Mine hoisting system twinborn monitoring method based on cloud edge collaboration

Abstract

The invention discloses a mine hoisting system twinborn monitoring method based on cloud edge collaboration, and the method comprises the steps: constructing a twinborn monitoring model of a mine hoisting system, and the twinborn monitoring model comprises a fault diagnosis model, an advanced prediction model, a steel wire rope surface damage recognition model, and a three-dimensional simulation model; determining the deployment position of the edge server by using an improved k-means + + method; the method comprises the following steps: associating terminal equipment with an edge server, distributing tasks on the terminal equipment to the edge server and a cloud server, and cooperatively processing the tasks in combination with the edge server and the cloud server. The twinborn monitoring model of the mine hoisting system is constructed under a cloud-side collaborative computing framework, so that full-state health monitoring of the mine hoisting system can be realized; according to the invention, by deploying the edge end calculation task distribution strategy, the calculation task is unloaded to the appropriate edge server, the time delay of the twinborn monitoring model calculation is reduced, and the real-time performance of the twinborn monitoring and early warning of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the field of mine monitoring, and in particular to a twin monitoring method for a mine hoisting system based on cloud-edge collaboration. Background Art

[0002] The mine hoisting system contains many sub-components and is widely distributed, so a large number of sensors of different types are needed to monitor the operation status. However, directly transmitting a large amount of data to the cloud for processing will cause delays, and the calculation speed is slow, and it is impossible to feedback to the control end in real time. Therefore, monitoring the operation status of the mine hoisting system and handling faults in a timely manner are of great practical significance to the safe and efficient production of mines.

[0003] Digital twin refers to the construction of a mapping body in virtual space that can reflect the real situation of mechanical equipment. Based on virtual-real mapping and virtual-real evolution methods, it reflects the spatiotemporal evolution of key performance parameters of mechanical equipment. On the technical level, digital twin technology has the potential to monitor the operating status of equipment in the mine hoisting system in real time. However, the traditional cloud computing method transmits sensor data to the central cloud server for centralized processing. The single cloud computing method will cause the underground communication network to be overloaded. In addition, the spatial distribution of the mine hoisting system is wide and the data transmission distance is long, which causes underground data transmission delays, resulting in the inability to process equipment operation data in a timely manner, affecting the real-time data interaction between the digital twin virtual body and the physical entity of the mine hoisting system. Summary of the invention

[0004] Purpose of the invention: In response to the above problems, the purpose of the present invention is to provide a twin monitoring method for mine hoisting systems based on cloud-edge collaboration.

[0005] Technical solution: A twin monitoring method for a mine hoisting system based on cloud-edge collaboration of the present invention comprises:

[0006] Construct a twin monitoring model for the mine hoisting system, which includes a fault diagnosis model, an advance prediction model, a wire rope surface damage identification model, and a three-dimensional simulation model;

[0007] The improved k-means++ method is used to determine the deployment location of the edge server;

[0008] Associate the terminal device with the edge server, distribute the tasks on the terminal device to the edge server and the cloud server, and coordinate the processing of tasks by combining the edge and the cloud.

[0009] Furthermore, the twin monitoring model of the mine hoisting system is constructed including:

[0010] Collect sensor signals of each subcomponent in the mine hoisting system, build a database D1 representing system faults, a database D2 representing system performance parameters, a database D3 representing wire rope fault information, and a database D4 representing system working conditions, and pre-process the data in each database and divide it into training sets and test sets in proportion;

[0011] Construct a fault diagnosis model M1, input the vibration signal data in the test set of database D1 into the trained fault diagnosis model M1, and evaluate the health status of the equipment according to the output results; represents the vibration signal driven sky wheel fault diagnosis sub-model, represents the intelligent roller fault diagnosis sub-model driven by vibration signal, represents the motor fault diagnosis sub-model driven by vibration signal;

[0012] Construct an advanced prediction model M2, input the real-time operation data of the equipment in the database D2 test set into the trained advanced prediction model M2, compare the output result with the threshold, and evaluate the equipment operation status in the future; the advanced prediction model represents the prediction sub-model of the motor current signal, The sub-prediction model representing the wire rope tension signal, a prediction sub-model representing a hydraulic oil pressure signal of a smart brake;

[0013] Construct a wire rope surface damage recognition model M3, input the wire rope image data in the database D3 test set into the trained wire rope surface damage recognition model M3, and obtain the wire rope damage result;

[0014] Construct a three-dimensional simulation model M4, input the real-time temperature data and stress data in the database D4 into the trained three-dimensional simulation model M4, compare the obtained temperature field data and stress field data with the threshold value, and evaluate the operating status of the equipment; the three-dimensional simulation model It is a three-dimensional finite element simulation system for mine hoisting system. is the temperature field model, It is a stress field model.

[0015] Furthermore, the improved k-means++ method is used to determine the deployment location of the edge server, including:

[0016] Each sensor in the mine hoisting system is connected to a terminal device, which processes the data obtained by the sensor and transmits it to the edge server. The calculation expression of the importance of each terminal device is:

[0017] WT i =α1Q i +α2D i +α3P i

[0018] In the formula, Q i represents the task load of terminal device i, D i represents the data volume of the load task of terminal device i, P i represents the priority of the load task of terminal device i, α1, α2, and α3 represent the weight coefficients of the load task amount, data amount, and priority of terminal device i, respectively;

[0019] The location of the edge server is determined according to the importance of each terminal device, and the distance between the edge server and the terminal device is calculated as:

[0020]

[0021] In the formula, represents the actual transmission distance between the terminal device i and the corresponding cluster center particle;

[0022] The distance d i Instead of the Euclidean distance in the k-means++ algorithm, the improved k-means++ algorithm is used to find the five cluster center mass points of all terminal devices on the ground, and the five cluster center mass points are used as the edge server deployment locations.

[0023] Furthermore, the twin monitoring model of the mine hoisting system is constructed including:

[0024] Deploy the fault diagnosis model, advance prediction model and wire rope surface damage identification model on edge servers and cloud servers;

[0025] Deploy the 3D simulation model on a cloud server;

[0026] Communication connection between edge server and cloud server.

[0027] Further, associating the terminal device with the edge server includes:

[0028] Associating all terminal devices located below the ground with a single edge server deployed in the mine;

[0029] The terminal device located above the ground is associated with the edge server above the ground. The association process includes:

[0030] According to the priority, data volume, task volume and distance from the edge server of the terminal device signal, the matching value between the terminal device i and the edge server k is calculated. The calculation expression is:

[0031]

[0032] In the formula, d(i,k) represents the actual distance between the terminal device and the edge server;

[0033] Select the maximum match value between all terminal devices and all edge servers If edge server k has not reached the maximum load limit, the association relationship between terminal device i and edge server k is determined; if the edge server reaches the maximum load limit, the edge server with the largest matching value among other edge servers within the maximum delay range that have not exceeded the maximum load limit is selected to associate with terminal device i; if all edge servers exceed the maximum load limit, the edge server with the lowest load is selected to associate with terminal device i until all terminal devices are associated with the edge server.

[0034] Furthermore, the calculation expression for computing the delay of task i on edge server j is:

[0035] T ij =TR ij +TC ij +TW ij

[0036] In the formula, TR ij Indicates communication delay, TC ij Indicates calculation delay, TW ij Indicates a wait delay.

[0037] Furthermore, associating the terminal device with the edge server includes:

[0038] Under the constraints of the interaction delay between the physical equipment of the mine hoisting system and its twin monitoring model, the interaction delay between different physical equipment, and the edge server resources, a deployment model of the edge server is established. The deployment model is described as an integer programming problem and optimized. The expression is:

[0039] Min:

[0040]

[0041] (2)D i ij ,1≤j≤5

[0042] (3)T i,max >T ij ,i=1,2,3…,n,j=1,2,3,4,5

[0043] In the formula, n represents the number of terminal devices, m represents the number of computing tasks, and x​ij represents the association between computing task i and edge server j. If computing task i is executed on edge server j, then x ij =1, otherwise x ij = 0; Constraint (1) indicates that each edge server can only process one computing task at a time, and each computing task can only be executed on one edge server; Constraint (2) indicates the data storage space D required when computing task i requests allocation i Must be smaller than the remaining storage capacity S of the edge server ij ; Constraint (3) indicates that the processing delay of each computing task is less than the maximum tolerance time T of the task i,max .

[0044] Further, allocating tasks on the terminal device to the edge server and the cloud server includes:

[0045] When computing task i is submitted to the edge server k associated with it, edge server k determines whether all edge servers at the edge can process the computing task i. If not, it will offload the computing task i to the cloud. If it can be processed, it will calculate the time delay T of all edge servers processing the computing task. ij , the edge server k will delay each time T ij After comparison, the edge server corresponding to the minimum delay is selected for task offloading.

[0046] Furthermore, when the computing task i is offloaded to the cloud, the cloud server uses the twin monitoring model to complete the calculation of the task and returns the calculation results to the edge server.

[0047] Furthermore, after the edge server processes the computing task i, it sends the computing result to the cloud server;

[0048] The cloud server compares the calculation results with the pre-set thresholds, evaluates the operating status of each device in the mine hoisting system, and issues an early warning if any abnormality occurs.

[0049] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages:

[0050] 1. Under the cloud-edge collaborative computing framework, the present invention deploys a vibration signal-driven fault diagnosis model, an advance prediction model, a wire rope surface defect recognition model, and a three-dimensional simulation model to achieve full-state health monitoring of the mine hoisting system;

[0051] 2. The present invention offloads computing tasks to suitable edge servers through edge-side computing task allocation strategies, thereby reducing the calculation delay of the twin monitoring model and ensuring the real-time performance of the twin monitoring and early warning of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is the cloud-edge collaborative computing relationship diagram of the twin monitoring model;

[0053] Figure 2 The flowchart is for associating terminal devices with edge servers. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0055] The twin monitoring method of a mine hoisting system based on cloud-edge collaboration described in this embodiment includes:

[0056] Construct a twin monitoring model for the mine hoisting system, which includes a fault diagnosis model, an advance prediction model, a wire rope surface damage identification model, and a three-dimensional simulation model;

[0057] The improved k-means++ method is used to determine the deployment location of the edge server;

[0058] Associate the terminal device with the edge server, distribute the tasks on the terminal device to the edge server and the cloud server, and coordinate the processing of tasks by combining the edge and the cloud.

[0059] The twin monitoring method for a mine hoisting system based on cloud-edge collaboration described in this embodiment designs a twin monitoring method for each component in the mine hoisting system, combines the real-time data processing on the edge with the powerful computing power of the cloud, and uses the cloud-edge collaborative computing mode to process the computing-intensive tasks and delay-sensitive tasks generated by the twin monitoring of the mine hoisting system, and conducts real-time monitoring and early warning of the equipment operating status of the mine hoisting system.

[0060] Furthermore, if Figure 1 The figure shows the cloud-edge collaborative computing relationship diagram of the twin monitoring model. The twin monitoring model for the mine hoisting system includes:

[0061] Collect sensor signals of each subcomponent in the mine hoisting system, build a database D1 representing system faults, a database D2 representing system performance parameters, a database D3 representing wire rope fault information, and a database D4 representing system working conditions, and pre-process the data in each database and divide it into training sets and test sets in proportion;

[0062] Construct a fault diagnosis model M1, input the vibration signal data in the test set of database D1 into the trained fault diagnosis model M1, and evaluate the health status of the equipment according to the output results; represents the vibration signal driven sky wheel fault diagnosis sub-model, represents the intelligent roller fault diagnosis sub-model driven by vibration signal, represents the motor fault diagnosis sub-model driven by vibration signal;

[0063] Construct an advanced prediction model M2, input the real-time operation data of the equipment in the database D2 test set into the trained advanced prediction model M2, compare the output result with the threshold, and evaluate the equipment operation status in the future; the advanced prediction model represents the prediction sub-model of the motor current signal, The sub-prediction model representing the wire rope tension signal, a prediction sub-model representing a hydraulic oil pressure signal of a smart brake;

[0064] Construct a wire rope surface damage recognition model M3, input the wire rope image data in the database D3 test set into the trained wire rope surface damage recognition model M3, and obtain the wire rope damage result;

[0065] Construct a three-dimensional simulation model M4, input the real-time temperature data and stress data in the database D4 into the trained three-dimensional simulation model M4, compare the obtained temperature field data and stress field data with the threshold value, and evaluate the operating status of the equipment; the three-dimensional simulation model It is a three-dimensional finite element simulation system for mine hoisting system. is the temperature field model, It is a stress field model.

[0066] Sensors are used to collect data signals from the operation of each subcomponent of the mine hoisting system, and they are constructed into databases D1, D2, D3 and D4. The database D1 representing system faults includes vibration signal data of the sheave, drum and motor, the database D2 representing system performance parameters includes motor current signal data, wire rope tension signal data and intelligent brake hydraulic oil pressure signal data, the database D3 representing wire rope fault information includes wire rope image data, and the database D4 representing system working conditions includes sheave speed, hoisting container running speed and docking position, drum speed and stress, and motor temperature data. After preprocessing such as denoising and data completion, the data in each database are divided into training sets and test sets in proportion, and the twin monitoring model is trained using the data in the training set.

[0067] Fault diagnosis model M1 includes the vibration signal driven sky wheel fault diagnosis sub-model Intelligent roller fault diagnosis sub-model driven by vibration signal Motor fault diagnosis sub-model driven by vibration signal Each fault diagnosis sub-model They are all composed of the same deep neural network, which includes Resnet and BiLSTM. Resnet is a residual module that uses CNN to extract local features, and BiLSTM is a bidirectional long short-term memory network that extracts time series features. The two types of features are fused and input into the classification layer FC to obtain the diagnosis results. The mathematical model of each fault diagnosis sub-model is:

[0068] Y1=FC(ResNet(X1)+BiLSTM(X1))

[0069] In the formula, X1 is the preprocessed vibration signal, and Y1 is the output result of the deep neural network. The deep neural network is used to obtain the classification results, and finally the classification results are matched one by one with the fault types to obtain the health status of the equipment during operation. The fault types include the deflection, abnormal noise, and bearing failure of the sheave, the shell cracking, the main shaft bending and breaking, the bearing failure of the drum, the rotor deformation, and the gear damage of the motor. After the fault is diagnosed, a warning is sent to the cloud through the edge server, and it is decided whether to suspend the operation and repair the equipment according to the actual situation.

[0070] The advance prediction model M2 includes a prediction sub-model for the motor current signal Sub-prediction model of wire rope tension signal and prediction sub-model of hydraulic oil pressure signal of intelligent brake Each sub-model is an LSTM model. Based on database D2, the LSTM model is trained using the existing operating data, and then the real-time operating data is input into the trained LSTM model to achieve advance prediction of important parameters. The mathematical model of each sub-model is:

[0071] Y2=LSTM(X2)

[0072] In the formula, X2 is the real-time operation data in the database D2, which is used as input data; Y2 is the prediction result of the operation data in the future. In this embodiment, the future period is 10 minutes, which can also be set according to the specific situation. Use the LSTM model to build an advanced prediction model for the motor current signal, wire rope tension signal, and intelligent brake hydraulic oil pressure signal, obtain the prediction data, and then evaluate the equipment operation status in the future period according to whether the prediction data exceeds the threshold; finally, adjust the current operation status of the equipment to ensure that the mine hoisting system is at a normal level throughout the operation process.

[0073] The wire rope surface damage recognition model M3 is a YOLOv5 network. The YOLOv5 network is trained based on the database D3, and then the captured wire rope image data is input into the trained wire rope surface damage recognition model M3 to obtain the wire rope damage results. The mathematical model of the wire rope surface damage recognition model M3 is:

[0074] Y3=YOLOv5(X3)

[0075] Where X3 is the input image data, and Y3 is the output damage recognition result.

[0076] The 3D simulation model M4 includes the 3D finite element simulation system of the mine hoisting system Temperature field model and stress field model According to the database D4 that characterizes the working conditions of the system, three-dimensional finite element simulation is performed on important components such as motors, intelligent sheaves, and intelligent rollers to obtain the simulated temperature field and stress field information, and a temperature field and stress field data set is constructed, where the input data is set as the temperature and stress data of the node where the sensor is deployed in the important component, and the output data is set as the temperature field and stress field data of the entire component. The constructed data set D4 is used to train the deep learning convolutional neural network, and the trained convolutional neural network is used to build the temperature field model and stress field model. The real-time temperature data and stress data in the database D4 are respectively input into the temperature field model and the stress field model to obtain the reconstructed temperature field and stress field data. The temperature, stress and other thresholds of each component of the mine hoisting system are set during operation, and an alarm is issued when the equipment is in an abnormal state.

[0077] In the mine hoisting system, the intelligent lifting container is mainly arranged below the ground, with a wide spatial distribution and sparse computing tasks. An edge server is arranged in the mine to realize all the task calculations of the intelligent lifting container. The motor, brake, intelligent drum and intelligent sheave are arranged above the ground and are relatively concentrated. The computing tasks include using vibration signals to diagnose motor and bearing faults, using LSTM networks to realize advance prediction of motor current signals, wire rope tension signals, and intelligent brake hydraulic oil pressure signals, and using wire rope images to identify wire rope surface damage. It is necessary to arrange 5 edge servers with strong computing capabilities around the terminal device, match the terminal device with an edge server at the edge end, and use the edge server to process the computing tasks.

[0078] Furthermore, the improved k-means++ method is used to determine the deployment location of the edge server, including:

[0079] Each sensor in the mine hoisting system is connected to a terminal device, which processes the data obtained by the sensor and transmits it to the edge server. The calculation expression of the importance of each terminal device is:

[0080] WT i =α1Q i +α2D i +α3P i

[0081] In the formula, Q i represents the task load of terminal device i, D i represents the data volume of the load task of terminal device i, P i represents the priority of the load task of terminal device i, α1, α2, and α3 represent the weight coefficients of the load task amount, data amount, and priority of terminal device i, respectively;

[0082] The location of the edge server is determined according to the importance of each terminal device, and the distance between the edge server and the terminal device is calculated as:

[0083]

[0084] In the formula, represents the actual transmission distance between the terminal device i and the corresponding cluster center particle;

[0085] The distance d i Instead of the Euclidean distance in the k-means++ algorithm, the improved k-means++ algorithm is used to find the five cluster center mass points of all terminal devices on the ground, and the five cluster center mass points are used as the edge server deployment locations.

[0086] Furthermore, the twin monitoring model of the mine hoisting system is constructed including:

[0087] Deploy the fault diagnosis model, advance prediction model and wire rope surface damage identification model on edge servers and cloud servers;

[0088] Deploy the 3D simulation model on a cloud server;

[0089] Communication connection between edge server and cloud server.

[0090] Further, associating the terminal device with the edge server includes:

[0091] Associating all terminal devices located below the ground with a single edge server deployed in the mine;

[0092] like Figure 2 As shown, the terminal device located above the ground is associated with the edge server above the ground, and the association process includes:

[0093] According to the priority, data volume, task volume and distance of the terminal device signal from the edge server, the matching value between the terminal device i and the edge server k is calculated. The calculation expression is:

[0094]

[0095] In the formula, d(i,k) represents the actual distance between the terminal device and the edge server;

[0096] Select the maximum match value between all terminal devices and all edge servers If the edge server k does not reach the maximum load limit, determine the maximum matching value The corresponding association relationship between terminal device i and edge server k; if the edge server reaches the maximum load limit, the edge server with the largest matching value among other edge servers within the maximum delay range that do not exceed the maximum load limit is selected to associate with terminal device i; if all edge servers exceed the maximum load limit, the edge server with the lowest load is selected to associate with terminal device i; eliminate the matched terminal devices and their matching values, and continue to match the remaining terminal devices until all terminal devices are associated with the edge server.

[0097] The calculation expression for computing the delay of task i on edge server j is:

[0098] T ij =TC ij +TR ij +TW ij

[0099] Where TC ij Indicates communication delay, TR ij Indicates calculation delay, TW ij Indicates a wait delay.

[0100] Communication delay TC ij It refers to the communication delay between the terminal device and the edge server, among which the uplink communication that transmits data from the terminal device to the edge server is the main one, including the vibration signals in the motor, brake, smart drum and smart wheel, motor current signal, wire rope tension signal and image signal, brake tank hydraulic signal. Therefore, the uplink communication delay of computing task i on edge server j is:

[0101]

[0102] Where N ij represents the number of hops required to transmit computing task i to the edge server, D irepresents the data volume of computing task i, and B represents the network bandwidth between devices.

[0103] Calculate the delay TR ij It represents the time delay for the edge server to process the transmitted real-time data. The calculation expression is:

[0104]

[0105] In the formula, Q i represents the amount of computing task i, C j represents the computing capacity of edge server j.

[0106] When computing task i is offloaded to edge server j, it cannot be processed in time due to the backlog of previous tasks, and the waiting delay TW ij It refers to the time to complete processing of existing tasks in edge server j, and the calculation expression is:

[0107]

[0108] In the formula, Q j represents the amount of backlogged tasks in edge server j.

[0109] Furthermore, associating the terminal device with the edge server includes:

[0110] Under the constraints of the interaction delay between the physical equipment of the mine hoisting system and its twin monitoring model, the interaction delay between different physical equipment, and the edge server resources, a deployment model of the edge server is established. The deployment model is described as an integer programming problem and optimized. The expression is:

[0111] Min:

[0112]

[0113] (2)D i ij ,1≤j≤5

[0114] (3)T i,max >T ij ,i=1,2,3…,n,j=1,2,3,4,5

[0115] In the formula, n represents the number of terminal devices, m represents the number of computing tasks, and x ij represents the association between computing task i and edge server j. If computing task i is executed on edge server j, then x ij =1, otherwise x ij ​= 0; Constraint (1) indicates that each edge server can only process one computing task at a time, and each computing task can only be executed on one edge server; Constraint (2) indicates the data storage space D required when computing task i requests allocation i Must be smaller than the remaining storage capacity S of the edge server ij ; Constraint (3) indicates that the processing delay of each computing task is less than the maximum tolerance time T of the task i,max .

[0116] Further, allocating tasks on the terminal device to the edge server and the cloud server includes:

[0117] When computing task i is submitted to the edge server k associated with it, edge server k determines whether all edge servers at the edge can process the computing task i. If not, it will offload the computing task i to the cloud. If it can be processed, it will calculate the time delay T of all edge servers processing the computing task. ij , the edge server k will delay each time T ij After comparison, the edge server corresponding to the minimum delay is selected for task offloading.

[0118] When computing task i is offloaded to the cloud, the cloud server uses the twin monitoring model to complete the calculation of the task and returns the calculation results to the edge server.

[0119] After the edge server processes computing task i, it sends the computing result to the cloud server;

[0120] The cloud server compares the calculation results with the pre-set thresholds of temperature, stress, speed, etc. when each component is running, evaluates the operating status of each equipment in the mine hoisting system, and issues an early warning if any abnormality occurs.

Claims

1. A twin monitoring method for mine hoisting system based on cloud-edge collaboration, characterized in that: include: Construct a twin monitoring model for the mine hoisting system, which includes a fault diagnosis model, an advance prediction model, a wire rope surface damage identification model, and a three-dimensional simulation model; The improved k-means++ method is used to determine the deployment location of the edge server; Associate the terminal device with the edge server, distribute the tasks on the terminal device to the edge server and the cloud server, and coordinate the processing of tasks by combining the edge and the cloud.

2. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 1 is characterized in that: The twin monitoring model of the mine hoisting system includes: Collect sensor signals of each subcomponent in the mine hoisting system, build a database D1 representing system faults, a database D2 representing system performance parameters, a database D3 representing wire rope fault information, and a database D4 representing system working conditions, and pre-process the data in each database and divide it into training sets and test sets in proportion; Construct a fault diagnosis model M1, input the vibration signal data in the test set of database D1 into the trained fault diagnosis model M1, and evaluate the health status of the equipment according to the output results; represents the vibration signal driven sky wheel fault diagnosis sub-model, represents the intelligent roller fault diagnosis sub-model driven by vibration signal, represents the motor fault diagnosis sub-model driven by vibration signal; Construct an advanced prediction model M2, input the real-time operation data of the equipment in the database D2 test set into the trained advanced prediction model M2, compare the output result with the threshold, and evaluate the equipment operation status in the future; the advanced prediction model represents the prediction sub-model of the motor current signal, The sub-prediction model representing the wire rope tension signal, a prediction sub-model representing a hydraulic oil pressure signal of a smart brake; Construct a wire rope surface damage recognition model M3, input the wire rope image data in the database D3 test set into the trained wire rope surface damage recognition model M3, and obtain the wire rope damage result; Construct a three-dimensional simulation model M4, input the real-time temperature data and stress data in the database D4 into the trained three-dimensional simulation model M4, compare the obtained temperature field data and stress field data with the threshold value, and evaluate the operating status of the equipment; the three-dimensional simulation model It is a three-dimensional finite element simulation system for mine hoisting system. is the temperature field model, It is a stress field model.

3. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 2 is characterized in that: Determining the deployment location of edge servers using the improved k-means++ method includes: Each sensor in the mine hoisting system is connected to a terminal device, which processes the data obtained by the sensor and transmits it to the edge server. The calculation expression of the importance of each terminal device is: WT i =α1Q i +α2D i +α3P i In the formula, Q i represents the task load of terminal device i, D i represents the data volume of the load task of terminal device i, P i represents the priority of the load task of terminal device i, α1, α2, and α3 represent the weight coefficients of the load task amount, data amount, and priority of terminal device i, respectively; The location of the edge server is determined according to the importance of each terminal device, and the distance between the edge server and the terminal device is calculated as: In the formula, represents the actual transmission distance between the terminal device i and the corresponding cluster center particle; The distance d i Instead of the Euclidean distance in the k-means++ algorithm, the improved k-means++ algorithm is used to find the five cluster center mass points of all terminal devices on the ground, and the five cluster center mass points are used as the edge server deployment locations.

4. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 3 is characterized in that: The twin monitoring model of the mine hoisting system is constructed including: Deploy the fault diagnosis model, advance prediction model and wire rope surface damage identification model on edge servers and cloud servers; Deploy the 3D simulation model on a cloud server; Communication connection between edge server and cloud server.

5. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 4 is characterized in that: Associating an end device with an edge server involves: Associating all terminal devices located below the ground with a single edge server deployed in the mine; The terminal device located above the ground is associated with the edge server above the ground. The association process includes: According to the priority, data volume, task volume and distance of the terminal device signal from the edge server, the matching value between the terminal device i and the edge server k is calculated. The calculation expression is: In the formula, d(i,k) represents the actual distance between the terminal device and the edge server; Select the maximum match value between all terminal devices and all edge servers If edge server k has not reached the maximum load limit, the association relationship between terminal device i and edge server k is determined; if the edge server reaches the maximum load limit, the edge server with the largest matching value among other edge servers within the maximum delay range that have not exceeded the maximum load limit is selected to associate with terminal device i; if all edge servers exceed the maximum load limit, the edge server with the lowest load is selected to associate with terminal device i until all terminal devices are associated with the edge server.

6. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 5 is characterized in that: The calculation expression for computing the delay of task i on edge server j is: T ij =TR ij +TC ij +TW ij In the formula, TR ij Indicates communication delay, TC ij Indicates calculation delay, TW ij Indicates a wait delay.

7. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 6 is characterized in that: Associating the terminal device with the edge server includes: Under the constraints of the interaction delay between the physical equipment of the mine hoisting system and its twin monitoring model, the interaction delay between different physical equipment, and the edge server resources, a deployment model of the edge server is established. The deployment model is described as an integer programming problem and optimized. The expression is: (2)D i <S ij ,1≤j≤5 (3)T i，max >T ij ,i=1,2,3...,n,j=1,2,3,4,5 In the formula, n represents the number of terminal devices, m represents the number of computing tasks, and x ij represents the association between computing task i and edge server j. If computing task i is executed on edge server j, then x ij =1, otherwise x ij = 0; Constraint (1) indicates that each edge server can only process one computing task at a time, and each computing task can only be executed on one edge server; Constraint (2) indicates the data storage space D required when computing task i requests allocation i Must be smaller than the remaining storage capacity S of the edge server ij ; Constraint (3) indicates that the processing delay of each computing task is less than the maximum tolerance time T of the task i，max .

8. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 7 is characterized in that: Distributing tasks on terminal devices to edge servers and cloud servers includes: When computing task i is submitted to the edge server k associated with it, edge server k determines whether all edge servers at the edge can process the computing task i. If not, it will offload the computing task i to the cloud. If it can be processed, it will calculate the time delay T of all edge servers processing the computing task. ij , the edge server k will delay each time T ij After comparison, the edge server corresponding to the minimum delay is selected for task offloading.

9. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 8 is characterized in that: When computing task i is offloaded to the cloud, the cloud server uses the twin monitoring model to complete the calculation of the task and returns the calculation results to the edge server.

10. The twin monitoring method for mine hoisting system based on cloud-edge collaboration according to claim 9 is characterized in that: After the edge server processes computing task i, it sends the computing result to the cloud server; The cloud server compares the calculation results with the pre-set thresholds, evaluates the operating status of each device in the mine hoisting system, and issues an early warning if any abnormality occurs.

Images