An intelligent fault diagnosis system for industrial equipment based on the Internet of Things

Abstract

The present invention belongs to the field of industrial equipment fault diagnosis and involves data analysis technology. It is used to solve the problem that traditional fault diagnosis methods cannot combine historical fault data with equipment operating parameters to rank the diagnostic priorities of equipment on a production line. Specifically, it is an intelligent fault diagnosis system for industrial equipment based on the Internet of Things, including an operation monitoring module, a production line supervision module, a fault processing module and a diagnostic training model. The operation monitoring module, the production line supervision module and the fault processing module are communicatively connected in sequence; the operation monitoring module is used to perform operation monitoring and analysis on industrial equipment; the production line supervision module is used to perform operation supervision and analysis on production lines in industrial plants and mark production lines whose operating status does not meet the requirements as faulty production lines; the present invention can analyze the historical data of industrial equipment, group industrial equipment according to equipment type and operating space, and perform statistics on the historical fault data of industrial equipment from different dimensions.

Description

Technical Field

[0001] The present invention belongs to the field of industrial equipment fault diagnosis and relates to data analysis technology, and specifically is an industrial equipment fault intelligent diagnosis system based on the Internet of Things. Background Art

[0002] Smart factories use various modern technologies to realize the automation of factory office, management and production, so as to strengthen and standardize enterprise management, reduce work errors, plug various loopholes, improve work efficiency, ensure safe production, provide decision-making references, strengthen external contacts, and expand international markets. Smart factories realize the mutual coordination and cooperation between people and machines, and their essence is human-computer interaction.

[0003] The intelligent fault diagnosis system for industrial equipment in the prior art generally realizes the fault diagnosis function by monitoring various operating parameters of the equipment. However, when a production abnormality occurs on the production line but the equipment on the production line does not show obvious operating abnormality, the traditional method cannot combine historical fault data with equipment operating parameters to rank the diagnostic priority of the equipment on the production line, resulting in low fault diagnosis efficiency.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent fault diagnosis system for industrial equipment based on the Internet of Things, which is used to solve the problem that traditional fault diagnosis methods cannot combine historical fault data with equipment operating parameters to prioritize the equipment on the production line;

[0006] The technical problem to be solved by the present invention is: how to provide an intelligent industrial equipment fault diagnosis system based on the Internet of Things that can combine historical fault data and equipment operating parameters to rank the diagnostic priorities of equipment on the production line.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent fault diagnosis system for industrial equipment based on the Internet of Things, comprising an operation monitoring module, a production line supervision module, a fault processing module and a diagnosis training model, wherein the operation monitoring module, the production line supervision module and the fault processing module are sequentially connected in communication;

[0009] The operation monitoring module is used to perform operation monitoring and analysis on industrial equipment;

[0010] The production line supervision module is used to perform operation supervision analysis on the production lines in the industrial plant and mark the production lines whose operation status does not meet the requirements as faulty production lines;

[0011] The diagnostic training model includes a historical data analysis module and a diagnostic analysis module;

[0012] The historical data analysis module is used to analyze the historical data of the industrial equipment and obtain the type value LX and the space value KJ of the industrial equipment, and send the type value LX of the type object and the space value KJ of the space object to the diagnosis analysis module;

[0013] The diagnostic analysis module is used to analyze the diagnostic priority of industrial equipment in the faulty production line: mark the industrial equipment in the faulty production line as analysis objects, perform a comprehensive analysis based on the type value LX, space value KJ, operation monitoring parameters and operation monitoring threshold of the analysis object to obtain the diagnostic priority value of the analysis object, arrange the analysis objects in the faulty production line in order from small to large according to the diagnostic priority value to obtain a diagnostic priority ranking, and send the diagnostic priority ranking to the fault handling module.

[0014] As a preferred embodiment of the present invention, the specific process of the operation monitoring module performing operation monitoring and analysis on industrial equipment includes: setting operation monitoring parameters and operation monitoring thresholds according to the type of industrial equipment, determining that there is a fault in the industrial equipment when the operation monitoring parameters exceed the operation monitoring threshold, generating a fault alarm signal and sending the fault alarm signal to the fault handling module.

[0015] As a preferred embodiment of the present invention, the specific process of the production line supervision module performing operation supervision and analysis on the production line of the industrial plant includes: generating a supervision cycle and dividing the supervision cycle into several supervision time periods, obtaining the output and scrap rate of the production line at the end of the supervision time period, and comparing the output and scrap rate with the preset output threshold and scrap threshold respectively: if the output is greater than or equal to the output threshold and the scrap rate is less than the scrap threshold, then it is determined that the operation status of the production line during the supervision time period meets the requirements; otherwise, it is determined that the operation status of the production line during the supervision time period does not meet the requirements, and the corresponding production line is marked as a faulty production line, and it is determined whether there is an operation fault in the industrial equipment on the production line during the supervision time period: if so, the fault is handled by the fault handling module; if not, a diagnostic analysis signal is generated and the diagnostic analysis signal is sent to the diagnostic training model.

[0016] As a preferred embodiment of the present invention, the specific process of the historical data analysis module analyzing the historical data of industrial equipment includes: grouping the industrial equipment according to the equipment type and the operating space in which it is located to obtain a type data group and a space data group, the type data group includes a number of type objects, and the space data group includes a number of space objects. The total number of equipment failures in the previous supervision cycle is marked as the overall value, and the ratio of the total number of operating failures of the industrial equipment corresponding to the type object in the previous supervision cycle to the overall value is marked as the type value LX of the type object, and the ratio of the total number of operating failures of the industrial equipment corresponding to the space object in the previous supervision cycle to the overall value is marked as the space value KJ of the space object.

[0017] As a preferred embodiment of the present invention, the specific process of the diagnostic analysis module analyzing the diagnostic priority of the industrial equipment in the faulty production line includes: marking the industrial equipment in the faulty production line as an analysis object, obtaining the type value LX of the type object where the analysis object is located and the space value KJ of the space object where the analysis object is located, and using the formula Obtain the priority coefficient YX of the analysis object, where m1 and m2 are the preset proportional coefficients of the type value LX and the space value KJ respectively, and m1+m2=1; arrange the analysis objects in the faulty production line in descending order according to the priority coefficient YX to obtain a historical priority ranking; arrange the analysis objects in the faulty production line in ascending order according to the operating performance value to obtain an operating priority ranking; mark the sum of the serial number of the analysis object in the historical priority ranking and the serial number in the operating priority ranking as the diagnostic priority value of the analysis object.

[0018] As a preferred embodiment of the present invention, the value determination process of m1 includes: summing and averaging the type values ​​LX of the type objects of all analysis objects in the faulty production line to obtain the type coefficient, summing and averaging the spatial values ​​KJ of the spatial objects of all analysis objects in the faulty production line to obtain the spatial coefficient, and comparing the type coefficient with the spatial coefficient: if the type coefficient is less than the spatial coefficient, it is determined that the faulty production line has a spatial tendency characteristic, and the value range of m1 is (0.4, 0.5); if the type coefficient is greater than or equal to the spatial coefficient, it is determined that the faulty production line has a type tendency characteristic, and the value range of m1 is (0.5, 0.6).

[0019] As a preferred embodiment of the present invention, the process of obtaining the operating performance value of the analysis object includes: summing up the operating monitoring parameters of the analysis object within the supervision period and taking the average value to obtain the monitoring coefficient, marking the difference between the operating monitoring threshold and the monitoring coefficient as a floating value, and marking the ratio of the floating value to the operating monitoring threshold as the operating performance value of the analysis object.

[0020] The present invention has the following beneficial effects:

[0021] 1. The operation monitoring module and the production line supervision module can monitor the production line as a whole from the perspective of equipment operation and production line output respectively, and issue early warnings in time when equipment fails. When the production line output is abnormal but the industrial equipment does not have obvious operation failures, fault diagnosis analysis is triggered. A reasonable diagnosis priority ranking is generated through the diagnosis training model, and equipment with a high probability of failure is checked first;

[0022] 2. The historical data analysis module can be used to analyze the historical data of industrial equipment, group industrial equipment by equipment type and operation space, and collect statistics on the historical failure data of industrial equipment from different dimensions, thereby improving the accuracy of the failure probability analysis results;

[0023] 3. The diagnostic analysis module can be used to analyze the diagnostic priority of industrial equipment in the faulty production line. A comprehensive analysis can be performed based on the type value and space value in the historical data and the monitoring coefficient in the real-time monitoring data to obtain diagnostic priority, so that the industrial equipment with the highest probability of failure can be troubleshooted first, thereby improving the efficiency of fault diagnosis when there is no obvious abnormality in the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 is the overall system block diagram of the present invention;

[0026] Figure 2 is a system block diagram of Embodiment 1 of the present invention;

[0027] Figure 3 is a system block diagram of Embodiment 2 of the present invention;

[0028] Figure 4 This is a method flow chart of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0029] The technical scheme of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] like Figure 1As shown, an intelligent fault diagnosis system for industrial equipment based on the Internet of Things includes an operation monitoring module, a production line supervision module, a fault processing module and a diagnosis training model.

[0031] Embodiment 1

[0032] like Figure 2 As shown, the operation monitoring module, the production line supervision module and the fault handling module are communicatively connected in sequence. The operation monitoring module is used to perform operation monitoring and analysis on the industrial equipment: the operation monitoring parameters and the operation monitoring threshold are set according to the type of industrial equipment. When the operation monitoring parameters exceed the operation monitoring threshold, it is determined that the industrial equipment has a fault, a fault alarm signal is generated and the fault alarm signal is sent to the fault handling module.

[0033] For example, the operation monitoring parameters of industrial equipment can be one or more. Generally, the parameters that best reflect its operating status are set according to the type of industrial equipment. For example, when the industrial equipment type is an industrial machine tool, its operation monitoring parameters can be chassis vibration frequency value and operation noise decibel value. The operation monitoring threshold is set corresponding to the operation monitoring parameter.

[0034] The production line supervision module is used to perform operation supervision and analysis on the production lines in industrial plants: generate a supervision cycle and divide the supervision cycle into several supervision periods, obtain the output and scrap rate of the production line at the end of the supervision period, and compare the output and scrap rate with the preset output threshold and scrap threshold respectively: if the output is greater than or equal to the output threshold and the scrap rate is less than the scrap threshold, then it is determined that the operation status of the production line during the supervision period meets the requirements; otherwise, it is determined that the operation status of the production line during the supervision period does not meet the requirements, and the corresponding production line is marked as a faulty production line, and it is determined whether there is an operation fault on the industrial equipment on the production line during the supervision period: if so, the fault is handled through the fault handling module; if not, a diagnostic analysis signal is generated and sent to the diagnostic training model; the production line is monitored as a whole from the perspective of equipment operation and the perspective of production line output, and timely warnings are issued when equipment faults exist. When the production line output is abnormal but the industrial equipment does not have an obvious operation fault, the fault diagnosis analysis is triggered, and a reasonable diagnostic priority ranking is generated through the diagnostic training model, and equipment with a high probability of failure is checked first.

[0035] Embodiment 2

[0036] like Figure 3 As shown, the diagnosis training model includes a historical data analysis module and a diagnosis analysis module.

[0037] The historical data analysis module is used to analyze the historical data of industrial equipment: the industrial equipment is grouped according to the equipment type and the operating space to obtain a type data group and a space data group, the type data group includes several type objects, and the space data group includes several space objects. The total number of equipment failures in the previous supervision cycle is marked as the overall value, and the ratio of the total number of operating failures of the industrial equipment corresponding to the type object in the previous supervision cycle to the overall value is marked as the type value LX of the type object, and the ratio of the total number of operating failures of the industrial equipment corresponding to the space object in the previous supervision cycle to the overall value is marked as the space value KJ of the space object; the type value LX of the type object and the space value KJ of the space object are sent to the diagnosis and analysis module; the historical data of the industrial equipment is analyzed, the industrial equipment is grouped according to the equipment type and the operating space, and the historical failure data of the industrial equipment is counted from different dimensions, so as to improve the accuracy of the failure probability analysis results.

[0038] The diagnostic analysis module is used to analyze the diagnostic priority of industrial equipment in the faulty production line: mark the industrial equipment in the faulty production line as the analysis object, obtain the type value LX of the type object where the analysis object is located and the space value KJ of the space object where it is located, and use the formula The priority coefficient YX of the analysis object is obtained, where m1 and m2 are preset proportional coefficients of the type value LX and the space value KJ respectively, and m1+m2=1. The value determination process of m1 includes: summing and averaging the type values ​​LX of the type objects of all analysis objects in the faulty production line to obtain the type coefficient, summing and averaging the space values ​​KJ of the space objects of all analysis objects in the faulty production line to obtain the space coefficient, and comparing the type coefficient with the space coefficient: if the type coefficient is less than the space coefficient, it is determined that the faulty production line has a spatial tendency feature, and the value range of m1 is (0.4, 0.5); if the type coefficient is greater than or equal to the space coefficient, it is determined that the faulty production line has a type tendency feature, and the value range of m1 is (0.5, 0.6); the analysis objects in the faulty production line are arranged in descending order according to the priority coefficient YX to obtain a historical priority ranking; the operation monitoring parameters of the analysis objects during the supervision period are compared. The monitoring coefficient is obtained by summing and averaging, the difference between the operation monitoring threshold and the monitoring coefficient is marked as a floating value, the ratio of the floating value to the operation monitoring threshold is marked as the operation performance value of the analysis object, and the analysis objects in the faulty production line are arranged in order of the operation performance value from small to large to obtain the operation priority ranking; the sum of the sequence number of the analysis object in the historical priority ranking and the sequence number in the operation priority ranking is marked as the diagnosis priority value of the analysis object, and the analysis objects in the faulty production line are arranged in order of the diagnosis priority value from small to large to obtain the diagnosis priority ranking, and the diagnosis priority ranking is sent to the fault processing module; the diagnosis priority of the industrial equipment in the faulty production line is analyzed, and a comprehensive analysis is performed on the type value and space value in the historical data and the monitoring coefficient in the real-time monitoring data to obtain the diagnosis priority ranking, so that the industrial equipment with the highest probability of failure is first troubleshooted, thereby improving the fault diagnosis efficiency when there is no obvious abnormality in the equipment.

[0039] Embodiment 3

[0040] like Figure 4 As shown, an intelligent diagnosis method for industrial equipment faults based on the Internet of Things includes the following steps:

[0041] Step 1: Perform operation monitoring and analysis of industrial equipment and production line supervision analysis. When an abnormality occurs on the production line but there is no monitoring fault on the industrial equipment on the production line, execute step 2;

[0042] Step 2: Analyze the historical data of industrial equipment and obtain the type value LX and space value KJ of the industrial equipment;

[0043] Step 3: Analyze the diagnostic priority of industrial equipment in the faulty production line: Mark the industrial equipment in the faulty production line as the analysis object, obtain the diagnostic priority value of the analysis object, and arrange the analysis objects in order from small to large according to the diagnostic priority value to obtain the diagnostic priority ranking, and perform fault diagnosis and troubleshooting on the industrial equipment on the faulty production line in the order of the diagnostic priority ranking.

[0044] An intelligent fault diagnosis system for industrial equipment based on the Internet of Things performs operation monitoring and analysis and production line supervision analysis on industrial equipment during operation. When an abnormality occurs in the production line but there is no monitoring fault in the industrial equipment on the production line, the historical data of the industrial equipment is analyzed to obtain the type value LX and the space value KJ of the industrial equipment; the diagnosis priority of the industrial equipment in the faulty production line is analyzed: the industrial equipment in the faulty production line is marked as an analysis object, the diagnosis priority value of the analysis object is obtained, and the analysis objects are arranged in order from small to large according to the diagnosis priority value to obtain a diagnosis priority ranking, and the industrial equipment on the faulty production line is diagnosed and checked in the order of the diagnosis priority ranking.

[0045] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0046] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0047] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent fault diagnosis system for industrial equipment based on the Internet of Things, characterized in that: It includes an operation monitoring module, a production line supervision module, a fault processing module and a diagnostic training model, wherein the operation monitoring module, the production line supervision module and the fault processing module are sequentially connected in communication; The operation monitoring module is used to perform operation monitoring and analysis on industrial equipment; The production line supervision module is used to perform operation supervision analysis on the production lines in the industrial plant and mark the production lines whose operation status does not meet the requirements as faulty production lines; The diagnostic training model includes a historical data analysis module and a diagnostic analysis module; The historical data analysis module is used to analyze the historical data of the industrial equipment and obtain the type value LX and the space value KJ of the industrial equipment, and send the type value LX of the type object and the space value KJ of the space object to the diagnosis analysis module; The diagnostic analysis module is used to analyze the diagnostic priority of industrial equipment in the faulty production line: mark the industrial equipment in the faulty production line as the analysis object, perform a comprehensive analysis based on the type value LX, space value KJ, operation monitoring parameters and operation monitoring threshold of the analysis object to obtain the diagnostic priority value of the analysis object, arrange the analysis objects in the faulty production line in order from small to large according to the diagnostic priority value to obtain the diagnostic priority ranking, and send the diagnostic priority ranking to the fault processing module; The specific process of the historical data analysis module analyzing the historical data of industrial equipment includes: grouping the industrial equipment according to the equipment type and the operating space in which it is located to obtain a type data group and a space data group, the type data group includes a number of type objects, and the space data group includes a number of space objects, marking the total number of equipment failures in the previous supervision cycle as the overall value, marking the ratio of the total number of operating failures of the industrial equipment corresponding to the type object in the previous supervision cycle to the overall value as the type value LX of the type object, and marking the ratio of the total number of operating failures of the industrial equipment corresponding to the space object in the previous supervision cycle to the overall value as the space value KJ of the space object; The specific process of the diagnostic analysis module analyzing the diagnostic priority of industrial equipment in the faulty production line includes: marking the industrial equipment in the faulty production line as the analysis object, obtaining the type value LX of the type object where the analysis object is located and the space value KJ of the space object where it is located, and using the formula Obtain the priority coefficient YX of the analysis object, where m1 and m2 are the preset proportional coefficients of the type value LX and the space value KJ respectively, and m1+m2=1; arrange the analysis objects in the faulty production line in descending order according to the priority coefficient YX to obtain a historical priority ranking; arrange the analysis objects in the faulty production line in ascending order according to the operating performance value to obtain an operating priority ranking; mark the sum of the serial number of the analysis object in the historical priority ranking and the serial number in the operating priority ranking as the diagnostic priority value of the analysis object.

2. According to the IoT-based intelligent fault diagnosis system for industrial equipment according to claim 1, it is characterized in that: The specific process of the operation monitoring module performing operation monitoring and analysis on industrial equipment includes: setting the operation monitoring parameters and operation monitoring thresholds according to the type of industrial equipment, determining that the industrial equipment has a fault when the operation monitoring parameters exceed the operation monitoring thresholds, generating a fault alarm signal and sending the fault alarm signal to the fault handling module.

3. According to the IoT-based industrial equipment fault intelligent diagnosis system of claim 2, it is characterized in that: The specific process of the production line supervision module to conduct operation supervision and analysis on the production lines in industrial plants includes: generating a supervision cycle and dividing the supervision cycle into several supervision periods, obtaining the output and scrap rate of the production line at the end of the supervision period, and comparing the output and scrap rate with the preset output threshold and scrap threshold respectively: if the output is greater than or equal to the output threshold and the scrap rate is less than the scrap threshold, then it is determined that the operating status of the production line during the supervision period meets the requirements; otherwise, it is determined that the operating status of the production line during the supervision period does not meet the requirements, and the corresponding production line is marked as a faulty production line, and it is determined whether there is an operating fault in the industrial equipment on the production line during the supervision period: if so, the fault is handled by the fault handling module; if not, a diagnostic analysis signal is generated and sent to the diagnostic training model.

4. The intelligent fault diagnosis system for industrial equipment based on the Internet of Things according to claim 3 is characterized in that: The value determination process of m1 includes: summing up and averaging the type values ​​LX of the type objects where all analysis objects in the faulty production line are located to obtain the type coefficient, summing up and averaging the space values ​​KJ of the space objects where all analysis objects in the faulty production line are located to obtain the space coefficient, and comparing the type coefficient with the space coefficient: if the type coefficient is less than the space coefficient, it is determined that the faulty production line has a spatial tendency feature, and the value range of m1 is (0.4, 0.5); if the type coefficient is greater than or equal to the space coefficient, it is determined that the faulty production line has a type tendency feature, and the value range of m1 is (0.5, 0.6).

5. The intelligent fault diagnosis system for industrial equipment based on the Internet of Things according to claim 4 is characterized in that: The process of obtaining the operation performance value of the analysis object includes: summing up the operation monitoring parameters of the analysis object during the supervision period and taking the average value to obtain the monitoring coefficient, marking the difference between the operation monitoring threshold and the monitoring coefficient as a floating value, and marking the ratio of the floating value to the operation monitoring threshold as the operation performance value of the analysis object.

Images