Numerical control program control operation method and system

Abstract

The invention discloses a numerical control program control operation method and system, and relates to the technical field of numerical control program control, and the method comprises the steps: installing a multi-mode sensor network to collect numerical control machine tool program control data in real time, and generating a numerical control machine tool program preliminary control optimization strategy; predicting the fault probability of the numerical control machine tool program based on real-time collected numerical control machine tool program control data; adjusting and controlling the operation of the numerical control machine tool program based on the preliminary control optimization strategy and the predicted fault probability; and constructing an AR interface to display an operation interface in real time, and storing, collecting and analyzing generated numerical control machine tool program data. According to the method, the preliminary control optimization strategy of the numerical control machine tool program is generated, the fault probability of the numerical control machine tool program is predicted, the operation of the numerical control machine tool program is adjusted and controlled, and the operation performance and reliability of the numerical control program control tool are remarkably improved; and a visual operation interface and real-time feedback are provided through a prediction model and an augmented reality (AR) technology.

Description

Technical Field

[0001] The present invention relates to the technical field of numerical control program control, in particular to a numerical control program control operation method and system. Background Art

[0002] In modern manufacturing, the application of CNC program-controlled machine tools is crucial. They achieve high-precision and high-efficiency processing by precisely controlling the position and speed of cutting tools. Traditional CNC machine tool program control mainly relies on pre-set programs and manual adjustments. Although this method has achieved remarkable results in the early days, its flexibility and adaptability are obviously insufficient when facing complex processing tasks and dynamically changing working environments. The integration of multi-mode sensor technology and data analysis technology provides new solutions for the intelligent management and optimized control of CNC machine tools. Multi-mode sensors can monitor multiple operating parameters of CNC machine tools in real time, such as operating environment, program execution status and mechanical condition. These data are crucial for optimizing machine tool performance and preventive maintenance.

[0003] Although existing technologies have made certain progress in the application of multi-mode sensors and data processing, there are still many shortcomings. Traditional CNC machine tool program control methods lack effective use of real-time data and cannot achieve dynamic adaptation to complex operating environments. Existing control strategies mostly rely on the experience of operators and lack systematic optimization methods, resulting in control accuracy and efficiency that are difficult to meet the high requirements of modern manufacturing, and the inability to achieve data-driven decision making. Although some systems attempt to predict machine tool failures through simple predictive models, these models are often not accurate because they do not fully utilize the complexity of historical operating data, and cannot meet the needs of high reliability and precise control in industrial applications. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing numerical control program control operation method and system, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the traditional CNC machine tool program control method lacks effective utilization of real-time data and cannot achieve dynamic adaptation to complex operating environments. The existing control strategies mostly rely on the experience of operators and lack systematic optimization methods, resulting in control accuracy and efficiency that are difficult to meet the high requirements of modern manufacturing industries, and cannot achieve data-driven decision making.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a CNC program control operation method, which includes installing a multi-mode sensor network to collect CNC machine program control data in real time, generating a preliminary control optimization strategy for the CNC machine program, and predicting the failure probability of the CNC machine program based on the real-time collection of CNC machine program control data; adjusting and controlling the operation of the CNC machine program based on the preliminary control optimization strategy and the predicted failure probability; constructing an AR interface to display the operation interface in real time, and storing, collecting and analyzing the generated CNC machine program data.

[0007] As a preferred solution of the numerical control program control operation method of the present invention, wherein: the installation of a multi-mode sensor network to collect machine tool program data in real time refers to installing a multi-mode sensor on the operation panel to collect the operation data of the machine tool numerical control program in real time, including program operation log, operation command status, communication status and the operation environment of the numerical control program controlled machine tool;

[0008] Unify the timestamps of the collected data;

[0009] Collect historical operation data and importance survey questionnaires of machine tool CNC programs;

[0010] Formulate a square judgment matrix C, where the rows and columns of the matrix correspond to the same data dimension;

[0011] The comparison criteria are set as follows: 1 represents that both dimensions are equally important, 9 represents that one dimension is extremely more important than the other, and 2 to 8 fill in the middle values ​​to compare the dimensions;

[0012] Fill in the matrix based on the importance survey questionnaire;

[0013] Use the hierarchical analysis method AHP to normalize the filled matrix B, calculate the average value of each row of the normalized matrix, and obtain the weight of the evaluation dimension:

[0014] The formula for the normalized matrix B is:

[0015]

[0016] in is the importance of the i-th dimension relative to the l-th dimension after normalization, is the importance of the i-th dimension relative to the l-th dimension,

[0017] The corresponding weights of historical operation data integrity I, accuracy A and noise level N on the total data quality are calculated by taking the average value of each row of the normalized matrix B , and , the formula is:

[0018]

[0019] in is the weight of the rth dimension;

[0020] Calculate quality scores for historical operational data , the formula is:

[0021]

[0022] The weights are assigned according to the results of the comprehensive quality score, and the formula is:

[0023]

[0024] in is the weight of the u-th sensor, is the quality score of the jth historical operation data, is the comprehensive quality score of the vth historical operation data, V is the number of historical operation data;

[0025] The data is weighted averaged according to the adjusted weights and integrated into comprehensive CNC machine tool program operation data. The formula is:

[0026]

[0027] in is the fused CNC machine program operation data, U is the total number of sensors, is the weight of the multimodal sensor u, is the data of the u-th sensor;

[0028] Extract fused CNC machine tool program control data using principal component analysis (PCA) Features F.

[0029] As a preferred solution of the CNC program control operation method of the present invention, wherein: the generating of the preliminary control optimization strategy of the CNC machine tool program refers to collecting the historical operation data of the CNC machine tool program for cleaning, removing outliers and standardizing, and using the principal component analysis PCA method to extract the characteristics of the historical operation data of the CNC machine tool program Generate model training set;

[0030] The input layer format of the linear regression model is set as the features of the data, and the output layer output is the decision of the CNC machine tool program control;

[0031] Use the model training set to train the linear regression model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0032] The linear regression model formula is:

[0033]

[0034] Where a is the decision of CNC machine tool program control, is the linear regression coefficient, F is the eigenvector of the data, is the error term;

[0035] The fused CNC machine tool program operation data The feature F is input into the trained linear regression model to generate the optimal control decision a;

[0036] The control decisions and strategies in the standardized historical operation data of the CNC machine tool program are input into the linear regression analysis formula, and the parameters m and z are determined using the least squares method;

[0037] The linear regression analysis formula is:

[0038]

[0039] According to the generated optimal control decision a, the initial control optimization strategy Z of the CNC machine tool program is obtained by inputting it into the linear regression analysis formula.

[0040] As a preferred solution of the CNC program control operation method of the present invention, wherein: the prediction of the failure probability of the CNC machine tool program based on real-time collection of CNC machine tool program control refers to collecting historical CNC machine tool program operation failure data for cleaning and formatting, removing noise and outliers, and using statistical methods to extract failure characteristics Generate a fault dataset;

[0041] Input the fault data set into the logistic regression model for model training to predict the failure probability of the CNC machine tool program , the formula is:

[0042]

[0043] in are the logistic regression model parameters, Extracting features for historical CNC machine program operation fault data;

[0044] Optimize model parameters using a cross-validation approach using a failure dataset;

[0045] After fusion, the CNC machine tool program control data The feature F is input into the trained logistic regression model to predict the failure probability of the CNC machine tool program ;

[0046] The threshold Q is set based on the historical CNC machine tool program control fault data. If the failure probability of the CNC machine tool program When the threshold Q is reached, an alarm is automatically triggered and the operator is notified via SMS. When it is less than the threshold Q, the monitoring continues;

[0047] Use the scheduling function in the operation and maintenance management software, combined with the prediction of the probability of CNC machine tool program failure Output, automatically recommend maintenance time.

[0048] As a preferred solution of the CNC program control operation method of the present invention, wherein: the adjustment and control of the CNC machine tool program operation based on the preliminary control optimization strategy and the predicted fault probability refers to designing an adaptive controller through the preliminary control optimization strategy Z and the fault probability Results Dynamic adjustment of CNC machine tool program parameters;

[0049] Implement parameter adjustment formula to update CNC machine program parameters:

[0050]

[0051] in For the adjusted CNC machine tool program parameters, is the learning rate, For the historical CNC machine program parameters, For the optimal control strategy for CNC machine tool program parameters The gradient of The failure probability For CNC machine program parameters gradient.

[0052] As a preferred solution of the numerical control program control operation method of the present invention, wherein: the construction of an AR interface to display the operation interface in real time refers to using a head-mounted display device Microsoft HoloLens to construct an AR interface to display the data, control strategy, and operation guide of the numerical control machine tool program operation in real time;

[0053] Train operators to use the AR interface according to the operating instructions;

[0054] A pop-up window is designed on the AR interface, and the operator uses voice commands through the AR interface to adjust the CNC machine tool program parameters and update the display information on the AR interface at the same time.

[0055] As a preferred solution of the numerical control program control operation method of the present invention, wherein: the storing, collecting and analyzing the numerical control machine program data refers to sorting and storing the collected numerical control machine program control data, optimization strategy, and the results predicted by the logistic regression model in a database according to timestamps, and setting security access measures, and the database backs up the stored data in the cloud;

[0056] The operator queries the CNC machine program operation data and CNC machine program parameters through the database.

[0057] Another object of the present invention is to provide a numerical control program control operation system, which comprises:

[0058] A collection optimization module is used to install a multi-mode sensor network to collect CNC machine tool program operation data in real time and generate a preliminary control optimization strategy for the CNC machine tool program;

[0059] A fault prediction module is used to collect CNC machine tool program control data in real time to predict the fault probability of the CNC machine tool program;

[0060] Adaptive adjustment module, which adjusts and controls the CNC machine tool program operation based on the preliminary control optimization strategy and predicted failure probability;

[0061] The visualization storage module is used to build an AR interface to display the operation interface in real time, to display the operation data and control strategy of the CNC machine tool program control in real time, and to store, collect and analyze the generated CNC machine tool program data.

[0062] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned numerical control program control operation method when executing the computer program.

[0063] A computer-readable storage medium stores a computer program, which implements the steps of the numerical control program control operation method when executed by a processor.

[0064] The beneficial effects of the present invention are as follows: the present invention collects CNC machine program control data in real time by installing a multi-mode sensor network, generates a preliminary control optimization strategy for the CNC machine program, predicts the failure probability of the CNC machine program, and adjusts and controls the operation of the CNC machine program, thereby significantly improving the operational performance and reliability of the CNC program control operation. It can not only significantly improve the processing accuracy and adaptability of the CNC program control operation, but also provide an intuitive operating interface and real-time feedback through predictive models and augmented reality AR technology, thereby further improving operational efficiency and maintenance convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0066] Figure 1 The figure is a flow chart of the numerical control program control operation method.

[0067] Figure 2 The figure is a schematic diagram of the operation flow of the numerical control program control operation method.

[0068] Figure 3 This is a module diagram of the CNC program control operation system. DETAILED DESCRIPTION

[0069] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0070] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0071] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0072] Example 1

[0073] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and which provides a numerical control program control operation method, the numerical control program control operation method comprising:

[0074] S1. Install a multi-mode sensor network to collect CNC machine tool program control data in real time, generate a preliminary control optimization strategy for the CNC machine tool program, and predict the failure probability of the CNC machine tool program based on the real-time collection of CNC machine tool program control data;

[0075] Specifically, installing a multi-mode sensor network to collect machine tool program data in real time refers to installing a multi-mode sensor on an operation panel to collect operation data of a machine tool CNC program in real time, including program operation logs, operation command status, communication status, and an operation environment of a CNC program controlling a machine tool;

[0076] Unify the timestamps of the collected data;

[0077] Collect historical operation data and importance survey questionnaires of machine tool CNC programs;

[0078] Formulate a square judgment matrix C, where the rows and columns of the matrix correspond to the same data dimension;

[0079] The comparison criteria are set as follows: 1 represents that both dimensions are equally important, 9 represents that one dimension is extremely more important than the other, and 2 to 8 fill in the middle values ​​to compare the dimensions;

[0080] Fill in the matrix based on the importance survey questionnaire;

[0081] Use the hierarchical analysis method AHP to normalize the filled matrix B, calculate the average value of each row of the normalized matrix, and obtain the weight of the evaluation dimension:

[0082] The formula for the normalized matrix B is:

[0083]

[0084] in is the normalized importance of the ith dimension relative to the lth dimension, obtained from the importance survey questionnaire, is the importance of the i-th dimension relative to the l-th dimension,

[0085] The corresponding weights of historical operation data integrity I, accuracy A and noise level N on the total data quality are calculated by taking the average value of each row of the normalized matrix B , and , the formula is:

[0086]

[0087] in is the weight of the rth dimension;

[0088] Calculate quality scores for historical operational data , the formula is:

[0089]

[0090] The weights are assigned according to the results of the comprehensive quality score, and the formula is:

[0091]

[0092] in is the weight of the u-th sensor, is the quality score of the jth historical operation data, is the comprehensive quality score of the vth historical operation data, V is the number of historical operation data;

[0093] The data is weighted averaged according to the adjusted weights and integrated into comprehensive CNC machine tool program operation data. The formula is:

[0094]

[0095] in is the fused CNC machine program operation data, U is the total number of sensors, is the weight of the multimodal sensor u, is the data of the u-th sensor;

[0096] Extract fused CNC machine tool program control data using principal component analysis (PCA) Features F.

[0097] The data collected by the multi-mode sensor network is equipped with a unified timestamp, so that each piece of data can accurately reflect the time point when it is generated. This is crucial for the response speed of the real-time monitoring system and the accuracy of data analysis. The use of timestamps not only improves the temporal nature of the data, but also provides the possibility for subsequent data synchronization and historical data comparative analysis. Through the importance survey questionnaire and judgment matrix method, the quality of different data dimensions, such as completeness, accuracy and noise level, can be accurately evaluated and compared. This evaluation helps to identify key issues in data processing, improve data quality by improving data acquisition and processing strategies, thereby improving the reliability and effectiveness of the entire control system. By weighted averaging the data with adjusted weights, data from different sensors can be effectively integrated to improve the representativeness and accuracy of the data. The features extracted using PCA provide a scientific basis for the program control of CNC machine tools, making the control strategy more accurate and effective, especially when dealing with complex operating environments, which can significantly improve the operating performance and safety of machine tools.

[0098] Furthermore, generating a preliminary control optimization strategy for CNC machine tool programs involves collecting historical operation data of CNC machine tool programs for cleaning, removing outliers and standardizing them, and using principal component analysis (PCA) to extract the features of historical operation data of CNC machine tool programs. Generate model training set;

[0099] The input layer format of the linear regression model is set as the features of the data, and the output layer output is the decision of the CNC machine tool program control;

[0100] Use the model training set to train the linear regression model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0101] The linear regression model formula is:

[0102]

[0103] Where a is the decision of CNC machine tool program control, is the linear regression coefficient, the contribution of each feature to the control decision, F is the feature vector of the data, is the error term;

[0104] The fused CNC machine tool program operation data The feature F is input into the trained linear regression model to generate the optimal control decision a;

[0105] The control decisions and strategies in the standardized historical operation data of the CNC machine tool program are input into the linear regression analysis formula, and the parameters m and z are determined using the least squares method;

[0106] The linear regression analysis formula is:

[0107]

[0108] According to the generated optimal control decision a, the linear regression analysis formula is input to obtain the preliminary control optimization strategy Z of the CNC machine tool program.

[0109] In the process of generating the preliminary control optimization strategy for CNC machine tool programs, the historical operation data is first cleaned and standardized. This step can effectively remove outliers and noise in the data and ensure the quality and consistency of the input data. The standardization process further eliminates the dimensional differences between different features, making the subsequent feature extraction and model training more accurate and reliable. This not only improves the accuracy of data analysis, but also provides a high-quality data foundation for model training. The PCA method is used to extract features from the historical operation data of CNC machine tool programs to generate a model training set. PCA retains the main information in the data and reduces the redundancy and noise of the data through dimensionality reduction processing. This not only reduces the complexity of the model and improves the training efficiency, but also enhances the generalization ability of the model, enabling it to have better prediction effects when processing new data. When establishing a linear regression model, the features extracted by PCA are used as The input is the decision of CNC machine tool program control, and the output is the decision of CNC machine tool program control. By using the model training set to train the linear regression model, the linear relationship between the features and the control decisions can be learned. This step ensures that the model can generate reasonable control decisions based on the input data, and provides a scientific basis for the optimization of CNC machine tool programs. The features of the fused CNC machine tool program operation data are input into the trained linear regression model to generate the optimal control decision. This decision is based on high-quality historical data and optimized models, and can provide accurate and reliable control strategies, significantly improving the operating efficiency and stability of CNC machine tools. The control decisions and strategies in the standardized CNC machine tool program historical operation data are input into the linear regression analysis formula, and the model parameters are determined using the least squares method. This step ensures the accuracy and effectiveness of the model parameters, and provides a solid mathematical foundation for generating preliminary control optimization strategies.

[0110] Furthermore, based on real-time collection of CNC machine program control, the prediction of the failure probability of CNC machine program refers to collecting historical CNC machine program operation failure data for cleaning and formatting, removing noise and outliers, and using statistical methods to extract failure characteristics. Generate a fault dataset;

[0111] Input the fault data set into the logistic regression model for model training to predict the fault probability of the CNC machine tool program , the formula is:

[0112]

[0113] in are the logistic regression model parameters, Extracting features for historical CNC machine program operation fault data;

[0114] Optimize model parameters using cross-validation method using failure dataset;

[0115] After fusion, the CNC machine tool program control data The feature F is input into the trained logistic regression model to predict the failure probability of the CNC machine tool program ;

[0116] The threshold Q is set based on the historical CNC machine tool program control fault data. If the failure probability of the CNC machine tool program When the threshold Q is reached, an alarm is automatically triggered and the operator is notified via SMS. When it is less than the threshold Q, monitoring continues;

[0117] Use the scheduling function in the operation and maintenance management software, combined with the prediction of the probability of CNC machine tool program failure Output, automatically recommend maintenance time.

[0118] The historical operation fault data is cleaned and formatted. This step can effectively remove noise and outliers in the data and ensure the quality and consistency of the input data. The cleaning and formatting process improves the credibility of the data and provides a reliable basis for subsequent feature extraction and model training. Statistical methods are used to extract fault features from the cleaned data to generate a fault data set. By extracting these key features, meaningful data input can be provided for the model to enhance the model's prediction ability and accuracy. The generated fault data set is input into the logistic regression model for training. By learning the fault modes in the historical data, a fault prediction model is established. The features of the fused CNC machine tool program control data are input into the trained logistic regression model to predict the failure probability of the CNC machine tool program in real time. This step can monitor the operating status of the CNC machine tool in real time during its operation and predict possible failures. The real-time early warning mechanism can promptly remind operators to pay attention to potential failures and take necessary maintenance measures to reduce downtime and maintenance costs caused by equipment failures. Through this intelligent maintenance schedule, the maintenance plan of the equipment can be optimized to avoid excessive or insufficient maintenance and improve the use efficiency and life of the equipment.

[0119] S2, adjusting and controlling the CNC machine tool program operation based on the preliminary control optimization strategy and predicted failure probability;

[0120] Specifically, adjusting the control of the CNC machine tool program operation based on the preliminary control optimization strategy and the predicted fault probability refers to designing an adaptive controller based on the preliminary control optimization strategy Z and the fault probability Results Dynamic adjustment of CNC machine tool program parameters;

[0121] Implement parameter adjustment formula to update CNC machine program parameters:

[0122]

[0123] in For the adjusted CNC machine tool program parameters, is the learning rate, For the historical CNC machine program parameters, For the optimal control strategy for CNC machine tool program parameters The gradient of The failure probability For CNC machine program parameters gradient.

[0124] Based on the preliminary control optimization strategy A, the program parameters of the CNC machine tool are adjusted. Through the analysis of historical operation data and model training, the optimization strategy obtained can effectively improve the operating efficiency and accuracy of the CNC machine tool. The application of this optimization strategy can reduce the errors of the CNC machine tool in the processing process, improve product quality, and reduce energy consumption and material waste. By predicting the failure probability of the CNC machine tool program, potential failure risks can be identified in advance, and preventive adjustments can be made before the failure occurs. Parameter adjustment based on the failure probability results can significantly improve the reliability of the CNC machine tool, reduce downtime and maintenance costs. This dynamic adjustment method based on failure probability enables the CNC machine tool to maintain stability in a complex and changing environment. The design of the adaptive controller is the core of the present invention. By real-time monitoring and analysis of the operating data of the CNC machine tool, the control parameters are automatically adjusted to ensure that the CNC machine tool always runs in the optimal state. The adaptive controller can adjust the parameters autonomously according to the actual operating conditions, reducing the dependence on manual intervention, and improving the degree of automation and work efficiency. Through the synergistic effect of the above key steps, the present invention not only improves the operating efficiency, accuracy and reliability of the CNC machine tool, but also significantly reduces the failure rate and maintenance cost of the equipment. The adaptive controller combines the preliminary control optimization strategy and the fault probability prediction, which not only improves the intelligence level of the CNC machine tool, but also provides advanced technical support for the automation and intelligent development of the manufacturing industry.

[0125] S3, build an AR interface to display the operation interface in real time, store the CNC machine program data generated by the collection and analysis;

[0126] Furthermore, constructing an AR interface to display an operation interface in real time refers to using a head mounted display device Microsoft HoloLens to construct an AR interface to display data, control strategies, and operation guides of CNC machine tool program operations in real time;

[0127] Train operators to use the AR interface according to the operating instructions;

[0128] A pop-up window is designed on the AR interface, and the operator uses voice commands through the AR interface to adjust the CNC machine tool program parameters and update the display information on the AR interface at the same time.

[0129] Using Microsoft HoloLens to build an AR interface, the operating data, control strategy and operation guide of the CNC machine tool program can be displayed in front of the operator in the form of a holographic image. This intuitive display method can help the operator better understand and master the operation process of the CNC machine tool and improve the accuracy and efficiency of the operation. The AR interface can update the operating status of the CNC machine tool in real time and provide dynamic operation feedback, so that the operator can promptly discover and deal with potential problems. Designing pop-up windows on the AR interface can provide the operator with important information prompts and operation suggestions. These pop-up windows can give corresponding feedback and guidance in time according to the operating status of the CNC machine tool and the operator's operating behavior, helping the operator to make correct operation decisions and reduce the occurrence of operation errors and accidents. The operator does not need to manually operate the interface, but only needs to complete the parameter adjustment through voice input commands, which not only reduces the operation steps and time, but also provides a more flexible and efficient operation method when the operator's hands are busy. The real-time update function keeps the information on the operation interface up to date and accurate, providing a reliable operation basis for the operator and improving the accuracy and safety of the operation.

[0130] Furthermore, storing the CNC machine tool program data generated by the collection and analysis means storing the collected CNC machine tool program control data, optimization strategies, and the results predicted by the logistic regression model in a database in order according to timestamps, and setting security access measures, and the database will store the data for cloud backup;

[0131] The operator queries the CNC machine program operation data and CNC machine program parameters through the database.

[0132] The collected CNC machine program control data, optimization strategies and logistic regression model prediction results are sorted by timestamp and stored in the database. This process ensures the systematic and temporal nature of the data. The use of timestamps enables each piece of data to accurately reflect the time point when it is generated or modified, providing a reliable temporal basis for subsequent data analysis and processing. By systematically storing data, historical data can be easily traced back and trend analyzed, which improves the efficiency and scientificity of data management. Operators can query CNC machine program operation data and CNC machine program parameters through the database to easily obtain the required information. This centralized data management method greatly facilitates data storage, retrieval and analysis, and improves the convenience and efficiency of operations. The use of databases can also realize hierarchical management and authority control of data, ensuring the security and compliance of data access. Backing up data in the database in the cloud can effectively prevent data loss and provide data recovery support.

[0133] Example 2

[0134] Reference Figure 3 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a numerical control program control operation system, which includes:

[0135] A collection optimization module is used to install a multi-mode sensor network to collect CNC machine tool program operation data in real time and generate a preliminary control optimization strategy for the CNC machine tool program;

[0136] A fault prediction module is used to collect CNC machine tool program control data in real time to predict the fault probability of the CNC machine tool program;

[0137] Adaptive adjustment module, which adjusts and controls the CNC machine tool program operation based on the preliminary control optimization strategy and predicted failure probability;

[0138] The visualization storage module is used to build an AR interface to display the operation interface in real time, to display the operation data and control strategy of the CNC machine tool program control in real time, and to store, collect and analyze the generated CNC machine tool program data.

[0139] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0140] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0141] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0142] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A numerical control program control operation method, characterized in that: include, Install a multi-mode sensor network to collect CNC machine tool program control data in real time, generate a preliminary control optimization strategy for the CNC machine tool program, and predict the failure probability of the CNC machine tool program based on the real-time collection of CNC machine tool program control data; Adjust the control of CNC machine tool program operation based on preliminary control optimization strategy and predicted failure probability; Build an AR interface to display the operation interface in real time, and store, collect and analyze the generated CNC machine program data.

2. The numerical control program control operation method according to claim 1, characterized in that: The installation of a multi-mode sensor network to collect machine tool program data in real time refers to installing a multi-mode sensor on the operation panel to collect the operation data of the machine tool CNC program in real time, including program running logs, operation command status, communication status, and the operation environment of the CNC program controlling the machine tool; Unify the timestamps of the collected data; Collect historical operation data and importance survey questionnaires of machine tool CNC programs; Formulate a square judgment matrix C, where the rows and columns of the matrix correspond to the same data dimension; The comparison criteria are set as follows: 1 represents that both dimensions are equally important, 9 represents that one dimension is extremely more important than the other, and 2 to 8 fill in the middle values ​​to compare the dimensions; Fill in the matrix based on the importance survey questionnaire; Use the hierarchical analysis method AHP to normalize the filled matrix B, calculate the average value of each row of the normalized matrix, and obtain the weight of the evaluation dimension: The formula for the normalized matrix B is: ， in is the importance of the i-th dimension relative to the l-th dimension after normalization, is the importance of the i-th dimension relative to the l-th dimension, The corresponding weights of historical operation data integrity I, accuracy A and noise level N on the total data quality are calculated by taking the average value of each row of the normalized matrix B , and , the formula is: ， in is the weight of the rth dimension; Calculate quality scores for historical operational data , the formula is: ； The weights are assigned according to the results of the comprehensive quality score, and the formula is: ， in is the weight of the u-th sensor, is the quality score of the jth historical operation data, is the comprehensive quality score of the vth historical operation data, V is the number of historical operation data; The data is weighted averaged according to the adjusted weights and integrated into comprehensive CNC machine tool program operation data. The formula is: ， in is the fused CNC machine program operation data, U is the total number of sensors, is the weight of the multimodal sensor u, is the data of the u-th sensor; Extract fused CNC machine tool program control data using principal component analysis (PCA) Features F.

3. The numerical control program control operation method according to claim 2, characterized in that: The generation of the preliminary control optimization strategy for the CNC machine tool program refers to collecting the historical operation data of the CNC machine tool program for cleaning, removing outliers and standardizing, and using the principal component analysis (PCA) method to extract the characteristics of the historical operation data of the CNC machine tool program. Generate model training set; The input layer format of the linear regression model is set as the features of the data, and the output layer output is the decision of the CNC machine tool program control; Use the model training set to train the linear regression model, and use the loss function and Adam optimizer to iteratively optimize the model parameters; The linear regression model formula is: ， Where a is the decision of CNC machine tool program control, is the linear regression coefficient, (the contribution of each feature to the control decision) F is the feature vector of the data, is the error term; The fused CNC machine tool program operation data The feature F is input into the trained linear regression model to generate the optimal control decision a; The control decisions and strategies in the standardized historical operation data of the CNC machine tool program are input into the linear regression analysis formula, and the parameters m and z are determined using the least squares method; The linear regression analysis formula is: ， According to the generated optimal control decision a, the linear regression analysis formula is input to obtain the preliminary control optimization strategy Z of the CNC machine tool program.

4. The numerical control program control operation method according to claim 3, characterized in that: The prediction of the failure probability of a CNC machine tool program based on real-time collection of CNC machine tool program control refers to collecting historical CNC machine tool program operation failure data for cleaning and formatting, removing noise and outliers, and using statistical methods to extract failure features. Generate a fault dataset; Input the fault data set into the logistic regression model for model training to predict the fault probability of the CNC machine tool program , the formula is: ， in are the logistic regression model parameters, Extracting features for historical CNC machine program operation fault data; Optimize model parameters using a cross-validation approach using a failure dataset; After fusion, the CNC machine tool program control data The feature F is input into the trained logistic regression model to predict the failure probability of the CNC machine tool program ; The threshold Q is set based on the historical CNC machine tool program control fault data. If the failure probability of the CNC machine tool program When the threshold Q is reached, an alarm is automatically triggered and the operator is notified via SMS. When it is less than the threshold Q, the monitoring continues; Use the scheduling function in the operation and maintenance management software, combined with the prediction of the probability of CNC machine tool program failure Output, automatically recommend maintenance time.

5. The numerical control program control operation method according to claim 4, characterized in that: The method of adjusting and controlling the operation of the CNC machine tool program based on the preliminary control optimization strategy and the predicted fault probability refers to designing an adaptive controller based on the preliminary control optimization strategy Z and the fault probability Results Dynamic adjustment of CNC machine tool program parameters; Implement parameter adjustment formula to update CNC machine program parameters: ， in For the adjusted CNC machine tool program parameters, is the learning rate, For the historical CNC machine program parameters, For the optimal control strategy for CNC machine tool program parameters The gradient of The failure probability For CNC machine program parameters gradient.

6. The numerical control program control operation method according to claim 5, characterized in that: The construction of an AR interface to display the operation interface in real time refers to using a head mounted display device Microsoft HoloLens to construct an AR interface to display the data, control strategy, and operation guide of the CNC machine tool program operation in real time; Train operators to use the AR interface according to the operating instructions; A pop-up window is designed on the AR interface, and the operator uses voice commands through the AR interface to adjust the CNC machine tool program parameters and update the display information on the AR interface at the same time.

7. The numerical control program control operation method according to claim 6, characterized in that: The storing, collecting and analyzing the generated CNC machine tool program data refers to collecting the CNC machine tool program control data, optimization strategies, and the results predicted by the logistic regression model, sorting them according to timestamps and storing them in a database, and setting security access measures. The database will store the data for cloud backup; The operator queries the CNC machine program operation data and CNC machine program parameters through the database.

8. A numerical control program control operation system based on the numerical control program control operation method according to any one of claims 1 to 7, characterized in that: include, A collection optimization module is used to install a multi-mode sensor network to collect CNC machine tool program operation data in real time and generate a preliminary control optimization strategy for the CNC machine tool program; A fault prediction module is used to collect CNC machine tool program control data in real time to predict the fault probability of the CNC machine tool program; Adaptive adjustment module, which adjusts and controls the CNC machine tool program operation based on the preliminary control optimization strategy and predicted failure probability; The visualization storage module is used to build an AR interface to display the operation interface in real time, to display the operation data and control strategy of the CNC machine tool program control in real time, and to store, collect and analyze the generated CNC machine tool program data.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the numerical control program control operation method described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the numerical control program control operation method described in any one of claims 1 to 7 are implemented.

Images