiece material can also cause the cutting force to exhibit specific fluctuation patterns. While the statistical characteristics of the first distance optimization factor can reflect the fluctuation amplitude to a certain extent, they are inherently "static" and cannot describe the dynamic characteristics of the cutting force signal over time, thus failing to distinguish data windows with different fluctuation patterns. Since different cutting states (especially slight chatter) often correspond to different fluctuation patterns, and these patterns contain important information about the machining process, accurately identifying these fluctuation patterns is crucial for cutting state monitoring. Early detection of slight chatter is particularly important, as timely detection and action can prevent further development of chatter, thereby ensuring machining quality and tool life. At the same time, different cutting states require different PID control parameters. If these states cannot be accurately distinguished, adaptive adjustment of the PID parameters cannot be achieved. Therefore, after obtaining the first optimized distance between the tool cutting force monitoring time series data windows, it is necessary to further divide the tool cutting force monitoring time series data window into a second data window. Based on all the second data windows in the tool cutting force monitoring time series data window, the local autocorrelation function of the tool cutting force monitoring time series data window is obtained, including:

[0054] Obtain a set second data window length, divide the tool cutting force monitoring time series data window into two parts according to the second data window length, and obtain all second data windows in the tool cutting force monitoring time series data window; obtain a set autocorrelation lag parameter, and evaluate the local autocorrelation function corresponding to the tool cutting force monitoring time series data window for all second data windows in the tool cutting force monitoring time series data window according to the set autocorrelation lag parameter, and obtain the local autocorrelation function corresponding to the tool cutting force monitoring time series data window.

[0055] In one embodiment, the second data window length is set to , divide each tool cutting force time series data window into A second data window is formed. The length of the second data window can be adjusted according to the actual scenario and is not required. It should be noted that during the secondary division process, the central data point in the time series data window is removed and divided to obtain the entire second data window.

[0056] In one embodiment, the autocorrelation lag parameter is set to The autocorrelation lag parameter can be adjusted according to the actual scenario and is not required, so as to obtain the autocorrelation function of each second data window corresponding to the autocorrelation lag parameter.

[0057] After obtaining the autocorrelation function of each second data window in the tool cutting force monitoring time series data window, the autocorrelation functions of all the second data windows in the tool cutting force monitoring time series data window are averaged, and the averaged result is used as the local autocorrelation function of the tool cutting force monitoring time series data window.

[0058] Step S104, obtain the second distance optimization factor between the tool cutting force monitoring time series data windows according to the local autocorrelation function of the tool cutting force monitoring time series data window, and optimize the first optimized distance between the tool cutting force monitoring time series data windows according to the second distance optimization factor to obtain the second optimized distance between the tool cutting force monitoring time series data windows.

[0059] After obtaining the local autocorrelation function of the tool cutting force monitoring time series data window, the second distance optimization factor between the tool cutting force monitoring time series data windows can be obtained according to the local autocorrelation function of the tool cutting force monitoring time series data window, including:

[0060] Obtain any two of the tool cutting force monitoring time series data windows, obtain the distribution distance between the local autocorrelation functions corresponding to each of the any two tool cutting force monitoring time series data windows, and use the constant 1 and the inverse of the sum of the distribution distances between the local autocorrelation functions corresponding to each of the any two tool cutting force monitoring time series data windows as the second distance optimization factor between the tool cutting force monitoring time series data windows.

[0061] In one embodiment, assuming that The local autocorrelation function of a tool cutting force monitoring time series data window is: , No. The local autocorrelation function of a tool cutting force monitoring time series data window is: , then The tool cutting force monitoring time series data window and the The calculation expression of the second distance optimization factor between the tool cutting force monitoring time series data windows is:

[0062]

[0063] in, Indicates the The tool cutting force monitoring time series data window and the A second distance optimization factor between tool cutting force monitoring time series data windows; Indicates the The local autocorrelation function of the tool cutting force monitoring time series data window; Indicates the The local autocorrelation function of the tool cutting force monitoring time series data window; Indicates the The local autocorrelation function of the tool cutting force monitoring time series data window is The local autocorrelation function between the tool cutting force monitoring time series data windows distance; Represents a constant .

[0064] After obtaining the second distance optimization factor between the tool cutting force monitoring time series data windows, the first optimized distance between the tool cutting force monitoring time series data windows can be optimized according to the second distance optimization factor to obtain the second optimized distance between the tool cutting force monitoring time series data windows, including:

[0065] Obtain the first optimized distance between the tool cutting force monitoring time series data windows and the second distance optimization factor between the tool cutting force monitoring time series data windows, and use the calculation result of multiplying the second distance optimization factor between the tool cutting force monitoring time series data windows by the first optimized distance between the tool cutting force monitoring time series data windows as the second optimized distance between the tool cutting force monitoring time series data windows.

[0066] In one embodiment, the calculation expression of the second optimized distance between the tool cutting force monitoring time series data windows is:

[0067]

[0068] in, Indicates the The tool cutting force monitoring time series data window and the a second optimized distance between tool cutting force monitoring time series data windows; Indicates the The tool cutting force monitoring time series data window and the A second distance optimization factor between tool cutting force monitoring time series data windows; Indicates the The tool cutting force monitoring time series data window and the The first optimized distance between the tool cutting force monitoring time series data windows.

[0069] It should be noted that when the fluctuation patterns of two data windows are similar, Smaller, Larger; when the fluctuation pattern difference is large, Larger, Specifically, if the two data windows and The fluctuation pattern is similar to that of Larger, close to ), then for the first optimized distance The impact is small, the second optimization distance Close to If two data windows and The fluctuation patterns of smaller), the distance between them will be reduced , so that even if their statistical characteristics are not very different, they may be divided into different clusters.

[0070] Step S105, perform distance measurement based on the second optimized distance between the tool cutting force monitoring time series data windows and complete the clustering process, obtain the clustering results of the tool cutting force monitoring time series data windows, optimize the tool cutting force control parameters of the automatic machine tool based on the clustering results, and perform tool cutting force control of the automatic machine tool based on the optimized tool cutting force control parameters.

[0071] After obtaining the second optimized distance between the tool cutting force monitoring time series data windows, distance measurement can be performed based on the second optimized distance between the tool cutting force monitoring time series data windows and a clustering process can be completed to obtain clustering results of the tool cutting force monitoring time series data windows, including:

[0072] Get the set number of clusters, and use the second optimized distance between the tool cutting force monitoring time series data windows as the distance metric to perform Clustering, obtaining the clustering results of the tool cutting force monitoring time series data window. In the embodiment of the present invention, the set number of clusters is obtained by the elbow method, and the elbow method is used to determine The number of clusters for clustering is well known in the art and will not be described in detail here.

[0073] After obtaining the clustering results of the tool cutting force monitoring time series data window, the tool cutting force control parameters of the automated machine tool can be optimized based on the clustering results, and the tool cutting force control of the automated machine tool can be performed based on the optimized tool cutting force control parameters, including:

[0074] Obtaining the clustering result of the tool cutting force monitoring time series data window and the real-time tool cutting force monitoring time series data of the automatic machine tool, dividing the real-time tool cutting force monitoring time series data of the automatic machine tool into windows, obtaining the real-time tool cutting force monitoring time series data window of the automatic machine tool, clustering the real-time tool cutting force monitoring time series data window of the automatic machine tool according to the clustering result of the tool cutting force monitoring time series data window, and obtaining the cluster to which the real-time tool cutting force monitoring time series data window of the automatic machine tool belongs; optimizing the tool cutting force control parameters of the automatic machine tool according to the cluster information of the real-time tool cutting force monitoring time series data window of the automatic machine tool, specifically, optimizing the tool cutting force control parameters of the automatic machine tool according to the cluster information of the real-time tool cutting force monitoring time series data window of the automatic machine tool, including:

[0075] Obtain the cutting force mean, standard deviation mean and average zero-crossing rate of the cluster center corresponding to each cluster in the clustering result of the tool cutting force monitoring time series data window; obtain the cluster information to which the real-time tool cutting force monitoring time series data window of the automatic machine tool belongs, and divide the cutting force mean corresponding to the real-time tool cutting force monitoring time series data window of the automatic machine tool by the cutting force mean of the cluster in the real-time tool cutting force monitoring time series data window as a proportional gain adjustment factor; divide the cutting force standard deviation corresponding to the real-time tool cutting force monitoring time series data window of the automatic machine tool by the cutting force standard deviation of the cluster in the real-time tool cutting force monitoring time series data window as an integral gain adjustment factor; The average zero-crossing rate of the cutting force corresponding to the real-time tool cutting force monitoring time series data window of the automated machine tool is divided by the average zero-crossing rate of the cutting force of the cluster in the real-time tool cutting force monitoring time series data window, and the result of calculation is used as the differential gain adjustment factor; the real-time PID control parameters of the automated machine tool are obtained; the product of the proportional gain adjustment factor and the proportional gain parameter of the real-time PID control of the automated machine tool is used as the proportional gain optimization parameter; the integral gain parameter of the real-time PID control of the automated machine tool is divided by the integral gain adjustment factor, and the integral gain optimization parameter is used; the product of the differential gain adjustment factor and the differential gain parameter of the real-time PID control of the automated machine tool is used as the differential gain optimization parameter. The optimized tool cutting force PID control parameters, including the proportional gain optimization parameter, the integral gain optimization parameter, and the differential gain optimization parameter, are output as control signals to the machine tool actuator to achieve optimized control of the cutting force.

[0076] In summary, the embodiment of the present invention collects data from the tool cutting force sensor of the machine tool automation to obtain tool cutting force monitoring time series data; performs a first data window division on the tool cutting force monitoring time series data to obtain the first time series data window of all tool cutting force monitoring time series data; obtains a first distance optimization factor by performing feature analysis on the first time series data window; optimizes the distance between the first time series data windows by the first distance optimization factor to obtain the first optimized distance between the first time series data windows; performs a second data window division on the first time series data window of the tool cutting force monitoring time series data to obtain the second time series data window of all tool cutting force monitoring time series data; performs fitting analysis on the second time series data window to obtain to the local autocorrelation function of the first time series data window; obtain the second distance optimization factor between the first time series data windows through the distribution distance analysis between the local autocorrelation functions; optimize the first optimized distance between the first time series data windows of the tool cutting force monitoring time series data through the second distance optimization factor to obtain the second optimized distance; perform clustering analysis on the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data to obtain the clustering result of the first time series data window of the tool cutting force monitoring time series data; optimize the tool cutting force control parameters through the clustering result to obtain the optimized tool cutting force control parameters, and perform automated machine tool tool cutting force control through the optimized tool cutting force control parameters. Among them, by performing statistical feature extraction on all tool cutting force monitoring time series data windows, the overall feature vector of all time series data windows is obtained, and the first optimization factor is obtained according to the difference between the feature vector of each time series data window and the overall feature vector, thereby eliminating the influence of slight vibration data windows with large standard deviation, abnormal skewness or kurtosis in the distance measurement process, and on this basis, the second optimization factor is further obtained through the local autocorrelation information of the second window in the time series data window and further distance optimization is performed, so as to accurately evaluate the distance between data windows with different fluctuation modes, obtain accurate clustering results, and improve the optimization accuracy of PID control parameters through clustering results.

[0077] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A machine tool automation control optimization method based on sensor monitoring data, characterized in that: include: Collect data from the cutting force sensor of the machine tool automation tool to obtain the tool cutting force monitoring time series data; Performing a first data window division on the tool cutting force monitoring time series data to obtain a first time series data window of all the tool cutting force monitoring time series data; obtaining a first distance optimization factor by performing feature analysis on the first time series data window; Optimizing the distance between the first time series data windows using a first distance optimization factor to obtain a first optimized distance between the first time series data windows; Perform a second data window division on the first time series data window of the tool cutting force monitoring time series data to obtain a second time series data window of all the tool cutting force monitoring time series data; perform fitting analysis on the second time series data window to obtain a local autocorrelation function of the first time series data window; perform distribution distance analysis between the local autocorrelation functions to obtain a second distance optimization factor between the first time series data windows; optimize the first optimized distance between the first time series data windows of the tool cutting force monitoring time series data by the second distance optimization factor to obtain a second optimized distance; perform cluster analysis on the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data to obtain a clustering result of the first time series data window of the tool cutting force monitoring time series data; optimize the tool cutting force control parameter by the clustering result to obtain the optimized tool cutting force control parameter, and perform automated machine tool tool cutting force control by using the optimized tool cutting force control parameter; The method obtains the first distance optimization factor by performing feature analysis on the first time series data window, including: obtaining the first time series data window of all tool cutting force monitoring time series data, obtaining the mean of the numerical means of all first time series data windows, the mean of the numerical standard deviations of all first time series data windows, the mean of the numerical skewness of all first time series data windows and the mean of the numerical kurtosis of all time series data windows according to all first time series data windows in the tool cutting force monitoring time series data; obtaining the mean of the numerical means of all first time series data windows, the mean of the numerical standard deviations of all first time series data windows, the mean of the numerical skewness of all first time series data windows and the mean of the numerical kurtosis of all time series data windows; obtaining the mean of the numerical means of all first time series data windows, the mean of the numerical standard deviations of all first time series data windows, the mean of the numerical kurtosis of all first ... According to the mean of the numerical skewness in the window and the mean of the numerical kurtosis in all the time series data windows, an overall mean vector of all the time series data windows is formed; according to the overall mean vector of all the first time series data windows, the Mahalanobis distance between the first time series data window of the tool cutting force monitoring time series data and the overall mean vector of all the first time series data windows is obtained; a constant 1 and the reciprocal of the sum of the Mahalanobis distances between the first time series data window of the tool cutting force monitoring time series data and the overall mean vector of all the first time series data windows are used as the first distance optimization factor of the first time series data window of the tool cutting force monitoring time series data; The method of obtaining a second distance optimization factor between first time series data windows by analyzing the distribution distance between the local autocorrelation functions includes: obtaining any two first time series data windows of the tool cutting force monitoring time series data, obtaining the distribution distance between the local autocorrelation functions corresponding to the two first time series data windows, and using a constant 1 and the reciprocal of the sum of the distribution distances between the local autocorrelation functions corresponding to the two first time series data windows as the second distance optimization factor between the first time series data windows; The method of performing a second data window division on the first time series data window of the tool cutting force monitoring time series data to obtain the second time series data window of all the tool cutting force monitoring time series data, and performing fitting analysis through the second time series data window to obtain the local autocorrelation function of the first time series data window includes: obtaining a set second data window length, dividing the first time series data window of the tool cutting force monitoring time series data for a second time according to the second data window length, and obtaining the second time series data window in the first time series data window of all the tool cutting force monitoring time series data; obtaining a set autocorrelation lag parameter, and performing local autocorrelation function evaluation corresponding to the first time series data window of the tool cutting force monitoring time series data on all the second time series data windows according to the set autocorrelation lag parameter to obtain the local autocorrelation function of the first time series data window.

2. The machine tool automation control optimization method based on sensor data according to claim 1, characterized in that: The data collection of the tool cutting force sensor of the machine tool automation is performed to obtain the tool cutting force monitoring time series data, and the tool cutting force monitoring time series data is divided into a first data window to obtain the first time series data window of all the tool cutting force monitoring time series data, including: Set the sampling frequency of the tool cutting force sensor and collect data on the tool cutting force values ​​in the automated machine tool according to the set sampling frequency to obtain tool cutting force monitoring time series data; set the tool cutting force monitoring time series data window length, and divide the tool cutting force monitoring time series data into windows according to the tool cutting force monitoring time series data window length to obtain the first time series data window of all tool cutting force monitoring time series data.

3. The machine tool automation control optimization method based on sensor data according to claim 1, characterized in that: The step of optimizing the distance between the first time series data windows by using the first distance optimization factor to obtain the first optimized distance between the first time series data windows includes: Obtain the first time series data windows of any two of the tool cutting force monitoring time series data, multiply the first distance optimization factors of each of the any two first time series data windows as the optimization weight of the distance measurement between the any two first time series data windows; and use the calculation result of multiplying the optimization weight of the distance measurement between any two first time series data windows by the Euclidean distance between any two first time series data windows as the first optimized distance between the first time series data windows.

4. The machine tool automation control optimization method based on sensor data according to claim 1, characterized in that: The step of optimizing the first optimized distance between the first time series data windows of the tool cutting force monitoring time series data by using the second distance optimization factor to obtain the second optimized distance includes: Obtain the first optimized distance between the first time series data windows and the second distance optimization factor between the first time series data windows, and use the result of multiplying the second distance optimization factor between the first time series data windows by the first optimized distance between the first time series data windows as the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data.

5. The machine tool automation control optimization method based on sensor data according to claim 1, characterized in that: The cluster analysis is performed based on the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data to obtain the clustering result of the first time series data window of the tool cutting force monitoring time series data, including: Obtain the set number of clusters, and use the second optimized distance between the first time series data windows of the tool cutting force monitoring time series data as a distance metric to perform Clustering is performed to obtain the clustering result of the first time series data window of the tool cutting force monitoring time series data.

6. The machine tool automation control optimization method based on sensor data according to claim 1, characterized in that: The method of optimizing the tool cutting force control parameters by using the clustering results to obtain the optimized tool cutting force control parameters, and performing automatic machine tool tool cutting force control by using the optimized tool cutting force control parameters, includes: Obtain the clustering result and the real-time tool cutting force monitoring time series data of the automatic machine tool, divide the real-time tool cutting force monitoring time series data of the automatic machine tool into a first time series data window, obtain the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool, perform cluster evaluation on the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool according to the clustering result, and obtain the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool belongs; optimize the tool cutting force control parameters of the automatic machine tool according to the cluster information of the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool, and output the optimized tool cutting force control parameter as a control signal to the machine tool actuator to achieve optimization of cutting force control.

7. The machine tool automation control optimization method based on sensor data according to claim 6, characterized in that: Optimizing the tool cutting force control parameters of the automated machine tool based on cluster information of a first time series data window of the real-time tool cutting force monitoring time series data of the automated machine tool, including: Obtain the cutting force mean, standard deviation mean and average zero-crossing rate of the cluster center corresponding to each cluster in the clustering result of the first time series data window of the tool cutting force monitoring time series data; obtain the cluster information to which the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool belongs, and divide the cutting force mean corresponding to the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool by the cutting force mean of the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data belongs as the proportional gain adjustment factor; divide the cutting force standard deviation corresponding to the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool by the cutting force standard deviation of the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data belongs as the proportional gain adjustment factor. Integral gain adjustment factor; dividing the average zero-crossing rate of the cutting force corresponding to the first time series data window of the real-time tool cutting force monitoring time series data of the automatic machine tool by the average zero-crossing rate of the cutting force of the cluster to which the first time series data window of the real-time tool cutting force monitoring time series data belongs as the differential gain adjustment factor; obtaining the real-time PID control parameter of the automatic machine tool; taking the product of the proportional gain adjustment factor and the proportional gain parameter of the real-time PID control of the automatic machine tool as the proportional gain optimization parameter; dividing the integral gain parameter of the real-time PID control of the automatic machine tool by the integral gain adjustment factor as the integral gain optimization parameter; taking the product of the differential gain adjustment factor and the differential gain parameter of the real-time PID control of the automatic machine tool as the differential gain optimization parameter.

Images