Coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge calculation

Abstract

The invention discloses a coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge calculation, and relates to the technical field of fault diagnosis, and the method comprises the steps: sending the state data of coal mining equipment to an edge calculation server, and predicting the health condition of the coal mining equipment; the edge computing server inputs the state data into a state recognition knowledge graph to obtain a health condition recognition result of the coal mining equipment; when the coal mining equipment is about to break down, a health condition identification result is sent to a maintainer; and a maintainer wears AR equipment to collect an image of the coal mining equipment, the state data, the health condition recognition result and the image are sent to remote equipment, and a remote expert guides the maintainer. Compared with the prior art, the method has high processing real-time performance by utilizing the edge computing technology, maintenance personnel do not need to go down a well frequently, the labor cost is greatly saved, the coal mining equipment is identified and diagnosed based on scientific and objective standards, and the accuracy of a diagnosis result is improved.

Description

Technical Field

[0001] The present application relates to the field of fault diagnosis technology, and in particular to a coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing. Background Art

[0002] After decades of rapid development, coal mining enterprises in my country have made the leap from mechanization to automation and are gradually moving towards digitalization and intelligence. More and more high-tech technologies have been applied to various links of coal production and manufacturing of coal mining equipment. More and more automated and intelligent equipment have been applied to every process of coal mining. While improving the efficiency and intelligence level of coal mining, it has also brought challenges to the data collection and monitoring, fault diagnosis, remote operation and maintenance of coal mining equipment.

[0003] At present, the operation and maintenance of coal mining equipment by coal mining enterprises has remained at a relatively low technical level. Most of the key coal mining equipment obtains equipment status data through regular maintenance, spot inspection, patrol inspection and other detection strategies; some coal mining equipment has been installed with online monitoring systems, but they are mainly used for status alarms and do not have precise analysis and fault location functions. Large equipment mainly relies on scheduled maintenance or daily maintenance. Maintenance personnel need to go down the mine frequently and rely on their own experience to determine the cause and location of the fault. Not only is the labor cost high, but the results of fault location are not very accurate and have a strong subjective factor. Summary of the invention

[0004] The embodiment of the present application provides a coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing, which is used to solve the problems of high labor cost and inaccurate fault location structure in manual inspection in the prior art.

[0005] The embodiment of the present application provides a coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing, including:

[0006] Obtain status data of coal mining equipment;

[0007] The state data is sent to the edge computing server, and the state data is analyzed by using edge computing technology to predict the health status of the coal mining equipment; wherein the edge computing server has a state recognition knowledge graph established based on big data, and the edge computing server inputs the state description statement containing the state data into the state recognition knowledge graph to obtain the health status recognition result of the coal mining equipment;

[0008] When the health status identification result indicates that the coal mining equipment is about to fail, the health status identification result is sent to the maintenance personnel;

[0009] Maintenance personnel wear AR (augmented reality) equipment to observe coal mining equipment. The AR equipment collects images of the coal mining equipment and sends status data, health status identification results and images to remote equipment used by remote experts. After viewing the status data, health status identification results and images, the remote experts guide the maintenance personnel to resolve the failure of the coal mining equipment.

[0010] The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing in this application has the following advantages:

[0011] The use of edge computing technology not only realizes the prediction of the health status of coal mining equipment, but also has a high degree of real-time processing. Real-time communication between maintenance personnel and remote experts is achieved through AR technology. When maintenance personnel encounter difficult problems, remote experts will guide maintenance personnel to complete maintenance operations. Maintenance personnel do not need to go down the mine frequently. They only need to check and repair the coal mining equipment when the edge computing server determines that the coal mining equipment is about to fail. This greatly saves labor costs, and identifies and diagnoses coal mining equipment based on scientific and objective standards, which improves the accuracy of diagnostic results. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 A flow chart of a coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0015] Figure 1 A flowchart of a coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing provided in an embodiment of the present application. An embodiment of the present application provides a coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing, the method comprising the following steps:

[0016] S100, obtaining status data of coal mining equipment.

[0017] Exemplarily, the state data includes sensor data collected by the state sensor installed on the coal mining equipment and the operation data of the operator on the coal mining equipment recorded by the recording unit. The sensor data includes the temperature, current and vibration data of the coal mining equipment. These sensor data are detected by sensors such as temperature sensors, current sensors and vibration sensors respectively installed on the coal mining equipment. The sensor data detected by these sensors are collected by the acquisition card and transmitted to the host computer installed on the coal mining equipment, and the host computer saves and forwards the state data. The operation data includes data such as speed and frequency generated by the operator when operating the coal mining equipment. After the operator inputs these operation data through the host computer, the host computer will control the coal mining equipment according to these operation data, and the host computer will also save the operation data.

[0018] S110, sending the status data to the edge computing server, using edge computing technology to analyze the status data, and predicting the health status of the coal mining equipment; wherein the edge computing server has a status recognition knowledge graph established based on big data, and the edge computing server inputs the status description statement containing the status data into the status recognition knowledge graph to obtain the health status recognition result of the coal mining equipment.

[0019] Exemplarily, the edge computing server is set within a certain distance from the mine, can be shared by multiple mines, and multiple edge computing servers can be set up. The host computer set on the coal mining equipment communicates with each edge computing server through a dedicated network to send status data to any edge computing server in real time.

[0020] In an embodiment of the present application, after receiving the status data, the edge computing server determines whether to execute on the edge computing server or offload to the central server based on the current computing task and the set feedback time limit; if it is determined to be executed on the edge computing server, the edge computing server analyzes the status data and predicts the health status of the coal mining equipment; if it is determined to be offloaded to the central server, the edge computing server sends the status data to the central server, and the central server uses the status recognition knowledge graph to analyze the status data and predict the health status of the coal mining equipment.

[0021] Only one central server can be set within the distribution range of multiple edge computing servers. Each edge computing server shares the current computing task in real time. It should be understood that the computing task only includes the remaining processing resources of each edge computing server, including bandwidth resources, storage resources, and computing resources. After obtaining the status data, the host computer will randomly send it to an edge computing server. After receiving the status data, the edge computing server determines the feedback time after each edge computing server processes the status data. If the shortest feedback time is less than or equal to the set feedback time, the status data will be forwarded to the edge computing server with the shortest feedback time, and the edge computing server will process the status data to obtain the health status of the coal mining equipment. If the shortest feedback time is greater than the feedback time, it means that all edge computing servers cannot meet the processing requirements of the status data at this time, so the edge computing server will forward the status data to the central server, and the central server will process the status data to obtain the health status of the coal mining equipment.

[0022] The edge computing server and the central server in the embodiment of the present application have the same state recognition knowledge graph, which is established based on the electronic maintenance manual and historical data of each coal mining equipment. When establishing the state recognition knowledge graph, it is necessary to pre-extract keywords related to the electronic maintenance manual and the fault phenomena of the coal mining equipment a period of time before the failure occurs, and combine these keywords with the keywords in the operation data, or combine the keywords related to the fault phenomenon separately to form a variety of different historical state descriptions. Each historical state description has a corresponding fault location and fault cause. After establishing a correspondence between these historical state descriptions and the fault location and fault cause, they are stored in the Neo4j database to obtain the state recognition knowledge graph.

[0023] After obtaining the state recognition knowledge graph, the state recognition knowledge graph can be used to predict the health status of coal mining equipment. The state data sent by the host computer is time series data. The edge computing server or central server calculates the similarity between the state data and each historical state description, and takes the health status corresponding to the historical state description with the highest similarity as the health status of the coal mining equipment. Since the state recognition knowledge graph stores the historical state description of the coal mining equipment a period of time before the failure, once the current state description statement of the coal mining equipment has a sufficiently high similarity with any historical state description, it means that the coal mining equipment is very likely to have the same failure as the historical state description after a period of time. Therefore, the present application realizes the prediction of coal mining equipment failures so as to respond before the failure actually occurs.

[0024] Furthermore, after the edge computing server receives the status data, the edge computing server fills the status data into a description statement having a set format to form a status description statement.

[0025] S120, when the health status identification result indicates that the coal mining equipment is about to fail, the health status identification result is sent to maintenance personnel.

[0026] For example, if the similarity between the state description statement of the coal mining equipment and each historical state description is not high, it means that the state of the coal mining equipment is normal and no fault will occur. If the state description statement of the coal mining equipment has a sufficiently high similarity with any historical state description, it means that the coal mining equipment will fail. At this time, the edge computing server will not only send the health status identification result to the maintenance personnel, but also generate a fault location result corresponding to the health status identification result. The fault location result includes the fault cause and the fault location. The edge computing server sends the health status identification result and the fault location result to the maintenance personnel at the same time, so that the maintenance personnel can repair the coal mining equipment. Since the fault cause and fault location corresponding to each historical state description are stored in the state recognition knowledge graph, after determining the historical state description corresponding to the state description statement by calculating the similarity, the fault cause and fault location corresponding to the state description statement can be determined based on the correspondence between the historical state description and the fault cause and fault location.

[0027] Furthermore, the edge computing server also sends the status data and health status identification results to the monitoring center, and the monitoring screen of the monitoring center displays the status data and health status identification results.

[0028] S130, the maintenance personnel wear AR equipment to observe the coal mining equipment. The AR equipment collects images of the coal mining equipment and sends the status data, health status identification results and images to a remote device used by a remote expert. After the remote expert checks the status data, health status identification results and images, he / she guides the maintenance personnel to solve the fault of the coal mining equipment.

[0029] For example, after the terminal device used by the maintenance personnel receives the notification information containing the health status identification result, the cause of the fault and the fault location, the maintenance personnel can carry the corresponding tools or parts to go underground to perform on-site maintenance of the coal mining equipment.

[0030] Since the state recognition knowledge graph stores limited information, it cannot identify all potential faults. Therefore, although the state recognition knowledge graph identifies potential faults and determines the corresponding fault causes and fault locations, the maintenance personnel still cannot eliminate the faults after repairing according to the fault causes and fault locations. This may be because the coal mining equipment has fault data that is not stored in the state recognition knowledge graph, or there are multiple faults in the coal mining equipment, but the state recognition knowledge graph only identifies some of them, or because the maintenance personnel have limited capabilities and cannot completely eliminate the faults according to the fault causes and fault locations identified by the state recognition knowledge graph. At this time, the maintenance personnel can wear AR equipment to collect images of the coal mining equipment and communicate with remote experts.

[0031] In an embodiment of the present application, the edge computing server sends status data and health status identification results to the central server, and the AR device also sends images to the central server. The central server stores a three-dimensional model of the coal mining equipment. The central server determines the position of the coal mining equipment facing the maintenance personnel based on the image, and sends the corresponding position of the facing position in the three-dimensional model, the status data and the health status identification results to the remote terminal.

[0032] The AR device in the embodiment of the present application can adopt AR glasses, which, in addition to the lens as a display unit, also has an image acquisition unit capable of acquiring images and a communication unit for sending images to a central server. The display unit in the present application will display the required information after being powered on, and the area where the information is displayed will not occupy the entire lens, so the maintenance personnel can observe the coal mining equipment through other areas of the lens where no information is displayed. The three-dimensional model stored in the central server has the detailed structure of each coal mining equipment, including each component in the coal mining equipment, as well as the positional relationship and assembly relationship, etc., that is, the three-dimensional model is an electronic mapping of the coal mining equipment. After the maintenance personnel wear the AR device, the collected image is the image of the coal mining equipment in the direction of the maintenance personnel, and the image contains the information of each component in the coal mining equipment. By extracting the information of these components and comparing it with the three-dimensional model, the corresponding position of the maintenance personnel's direction in the three-dimensional model can be obtained.

[0033] Furthermore, in the process of remote experts guiding maintenance personnel, the central server obtains the guidance information issued by the remote experts, extracts the key information representing the components in the coal mining equipment in the guidance information, and determines the positions of the components in the guidance information in the three-dimensional model based on the key information and the three-dimensional model. The central server also performs real-time analysis on the image to determine the positions of each component in the image in the three-dimensional model, and marks the components in the image whose positions match the positions of the components in the guidance information in the three-dimensional model.

[0034] After obtaining the corresponding position of the maintenance personnel's orientation position in the three-dimensional model, the status data and the health status identification results, the remote terminal will display this information. After the remote expert makes a judgment based on this information, the remote expert will send the guidance information to the maintenance personnel through a voice call. While the central server forwards the guidance information, it will also extract key information, such as the names of parts and components in the coal mining equipment, processing actions, etc. For the names of parts, since the three-dimensional model has stored the names of each part in the coal mining equipment, after extracting the part name in the guidance information, the position of the part in the three-dimensional model corresponding to the part name can be determined. Finally, based on the correspondence between the three-dimensional model and the image, the position of the part corresponding to the part name in the image can be obtained. The marking of the parts and the corresponding processing actions are displayed on the display unit of the AR device, which allows maintenance personnel to quickly determine the location of the parts that need to be operated, as well as the corresponding processing actions, which is of great help in improving the efficiency and accuracy of maintenance.

[0035] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0036] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing, characterized in that: include: Obtain status data of coal mining equipment; The state data is sent to an edge computing server, and the state data is analyzed by using edge computing technology to predict the health status of the coal mining equipment; wherein the edge computing server has a state recognition knowledge graph established based on big data, and the edge computing server inputs a state description statement containing the state data into the state recognition knowledge graph to obtain a health status recognition result of the coal mining equipment; When the health status identification result indicates that the coal mining equipment is about to fail, the health status identification result is sent to maintenance personnel; The maintenance personnel wear AR equipment to observe the coal mining equipment. The AR equipment collects images of the coal mining equipment and sends the status data, the health status identification results and the images to a remote device used by a remote expert. After the remote expert checks the status data, the health status identification results and the images, he / she guides the maintenance personnel to solve the faults of the coal mining equipment.

2. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 1 is characterized in that: After receiving the status data, the edge computing server determines whether to execute the data on the edge computing server or offload the data to the central server according to the current computing task and the set feedback time limit; if the data is determined to be executed on the edge computing server, the edge computing server analyzes the status data to predict the health status of the coal mining equipment; If it is determined to offload to the central server, the edge computing server sends the status data to the central server, and the central server analyzes the status data using the status recognition knowledge graph to predict the health status of the coal mining equipment.

3. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 2 is characterized in that: The status data is time series data, and the status recognition knowledge graph is established using historical data of coal mining equipment. The status recognition knowledge graph contains historical status descriptions of coal mining equipment for a period of time before a failure occurs. The edge computing server or the central server calculates the similarity between the status data and each of the historical status descriptions, and takes the health status corresponding to the historical status description with the highest similarity as the health status of the coal mining equipment.

4. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 2 is characterized in that: The edge computing server sends the status data and the health status identification result to the central server, and the AR device also sends the image to the central server. The central server stores a three-dimensional model of the coal mining equipment. The central server determines the position of the coal mining equipment that the maintenance personnel are facing based on the image, and sends the corresponding position of the facing position in the three-dimensional model, the status data and the health status identification result to the remote terminal.

5. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 2 is characterized in that: During the process of remote experts guiding maintenance personnel, the central server obtains the guidance information issued by the remote experts, extracts key information representing components in the coal mining equipment in the guidance information, and determines the positions of the components in the guidance information in the three-dimensional model in combination with the key information and the three-dimensional model. The central server also performs real-time analysis on the image to determine the positions of each component in the image in the three-dimensional model, and marks the components in the image whose positions match the positions of the components in the guidance information in the three-dimensional model.

6. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 5 is characterized in that: The AR device has a display unit, and the display unit displays the image and the annotations of the parts.

7. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 1 is characterized in that: When the health status identification result indicates that the coal mining equipment is about to fail, the edge computing server also generates a fault location result corresponding to the health status identification result, and the fault location result includes the cause of the fault and the location of the fault. The edge computing server sends the health status identification result and the fault location result to the maintenance personnel at the same time, so that the maintenance personnel can repair the coal mining equipment.

8. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 1 is characterized in that: The state data includes sensor data collected by a state sensor arranged on the coal mining equipment and operation data of the coal mining equipment by an operator recorded by a recording unit.

9. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 1 is characterized in that: After receiving the status data, the edge computing server fills the status data into a description statement with a set format to form the status description statement.

10. The coal mining equipment monitoring and predictive operation and maintenance method based on big data and edge computing according to claim 1, characterized in that: The edge computing server also sends the status data and the health status identification result to the monitoring center, and the monitoring screen of the monitoring center displays the status data and the health status identification result.

Images