Industrial control data abnormity self-learning detection system based on neural network

Abstract

The invention relates to the field of self-learning detection, in particular to an industrial control data anomaly self-learning detection system based on a neural network, which comprises a continuous command module used for sending an operation command to an industrial control system at preset time intervals, a data collection module used for collecting real-time industrial control data of the industrial control system, and an anomaly prediction module. The learning module is used for selecting a plurality of learning features, preprocessing the real-time industrial control data, learning the industrial control preprocessed data by utilizing a neural network model and generating a corresponding abnormal possibility prediction map, and the fault regulation module is used for comparing a possibility numerical value in the abnormal possibility prediction map with an abnormal possibility threshold value and generating an abnormal possibility prediction result. When the fault adjusting module judges that the industrial control data is abnormal, the abnormal shaft of the machine tool is positioned, full-process automation from data collection to anomaly detection and fault positioning is achieved, the anomaly detection precision and efficiency are improved, the detection model is continuously optimized through the self-learning function, and the system adapts to dynamic changes of an industrial control system.

Description

Technical Field

[0001] The present invention relates to the field of self-learning detection, and in particular to a self-learning detection system for abnormal industrial control data based on a neural network. Background Art

[0002] Industrial control systems are systems used to monitor and manage physical equipment and processes in industrial environments. They are widely used in manufacturing, energy, chemical industry, transportation and other fields. These systems usually include programmable logic controllers (PLC), distributed control systems (DCS), supervisory control and data acquisition systems (SCADA), etc. With the rapid development of industrial automation and informatization, the complexity and scale of industrial control systems are increasing, and higher requirements are placed on the reliability and security of the systems. With the rapid development of industrial automation and informatization, the complexity and scale of industrial control systems are increasing, and traditional anomaly detection methods can no longer meet the needs of modern industrial production. The industrial control data anomaly self-learning detection system based on neural networks came into being. Through the advantages of self-learning ability and nonlinear modeling, it can monitor and automatically detect anomalies in industrial control systems in real time, and improve the reliability, safety and production efficiency of the system.

[0003] China Patent Authorization Announcement No.: CN107370732B discloses an abnormal behavior detection system for industrial control systems based on neural networks and optimal recommendations. It analyzes the flow data of industrial control systems, reduces the dimensionality of high-dimensional data in industrial control systems, deletes irrelevant attributes and removes redundant attributes, and dynamically selects intrusion features while following the inherent connection between real input and output samples. The system models the flow data detected in different scenarios, compares the sample flow with the flow after successful modeling to detect the difference between the characteristics of the measured flow data and the normal flow characteristics, and discovers abnormal flow. Based on the optimal recommendation theory, the invention compares and mines the flow scenarios, establishes the optimal recommendation model for malicious flow (scenario), and uses cloud computing technology to design and implement the malicious attack behavior discovery and detection function of customized industrial control equipment and systems based on cloud platforms.

[0004] China Patent Authorization Announcement No.: CN115081585B discloses a human-machine-object collaborative abnormal state detection method of strengthening heterogeneous graph neural network, including collecting data from multiple sensor measurement and control systems on intelligent production lines in industrial production to form raw data for state detection; determining the association between multi-source heterogeneous raw data, establishing a heterogeneous information network graph, using the strengthening graph neural network for representation learning and classification, and obtaining an abnormal state detection discriminator; automatically exploring the meta-structure, performing information aggregation based on the meta-structure, and realizing abnormal state detection. This invention is to ensure the production safety of workshop employees, realize the full-cycle monitoring and timely maintenance of production line equipment and assembly products, and the full-cycle monitoring and timely maintenance of production line equipment and assembly products. It can synchronously detect the human-machine-object collaborative abnormal state detection method of multi-source heterogeneous data, thereby meeting the monitoring needs of the production line data life cycle in intelligent manufacturing.

[0005] However, the above method has the following problems: it is impossible to trace the fault location in real time, thereby failing to improve the efficiency of data anomaly detection. Summary of the invention

[0006] To this end, the present invention provides a self-learning detection system for industrial control data anomalies based on a neural network, so as to overcome the problem in the prior art that the fault location cannot be traced in real time, thereby failing to improve the efficiency of data anomaly detection.

[0007] To achieve the above object, the present invention provides a self-learning detection system for abnormal industrial control data based on a neural network, comprising: Continuous command module, used to send operation commands to the industrial control system at preset intervals; A data collection module, connected to the continuous command module, for collecting real-time industrial control data during the process of the industrial control system executing the operation command; An abnormality prediction module, which is connected to the data collection module, is used to select a number of learning features according to the real-time industrial control data, pre-process the real-time industrial control data to form corresponding industrial control pre-processed data, and use a neural network model to learn the industrial control pre-processed data to generate a corresponding abnormality possibility prediction map; A fault adjustment module, which is connected to the abnormality prediction module and is used to compare the possibility value in the abnormality possibility prediction diagram with the abnormality possibility threshold. When the possibility value is greater than the abnormality possibility threshold, the fault adjustment module determines that the industrial control data is abnormal and locates the abnormal axis of the machine tool; Wherein, the preset time is related to the operating performance of the industrial control system; The real-time industrial control data are industrial control parameters generated by each axis of the machine tool during the process of the industrial control system executing the operation command; The industrial control parameters include the speed, acceleration and torque of each axis of the machine tool; The learning characteristics include velocity change rate, acceleration change rate and torque change rate; The neural network model is generated by training an industrial control training set formed by the industrial control preprocessing data; The abnormality possibility threshold is a critical value of the possibility of abnormality occurring in each axis of the machine tool, and is related to the synchronization of each axis of the machine tool when working.

[0008] Furthermore, the continuous command module includes: A storage device, used for storing the operation command; A command transmitting device, connected to the storage device, for sending a corresponding operation command to the industrial control system; A timing device is connected to the command transmitting device and is used to trigger the command transmitting device at intervals of the preset time and to time-mark the operation commands in the order of the transmitting time.

[0009] Furthermore, the data collection module includes: A data sensor, which is used to monitor and collect real-time industrial control data corresponding to each axis of the machine tool; A data adjuster connected to the data sensor for correcting data deviation of the real-time industrial control data; A data converter is connected to the data adjuster and is used to perform digital signal conversion processing on the real-time industrial control data and transmit the real-time industrial control data to the abnormality prediction module.

[0010] Furthermore, the abnormality prediction module includes: A feature selector, which is used to select corresponding learning features according to the real-time industrial control data; A preprocessor, connected to the feature selector, for preprocessing the real-time industrial control data and generating corresponding industrial control preprocessing data; A learner is connected to the preprocessor and is used to learn the industrial control preprocessing data according to the learning features and generate a corresponding abnormality possibility prediction map.

[0011] Furthermore, the fault adjustment module includes: A comparator, which is used to extract the possibility value in the abnormal possibility prediction map, and compare the possibility value with the abnormal possibility threshold to form a corresponding comparison result; A determiner, connected to the comparator, for determining the operating state of the industrial control data according to the comparison result; A tracer is connected to the determiner and is used to locate the abnormal axis of the machine tool according to the emission time sequence when the industrial control data is abnormal.

[0012] Furthermore, the timing device generates a trigger signal according to a corresponding preset time, the command transmitting device receives the trigger signal from the timing device, reads the operation command from the storage device and sends it to the industrial control system according to the order of the trigger signal.

[0013] Furthermore, the data sensor is placed on each axis of the machine tool and connected to each axis of the machine tool through a network to monitor and collect real-time industrial control data corresponding to each axis of the machine tool; the data adjuster reads the collected real-time industrial control data and performs data deviation correction; the data converter converts the analog signal in the real-time industrial control data into a digital signal, and transmits the converted real-time industrial control data to the abnormality prediction module; The data deviation correction is to read the missing values ​​in the real-time industrial control data and perform linear interpolation filling on the missing values.

[0014] Furthermore, the feature selector selects a number of learning features according to the real-time industrial control data, the preprocessor cuts the real-time industrial control data according to the sampling rate to form a number of industrial control preprocessing data with a sampling rate of a standard sampling rate, the industrial control preprocessing data enters the neural network model for learning, and generates a corresponding abnormal possibility prediction map; The standard sampling rate is a sampling rate that can be recognized by the neural network model, and during the learning process of the neural network model, the standard sampling rate remains unchanged.

[0015] Further, when the possibility value is less than the abnormal possibility threshold, the determiner determines that the industrial control data is normal, and the fault adjustment module does not adjust the industrial control system.

[0016] Furthermore, when the possibility value is greater than the abnormal possibility threshold, the determiner determines that the industrial control data is abnormal, and the tracer traces the current possibility value according to the emission time sequence and locates the abnormal axis of the machine tool.

[0017] Compared with the prior art, the present invention utilizes a continuous command module to send operating commands to the industrial control system at preset intervals, a data collection module to collect real-time industrial control data of the industrial control system, an abnormality prediction module to select a number of learning features, pre-process the real-time industrial control data, and use a neural network model to learn the industrial control pre-processed data to generate a corresponding abnormality possibility prediction map, a fault adjustment module to compare the possibility value in the abnormality possibility prediction map with the abnormality possibility threshold, and when the fault adjustment module determines that the industrial control data is abnormal, the abnormal axis of the machine tool is located, thereby realizing the full process automation from data collection to abnormality detection and fault location, which not only improves the accuracy and efficiency of abnormality detection, but also continuously optimizes the detection model through the self-learning function to adapt to the dynamic changes of the industrial control system.

[0018] Furthermore, by setting a timing device to trigger the command transmitting device at preset time intervals, and marking the operating commands in the order of the transmitting time, and utilizing the coordinated work of the storage device, the command transmitting device and the timing device, precise control and sending of the operating commands of the industrial control system are achieved, which not only improves the automation level of the industrial control system, but also provides basic support for subsequent anomaly detection and fault prediction.

[0019] Furthermore, by performing data deviation correction processing on real-time industrial control data and using a data converter to convert real-time industrial control data into digital signals, real-time monitoring, data processing and abnormality prediction of the machine tool operating status are achieved, thereby improving the reliability and operating efficiency of the equipment.

[0020] Furthermore, the key features are screened out from the collected real-time industrial control data through the feature selector, and the preprocessed data is input into the neural network model to predict the possibility of abnormality in the industrial control system, which reduces the data dimension, reduces the complexity of calculation, removes irrelevant features, improves the neural network model's ability to recognize abnormal data, and converts the original data into a format suitable for subsequent learning and analysis, thereby improving data quality and consistency.

[0021] Furthermore, by utilizing a comparator to extract a possibility value from an abnormality possibility prediction diagram and comparing it with a preset abnormality possibility threshold, a comparison result is generated, and the operating status of the industrial control data is determined based on the comparison result. The abnormal axis of the machine tool is located according to the emission time sequence. This not only enables efficient handling of abnormal situations, but also enables rapid location of the source of the fault, thereby improving the overall performance and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a structural schematic diagram of a self-learning detection system for abnormal industrial control data based on a neural network according to the present invention; Figure 2This is a schematic diagram of the structure of a continuous command module according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a data collection module according to an embodiment of the present invention; Figure 4 The figure is a schematic diagram of the structure of a fault adjustment module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0024] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0025] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0026] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] See also Figure 1 As shown, it is a structural schematic diagram of a self-learning detection system for abnormal industrial control data based on a neural network of the present invention, comprising: Continuous command module, used to send operation commands to the industrial control system at preset intervals; A data collection module, which is connected to the continuous command module and is used to collect real-time industrial control data during the process of the industrial control system executing the running command; The abnormality prediction module is connected to the data collection module and is used to select a number of learning features according to the real-time industrial control data, pre-process the real-time industrial control data to form corresponding industrial control pre-processed data, and use the neural network model to learn the industrial control pre-processed data to generate a corresponding abnormality possibility prediction map; A fault adjustment module is connected to the abnormality prediction module and is used to compare the possibility value in the abnormality possibility prediction diagram with the abnormality possibility threshold. When the possibility value is greater than the abnormality possibility threshold, the fault adjustment module determines that the industrial control data is abnormal and locates the abnormal axis of the machine tool; Among them, the preset time is related to the operating performance of the industrial control system; Real-time industrial control data refers to the industrial control parameters generated by each axis of the machine tool during the process of the industrial control system executing the operation command; Industrial control parameters include speed, acceleration and torque of each axis of the machine tool; The learned features include the rate of change of velocity, rate of change of acceleration, and rate of change of torque; The neural network model is generated by training the industrial control training set formed by industrial control preprocessing data; The abnormal possibility threshold is the critical value of the possibility of abnormality occurring in each axis of the machine tool, and is related to the synchronization of each axis of the machine tool when working.

[0028] By setting up a continuous command module to send operating commands to the industrial control system at preset intervals, a data collection module to collect real-time industrial control data of the industrial control system, an abnormality prediction module to select several learning features, pre-process the real-time industrial control data, and use the neural network model to learn the industrial control pre-processed data to generate a corresponding abnormality possibility prediction map, a fault adjustment module to compare the possibility value in the abnormality possibility prediction map with the abnormality possibility threshold, when the fault adjustment module determines that the industrial control data is abnormal, the abnormal axis of the machine tool is located, and the whole process from data collection to abnormality detection and fault location is automated, which not only improves the accuracy and efficiency of abnormality detection, but also continuously optimizes the detection model through the self-learning function to adapt to the dynamic changes of the industrial control system.

[0029] See also Figure 2 As shown, it is a schematic diagram of the structure of a continuous command module according to an embodiment of the present invention, including: A storage device for storing operation commands; A command transmitting device, which is connected to the storage device and is used to send corresponding operation commands to the industrial control system; The timing device is connected to the command transmitting device and is used to trigger the command transmitting device at preset time intervals and mark the running commands in the order of the transmitting time.

[0030] In a specific implementation, the operation command is the basic instruction for the operation of the industrial control system. The storage device is used to save these instructions to ensure that they can be accurately called when needed. Preferably, a memory or storage chip is usually used to implement the storage process to store operation commands in multiple formats, such as binary code or ASCII code.

[0031] The command transmitter sends the command to the target device through the communication interface of the industrial computer (such as RS232, RS485, Ethernet, etc.). For example, the operating frequency command of the Fuji inverter can be sent in ASCII code format.

[0032] The timing device can be implemented by a hardware clock or a software timer, which can accurately control the frequency of sending commands.

[0033] In industrial control systems, sending operation commands is a key step in achieving equipment automation control. Through the continuous command module, it can ensure that the equipment executes tasks according to the preset frequency and sequence.

[0034] By setting the timing device to trigger the command transmitting device at preset time intervals, and marking the operating commands in the order of the transmitting time, and utilizing the coordinated work of the storage device, the command transmitting device and the timing device, precise control and sending of the operating commands of the industrial control system are achieved, which not only improves the automation level of the industrial control system, but also provides basic support for subsequent anomaly detection and fault prediction.

[0035] See also Figure 3 As shown, it is a schematic diagram of the structure of the data collection module according to an embodiment of the present invention, including: Data sensors, which are used to monitor and collect real-time industrial control data corresponding to each axis of the machine tool; A data adjuster, which is connected to the data sensor and is used to correct the data deviation of the real-time industrial control data; The data converter is connected to the data adjuster to perform digital signal conversion processing on the real-time industrial control data and transmit the real-time industrial control data to the abnormality prediction module.

[0036] In specific implementation, the data sensor is the front-end device of the entire data collection module, and its core function is to obtain the real-time data generated by each axis of the machine tool during operation. These data include position information, speed information, acceleration information, load information, etc., which are the basis for subsequent data processing and analysis.

[0037] The function of the data adjuster is to correct the deviation in the data collected by the data sensor. This deviation comes from the accuracy of the sensor itself, environmental interference, noise in the signal transmission process, etc. Through the data adjuster, the accuracy and reliability of the data can be improved, providing higher quality input for subsequent data processing.

[0038] The main task of the data converter is to convert the bias-corrected data into a digital signal format suitable for subsequent module processing. This involves operations such as analog-to-digital conversion (A / D conversion) to ensure that the data can be correctly identified and processed by the anomaly prediction module.

[0039] By performing data deviation correction on real-time industrial control data and converting it into digital signals using a data converter, real-time monitoring, data processing and abnormality prediction of the machine tool's operating status are achieved, thereby improving the reliability and operating efficiency of the equipment.

[0040] Specifically, the anomaly prediction module includes: A feature selector, which is used to select corresponding learning features according to real-time industrial control data; A preprocessor, which is connected to the feature selector, is used to preprocess the real-time industrial control data and generate corresponding industrial control preprocessed data; The learner is connected to the preprocessor and is used to learn the industrial control preprocessing data according to the learning characteristics and generate a corresponding abnormal possibility prediction map.

[0041] In the specific implementation, the feature selector selects the most valuable features for anomaly detection from a large amount of raw data by calculating the correlation or importance between the features and the target variables, and dynamically adjusts the feature selection strategy according to the operating status and historical data of the industrial control system to adapt to different working conditions.

[0042] The feature selector is used to screen out key features from the collected real-time industrial control data, and the preprocessed data is input into the neural network model to predict the possibility of abnormalities in the industrial control system. This reduces the data dimension, reduces the complexity of the calculation, removes irrelevant features, improves the neural network model's ability to recognize abnormal data, and converts the original data into a format suitable for subsequent learning and analysis, thereby improving data quality and consistency.

[0043] See also Figure 4 As shown, it is a schematic diagram of the structure of the fault adjustment module according to an embodiment of the present invention, including: A comparator, which is used to extract the possibility value in the abnormal possibility prediction map, and compare the possibility value with the abnormal possibility threshold to form a corresponding comparison result; A determiner, which is connected to the comparator and is used to determine the operating state of the industrial control data according to the comparison result; The tracer is connected to the determiner and is used to locate the abnormal axis of the machine tool according to the transmission time sequence when the industrial control data is abnormal.

[0044] In the specific implementation, if the industrial control data is determined to be abnormal, the tracer will locate the abnormal axis of the machine tool according to the transmission time sequence, and output the positioning result to the control system or operator interface so that corresponding measures can be taken.

[0045] By using a comparator to extract the possibility value from the abnormality possibility prediction diagram, comparing it with the preset abnormality possibility threshold, generating a comparison result, and judging the operating status of the industrial control data based on the comparison result, and locating the abnormal axis of the machine tool according to the emission time sequence, it can not only efficiently handle abnormal situations, but also quickly locate the source of the fault, thereby improving the overall performance and reliability of the system.

[0046] Specifically, the timing device generates a trigger signal according to the corresponding preset time, the command transmitting device receives the trigger signal from the timing device, reads the operation command from the storage device and sends it to the industrial control system according to the order of the trigger signal.

[0047] In the specific implementation, the timing device sets a preset time interval according to the operating performance and requirements of the industrial control system. This time interval can be adjusted according to the actual working conditions to ensure the real-time and stability of the system.

[0048] The timing device generates a trigger signal at a preset time interval, which is a precise time marker used to notify the command transmitter to send a run command.

[0049] Specifically, the data sensor is placed on each axis of the machine tool and connected to each axis of the machine tool through the network to monitor and collect the real-time industrial control data corresponding to each axis of the machine tool. The data adjuster reads the collected real-time industrial control data and performs data deviation correction. The data converter converts the analog signal in the real-time industrial control data into a digital signal and transmits the converted real-time industrial control data to the abnormality prediction module. Among them, data deviation correction is to read the missing values ​​in the real-time industrial control data and fill the missing values ​​with linear interpolation.

[0050] In the specific implementation, data sensors are installed on each axis of the machine tool and connected to the data collection system through a network. These sensors include position sensors, speed sensors, acceleration sensors, temperature sensors, current sensors, etc.

[0051] The data sensor monitors the operating status of each axis of the machine tool in real time, converts physical quantities (such as position, speed, temperature, etc.) into electrical signals, and samples them at a certain frequency to generate real-time data streams. The collected real-time data streams are transmitted to the data adjuster through the network (such as Ethernet, industrial bus, etc.).

[0052] Data deviation correction includes reading missing values ​​in real-time industrial control data and filling them with linear interpolation. Linear interpolation filling includes: detecting missing values ​​in real-time industrial control data, which may be caused by sensor failure, data transmission errors, or inconsistent sampling intervals. For the detected missing values, linear interpolation is used to fill them. Linear interpolation estimates missing values ​​by calculating the linear relationship between adjacent data points. By correcting data deviation, false positives caused by data quality issues are reduced.

[0053] The data converter converts the acquired analog signals (such as voltage, current, etc.) into digital signals. This process is usually achieved through an analog-to-digital converter (ADC).

[0054] Specifically, the feature selector selects several learning features based on the real-time industrial control data, and the preprocessor cuts the real-time industrial control data according to the sampling rate to form several industrial control preprocessing data with the sampling rate of the standard sampling rate. The industrial control preprocessing data enters the neural network model for learning and generates the corresponding abnormal possibility prediction map; The standard sampling rate is a sampling rate that can be recognized by the neural network model, and the standard sampling rate remains unchanged during the learning process of the neural network model.

[0055] In the specific implementation, when the standard sampling rate is 1700 / second, the neural network model has the best learning effect on the industrial control pre-processing data. According to the standard sampling rate that the neural network model can recognize, the real-time industrial control data is cut according to the sampling rate. The standard sampling rate is the sampling rate that the neural network model can recognize during the training process and remains unchanged during the learning process. The cut industrial control pre-processing data is formatted into the input format required by the neural network model, for example, the industrial control pre-processing data is converted into a sequence or matrix of fixed length.

[0056] The feature selector selects the most useful features by calculating the correlation or importance between the features and the target variable. For example, statistical analysis, correlation analysis, or model-based feature selection methods (such as Lasso regression, random forest, etc.) can be used.

[0057] Specifically, when the probability value is less than the abnormal probability threshold, the determiner determines that the industrial control data is normal, and the fault adjustment module does not adjust the industrial control system.

[0058] Specifically, when the possibility value is greater than the abnormal possibility threshold, the determiner determines that the industrial control data is abnormal, and the tracer traces the current possibility value according to the emission time sequence and locates the abnormal axis of the machine tool.

[0059] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A self-learning detection system for abnormal industrial control data based on neural network, characterized in that: include: Continuous command module, used to send operation commands to the industrial control system at preset intervals; A data collection module, connected to the continuous command module, for collecting real-time industrial control data during the process of the industrial control system executing the operation command; An abnormality prediction module, which is connected to the data collection module, is used to select a number of learning features according to the real-time industrial control data, pre-process the real-time industrial control data to form corresponding industrial control pre-processed data, and use a neural network model to learn the industrial control pre-processed data to generate a corresponding abnormality possibility prediction map; A fault adjustment module, which is connected to the abnormality prediction module and is used to compare the possibility value in the abnormality possibility prediction diagram with the abnormality possibility threshold. When the possibility value is greater than the abnormality possibility threshold, the fault adjustment module determines that the industrial control data is abnormal and locates the abnormal axis of the machine tool; Wherein, the preset time is related to the operating performance of the industrial control system; The real-time industrial control data are industrial control parameters generated by each axis of the machine tool during the process of the industrial control system executing the operation command; The industrial control parameters include the speed, acceleration and torque of each axis of the machine tool; The learning characteristics include velocity change rate, acceleration change rate and torque change rate; The neural network model is generated by training an industrial control training set formed by the industrial control preprocessing data; The abnormality possibility threshold is a critical value of the possibility of abnormality occurring in each axis of the machine tool, and is related to the synchronization of each axis of the machine tool when working.

2. The self-learning detection system for abnormal industrial control data based on neural network according to claim 1 is characterized in that: The continuous command module comprises: A storage device, used for storing the operation command; A command transmitting device, connected to the storage device, for sending a corresponding operation command to the industrial control system; A timing device is connected to the command transmitting device and is used to trigger the command transmitting device at intervals of the preset time and to time-mark the operation commands in the order of the transmitting time.

3. The self-learning detection system for abnormal industrial control data based on neural network according to claim 2 is characterized in that: The data collection module comprises: A data sensor, which is used to monitor and collect real-time industrial control data corresponding to each axis of the machine tool; A data adjuster connected to the data sensor for correcting data deviation of the real-time industrial control data; A data converter is connected to the data adjuster and is used to perform digital signal conversion processing on the real-time industrial control data and transmit the real-time industrial control data to the abnormality prediction module.

4. The self-learning detection system for abnormal industrial control data based on neural network according to claim 3 is characterized in that: The abnormality prediction module comprises: A feature selector, which is used to select corresponding learning features according to the real-time industrial control data; A preprocessor, connected to the feature selector, for preprocessing the real-time industrial control data and generating corresponding industrial control preprocessing data; A learner is connected to the preprocessor and is used to learn the industrial control preprocessing data according to the learning features and generate a corresponding abnormality possibility prediction map.

5. The self-learning detection system for abnormal industrial control data based on neural network according to claim 4 is characterized in that: The fault adjustment module comprises: A comparator, which is used to extract the possibility value in the abnormal possibility prediction map, and compare the possibility value with the abnormal possibility threshold to form a corresponding comparison result; A determiner, connected to the comparator, for determining the operating state of the industrial control data according to the comparison result; A tracer is connected to the determiner and is used to locate the abnormal axis of the machine tool according to the emission time sequence when the industrial control data is abnormal.

6. The self-learning detection system for abnormal industrial control data based on neural network according to claim 5 is characterized in that: The timing device generates a trigger signal according to the corresponding preset time, and the command transmitting device receives the trigger signal from the timing device, reads the operation command from the storage device and sends it to the industrial control system according to the order of the trigger signal.

7. The self-learning detection system for abnormal industrial control data based on neural network according to claim 6 is characterized in that: The data sensor is placed on each axis of the machine tool and connected to each axis of the machine tool through a network to monitor and collect real-time industrial control data corresponding to each axis of the machine tool. The data adjuster reads the collected real-time industrial control data and performs data deviation correction. The data converter converts the analog signal in the real-time industrial control data into a digital signal and transmits the converted real-time industrial control data to the abnormality prediction module. The data deviation correction is to read the missing values ​​in the real-time industrial control data and perform linear interpolation filling on the missing values.

8. The self-learning detection system for abnormal industrial control data based on neural network according to claim 7 is characterized in that: The feature selector selects a number of learning features according to the real-time industrial control data, the preprocessor cuts the real-time industrial control data according to the sampling rate to form a number of industrial control preprocessing data with a sampling rate of the standard sampling rate, the industrial control preprocessing data enters the neural network model for learning, and generates a corresponding abnormal possibility prediction map; The standard sampling rate is a sampling rate that can be recognized by the neural network model, and during the learning process of the neural network model, the standard sampling rate remains unchanged.

9. The self-learning detection system for abnormal industrial control data based on neural network according to claim 8 is characterized in that: When the possibility value is less than the abnormal possibility threshold, the determiner determines that the industrial control data is normal, and the fault adjustment module does not adjust the industrial control system.

10. The self-learning detection system for abnormal industrial control data based on neural network according to claim 9, characterized in that: When the possibility value is greater than the abnormal possibility threshold, the determiner determines that the industrial control data is abnormal, and the tracer traces the current possibility value according to the emission time sequence and locates the abnormal axis of the machine tool.

Images