Underground coal mine coal machine fault monitoring and diagnosing system based on edge calculation

Abstract

The invention relates to the technical field of coal mine production, in particular to a coal mine underground coal machine fault monitoring and diagnosing system based on edge calculation. The coal mine underground coal machine fault monitoring and diagnosing system based on edge calculation comprises an edge acquisition unit, an edge calculation unit and a visual terminal unit, according to the invention, the first diagnosis result obtained by fusing the fault diagnosis model constructed based on historical data and the second diagnosis result obtained by the data features extracted from the real-time data are combined to comprehensively judge whether the equipment is abnormal or not, so that multi-dimensional diagnosis can be realized, the situations of misjudgment and missed judgment are greatly reduced, and the fault diagnosis efficiency is improved. And meanwhile, after the fault is judged, a reasonable maintenance scheme can be quickly matched for the corresponding fault, and the maintenance efficiency and the refinement level of equipment operation and maintenance management are improved.

Description

Technical Field

[0001] The present invention relates to the field of coal mine production technology, and specifically to an underground coal machine fault monitoring and diagnosis system in a coal mine based on edge computing. Background Art

[0002] With the continuous development of the coal industry, the requirements for coal mining efficiency and safe production are increasing. As the core equipment of coal mining, the stable and efficient operation of coal mining equipment such as coal mining machines in coal mines is crucial. However, the underground environment is complex and harsh, with many unfavorable factors such as gas, dust, high humidity, and limited space. These factors make coal mining equipment prone to failure. Once a failure occurs, if it cannot be discovered and handled in time, it will not only affect the progress of coal mining and lead to a decrease in production, but may also cause serious safety accidents and threaten the lives of underground workers. However, the existing coal mining machine fault diagnosis in coal mines needs to send the operating data to the user end for fault diagnosis. The data scale is large, which affects the efficiency of diagnosis. In addition, the use of a single fault diagnosis can easily lead to inaccurate fault judgment and false alarms.

[0003] Based on this, the present invention provides a coal mine underground coal machinery fault monitoring and diagnosis system based on edge computing to solve the technical problems raised above. Summary of the invention

[0004] The purpose of the present invention is to provide a coal mine underground coal machinery fault monitoring and diagnosis system based on edge computing. The present invention combines a first diagnostic result obtained by a fault diagnosis model constructed based on historical data and a second diagnostic result obtained by data features extracted from real-time data, and comprehensively judges whether the equipment is abnormal. Multi-dimensional diagnosis can be achieved, which greatly reduces the possibility of misjudgment and missed judgment, and improves the accuracy of overall fault diagnosis. At the same time, after determining the fault, a reasonable maintenance plan can be quickly matched for the corresponding fault, thereby improving maintenance efficiency and the level of refinement of equipment operation and maintenance management.

[0005] To achieve the above object, the present invention provides the following technical solutions: The present invention provides a coal mining machine fault monitoring and diagnosis system based on edge computing in a coal mine, comprising an edge acquisition unit, an edge computing unit and a visualization terminal unit, wherein: The edge acquisition unit is used to collect real-time operation data of coal mining machines in coal mines, pre-process the collected real-time operation data, and upload the pre-processed real-time operation data to the edge computing unit; The edge computing unit constructs a fault diagnosis model based on the historically collected operation data of the coal mining machine in the coal mine, obtains a first diagnosis result of a detection period based on the constructed fault diagnosis model and uses the preprocessed real-time operation data, extracts data features from the preprocessed real-time operation data, obtains a second diagnosis result of a corresponding period, combines the first diagnosis result and the second diagnosis result, determines whether it is abnormal, and matches a corresponding maintenance plan based on the determination result, and the edge computing unit is connected to the edge acquisition unit; The visualization terminal unit is used for importing preset data and displaying received warning information and maintained fault preset solutions, and the visualization terminal unit is connected to the edge computing unit.

[0006] The present invention is further configured as follows: the edge acquisition unit includes a data acquisition module, a preprocessing module and a first communication module, wherein: The data acquisition module is used to collect real-time operation data of coal mining machinery in coal mines, and the real-time operation data includes temperature data, vibration data and pressure data; The preprocessing module is used to preprocess the collected real-time operation data, and the preprocessing module is connected to the data collection module; The first communication module is used to realize information interaction between the edge collection unit and the edge computing unit, and the first communication module is connected to the preprocessing module.

[0007] The present invention is further configured as follows: the preprocessing is to fill in missing values ​​in the real-time operation data using a linear interpolation method.

[0008] The present invention is further configured as follows: the edge computing unit includes a second communication module, a diagnostic model module and a database module, wherein: The second communication module is used to realize information interaction between the edge computing unit, the edge collection unit and the visualization terminal unit; The diagnostic model module constructs a fault diagnosis model according to the historically collected operation data of the coal mining machine in the coal mine, and obtains the first diagnosis result of the detection period based on the constructed fault diagnosis model and the pre-processed real-time operation data. The diagnostic model module is connected to the second communication module; The database module is used to store historically collected operation data of coal mining machinery in underground coal mines and store received real-time operation data, as well as to store preset diagnostic threshold information and fault preset solutions. The database module is connected to both the second communication module and the diagnostic model module.

[0009] The present invention is further configured as follows: the process of obtaining the first diagnosis result of the detection period is as follows: In diagnostic cycle n, obtaining a result of diagnostic cycle n corresponding to the real-time operation data; Then, in the diagnosis cycle n+1, the result of the diagnosis cycle n+1 corresponding to the real-time operation data is obtained; The result of diagnosis cycle n is compared with the result of diagnosis cycle n+1. If the two diagnosis results are the same, then any diagnosis result is determined to be the first diagnosis result. Otherwise, the first diagnosis result of the detection cycle is re-obtained.

[0010] The present invention is further configured as follows: the edge computing unit further includes a fault assessment module and a solution matching module, wherein: The fault assessment module extracts data features from the preprocessed real-time operation data, obtains the second diagnosis result of the corresponding period, and determines whether it is abnormal by combining the first diagnosis result and the second diagnosis result obtained. The fault assessment module is connected to both the diagnosis model module and the database module; The solution matching module matches the corresponding maintenance solution based on the determination result, and the solution matching module is connected to the second communication module, the database module and the fault assessment module.

[0011] The present invention is further configured as follows: the process of obtaining the second diagnosis result of the corresponding period is as follows: Extract data features from preprocessed real-time running data. The specific process is as follows: Calculate the RMS value , where Data points within the detection period Operational data of Select the maximum value of the data in the real-time running data preprocessed in the corresponding period ; Calculating the crest factor ; The obtained peak factor is compared with the corresponding preset threshold to obtain a second diagnosis result.

[0012] The present invention is further configured as follows: the process of combining the first diagnostic result and the second diagnostic result to determine whether it is abnormal is as follows: If the first diagnosis result and the second diagnosis result are related, the corresponding early warning instruction is initiated; Otherwise, the real-time operation data of the coal mining machinery in the coal mine is collected again to monitor and diagnose the coal mining machinery in the coal mine.

[0013] The present invention is further configured as follows: the visualization terminal unit includes a third communication module and a display module, wherein: The third communication module is used to realize information interaction between the visualization terminal unit and the edge computing unit; The display module is used to display the imported data, warning information and the received maintenance fault preset plan, and the display module is connected to the third communication module.

[0014] The present invention is further configured as follows: the visualization terminal unit further includes a data import module and an abnormal warning module, wherein: The data import module is used for importing preset data, and the data import module is connected to both the third communication module and the display module; The abnormal warning module issues corresponding warning information according to the received warning instruction, and the abnormal warning module is connected to both the third communication module and the display module.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention introduces edge computing technology into coal mining machinery fault monitoring and diagnosis in underground coal mines. By deploying edge computing units close to data sources, the pressure of data transmission is reduced. By integrating the first diagnostic result obtained by the fault diagnosis model constructed based on historical data and the second diagnostic result obtained by data features extracted from real-time data, the two are combined to comprehensively judge whether the equipment is abnormal. Multi-dimensional diagnosis can be achieved, and mutual verification and supplementation can be achieved, which greatly reduces the situation of misjudgment and missed judgment, and improves the accuracy of overall fault diagnosis. At the same time, after determining the fault, it can quickly match a reasonable maintenance plan for the corresponding fault based on the fault preset plan stored in the built-in database module, and display it to relevant personnel through a visual terminal unit, thereby improving the maintenance efficiency and the refinement level of equipment operation and maintenance management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a system diagram of a coal mining machine fault monitoring and diagnosis system based on edge computing in an underground coal mine of the present invention.

[0017] Figure 2 This is a system diagram of an edge acquisition unit in a coal mining machine fault monitoring and diagnosis system in an underground coal mine based on edge computing according to the present invention.

[0018] Figure 3 This is a system diagram of an edge computing unit in an underground coal mining machinery fault monitoring and diagnosis system based on edge computing in the present invention.

[0019] Figure 4 This is a system diagram of a visualization terminal unit in a coal mining machine fault monitoring and diagnosis system based on edge computing in an underground coal mining machine of the present invention.

[0020] Description of Figure Numbers: 100, edge acquisition unit; 110, data acquisition module; 120, preprocessing module; 130, first communication module; 200, edge computing unit; 210, second communication module; 220, diagnosis model module; 230, database module; 240, fault assessment module; 250, solution matching module; 300, visualization terminal unit; 310, third communication module; 320, display module; 330, data import module; 340, abnormal warning module. DETAILED DESCRIPTION

[0021] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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. Example

[0022] like Figure 1-Figure 4 As shown, this embodiment provides a coal mine underground coal machine fault monitoring and diagnosis system based on edge computing, including an edge acquisition unit 100, an edge computing unit 200 and a visualization terminal unit 300, wherein: the edge acquisition unit 100 is used to collect real-time operation data of the coal mine underground coal machine, and pre-process the collected real-time operation data, and upload the pre-processed real-time operation data to the edge computing unit 200; the edge computing unit 200 builds a fault diagnosis model according to the historically collected operation data of the coal mine underground coal machine, based on the constructed fault diagnosis model, using the pre-processed real-time operation data, obtains the first diagnosis result of the detection cycle, and extracts data features from the pre-processed real-time operation data to obtain the second diagnosis result of the corresponding cycle, combines the obtained first diagnosis result and the second diagnosis result, determines whether it is abnormal, and matches the corresponding maintenance plan based on the determination result, and the edge computing unit 200 is connected to the edge acquisition unit 100; the visualization terminal unit 300 is used to import preset data and display the received warning information and the preset fault plan for maintenance, and the visualization terminal unit 300 is connected to the edge computing unit 200.

[0023] In this embodiment, it should be noted that the edge acquisition unit 100 collects real-time operation data of coal mining machinery in the coal mine, and uses linear interpolation to fill missing values ​​in the collected real-time operation data to ensure the integrity of the operation data, and uploads the preprocessed real-time operation data to the edge computing unit 200. The edge computing unit 200 can be set in the coal mine. The edge computing unit 200 uses historical operation data to train the convolutional neural network model to obtain a trained convolutional neural network model. As an implementation method, a particle swarm optimization algorithm can also be used to obtain the optimal convolutional neural network parameters, and then obtain the required convolutional neural network model. The convolutional neural network model and the preprocessed real-time operation data are used to obtain the first diagnosis result of the detection period. The first diagnosis result has two detection The periodic diagnostic structure can effectively avoid misjudgment caused by a single periodic detection, thereby improving the reliability of diagnosis. At the same time, data features will be extracted from the pre-processed real-time operation data to obtain the second diagnostic result of the corresponding period. The second diagnostic result is measured by the peak factor. When an abnormality occurs, the operating data will undergo abnormal changes. The obtained peak factor is compared with the corresponding preset threshold to determine whether an abnormality has occurred. Combined with the first diagnostic result, it is further verified whether an abnormality has occurred, thereby further improving the reliability of diagnosis. In addition, the edge computing unit 200 will also match the corresponding processing plan to facilitate maintenance personnel to handle sudden abnormal events, and feedback relevant information to the visualization terminal unit 300 for management personnel to view, and issue early warning information to remind management personnel.

[0024] In the present invention, the edge acquisition unit 100 includes a data acquisition module 110, a preprocessing module 120 and a first communication module 130, wherein: the data acquisition module 110 is used to collect real-time operation data of coal mining machinery in coal mines, and the real-time operation data includes temperature data, vibration data and pressure data; the preprocessing module 120 is used to preprocess the collected real-time operation data, and the preprocessing module 120 is connected to the data acquisition module 110; the first communication module 130 is used to realize information interaction between the edge acquisition unit 100 and the edge computing unit 200, and the first communication module 130 is connected to the preprocessing module 120.

[0025] Among them, the preprocessing is to use linear interpolation method to fill in the missing values ​​in the real-time running data.

[0026] In this embodiment, it should be noted that the data acquisition module 110 collects the real-time operation data of the coal machine in the coal mine, uploads it to the preprocessing module 120, and the preprocessing module 120 uses the linear interpolation method to fill the missing values ​​in the real-time operation data, and then uploads the data to the edge computing unit 200 through the first communication module 130 for subsequent processing. The linear interpolation method is based on the characteristics of the linear function, and estimates the data corresponding to other positions between the two points through two known data points. As an implementation method, the temperature sensor collects data every 1 minute. In a certain period of time, due to a short communication failure in the mine, the data from 10:00 to 10:05 is missing, and the temperature data before and after it is 30°C at 9:59 and 32°C at 10:06. The missing temperature value can be calculated by linear interpolation. Assuming that the time is evenly spaced, the temperature change per minute is (32-30) ÷ (10:06-9:59) = 2÷7, and the temperature at 10:01 can be estimated as 30+2÷7≈30.29℃. This can be repeated to fill in the data for the entire missing time period.

[0027] In the present invention, the edge computing unit 200 includes a second communication module 210, a diagnostic model module 220 and a database module 230, wherein: the second communication module 210 is used to realize information interaction between the edge computing unit 200 and the edge acquisition unit 100 and the visualization terminal unit 300; the diagnostic model module 220 constructs a fault diagnosis model based on the historically collected operation data of the coal mining machine in the coal mine, and based on the constructed fault diagnosis model, uses the preprocessed real-time operation data to obtain the first diagnosis result of the detection cycle, and the diagnostic model module 220 is connected to the second communication module 210; the database module 230 is used to store the historically collected operation data of the coal mining machine in the coal mine and store the received real-time operation data, as well as store preset diagnostic threshold information and fault preset solutions, and the database module 230 is connected to both the second communication module 210 and the diagnostic model module 220.

[0028] The process of obtaining the first diagnosis result of the detection cycle is as follows: In diagnostic cycle n, obtaining a result of diagnostic cycle n corresponding to the real-time operation data; Then, in the diagnosis cycle n+1, the result of the diagnosis cycle n+1 corresponding to the real-time operation data is obtained; The result of diagnosis cycle n is compared with the result of diagnosis cycle n+1. If the two diagnosis results are the same, then any diagnosis result is determined to be the first diagnosis result. Otherwise, the first diagnosis result of the detection cycle is re-obtained.

[0029] In addition, the edge computing unit 200 also includes a fault assessment module 240 and a solution matching module 250, wherein: the fault assessment module 240 extracts data features from the preprocessed real-time operation data, obtains the second diagnostic result of the corresponding period, and determines whether it is abnormal in combination with the first diagnostic result and the second diagnostic result obtained. The fault assessment module 240 is connected to the diagnostic model module 220 and the database module 230; the solution matching module 250 matches the corresponding maintenance plan based on the judgment result, and the solution matching module 250 is connected to the second communication module 210, the database module 230 and the fault assessment module 240.

[0030] The process of obtaining the second diagnosis result of the corresponding period is as follows: Extract data features from preprocessed real-time running data. The specific process is as follows: Calculate the RMS value , where Data points within the detection period Operational data of Select the maximum value of the data in the real-time running data preprocessed in the corresponding period ; Calculating the crest factor ; The obtained peak factor is compared with the corresponding preset threshold to obtain a second diagnosis result.

[0031] In addition, the process of determining whether an abnormality is present by combining the first diagnosis result and the second diagnosis result is as follows: If the first diagnosis result and the second diagnosis result are related, the corresponding early warning instruction is initiated; Otherwise, the real-time operation data of the coal mining machinery in the coal mine is collected again to monitor and diagnose the coal mining machinery in the coal mine.

[0032] In this embodiment, it should be noted that the real-time operation data is received by the second communication module 210, and uploaded to the diagnosis model module 220. The diagnosis model module 220 diagnoses the operation data of different detection cycles, and compares the result of the diagnosis cycle n with the result of the diagnosis cycle n+1. When the diagnosis results of the two are the same, any diagnosis result is determined to be the first diagnosis result. The first diagnosis result is determined by comparing the results of adjacent diagnosis cycles, which can avoid diagnostic errors, improve the reliability of diagnosis, and avoid misjudgment of fault conditions due to instantaneous abnormal data fluctuations, so that the first diagnosis result finally obtained can more truly reflect the actual operating status of the coal machine. As a real-time method, assuming that the diagnosis cycle is 30 minutes, within the first 30 minutes, the collected coal machine vibration data is analyzed according to the constructed fault diagnosis model, and it is judged that the coal machine is in normal operating state; in the second 30 minutes, the analysis and diagnosis are performed again, and the result still shows normal operation. Since the diagnosis results of the two adjacent cycles are the same, it can be determined that the current normal operating state is the first diagnosis result. However, if the second 30-minute diagnostic result shows a fault, which is different from the first 30 minutes, then it is necessary to re-acquire the first diagnostic result of the detection cycle to accurately determine whether there is a fault. At the same time, the fault assessment module 240 will extract data features from the preprocessed real-time operation data to obtain the second diagnostic result of the corresponding cycle. Calculating the root mean square value can measure the discreteness of the data as a whole, reflecting the average fluctuation level of various vibration amplitudes during the operation of the equipment. Selecting the maximum value of the data can capture extreme conditions in the data sequence, and the peak factor combines these two features. It has a strong indicative effect on determining whether the equipment has an impact fault. Comparing it with the preset threshold can more accurately detect potential faults based on data features and provide verification basis for comprehensive judgment. As an implementation method, taking the vibration data of the coal machine as an example, a series of vibration acceleration data points are collected within a certain detection cycle (such as 30 minutes). The root mean square value is calculated by the formula, assuming that the root mean square value is calculated as 5m / s 2 ,. Then find the maximum value of 15m / s in the running data 2, and then calculate the peak factor to be 3. If the preset peak factor threshold is 2.5, since 3>2.5, this may indicate that there may be an impact fault, and then obtain the corresponding second diagnosis result. Assuming that the first diagnosis result shows that the coal machine is operating abnormally as a whole in the current detection cycle, the second diagnosis result judges that there may be a local impact fault according to the peak factor. At this time, the two are related, and the corresponding early warning instruction is started and fed back to the visualization terminal unit 300. The first diagnosis result based on the fault diagnosis model and the second diagnosis result based on data feature extraction are combined for abnormal judgment, which realizes multi-dimensional and multi-level fault judgment effects, avoids the misjudgment or missed judgment problems that may occur in a single judgment method, and greatly improves the accuracy and comprehensiveness of fault diagnosis.

[0033] In the present invention, the visualization terminal unit 300 includes a third communication module 310 and a display module 320, wherein: the third communication module 310 is used to realize information interaction between the visualization terminal unit 300 and the edge computing unit 200; the display module 320 is used to display the imported data, warning information and the received maintenance fault preset plan, and the display module 320 is connected to the third communication module 310.

[0034] In addition, the visualization terminal unit 300 also includes a data import module 330 and an abnormal warning module 340, wherein: the data import module 330 is used to import preset data, and the data import module 330 is connected to both the third communication module 310 and the display module 320; the abnormal warning module 340 issues corresponding warning information according to the received warning instruction, and the abnormal warning module 340 is connected to both the third communication module 310 and the display module 320.

[0035] In the present invention, it should be noted that the corresponding warning instructions are received by the third communication module 310, and the warning information is issued by the abnormal warning module 340 to remind the management personnel, and the preset data, warning information and maintenance fault preset plan) are concentrated on the visual terminal for display, which is convenient for the monitoring personnel or relevant technical personnel on the well to intuitively and comprehensively understand the operating status and response measures of the coal machine, improve the efficiency of information acquisition, and help to make decisions quickly. Especially in the face of emergency situations such as sudden failures of underground coal machines, corresponding measures can be taken quickly according to the displayed fault preset plan to ensure the normal operation and maintenance of the coal machine.

[0036] 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.

[0037] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. 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. The coal mining machine fault monitoring and diagnosis system based on edge computing is characterized by: It comprises an edge collection unit (100), an edge computing unit (200) and a visualization terminal unit (300), wherein: The edge acquisition unit (100) is used to collect real-time operation data of a coal mining machine in a coal mine, pre-process the collected real-time operation data, and upload the pre-processed real-time operation data to the edge computing unit (200); The edge computing unit (200) constructs a fault diagnosis model based on historically collected operation data of coal mining machinery in a coal mine, obtains a first diagnosis result of a detection period based on the constructed fault diagnosis model and utilizes preprocessed real-time operation data, extracts data features from the preprocessed real-time operation data, obtains a second diagnosis result of a corresponding period, determines whether an abnormality exists by combining the first diagnosis result and the second diagnosis result, and matches a corresponding maintenance plan based on the determination result, wherein the edge computing unit (200) is connected to the edge acquisition unit (100); The visualization terminal unit (300) is used for importing preset data and displaying received warning information and a preset fault solution for maintenance, and the visualization terminal unit (300) is connected to the edge computing unit (200).

2. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 1 is characterized in that: The edge acquisition unit (100) comprises a data acquisition module (110), a preprocessing module (120) and a first communication module (130), wherein: The data acquisition module (110) is used to collect real-time operation data of a coal mining machine in a coal mine, wherein the real-time operation data includes temperature data, vibration data and pressure data; The preprocessing module (120) is used to preprocess the collected real-time operation data, and the preprocessing module (120) is connected to the data collection module (110); The first communication module (130) is used to realize information interaction between the edge collection unit (100) and the edge computing unit (200), and the first communication module (130) is connected to the pre-processing module (120).

3. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 2 is characterized in that: The preprocessing is to fill in the missing values ​​in the real-time running data using a linear interpolation method.

4. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 1 is characterized in that: The edge computing unit (200) comprises a second communication module (210), a diagnostic model module (220) and a database module (230), wherein: The second communication module (210) is used to realize information interaction between the edge computing unit (200), the edge collection unit (100) and the visualization terminal unit (300); The diagnostic model module (220) constructs a fault diagnosis model based on historically collected operation data of coal mining machinery in underground coal mines, and obtains a first diagnostic result of a detection cycle based on the constructed fault diagnosis model and using pre-processed real-time operation data. The diagnostic model module (220) is connected to the second communication module (210); The database module (230) is used to store historically collected operation data of coal mining machinery in underground coal mines and store received real-time operation data, as well as to store preset diagnostic threshold information and fault preset solutions. The database module (230) is connected to both the second communication module (210) and the diagnostic model module (220).

5. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 4 is characterized in that: The process of obtaining the first diagnosis result of the detection cycle is as follows: In diagnostic cycle n, obtaining a result of diagnostic cycle n corresponding to the real-time operation data; Then, in the diagnosis cycle n+1, the result of the diagnosis cycle n+1 corresponding to the real-time operation data is obtained; The result of diagnosis cycle n is compared with the result of diagnosis cycle n+1. If the two diagnosis results are the same, then any diagnosis result is determined to be the first diagnosis result. Otherwise, the first diagnosis result of the detection cycle is re-obtained.

6. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 4 is characterized in that: The edge computing unit (200) further comprises a fault assessment module (240) and a solution matching module (250), wherein: The fault assessment module (240) extracts data features from the pre-processed real-time operation data, obtains a second diagnosis result of a corresponding period, and determines whether there is an abnormality by combining the obtained first diagnosis result and the second diagnosis result. The fault assessment module (240) is connected to both the diagnosis model module (220) and the database module (230); The solution matching module (250) matches a corresponding maintenance solution based on the determination result, and the solution matching module (250) is connected to the second communication module (210), the database module (230) and the fault assessment module (240).

7. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 6 is characterized in that: The process of obtaining the second diagnosis result of the corresponding cycle is as follows: Extract data features from preprocessed real-time running data. The specific process is as follows: Calculate the RMS value , where Data points within the detection period Operational data of Select the maximum value of the data in the real-time running data preprocessed in the corresponding period ; Calculating the crest factor ; The obtained peak factor is compared with the corresponding preset threshold to obtain a second diagnosis result.

8. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 6 is characterized in that: The process of combining the first diagnostic result and the second diagnostic result to determine whether there is an abnormality is as follows: If the first diagnosis result and the second diagnosis result are related, the corresponding early warning instruction is initiated; Otherwise, the real-time operation data of the coal mining machinery in the coal mine is collected again to monitor and diagnose the coal mining machinery in the coal mine.

9. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 1, characterized in that: The visualization terminal unit (300) comprises a third communication module (310) and a display module (320), wherein: The third communication module (310) is used to realize information interaction between the visualization terminal unit (300) and the edge computing unit (200); The display module (320) is used to display the imported data, warning information and the received maintenance fault preset solution, and the display module (320) is connected to the third communication module (310).

10. The coal mining machine fault monitoring and diagnosis system based on edge computing in coal mines according to claim 1, characterized in that: The visualization terminal unit (300) further comprises a data import module (330) and an abnormality warning module (340), wherein: The data import module (330) is used to import preset data, and the data import module (330) is connected to both the third communication module (310) and the display module (320); The abnormal warning module (340) issues corresponding warning information according to the received warning instruction, and the abnormal warning module (340) is connected to both the third communication module (310) and the display module (320).

Images