Human-computer interaction management method and system for CNC machine tools

Abstract

The present application relates to the field of CNC machine tool management, and provides a method and system for human-computer interaction management of CNC machine tools, which obtains user fault query requests through a voice input module, and based on the fault query requests, extracts historical data sets of machine tool loads and historical data sets of machine tool vibration amplitude values ​​from a data storage device, and uses an artificial intelligence-based data analysis algorithm to perform time series arrangement and association coding of the machine tool loads and the machine tool vibration amplitude values, thereby automatically obtaining a diagnosis result of a fault type label based on interactive response information between machine tool load time series association features and machine tool vibration amplitude value time series association features, and displays the diagnosis result. The voice input module can improve the accuracy of data input, and the user can receive machine tool fault diagnosis information in real time, which is conducive to realizing intelligent management of CNC machine tools.

Description

Technical Field

[0001] The present application relates to the field of CNC machine tool management, and more specifically, to a CNC machine tool human-computer interaction management method and system. Background Art

[0002] With the development of Industry 4.0, smart manufacturing has put forward higher requirements for real-time monitoring and health management of production equipment. As the core equipment of the manufacturing industry, the operating status of CNC machine tools is directly related to product quality and production efficiency. Therefore, real-time monitoring and fault diagnosis management of machine tool status are of great significance for preventing equipment failures, improving production efficiency and reducing costs.

[0003] However, traditional CNC machine tool management relies on manual input, which not only increases the complexity of operation, but also increases the workload of operators. Specifically, when manually inputting data, especially in emergency situations, operators may miss key information or enter incorrect data due to tension or time pressure, which may lead to inaccurate diagnosis or delays. Moreover, the inefficiency of manual input may cause response delays in a rapidly changing production environment, thus affecting the operation of the entire production line. In addition, users often cannot receive machine status updates and fault diagnosis information in real time, which makes it difficult for operators to respond quickly to possible equipment problems. This delay in obtaining information may lead to reduced production efficiency and even, in some cases, equipment damage or production accidents due to failure to detect and deal with problems in a timely manner.

[0004] Therefore, an optimized human-computer interaction management solution for CNC machine tools is needed to solve the above technical problems. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present application provides a method and system for human-computer interaction management of CNC machine tools.

[0006] According to one aspect of the present application, a method for human-machine interaction management of a CNC machine tool is provided, which comprises:

[0007] The user inputs a fault query request through the voice input module;

[0008] In response to receiving the fault query request, extracting a historical data set of machine tool load and a historical data set of machine tool vibration amplitude values ​​from a data storage;

[0009] The historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively regularized to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value, and then time series encoding is performed to obtain a machine tool load time series correlation feature vector and a machine tool vibration amplitude time series correlation feature vector;

[0010] Performing machine tool load-machine tool vibration amplitude interactive response encoding on the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector to obtain a machine tool load-machine tool vibration amplitude interactive response feature;

[0011] Obtaining a diagnosis result based on the machine tool load-machine tool vibration amplitude interactive response characteristics, and displaying the diagnosis result;

[0012] The machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector are subjected to machine tool load-machine tool vibration amplitude interactive response encoding to obtain the machine tool load-machine tool vibration amplitude interactive response feature, including:

[0013] Performing feature fine-grained decomposition on the time series correlation feature vector of the machine tool vibration amplitude to obtain a sequence of local time series correlation feature vectors of the machine tool vibration amplitude;

[0014] A local-global interactive response analysis is performed on a sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response feature.

[0015] In the above-mentioned human-computer interaction management method for CNC machine tools, the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively data-regularized to obtain the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value, and then time series encoding is performed to obtain the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector, including: the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively data-regularized in time sequence to obtain the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value; the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value are input into a time series encoder based on a Bi-LSTM model to obtain the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector.

[0016] In the above-mentioned human-machine interaction management method for CNC machine tools, a local-global interactive response analysis is performed on the sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response characteristics, including: calculating the correlation matrix between the machine tool load time series correlation feature vector and each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices; calculating each machine tool load-machine tool vibration amplitude in the sequence of the machine tool load-machine tool vibration amplitude correlation matrix. The characteristic interaction energy factors of the machine tool load-machine tool vibration amplitude correlation matrix are obtained to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors; the sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors is normalized to obtain a sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors; the sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors is used as a sequence of weights, and the position-weighted sum of the sequence of the machine tool load-machine tool vibration amplitude correlation matrix is ​​calculated to obtain a machine tool load-machine tool vibration amplitude local-global interaction response matrix as the machine tool load-machine tool vibration amplitude interaction response feature.

[0017] In the above-mentioned human-machine interaction management method for CNC machine tools, the correlation matrix between the machine tool load time series correlation feature vector and each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool vibration amplitude local time series correlation feature vector is calculated to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices, including: performing a nonlinear transformation on the machine tool load time series correlation feature vector to obtain a nonlinearly transformed machine tool load time series correlation feature vector; calculating the correlation matrix between the machine tool load time series correlation feature vector after the nonlinear transformation and each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool vibration amplitude local time series correlation feature vector to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices.

[0018] In the above-mentioned human-machine interaction management method for CNC machine tools, the characteristic interaction energy factors of each machine tool load-machine tool vibration amplitude association matrix in the sequence of the machine tool load-machine tool vibration amplitude association matrix are calculated to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors, including: calculating the kurtosis value of each machine tool load-machine tool vibration amplitude association matrix in the sequence of the machine tool load-machine tool vibration amplitude association matrix to obtain a sequence of machine tool load-machine tool vibration amplitude association kurtosis values; based on each machine tool load-machine tool vibration amplitude association kurtosis value in the sequence of the machine tool load-machine tool vibration amplitude association kurtosis values, calculating the characteristic interaction energy factors of each machine tool load-machine tool vibration amplitude association matrix to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors.

[0019] In the above-mentioned human-machine interaction management method for CNC machine tools, the kurtosis value of each machine tool load-machine tool vibration amplitude association matrix in the sequence of the machine tool load-machine tool vibration amplitude association matrix is ​​calculated to obtain a sequence of machine tool load-machine tool vibration amplitude association kurtosis values, including: respectively calculating the mean and variance of the machine tool load-machine tool vibration amplitude association matrix to obtain the machine tool load-machine tool vibration amplitude association mean and the machine tool load-machine tool vibration amplitude association variance; calculating the bitwise correlation of the machine tool load-machine tool vibration amplitude association matrix and the machine tool load-machine tool vibration amplitude association mean. The invention relates to a method for obtaining a machine tool load-machine tool vibration amplitude correlation difference matrix by setting the difference value to obtain a machine tool load-machine tool vibration amplitude correlation difference matrix; calculating the fourth power of each eigenvalue in the machine tool load-machine tool vibration amplitude correlation difference matrix to obtain a machine tool load-machine tool vibration amplitude correlation modulation difference matrix; calculating the expected value of the machine tool load-machine tool vibration amplitude correlation modulation difference matrix to obtain a machine tool load-machine tool vibration amplitude correlation expected value; dividing the machine tool load-machine tool vibration amplitude correlation expected value by the square of the machine tool load-machine tool vibration amplitude correlation variance to obtain the machine tool load-machine tool vibration amplitude correlation kurtosis value.

[0020] In the above-mentioned human-machine interaction management method for CNC machine tools, based on each machine tool load-machine tool vibration amplitude associated kurtosis value in the sequence of the machine tool load-machine tool vibration amplitude associated kurtosis value, the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude associated matrix is ​​calculated to obtain the sequence of the machine tool load-machine tool vibration amplitude characteristic interaction energy factor, including: calculating the sum of the machine tool load-machine tool vibration amplitude associated variance and the hyperparameter to obtain the machine tool load-machine tool vibration amplitude associated first energy factor; calculating the machine tool load-machine tool vibration amplitude associated kurtosis value and the machine tool load -The square of the difference between the associated mean values ​​of the machine tool load and the machine tool vibration amplitude is used to obtain the machine tool load-machine tool vibration amplitude associated difference value; the value obtained by multiplying the machine tool load-machine tool vibration amplitude associated variance by constant two and the value obtained by multiplying the hyperparameter by constant two are added to the machine tool load-machine tool vibration amplitude associated difference value to obtain the machine tool load-machine tool vibration amplitude associated second energy factor; the machine tool load-machine tool vibration amplitude associated first energy factor is divided by the machine tool load-machine tool vibration amplitude associated second energy factor to obtain the machine tool load-machine tool vibration amplitude characteristic interaction energy factor.

[0021] In the above-mentioned human-machine interaction management method for CNC machine tools, the sequence of the machine tool load-machine tool vibration amplitude characteristic interaction energy factors is normalized to obtain a sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors, including: inputting the sequence of the machine tool load-machine tool vibration amplitude characteristic interaction energy factors into a Sigmoid function to obtain the sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors.

[0022] In the above-mentioned human-machine interaction management method for CNC machine tools, a diagnosis result is obtained based on the machine tool load-machine tool vibration amplitude interaction response characteristics, and the diagnosis result is displayed, including: inputting the machine tool load-machine tool vibration amplitude local-global interaction response matrix into a classifier-based fault diagnoser to obtain the diagnosis result, and the diagnosis result is used to represent the fault type label; displaying the diagnosis result.

[0023] According to another aspect of the present application, a human-machine interaction management system for a numerically controlled machine tool is provided, comprising:

[0024] A fault query request data collection module is used to obtain the fault query request input by the user through the voice input module;

[0025] A machine tool load and machine tool vibration amplitude value historical data set extraction module is used to extract a machine tool load historical data set and a machine tool vibration amplitude value historical data set from a data storage in response to receiving the fault query request;

[0026] A machine tool load and machine tool vibration amplitude time series feature encoding module is used to perform data regularization on the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value, and then perform time series encoding to obtain a machine tool load time series associated feature vector and a machine tool vibration amplitude time series associated feature vector;

[0027] A machine tool load-machine tool vibration amplitude interactive response encoding module is used to perform machine tool load-machine tool vibration amplitude interactive response encoding on the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector to obtain a machine tool load-machine tool vibration amplitude interactive response feature;

[0028] A diagnosis result generating module, used for obtaining a diagnosis result based on the machine tool load-machine tool vibration amplitude interactive response characteristics, and displaying the diagnosis result;

[0029] Wherein, the machine tool load and machine tool vibration amplitude interactive response encoding module includes:

[0030] A machine tool vibration amplitude time series correlation feature decomposition unit, used for performing feature fine-grained decomposition on the machine tool vibration amplitude time series correlation feature vector to obtain a sequence of machine tool vibration amplitude local time series correlation feature vectors;

[0031] The machine tool load and machine tool vibration amplitude interactive response feature generating unit is used to perform local-global interactive response analysis on the sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response feature.

[0032] This application has significant technical effects due to the adoption of the above technical solutions:

[0033] The human-machine interactive management method and system for CNC machine tools provided in the present application obtains user fault query requests through a voice input module, and based on the fault query request, extracts a historical data set of machine tool load and a historical data set of machine tool vibration amplitude values ​​from a data storage device, and uses an artificial intelligence-based data analysis algorithm to perform time series arrangement and association coding of the machine tool load and the machine tool vibration amplitude values, thereby automatically obtaining the diagnosis result of the fault type label based on the interactive response information between the machine tool load time series association characteristics and the machine tool vibration amplitude value time series association characteristics, and displays the diagnosis result. In this way, the accuracy of data input can be improved through the voice input module, and the user can receive the machine tool fault diagnosis information in real time, which is conducive to realizing the intelligent management of CNC machine tools. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0035] Figure 1 The present invention is a flowchart of a method for human-computer interaction management of a CNC machine tool according to an embodiment of the present application.

[0036] Figure 2 Schematic diagram of data flow of the human-computer interaction management method for CNC machine tools according to an embodiment of the present application.

[0037] Figure 3 In the human-machine interaction management method for CNC machine tools according to an embodiment of the present application, the machine tool load timing association feature vector and the machine tool vibration amplitude timing association feature vector are encoded for machine tool load-machine tool vibration amplitude interaction response to obtain a flowchart of the machine tool load-machine tool vibration amplitude interaction response characteristics.

[0038] Figure 4 In the human-machine interaction management method for CNC machine tools according to an embodiment of the present application, a local-global interactive response analysis is performed on a sequence of the machine tool load timing correlation feature vector and the machine tool vibration amplitude local timing correlation feature vector to obtain a flowchart of the machine tool load-machine tool vibration amplitude interactive response characteristics.

[0039] Figure 5 In the human-machine interaction management method for CNC machine tools according to an embodiment of the present application, a flowchart of calculating the correlation matrix between the machine tool load timing correlation feature vector and each machine tool vibration amplitude local timing correlation feature vector in the sequence of the machine tool vibration amplitude local timing correlation feature vector is provided to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices.

[0040] Figure 6 This is a flowchart of a method for human-machine interaction management of CNC machine tools according to an embodiment of the present application, which calculates the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude correlation matrix in the sequence of the machine tool load-machine tool vibration amplitude correlation matrix to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors.

[0041] Figure 7 4 is a system block diagram of a human-computer interaction management system for CNC machine tools according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0043] In response to the technical problems in the background technology, the technical concept of the present application is that the user inputs a fault query request through a voice input module, and in response to receiving the fault query request, extracts a historical data set of machine tool load and a historical data set of machine tool vibration amplitude value from a data storage device, and uses an artificial intelligence-based data analysis and processing algorithm to perform time series arrangement and association coding of the machine tool load and the machine tool vibration amplitude value, so as to automatically obtain a diagnosis result of the fault type label based on the interactive response information between the machine tool load time series association characteristics and the machine tool vibration amplitude value time series association characteristics, and display the diagnosis result. By utilizing the voice input module, the user does not need to manually input data, which reduces errors and improves the accuracy of data input; at the same time, the user can receive real-time status updates and fault diagnosis information of the machine tool, so as to respond quickly and avoid equipment damage or production accidents, so as to realize the intelligent management of CNC machine tools.

[0044] Figure 1The present invention is a flowchart of a method for human-computer interaction management of a CNC machine tool according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the human-machine interaction management method for CNC machine tools according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the human-computer interaction management method of a CNC machine tool in an embodiment of the present application, the method includes: S110, a user inputs a fault query request through a voice input module; S120, in response to receiving the fault query request, extracting a historical data set of a machine tool load and a historical data set of a machine tool vibration amplitude value from a data storage device; S130, respectively performing data regularization on the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value, and then performing time series encoding to obtain a machine tool load timing association feature vector and a machine tool vibration amplitude timing association feature vector; S140, performing machine tool load-machine tool vibration amplitude interactive response encoding on the machine tool load timing association feature vector and the machine tool vibration amplitude timing association feature vector to obtain a machine tool load-machine tool vibration amplitude interactive response feature; S150, obtaining a diagnosis result based on the machine tool load-machine tool vibration amplitude interactive response feature, and displaying the diagnosis result.

[0045] In step S110 and step S120, the user inputs a fault query request through the voice input module, and in response to receiving the fault query request, the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are extracted from the data storage. Specifically, the user first uses the voice input module to input the fault query request, which is the starting point of the entire CNC machine tool human-computer interaction management, reflecting the convenience and efficiency of human-computer interaction. The voice input module integrates voice recognition technology and can accurately convert the user's voice instructions into a text format recognizable by the computer. Once the user receives the fault query request input by voice, it will immediately trigger the subsequent response mechanism. The core of this response mechanism is to extract the historical data set related to the machine tool status from the data storage, that is, the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value. As an important component for storing machine tool operation data, the data storage can record various parameter changes of the CNC machine tool during long-term operation. In the process of extracting data, the relevant historical data sets can be screened and located according to the specific content of the fault query request (such as the time range of the query), and these data sets will then be used for subsequent data processing. In the subsequent data processing steps, by analyzing the extracted historical data sets of machine tool loads and machine tool vibration amplitude values, users can timely understand the status of CNC machine tools, thereby managing CNC machine tool equipment more effectively. The diagnostic results of the data machine tool equipment obtained through analysis are directly displayed in text, which is convenient for users to intuitively obtain machine tool status information. This visual display is also an important part of human-computer interaction management of data machine tools.

[0046] In step S130, the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively data-ordered to obtain the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value, and then time series encoding is performed to obtain the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector. Specifically, in an embodiment of the present application, the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively data-ordered to obtain the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value, and then time series encoding is performed to obtain the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector, including: the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively data-ordered in time sequence to obtain the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value; the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value are input into a time series encoder based on a Bi-LSTM model to obtain the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector.

[0047] Specifically, the machine tool load and the machine tool vibration amplitude value are dynamic data that change over time, that is, the load and vibration amplitude value have time series characteristics in the time dimension, such as dynamic change patterns and periodic characteristics in the data. Based on this, in the technical solution of the present application, the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively regularized in chronological order to obtain the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value. Furthermore, in order to capture and mine the time series correlation characteristics of the machine tool load and the vibration amplitude value in different time scales, so as to better characterize and depict the time series dynamic change trend of the data, in the technical solution of the present application, the time queue of the machine tool load and the time queue of the machine tool vibration amplitude value are input into the time series encoder based on the Bi-LSTM model to obtain the time series correlation feature vector of the machine tool load and the time series correlation feature vector of the machine tool vibration amplitude.

[0048] In step S140, the machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector are subjected to machine tool load-machine tool vibration amplitude interactive response encoding to obtain machine tool load-machine tool vibration amplitude interactive response characteristics. Specifically, there are multiple potential correlation relationships between the machine tool load time series correlation feature and the machine tool vibration amplitude time series correlation feature, which reflect the complexity of the machine tool operation state. For example, when the machine tool is subjected to a larger load, it may cause additional stress on the mechanical components, thereby causing an increase in the vibration amplitude. At the same time, the two also contain different degrees of local (changes in a short time) and global (changes in a long time span) based on the entire time range. Therefore, in order to be able to understand and analyze the interactive relationship of the features in the local time period in a more fine-grained manner, in the technical solution of the present application, the machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector are subjected to machine tool load-machine tool vibration amplitude interactive response encoding to obtain a machine tool load-machine tool vibration amplitude local-global interactive response matrix as a machine tool load-machine tool vibration amplitude interactive response feature.

[0049] In detail, first, the machine tool vibration amplitude time series correlation feature vector is subjected to feature fine-grained decomposition to obtain a sequence of local time series correlation feature vectors of the machine tool vibration amplitude. That is, by performing feature fine-grained decomposition on the machine tool vibration amplitude time series correlation feature, the complex vibration amplitude time series feature vector can be decomposed into multiple specific, finer-grained local time series features, so as to more clearly show the specific changes of the vibration amplitude at different time points, so as to enhance the ability to capture the dynamics of local features. Then, the machine tool load time series correlation feature vector is subjected to nonlinear transformation to enhance the expression ability of the feature, so as to better understand the complex interaction between the load feature and the fault mode, and obtain the machine tool load time series correlation feature vector after nonlinear transformation. After that, the correlation matrix between the machine tool load feature and each vibration amplitude time series feature after nonlinear change is calculated to reveal the deeper connection between the load feature and the vibration amplitude feature, and obtain the sequence of machine tool load-machine tool vibration amplitude correlation matrix.

[0050] Then, in order to further quantify the interaction intensity between the machine tool load characteristics and the vibration amplitude characteristics, so as to help identify the most important feature interaction patterns, the feature interaction energy factor of each correlation matrix is ​​calculated to identify which interaction features contribute most to the diagnosis results, and the sequence of machine tool load-machine tool vibration amplitude feature interaction energy factors is obtained. Then, each feature interaction energy factor is normalized to convert it into a weight value to ensure the balance of the weight, so that the model can more reasonably allocate the attention to different feature interactions. Finally, the normalized factor is used as the weight value to weight each correlation matrix and sum it to obtain the machine tool load-machine tool vibration amplitude local-global interaction response matrix. That is, the various local interaction features are combined together to form a comprehensive response matrix, which can fully reflect the complex interaction relationship between the machine tool load and the vibration amplitude, and provide a response from a global perspective.

[0051] Specifically, Figure 3 The present invention is a flowchart of a method for human-machine interaction management of a CNC machine tool according to an embodiment of the present application, in which the machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector are encoded for the machine tool load-machine tool vibration amplitude interaction response to obtain the machine tool load-machine tool vibration amplitude interaction response feature. Figure 3As shown, the machine tool load timing association feature vector and the machine tool vibration amplitude timing association feature vector are subjected to machine tool load-machine tool vibration amplitude interactive response encoding to obtain machine tool load-machine tool vibration amplitude interactive response characteristics, including: S141, feature fine-grained decomposition of the machine tool vibration amplitude timing association feature vector to obtain a sequence of machine tool vibration amplitude local timing association feature vectors; S142, local-global interactive response analysis is performed on the sequence of the machine tool load timing association feature vector and the machine tool vibration amplitude local timing association feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response characteristics.

[0052] More specifically, Figure 4 The present invention is a flowchart of performing local-global interactive response analysis on the sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector in the CNC machine tool human-machine interactive management method according to the embodiment of the present application to obtain the machine tool load-machine tool vibration amplitude interactive response feature. Figure 4 As shown, a local-global interactive response analysis is performed on the sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response characteristics, including: S1421, calculating the correlation matrix between the machine tool load time series correlation feature vector and each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices; S1422, calculating each machine tool load-machine tool vibration amplitude correlation matrix in the sequence of the machine tool load-machine tool vibration amplitude correlation matrix to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors; S1423, normalizing the sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors to obtain a sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors; S1424, using the sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors as a sequence of weights, calculating the position-weighted sum of the sequence of machine tool load-machine tool vibration amplitude association matrices to obtain a machine tool load-machine tool vibration amplitude local-global interaction response matrix as the machine tool load-machine tool vibration amplitude interaction response feature.

[0053] More specifically, Figure 5 The present invention is a flowchart of calculating the correlation matrix between the machine tool load time series correlation feature vector and each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool vibration amplitude local time series correlation feature vector in the CNC machine tool human-machine interaction management method according to the embodiment of the present application to obtain the sequence of machine tool load-machine tool vibration amplitude correlation matrix. Figure 5As shown, calculating the correlation matrix between the machine tool load timing correlation feature vector and each machine tool vibration amplitude local timing correlation feature vector in the sequence of the machine tool vibration amplitude local timing correlation feature vector to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices, including: S14211, performing a nonlinear transformation on the machine tool load timing correlation feature vector to obtain the nonlinearly transformed machine tool load timing correlation feature vector; S14212, calculating the correlation matrix between the machine tool load timing correlation feature vector after the nonlinear transformation and each machine tool vibration amplitude local timing correlation feature vector in the sequence of the machine tool vibration amplitude local timing correlation feature vector to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices.

[0054] In an embodiment of the present application, specifically, a nonlinear transformation is performed on the machine tool load timing association characteristic vector to obtain the machine tool load timing association characteristic vector after the nonlinear transformation, including: multiplying the machine tool load timing association characteristic vector with the machine tool load transformation matrix, and then adding the obtained machine tool load transformation vector and the machine tool load offset vector by position to obtain the machine tool load timing association characteristic vector after the nonlinear transformation.

[0055] More specifically, Figure 6 The present invention is a flowchart of calculating the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude correlation matrix in the sequence of the machine tool load-machine tool vibration amplitude correlation matrix to obtain the sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors in the CNC machine tool human-machine interaction management method according to the embodiment of the present application. Figure 6 As shown, the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude association matrix in the sequence of the machine tool load-machine tool vibration amplitude association matrix is ​​calculated to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors, including: S14221, calculating the kurtosis value of each machine tool load-machine tool vibration amplitude association matrix in the sequence of the machine tool load-machine tool vibration amplitude association matrix to obtain a sequence of machine tool load-machine tool vibration amplitude association kurtosis values; S14222, based on each machine tool load-machine tool vibration amplitude association kurtosis value in the sequence of the machine tool load-machine tool vibration amplitude association kurtosis values, calculating the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude association matrix to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors.

[0056] More specifically, in an embodiment of the present application, the kurtosis value of each machine tool load-machine tool vibration amplitude association matrix in the sequence of the machine tool load-machine tool vibration amplitude association matrix is ​​calculated to obtain a sequence of machine tool load-machine tool vibration amplitude association kurtosis values, including: respectively calculating the mean and variance of the machine tool load-machine tool vibration amplitude association matrix to obtain the machine tool load-machine tool vibration amplitude association mean and the machine tool load-machine tool vibration amplitude association variance; calculating the position difference between the machine tool load-machine tool vibration amplitude association matrix and the machine tool load-machine tool vibration amplitude association mean. value to obtain a machine tool load-machine tool vibration amplitude correlation difference matrix; calculate the fourth power of each eigenvalue in the machine tool load-machine tool vibration amplitude correlation difference matrix to obtain a machine tool load-machine tool vibration amplitude correlation modulation difference matrix; calculate the expected value of the machine tool load-machine tool vibration amplitude correlation modulation difference matrix to obtain a machine tool load-machine tool vibration amplitude correlation expected value; divide the machine tool load-machine tool vibration amplitude correlation expected value by the square of the machine tool load-machine tool vibration amplitude correlation variance to obtain the machine tool load-machine tool vibration amplitude correlation kurtosis value.

[0057] More specifically, in an embodiment of the present application, based on each machine tool load-machine tool vibration amplitude associated kurtosis value in the sequence of the machine tool load-machine tool vibration amplitude associated kurtosis value, the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude associated matrix is ​​calculated to obtain the sequence of the machine tool load-machine tool vibration amplitude characteristic interaction energy factor, including: calculating the sum of the machine tool load-machine tool vibration amplitude associated variance and the hyperparameter to obtain the machine tool load-machine tool vibration amplitude associated first energy factor; calculating the machine tool load-machine tool vibration amplitude associated kurtosis value and the machine tool load- The square of the difference between the machine tool vibration amplitude correlation means is calculated to obtain the machine tool load-machine tool vibration amplitude correlation difference value; the value obtained by multiplying the machine tool load-machine tool vibration amplitude correlation variance by constant two and the value obtained by multiplying the hyperparameter by constant two are added to the machine tool load-machine tool vibration amplitude correlation difference value to obtain the machine tool load-machine tool vibration amplitude correlation second energy factor; the machine tool load-machine tool vibration amplitude correlation first energy factor is divided by the machine tool load-machine tool vibration amplitude correlation second energy factor to obtain the machine tool load-machine tool vibration amplitude characteristic interaction energy factor.

[0058] More specifically, in an embodiment of the present application, the sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors is normalized to obtain a sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors, including: inputting the sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors into a Sigmoid function to obtain the sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors.

[0059] In the embodiment of the present application, specifically, the local-global interactive response encoding is performed on the machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector, which can be expressed by the formula:

[0060]

[0061]

[0062]

[0063]

[0064]

[0065]

[0066]

[0067] in, is the time series correlation feature vector of the machine tool vibration amplitude, For fine-grained feature decomposition, are the first, second, ..., first, second, third, fourth, fifth, fifth, sixth, sixth, sixth, seventh ... ,..., The local time series correlation feature vector of the machine tool vibration amplitude, is the number of feature vectors in the sequence of local time series associated feature vectors of the machine tool vibration amplitude, is the machine tool load time series correlation feature vector, and are the multiplication of the machine tool load transformation matrix and the machine tool load offset vector, is the time series correlation feature vector of the machine tool load after the nonlinear transformation, yes The transposed vector of represents vector multiplication, For the A machine tool load-machine tool vibration amplitude correlation matrix between the local time series correlation feature vector of the machine tool vibration amplitude and the machine tool load time series correlation feature vector after the nonlinear transformation, yes The eigenvalues ​​at each position in , yes The mean of To calculate the expected value of a matrix, yes The variance of for The kurtosis value of is a hyperparameter, yes The corresponding machine tool load-machine tool vibration amplitude characteristic interaction energy factor, yes function, yes The corresponding normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factor, It is the point multiplication by position. is the local-global interaction response matrix of the machine tool load-machine tool vibration amplitude.

[0068] In step S150, based on the interactive response characteristics of the machine tool load and the machine tool vibration amplitude, a diagnosis result is obtained and displayed. Specifically, in an embodiment of the present application, based on the interactive response characteristics of the machine tool load and the machine tool vibration amplitude, a diagnosis result is obtained and displayed, including: inputting the local-global interactive response matrix of the machine tool load and the machine tool vibration amplitude into a fault diagnoser based on a classifier to obtain the diagnosis result, and the diagnosis result is used to represent the fault type label; displaying the diagnosis result. That is, the interactive response characteristics of the machine tool load and the machine tool vibration amplitude obtained by interactive response encoding using the machine tool load time series association feature vector and the machine tool vibration amplitude time series association feature vector are classified and processed to automatically obtain the diagnosis result of the fault type label, and the diagnosis result is displayed; by using the voice input module, the user does not need to manually input data, which reduces errors and improves the accuracy of data input. At the same time, the user can receive the status update and fault diagnosis information of the machine tool in real time, so as to respond quickly, avoid equipment damage or production accidents, and realize the intelligent management of CNC machine tools.

[0069] In particular, the present application takes into account that the machine tool load timing correlation feature vector and the machine tool vibration amplitude timing correlation feature vector respectively represent the bidirectional short-range-long-range timing correlation characteristics of the machine tool load and the machine tool vibration amplitude values. Therefore, when the machine tool load-machine tool vibration amplitude interaction response is encoded, the timing correlation feature distribution pattern based on the source timing distribution will also have local-global interaction response differences. Therefore, it is expected to improve the detailed interaction response semantic aggregation expression effect of the machine tool load-machine tool vibration amplitude local-global interaction response matrix based on the association pattern representation difference.

[0070] In a preferred example, inputting the machine tool load-machine tool vibration amplitude local-global interaction response matrix into a classifier-based fault diagnoser to obtain a diagnosis result includes: calculating the sum of the absolute values ​​of each eigenvalue of the machine tool load-machine tool vibration amplitude local-global interaction response matrix to obtain a first machine tool load-machine tool vibration amplitude local-global interaction response and modulation value, and calculating the square root of the sum of the squares of each eigenvalue of the machine tool load-machine tool vibration amplitude local-global interaction response matrix to obtain a second machine tool load-machine tool vibration amplitude local-global interaction response and modulation value; performing dot-wise subtraction of the machine tool load-machine tool vibration amplitude local-global interaction response matrix from the second machine tool load-machine tool vibration amplitude local-global interaction response and modulation value, and then performing dot-wise multiplication with the number of eigenvalues ​​of the machine tool load-machine tool vibration amplitude local-global interaction response matrix and the inverse of the first machine tool load-machine tool vibration amplitude local-global interaction response and modulation value, and taking the inverse of each eigenvalue to obtain the first machine tool load-machine tool vibration amplitude local-global interaction response matrix. amplitude local-global interaction response phase conversion matrix; after point-wise subtraction of the machine tool load-machine tool vibration amplitude local-global interaction response matrix and the first machine tool load-machine tool vibration amplitude local-global interaction response and modulation value, respectively multiply by the square root of the number of eigenvalues ​​of the machine tool load-machine tool vibration amplitude local-global interaction response matrix and the reciprocal of the second machine tool load-machine tool vibration amplitude local-global interaction response and modulation value, and take the reciprocal of each eigenvalue to obtain the second machine tool load-machine tool vibration amplitude local-global interaction response phase conversion matrix; point-wise subtraction of the first machine tool load-machine tool vibration amplitude local-global interaction response phase conversion matrix by the point product matrix of the second machine tool load-machine tool vibration amplitude local-global interaction response phase conversion matrix and the weighted hyperparameter to obtain an optimized machine tool load-machine tool vibration amplitude local-global interaction response matrix; the optimized machine tool load-machine tool vibration amplitude local-global interaction response matrix is ​​input into the classifier-based fault diagnoser to obtain the diagnosis result.

[0071] Specifically, the optimization expression of the machine tool load-machine tool vibration amplitude local-global interaction response matrix is:

[0072]

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079] in, is the local-global interaction response matrix of machine tool load-machine tool vibration amplitude, and denote the width and height of the local-global interaction response matrix of the machine tool load-machine tool vibration amplitude, respectively, R denotes the real number domain, represents the eigenvalue of each position in the local-global interaction response matrix of machine tool load-machine tool vibration amplitude, represents the number of eigenvalues ​​of the machine tool load-machine tool vibration amplitude local-global interaction response matrix, represents the first machine tool load-machine tool vibration amplitude local-global interaction response and modulation value, represents the local-global interaction response and modulation value of the load-machine vibration amplitude of the second machine tool, It means point multiplication by position. It means to subtract by position point. To take the inverse of each eigenvalue in the feature matrix, represents the first machine tool load-machine tool vibration amplitude local-global interaction response phase conversion matrix, represents the second machine tool load-machine tool vibration amplitude local-global interaction response phase conversion matrix, represents the weighted hyperparameter, The optimized machine tool load-machine tool vibration amplitude local-global interaction response matrix is ​​represented.

[0080] In the preferred example, the difference of the difference and modulation representation of the eigenvalue of the machine tool load-machine tool vibration amplitude local-global interaction response matrix relative to the overall feature set of the machine tool load-machine tool vibration amplitude local-global interaction response matrix is ​​used as the semantic change intensity information, and a phase-like transformation corresponding to the position-based intensity modulation is performed through different and modulation representations, so that the aggregation enhancement of semantic change phase perception can improve the axial aggregation receptive field along the feature aggregation direction by performing a spatial translation operation based on alternating stacking under the set scale balance of the machine tool load-machine tool vibration amplitude local-global interaction response matrix, thereby improving the perception effect of the aggregated semantics of the machine tool load-machine tool vibration amplitude local-global interaction response matrix on the detailed semantic changes, so as to improve the expression effect of the machine tool load-machine tool vibration amplitude local-global interaction response matrix, and improve the accuracy of the diagnosis result obtained by inputting it into a fault diagnoser based on a classifier. By utilizing the voice input module, users do not need to manually input data, which reduces errors and improves the accuracy of data input. At the same time, users can receive real-time status updates and fault diagnosis information of machine tools, so as to respond quickly and avoid equipment damage or production accidents, thus realizing intelligent management of CNC machine tools.

[0081] In summary, a human-computer interaction management method for CNC machine tools based on an embodiment of the present application is explained, which obtains a user fault query request through a voice input module, and based on the fault query request, extracts a historical data set of machine tool load and a historical data set of machine tool vibration amplitude value from a data storage device, and uses an artificial intelligence-based data analysis algorithm to perform time series arrangement and association coding of the machine tool load and the machine tool vibration amplitude value, so as to automatically obtain a diagnosis result of a fault type label based on the interactive response information between the machine tool load time series association characteristics and the machine tool vibration amplitude value time series association characteristics, and display the diagnosis result. The voice input module can improve the accuracy of data input, and the user can receive the machine tool fault diagnosis information in real time, which is conducive to realizing the intelligent management of CNC machine tools.

[0082] Figure 7 : is a system block diagram of a human-machine interaction management system for a CNC machine tool according to an embodiment of the present application. Figure 7As shown, according to the embodiment of the present application, the human-computer interaction management system 100 of a numerically controlled machine tool includes: a fault query request data acquisition module 110, which is used to obtain a fault query request input by a user through a voice input module; a machine tool load and machine tool vibration amplitude value historical data set extraction module 120, which is used to extract a historical data set of a machine tool load and a historical data set of a machine tool vibration amplitude value from a data storage device in response to receiving the fault query request; a machine tool load and machine tool vibration amplitude time series feature encoding module 130, which is used to respectively regularize the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value, and then perform time series encoding to obtain a machine tool load time series associated feature vector and a machine tool vibration amplitude time series associated feature vector; a machine tool load and machine tool vibration amplitude interactive response encoding module 140, which is used to encode the machine tool load time series associated feature vector. The machine tool load-machine tool vibration amplitude interactive response encoding is performed on the machine tool load-machine tool vibration amplitude interactive response feature vector and the machine tool vibration amplitude time series associated feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response feature; a diagnosis result generating module 150 is used to obtain a diagnosis result based on the machine tool load-machine tool vibration amplitude interactive response feature and display the diagnosis result; wherein the machine tool load-machine tool vibration amplitude interactive response encoding module includes: a machine tool vibration amplitude time series associated feature decomposition unit, which is used to perform feature fine-grained decomposition on the machine tool vibration amplitude time series associated feature vector to obtain a sequence of machine tool vibration amplitude local time series associated feature vectors; a machine tool load-machine tool vibration amplitude interactive response feature generating unit, which is used to perform local-global interactive response analysis on the sequence of the machine tool load time series associated feature vector and the machine tool vibration amplitude local time series associated feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response feature.

[0083] The specific functions and operations of each unit and module in the above-mentioned CNC machine tool human-machine interaction management system 100 have been referred to above. Figures 1 to 6 The description of the human-computer interaction management method for CNC machine tools has been introduced in detail, and therefore, its repeated description will be omitted.

[0084] In summary, a human-computer interaction management system 100 for CNC machine tools based on an embodiment of the present application is explained, which obtains a user fault query request through a voice input module, and based on the fault query request, extracts a historical data set of machine tool load and a historical data set of machine tool vibration amplitude values ​​from a data storage device, and uses an artificial intelligence-based data analysis algorithm to perform time series arrangement and association coding of the machine tool load and the machine tool vibration amplitude value, thereby automatically obtaining a diagnosis result of a fault type label based on the interactive response information between the machine tool load time series association characteristics and the machine tool vibration amplitude value time series association characteristics, and displays the diagnosis result. The voice input module can improve the accuracy of data input, and the user can receive machine tool fault diagnosis information in real time, which is conducive to realizing the intelligent management of CNC machine tools.

[0085] As described above, the CNC machine tool human-computer interaction management system 100 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server for CNC machine tool human-computer interaction management. In one example, the CNC machine tool human-computer interaction management system 100 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the CNC machine tool human-computer interaction management system 100 can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the CNC machine tool human-computer interaction management system 100 can also be one of the many hardware modules of the wireless terminal.

[0086] Alternatively, in another example, the CNC machine tool human-computer interaction management system 100 and the wireless terminal may also be separate devices, and the CNC machine tool human-computer interaction management system 100 may be connected to the wireless terminal via a wired and / or wireless network and transmit interaction information in accordance with an agreed data format.

[0087] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details of the above application are only for the purpose of illustration and ease of understanding, rather than limitation, and the above details do not limit the present application to the use of the above specific details to be implemented.

Claims

1. A human-machine interactive management method for CNC machine tools, characterized in that: include: The user inputs a fault query request through the voice input module; In response to receiving the fault query request, extracting a historical data set of machine tool load and a historical data set of machine tool vibration amplitude values ​​from a data storage; The historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively regularized to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value, and then time series encoding is performed to obtain a machine tool load time series correlation feature vector and a machine tool vibration amplitude time series correlation feature vector; Performing machine tool load-machine tool vibration amplitude interactive response encoding on the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector to obtain a machine tool load-machine tool vibration amplitude interactive response feature; Obtaining a diagnosis result based on the machine tool load-machine tool vibration amplitude interactive response characteristics, and displaying the diagnosis result; The machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector are subjected to machine tool load-machine tool vibration amplitude interactive response encoding to obtain the machine tool load-machine tool vibration amplitude interactive response feature, including: Performing feature fine-grained decomposition on the time series correlation feature vector of the machine tool vibration amplitude to obtain a sequence of local time series correlation feature vectors of the machine tool vibration amplitude; Performing a local-global interactive response analysis on a sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response feature; Among them, the local-global interactive response coding is performed on the machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector, which is expressed by the formula: in, is the time series correlation feature vector of the machine tool vibration amplitude, For fine-grained feature decomposition, are the first, second, ..., first, second, third, fourth, fifth, fifth, sixth, sixth, sixth, seventh ... ,..., The local time series correlation feature vector of the machine tool vibration amplitude, is the number of feature vectors in the sequence of local time series associated feature vectors of the machine tool vibration amplitude, is the machine tool load time series correlation feature vector, and are respectively the multiplication of the machine tool load transformation matrix and the machine tool load offset vector; wherein, after the machine tool load time series associated characteristic vector is multiplied by the machine tool load transformation matrix, the obtained machine tool load transformation vector and the machine tool load offset vector are added according to the position to obtain the nonlinear transformed machine tool load time series associated characteristic vector, is the time series correlation feature vector of the machine tool load after the nonlinear transformation, yes The transposed vector of represents vector multiplication, For the A machine tool load-machine tool vibration amplitude correlation matrix between the local time series correlation feature vector of the machine tool vibration amplitude and the machine tool load time series correlation feature vector after the nonlinear transformation, yes The eigenvalues ​​at each position in , yes The mean of To calculate the expected value of a matrix, yes The variance of for The kurtosis value of is a hyperparameter, yes The corresponding machine tool load-machine tool vibration amplitude characteristic interaction energy factor, yes function, yes The corresponding normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factor, It is the point multiplication by position. It is a machine tool load-machine tool vibration amplitude local-global interaction response matrix, and the machine tool load-machine tool vibration amplitude local-global interaction response matrix serves as the machine tool load-machine tool vibration amplitude interaction response feature.

2. The human-machine interactive management method for CNC machine tools according to claim 1, characterized in that: The historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value are respectively regularized to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value, and then time series encoding is performed to obtain a time series correlation feature vector of the machine tool load and a time series correlation feature vector of the machine tool vibration amplitude, including: Regularizing the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value in chronological order to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value; The time queue of the machine tool load and the time queue of the machine tool vibration amplitude value are input into a time series encoder based on a Bi-LSTM model to obtain the machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector.

3. The human-machine interactive management method for CNC machine tools according to claim 2, characterized in that: Performing a local-global interactive response analysis on a sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response feature, including: Calculating the correlation matrix between the machine tool load time series correlation feature vector and each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool vibration amplitude local time series correlation feature vector to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices; Calculating the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude correlation matrix in the sequence of machine tool load-machine tool vibration amplitude correlation matrices to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors; Normalizing the sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors to obtain a sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors; Taking the sequence of the normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors as the sequence of weights, the position-weighted sum of the sequence of the machine tool load-machine tool vibration amplitude association matrix is ​​calculated to obtain the machine tool load-machine tool vibration amplitude local-global interaction response matrix as the machine tool load-machine tool vibration amplitude interaction response feature.

4. The human-machine interactive management method for CNC machine tools according to claim 3, characterized in that: Calculating the correlation matrix between each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool load time series correlation feature vector and the machine tool vibration amplitude local time series correlation feature vector to obtain a sequence of machine tool load-machine tool vibration amplitude correlation matrices, including: Performing a nonlinear transformation on the machine tool load time series correlation characteristic vector to obtain a nonlinearly transformed machine tool load time series correlation characteristic vector; The correlation matrix between the machine tool load time series correlation feature vector after the nonlinear transformation and each machine tool vibration amplitude local time series correlation feature vector in the sequence of the machine tool vibration amplitude local time series correlation feature vector is calculated to obtain the sequence of the machine tool load-machine tool vibration amplitude correlation matrix.

5. The human-machine interactive management method for CNC machine tools according to claim 4, characterized in that: Calculating the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude correlation matrix in the sequence of the machine tool load-machine tool vibration amplitude correlation matrix to obtain a sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors, including: Calculating the kurtosis value of each machine tool load-machine tool vibration amplitude correlation matrix in the sequence of machine tool load-machine tool vibration amplitude correlation matrices to obtain a sequence of machine tool load-machine tool vibration amplitude correlation kurtosis values; Based on each machine tool load-machine tool vibration amplitude associated kurtosis value in the sequence of machine tool load-machine tool vibration amplitude associated kurtosis values, the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude associated matrix is ​​calculated to obtain the sequence of the machine tool load-machine tool vibration amplitude characteristic interaction energy factors.

6. The human-machine interactive management method for CNC machine tools according to claim 5, characterized in that: Calculating the kurtosis value of each machine tool load-machine tool vibration amplitude correlation matrix in the sequence of the machine tool load-machine tool vibration amplitude correlation matrix to obtain a sequence of machine tool load-machine tool vibration amplitude correlation kurtosis values, including: Respectively calculating the mean and variance of the machine tool load-machine tool vibration amplitude correlation matrix to obtain the machine tool load-machine tool vibration amplitude correlation mean and the machine tool load-machine tool vibration amplitude correlation variance; Calculating the position difference between the machine tool load-machine tool vibration amplitude correlation matrix and the machine tool load-machine tool vibration amplitude correlation mean to obtain a machine tool load-machine tool vibration amplitude correlation difference matrix; Calculating the fourth power of each eigenvalue in the machine tool load-machine tool vibration amplitude correlation difference matrix to obtain a machine tool load-machine tool vibration amplitude correlation modulation difference matrix; Calculating the expected value of the machine tool load-machine tool vibration amplitude correlation modulation difference matrix to obtain the machine tool load-machine tool vibration amplitude correlation expected value; The machine tool load-machine tool vibration amplitude association expected value is divided by the square of the machine tool load-machine tool vibration amplitude association variance to obtain the machine tool load-machine tool vibration amplitude association kurtosis value.

7. The human-machine interactive management method for CNC machine tools according to claim 6, characterized in that: Based on each machine tool load-machine tool vibration amplitude associated kurtosis value in the sequence of the machine tool load-machine tool vibration amplitude associated kurtosis value, calculating the characteristic interaction energy factor of each machine tool load-machine tool vibration amplitude associated matrix to obtain the sequence of the machine tool load-machine tool vibration amplitude characteristic interaction energy factor, including: Calculating the sum of the machine tool load-machine tool vibration amplitude correlation variance and the hyperparameter to obtain a machine tool load-machine tool vibration amplitude correlation first energy factor; Calculating the square of the difference between the machine tool load-machine tool vibration amplitude correlation kurtosis value and the machine tool load-machine tool vibration amplitude correlation mean value to obtain a machine tool load-machine tool vibration amplitude correlation difference value; Adding a value obtained by multiplying the machine tool load-machine tool vibration amplitude correlation variance by constant 2 and a value obtained by multiplying the hyper parameter by constant 2 to the machine tool load-machine tool vibration amplitude correlation difference value to obtain a machine tool load-machine tool vibration amplitude correlation second energy factor; The first energy factor associated with the machine tool load and the machine tool vibration amplitude is divided by the second energy factor associated with the machine tool load and the machine tool vibration amplitude to obtain the machine tool load and machine tool vibration amplitude characteristic interaction energy factor.

8. The human-machine interactive management method for CNC machine tools according to claim 7, characterized in that: The sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors is normalized to obtain a sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors, including: inputting the sequence of machine tool load-machine tool vibration amplitude characteristic interaction energy factors into a Sigmoid function to obtain the sequence of normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factors.

9. The human-machine interactive management method for CNC machine tools according to claim 8, characterized in that: Based on the machine tool load-machine tool vibration amplitude interactive response characteristics, a diagnosis result is obtained and displayed, including: Inputting the machine tool load-machine tool vibration amplitude local-global interaction response matrix into a classifier-based fault diagnostic device to obtain the diagnosis result, wherein the diagnosis result is used to represent a fault type label; The diagnosis result is displayed.

10. Human-machine interactive management system for CNC machine tools, characterized in that: include: A fault query request data collection module is used to obtain the fault query request input by the user through the voice input module; A machine tool load and machine tool vibration amplitude value historical data set extraction module is used to extract a machine tool load historical data set and a machine tool vibration amplitude value historical data set from a data storage in response to receiving the fault query request; A machine tool load and machine tool vibration amplitude time series feature encoding module is used to perform data regularization on the historical data set of the machine tool load and the historical data set of the machine tool vibration amplitude value to obtain a time queue of the machine tool load and a time queue of the machine tool vibration amplitude value, and then perform time series encoding to obtain a machine tool load time series associated feature vector and a machine tool vibration amplitude time series associated feature vector; A machine tool load-machine tool vibration amplitude interactive response encoding module is used to perform machine tool load-machine tool vibration amplitude interactive response encoding on the machine tool load time series associated feature vector and the machine tool vibration amplitude time series associated feature vector to obtain a machine tool load-machine tool vibration amplitude interactive response feature; A diagnosis result generating module, used for obtaining a diagnosis result based on the machine tool load-machine tool vibration amplitude interactive response characteristics, and displaying the diagnosis result; Wherein, the machine tool load and machine tool vibration amplitude interactive response encoding module includes: A machine tool vibration amplitude time series correlation feature decomposition unit, used for performing feature fine-grained decomposition on the machine tool vibration amplitude time series correlation feature vector to obtain a sequence of machine tool vibration amplitude local time series correlation feature vectors; A machine tool load and machine tool vibration amplitude interactive response feature generating unit is used to perform a local-global interactive response analysis on a sequence of the machine tool load time series associated feature vector and the machine tool vibration amplitude local time series associated feature vector to obtain the machine tool load-machine tool vibration amplitude interactive response feature; Among them, the local-global interactive response coding is performed on the machine tool load time series correlation feature vector and the machine tool vibration amplitude time series correlation feature vector, which is expressed by the formula: in, is the time series correlation feature vector of the machine tool vibration amplitude, For fine-grained feature decomposition, are the first, second, ..., first, second, third, fourth, fifth, fifth, sixth, sixth, sixth, seventh ... ,..., The local time series correlation feature vector of the machine tool vibration amplitude, is the number of feature vectors in the sequence of local time series associated feature vectors of the machine tool vibration amplitude, is the machine tool load time series correlation feature vector, and are respectively the multiplication of the machine tool load transformation matrix and the machine tool load offset vector; wherein, after the machine tool load time series associated characteristic vector is multiplied by the machine tool load transformation matrix, the obtained machine tool load transformation vector and the machine tool load offset vector are added according to the position to obtain the nonlinear transformed machine tool load time series associated characteristic vector, is the time series correlation feature vector of the machine tool load after the nonlinear transformation, yes The transposed vector of represents vector multiplication, For the A machine tool load-machine tool vibration amplitude correlation matrix between the local time series correlation feature vector of the machine tool vibration amplitude and the machine tool load time series correlation feature vector after the nonlinear transformation, yes The eigenvalues ​​at each position in , yes The mean of To calculate the expected value of a matrix, yes The variance of for The kurtosis value of is a hyperparameter, yes The corresponding machine tool load-machine tool vibration amplitude characteristic interaction energy factor, yes function, yes The corresponding normalized machine tool load-machine tool vibration amplitude characteristic interaction energy factor, It is the point multiplication by position. It is a machine tool load-machine tool vibration amplitude local-global interaction response matrix, and the machine tool load-machine tool vibration amplitude local-global interaction response matrix serves as the machine tool load-machine tool vibration amplitude interaction response feature.

Images