Industrial internet equipment health fault monitoring system and method

Abstract

The invention relates to the technical field of industrial Internet of Things and big data information processing, in particular to an industrial Internet equipment health fault monitoring system and method, which comprises a processing system and an acquisition subsystem, and is characterized in that the acquisition subsystem is arranged at industrial Internet equipment, the processing system is arranged in a remote monitoring room, and the processing system is connected with the processing system. The acquisition subsystem is in communication connection with the processing system; according to the method, the operation of the equipment is judged by detecting the workpiece, when it is judged that the workpiece is machined correctly, the processing system cannot analyze the collected equipment data, and only when it is detected that the workpiece machining does not meet the machining requirement, the processing system can analyze the collected corresponding equipment data; in the detection process, a large amount of collected equipment data does not need to be analyzed in real time, the problems of data redundancy and the like can be avoided, accurate and rapid analysis of the data is achieved, and the problems that a monitoring system is blocked and the analysis speed is affected due to analysis of a large amount of real-time data are solved.

Description

Technical Field

[0001] The present invention relates to the fields of industrial Internet of Things technology and big data information processing technology, and in particular to an industrial Internet equipment health fault monitoring system and method. Background Art

[0002] With the advancement of science and technology, the advancement of factory intelligence is getting faster and faster. In order to confirm whether the factory intelligent equipment is operating normally, multiple devices will be connected together through industrial Internet technology, and a fault monitoring system will be built to monitor the equipment. The existing equipment failure and health monitoring method is to monitor the physical conditions of the equipment itself, such as vibration, noise, temperature, voltage, current, power, etc. By selecting appropriate hardware monitoring sensors, the status signals of various mechanical parts of the equipment are continuously and multi-point collected and analyzed, so as to realize the health status evaluation and fault prevention of the equipment. In the process of equipment health fault status evaluation, the equipment status change is affected by its own characteristics as well as the external environmental conditions of the equipment, such as environment, energy supply, personnel skills, products, warehousing logistics, process-related, etc.

[0003] For example, an industrial Internet equipment health fault monitoring method and system with authorization announcement number CN202311274586.6 and publication date 20240105 solves the problem of inaccurate early warning by specifying a predictive maintenance plan in advance and implementing maintenance; the present invention uses the industrial application end to collect equipment health data of industrial Internet equipment, and uses the data status feature library as the basis to determine whether there is an abnormality in the collected equipment status data, and adopts the equipment status data and external process related data correlation analysis algorithm, combined with the internal mechanism of the fault, to eliminate the situation where the fault is caused by external reasons, and then perform more accurate health fault warning on the equipment, thereby reducing equipment health prediction false alarms and improving the accuracy of system fault monitoring.

[0004] Although the above-mentioned and existing industrial Internet equipment health fault monitoring can realize equipment fault monitoring, the collected data needs to be analyzed in real time during monitoring to determine whether there is a fault in the equipment operation. This process is prone to problems such as data redundancy due to the large amount of collected data, causing server jams, affecting the analysis speed, and resulting in workers being unable to discover equipment failures in time and repair faulty equipment, which will affect the factory's production. Therefore, it is urgent to design an industrial Internet equipment health fault monitoring system and method to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an industrial Internet equipment health fault monitoring system and method to solve the above-mentioned deficiencies in the prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] An industrial Internet equipment health fault monitoring system and method, comprising a processing system and a collection subsystem, characterized in that: the collection subsystem is arranged at the industrial Internet equipment, the processing system is arranged in a remote monitoring room, and the collection subsystem and the processing system are connected by communication;

[0008] The acquisition subsystem includes multiple data acquisition boxes and multiple acquisition devices. Multiple acquisition devices are installed on corresponding industrial Internet devices. The acquisition devices are used to collect data when the industrial Internet devices are running, and data of the workpieces during and after processing. The acquisition devices include sensors and AI cameras. The sensors are used to detect various data when the industrial Internet devices are operating. The AI ​​cameras are used to collect data on whether the workpiece size and appearance meet the processing requirements during and after the workpiece is processed.

[0009] The data acquisition box includes a main node, a backup node, and a monitoring service function module. The main node and the backup node are used to store the data collected by the acquisition device in real time. The main node and the backup node are also used for communication and transmission between the main node and the backup node and the acquisition device and the processing system. The monitoring service function module is used to detect the process of data transmission by the main node. When a fault is detected, the monitoring service function module switches the main node to the backup node. The monitoring service function module uses a CRC algorithm to monitor the main node.

[0010] The processing system includes a serial port unit, a sorting unit, an analysis unit, a storage unit, and a push unit;

[0011] The serial port unit is connected to the data collection box through a network cable. The serial port unit is used to receive data collected by the data collection box. The sorting unit summarizes and sorts the data received by the serial port unit according to the correlation of the data. The analysis unit is used to analyze the data sorted and summarized by the sorting unit. The push unit pushes information to the workers according to the analysis results of the analysis unit. The storage unit is used to store the analysis results of the analysis unit, the data sorted by the sorting unit and the information pushed by the push unit. The serial port unit uses an RS-485 network serial port. The storage unit is divided into a cloud database and a storage server. The information pushed by the push unit is a WeChat message and a text message. The sorting unit uses the Pearson correlation coefficient when sorting the data, and the formula is as follows:

[0012]

[0013] Among them, R is the Pearson correlation coefficient. When R is between 0.8-1.0, it is a very strong correlation; when R is between 0.6-0.8, it is a strong correlation; when R is between 0.4-0.6, it is a moderate correlation; when R is between 0.2-0.4, it is a weak correlation; when R is between 0.0-0.2, it is no correlation; Z X is the z-score of variable X, Z Y is the z-score of variable X,

[0014] Furthermore, the analysis unit includes a workpiece analysis module and an equipment analysis module. The workpiece analysis module is used to analyze the workpiece data sorted by the sorting unit. The equipment analysis module analyzes the equipment data sorted by the sorting unit according to the analysis results of the workpiece analysis module. The equipment analysis module uses a machine learning algorithm for analysis. The equipment analysis module classifies and predicts equipment failures by constructing a decision tree model; and subsequently uses random forest, support vector machine, neural network and other algorithms for fault classification and prediction.

[0015] Furthermore, it also includes an industrial Internet equipment health fault monitoring method, and its specific steps are as follows:

[0016] Step S1. Collecting data: When the workpiece is processed and produced by industrial equipment, the data before, during and after the workpiece processing and the data when the equipment is running are collected by the collection equipment;

[0017] Step S2. Data transmission: temporarily storing the data collected by the data collection device through the data collection box, and then transmitting the data to the processing system;

[0018] Step S3. Data summarization: The serial port unit in the processing system receives the data transmitted by the data acquisition box, and the post-processing unit summarizes and sorts the received data to confirm the relevance between the data;

[0019] Step S4. Data analysis and corresponding measures: When the workpiece analysis module in the analysis unit detects that the workpiece meets the production requirements after processing, the push unit does not push information to the workers. When the workpiece analysis module detects that the size of the workpiece does not meet the requirements after processing, the equipment analysis module will call the corresponding data according to the analysis of the workpiece module, and analyze the data to confirm the equipment failure problem. The push unit pushes information to the workers according to the analysis results of the analysis unit, so that the workers can repair the equipment in time.

[0020] Furthermore, in the step S2, the monitoring service function module will monitor the transmission of the main node. When the monitoring is correct, the main node operates normally. When the main node transmission is detected, the backup node is started, and the backup node transmits the data collected by the acquisition device; in the step S3, the sorting unit will divide the data into two types after sorting and summarizing the data, namely workpiece data and equipment data; in the step S4, the push unit will forcibly push information to the workers through pop-up windows when pushing information.

[0021] In the above technical solution, the present invention provides an industrial Internet equipment health fault monitoring system and method, which has the following beneficial effects:

[0022] (1) The processing system designed by the present invention can judge the operation of the equipment by detecting the workpiece. When it is judged that the workpiece processing is correct, the processing system will not analyze the collected equipment data. Only when it is detected that the workpiece processing does not meet the processing requirements, the processing system will analyze the collected corresponding equipment data. This process does not require real-time analysis of a large amount of collected equipment data during detection, which can avoid the occurrence of problems such as data redundancy, realize accurate and fast analysis of data, and solve the problem that the analysis of a large amount of real-time data causes the monitoring system to freeze and affects the analysis speed.

[0023] (2) In the data collection box designed by the present invention, when the collection subsystem transmits the collected data, the monitoring service function module will monitor the transmission of the main node. When the monitoring is correct, the main node operates normally. When the main node transmission is detected, the backup node is started, and the backup node transmits the data collected by the collection device. This process effectively solves the problems of data lag, single point failure and long recovery time existing in the prior art, can significantly improve the reliability and business continuity of the system, and improves the disaster recovery capability of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0025] Figure 1 A system flow chart of an industrial Internet equipment health fault monitoring system and method embodiment provided by the present invention.

[0026] Figure 2 A schematic diagram of a data collection box provided for an industrial Internet equipment health fault monitoring system and method embodiment of the present invention.

[0027] Figure 3A schematic diagram of the analysis unit structure provided for an industrial Internet equipment health fault monitoring system and method embodiment of the present invention.

[0028] Figure 4 A method flow chart is provided for an industrial Internet equipment health fault monitoring system and method embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0030] like Figure 1-4 As shown, an embodiment of the present invention provides an industrial Internet equipment health fault monitoring system and method, the system includes a processing system and a collection subsystem, characterized in that: the collection subsystem is arranged at the industrial Internet equipment, the processing system is arranged in a remote monitoring room, and the collection subsystem and the processing system are connected by communication;

[0031] The acquisition subsystem includes multiple data acquisition boxes and multiple acquisition devices. Multiple acquisition devices are installed on corresponding industrial Internet devices. The acquisition devices are used to collect data when the industrial Internet devices are running, and data when the workpieces are being processed and after processing. The acquisition devices include sensors and AI cameras. The sensors are used to detect various data when the industrial Internet devices are operating, and the AI ​​cameras are used to collect data during the workpiece processing process and whether the workpiece size and appearance meet the processing requirements after processing.

[0032] The data collection box includes a main node, a backup node, and a monitoring service function module. The main node and the backup node are used to store the data collected by the collection device in real time. The main node and the backup node are also used for communication and transmission between the main node and the backup node and the collection device and the processing system. The monitoring service function module is used to detect the process of data transmission by the main node. When the monitoring service function module detects a fault, the main node will be switched to the backup node. The monitoring service function module uses the CRC algorithm to monitor the main node.

[0033] It should be noted that the CRC (Cyclic Redundancy Check) algorithm is an error detection method widely used in communication and storage systems. CRC detects errors that may occur during data transmission by calculating a check code of a fixed length.

[0034] CRC16 code derivation process and source code

[0035] 2.1 From polynomial to C source code

[0036] CRC (Cyclic Redundancy Check) is an effective method for detecting errors in data transmission. It detects errors in data by calculating a fixed-length checksum. The CRC checksum is usually calculated and appended to the data at the data sending end, and then calculated and compared again at the receiving end to determine whether the data has been changed during transmission.

[0037] The basic principle of CRC check algorithm:

[0038] (1) Polynomial representation:

[0039] The calculation of the CRC checksum is based on binary modulo 2 division, usually using a fixed polynomial as the divisor.

[0040] The data bit stream is also represented as a polynomial.

[0041] (2) Calculation steps:

[0042] Represent the data bit stream as a polynomial.

[0043] Divide this polynomial by a fixed generator polynomial.

[0044] The remainder (the remainder of the modulo-2 division) is the CRC checksum.

[0045] (3) CRC16 checksum algorithm

[0046] The CRC16 checksum algorithm is a commonly used CRC checksum algorithm that generates a 16-bit checksum. There are many different variants of CRC16, such as CRC16-CCITT, CRC16-X25, etc. The main difference lies in the different generator polynomials used.

[0047] Assume that CRC16-CCITT uses the polynomial x^16+x^12+x^5+1, which is represented in hexadecimal as 0x1021

[0048] The processing system includes a serial port unit, a sorting unit, an analysis unit, a storage unit, and a push unit;

[0049] The serial port unit is connected to the data acquisition box through a network cable. The serial port unit is used to receive the data collected by the data acquisition box. The serial port unit uses the RS-485 network serial port;

[0050] It should be noted that the main function of the RS-485 network serial port is to achieve reliable data transmission for multi-device communication in industrial automation and control systems. RS-485 is a half-duplex serial interface that uses differential signal transmission and has the advantages of long-distance transmission, multi-device connection, anti-interference and low cost.

[0051] How it works

[0052] The RS-485 interface transmits data through a pair of twisted wires (A and B). When the data is 1, the voltage of line A is higher than that of line B; when the data is 0, the voltage of line A is lower than that of line B. The receiving end of the differential signal judges the data by comparing the voltage difference between lines A and B.

[0053] The sorting unit summarizes and sorts the data received by the serial port unit according to the correlation of the data. The sorting unit uses the Pearson correlation coefficient when sorting the data, and the formula is as follows:

[0054]

[0055] Among them, R is the Pearson correlation coefficient. When R is between 0.8-1.0, it is a very strong correlation; when R is between 0.6-0.8, it is a strong correlation; when R is between 0.4-0.6, it is a moderate correlation; when R is between 0.2-0.4, it is a weak correlation; when R is between 0.0-0.2, it is no correlation; Z X is the z-score of variable X, Z Y is the z-score of variable X,

[0056]

[0057] The analysis unit is used to analyze the data sorted and summarized by the sorting unit. The analysis unit includes a workpiece analysis module and an equipment analysis module. The workpiece analysis module is used to analyze the workpiece data sorted by the sorting unit. The equipment analysis module analyzes the equipment data sorted by the sorting unit according to the analysis results of the workpiece analysis module.

[0058] It should be noted that the workpiece analysis module uses an AI camera to detect the size and appearance of the workpiece, and then compares it with the workpiece data in the workpiece processing requirements stored in the storage unit to determine whether the workpiece is normal;

[0059] The equipment analysis module uses a machine learning algorithm: it builds a decision tree model to classify and predict equipment failures; it then uses random forest, support vector machine, neural network and other algorithms to classify and predict failures.

[0060] In another embodiment provided by the present invention, the storage unit is used to store the results analyzed by the analysis unit, the data sorted by the sorting unit, and the information pushed by the pushing unit, and the storage unit is divided into two types: a cloud database and a storage server;

[0061] The push unit pushes information to the workers based on the analysis results of the analysis unit. The information pushed by the push unit is WeChat messages and SMS messages.

[0062] In another embodiment provided by the present invention, Figure 4 As shown, it also includes an industrial Internet equipment health fault monitoring method, and its specific steps are as follows:

[0063] Step S1. Collecting data: When the workpiece is processed and produced by industrial equipment, the data before, during and after the workpiece processing and the data when the equipment is running are collected by the collection equipment;

[0064] Step S2. Data transmission: The data collected by the collection device is temporarily stored in the data collection box, and then the data is transmitted to the processing system. The process monitoring service function module will monitor the transmission of the master node. When the monitoring is correct, the master node operates normally. When the master node is detected to be transmitting, the backup node is started, and the backup node transmits the data collected by the collection device;

[0065] Step S3. Data summarization: The serial port unit in the processing system receives the data transmitted by the data acquisition box, and the post-sorting unit summarizes and sorts the received data to confirm the relevance between the data. After sorting and summarizing the data, the sorting unit divides the data into two types, namely workpiece data and equipment data;

[0066] Step S4. Data analysis and corresponding measures: When the workpiece analysis module in the analysis unit detects that the workpiece meets the production requirements after processing, the push unit does not push information to the workers. When the workpiece analysis module detects that the size of the workpiece does not meet the requirements after processing, the equipment analysis module will call the corresponding data according to the analysis of the workpiece module, and analyze the data to confirm the equipment failure problem. The push unit pushes information to the workers according to the results of the analysis of the analysis unit, so that the workers can repair the equipment in time. When the push unit pushes information, it will forcibly push the information to the workers through pop-up windows.

[0067] Working principle: When the workpiece is processed and produced by industrial equipment, the data before, during and after the workpiece processing and the data during the operation of the equipment are collected by the acquisition equipment; the data collected by the acquisition equipment is temporarily stored in the data acquisition box, and then the data is transmitted to the processing system. The monitoring service function module will monitor the transmission of the main node. When the monitoring is correct, the main node operates normally. When the main node transmission is detected, the backup node is started, and the backup node transmits the data collected by the acquisition equipment; then the serial port unit in the processing system receives the data transmitted by the data acquisition box, and the post-processing unit summarizes and sorts the received data to confirm the data The data will be divided into two types after sorting and summarizing, namely workpiece data and equipment data. During analysis, when the workpiece analysis module in the analysis unit detects that the workpiece meets the production requirements after processing, the push unit will not push information to the workers. When the workpiece analysis module detects that the size of the workpiece does not meet the requirements after processing, the equipment analysis module will call the corresponding data according to the analysis of the workpiece module, and analyze the data to confirm the equipment failure problem. The push unit will push information to the workers according to the results of the analysis unit's analysis, so that the workers can repair the equipment in time. During this process, the push unit will forcibly push information to the workers by means of pop-up windows.

[0068] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An industrial Internet equipment health fault monitoring system, including a processing system and a collection subsystem, characterized in that: The acquisition subsystem is arranged at the industrial Internet device, the processing system is arranged in the remote monitoring room, and the acquisition subsystem and the processing system are connected by communication; The acquisition subsystem includes multiple data acquisition boxes and multiple acquisition devices. Multiple acquisition devices are installed on corresponding industrial Internet devices. The acquisition devices are used to collect data when the industrial Internet devices are running, and data when and after the workpiece is processed; The data collection box includes a main node, a backup node, and a monitoring service function module. The main node and the backup node are used to store the data collected by the collection device in real time. The main node and the backup node are also used for communication and transmission between the main node and the backup node and the collection device and the processing system. The monitoring service function module is used to detect the process of data transmission by the main node. When a fault is detected, the monitoring service function module will switch the main node to the backup node. The processing system includes a serial port unit, a sorting unit, an analysis unit, a storage unit, and a push unit; The serial port unit is connected to the data collection box through a network cable. The serial port unit is used to receive data collected by the data collection box. The sorting unit summarizes and organizes the data received by the serial port unit according to the correlation of the data. The analysis unit is used to analyze the data sorted and summarized by the sorting unit. The push unit pushes information to the workers according to the results of the analysis by the analysis unit. The storage unit is used to store the results of the analysis by the analysis unit, the data sorted by the sorting unit, and the information pushed by the push unit.

2. The industrial Internet equipment health fault monitoring system according to claim 1 is characterized in that: The acquisition equipment includes two types: sensors and AI cameras. The sensors are used to detect various data during the operation of industrial Internet equipment, and the AI ​​cameras are used to collect data on the workpiece processing process and whether the workpiece size and appearance meet the processing requirements after processing.

3. The industrial Internet equipment health fault monitoring system according to claim 2 is characterized in that: The monitoring service function module uses a CRC algorithm to monitor the master node.

4. The industrial Internet equipment health fault monitoring system according to claim 3 is characterized in that: The serial port unit uses an RS-485 network serial port, the storage unit is divided into two types: a cloud database and a storage server, and the information pushed by the push unit is two types: WeChat messages and SMS messages.

5. The industrial Internet equipment health fault monitoring system according to claim 4 is characterized in that: The collating unit uses the Pearson correlation coefficient when collating the data, and the formula is as follows: Among them, R is the Pearson correlation coefficient. When R is between 0.8-1.0, it is a very strong correlation; when R is between 0.6-0.8, it is a strong correlation; when R is between 0.4-0.6, it is a moderate correlation; when R is between 0.2-0.4, it is a weak correlation; when R is between 0.0-0.2, it is no correlation; Z X is the z-score of variable X, Z Y is the z-score of variable X, 6. The industrial Internet equipment health fault monitoring system according to claim 1 is characterized in that: The analysis unit includes a workpiece analysis module and an equipment analysis module. The workpiece analysis module is used to analyze the workpiece data sorted by the sorting unit. The equipment analysis module analyzes the equipment data sorted by the sorting unit according to the analysis results of the workpiece analysis module. The equipment analysis module uses a machine learning algorithm for analysis. The equipment analysis module classifies and predicts equipment failures by constructing a decision tree model; and subsequently uses random forest, support vector machine, neural network and other algorithms for fault classification and prediction.

7. According to claim 1, an industrial Internet equipment health fault monitoring system and an industrial Internet equipment health fault monitoring method are characterized in that: The specific steps are as follows: Step S1. Collecting data: When the workpiece is processed and produced by industrial equipment, the data before, during and after the workpiece processing and the data when the equipment is running are collected by the collection equipment; Step S2. Data transmission: temporarily storing the data collected by the data collection device through the data collection box, and then transmitting the data to the processing system; Step S3. Data summarization: The serial port unit in the processing system receives the data transmitted by the data acquisition box, and the post-processing unit summarizes and sorts the received data to confirm the relevance between the data; Step S4. Data analysis and corresponding measures: When the workpiece analysis module in the analysis unit detects that the workpiece meets the production requirements after processing, the push unit does not push information to the workers. When the workpiece analysis module detects that the size of the workpiece does not meet the requirements after processing, the equipment analysis module will call the corresponding data according to the analysis of the workpiece module, and analyze the data to confirm the equipment failure problem. The push unit pushes information to the workers according to the analysis results of the analysis unit, so that the workers can repair the equipment in time.

8. The method for monitoring the health failure of industrial Internet equipment according to claim 7 is characterized in that: In step S2, the monitoring service function module monitors the transmission of the master node. When the monitoring is correct, the master node operates normally. When the transmission of the master node is detected, the backup node is started and the backup node transmits the data collected by the collection device.

9. The method for monitoring the health failure of industrial Internet equipment according to claim 7, characterized in that: In step S3, the sorting unit sorts and summarizes the data and divides the data into two types, namely workpiece data and equipment data.

10. The method for monitoring the health failure of industrial Internet equipment according to claim 7, characterized in that: In step S4, when the push unit pushes information, it will forcibly push the information to the worker in the form of a pop-up window.

Images