A method and system for monitoring and diagnosing the condition of key mine equipment

Abstract

The present invention discloses a method and system for monitoring and diagnosing the state of key equipment in a mine, and relates to the field of mine monitoring technology. The method comprises the following steps: extracting the operating characteristic parameters of a coal mining machine; identifying the key factors that affect the operating state of the coal mining machine; establishing a coal mining machine fault prediction model based on the key factors, and using the coal mining machine fault prediction model to predict the health state of the coal mining machine at future moments, and identifying the changing trend of the health state of the coal mining machine; according to the changing trend of the health state of the coal mining machine, combined with the operating conditions and safety thresholds of the coal mining machine, issuing an early warning signal, monitoring the operating state of the coal mining machine in real time, and dynamically adjusting the operating strategy of the coal mining machine. The present invention dynamically adjusts the operating strategy, and combines the health state prediction results and the working condition requirements to optimize the operating efficiency of the coal mining machine, while reducing energy consumption and maintenance costs, and helping coal mines to mine efficiently.

Description

Technical Field

[0001] The present invention relates to the technical field of mine monitoring, and in particular to a method and system for monitoring and diagnosing the status of key mine equipment. Background Art

[0002] Intelligent coal mining is a new stage in the development of comprehensive coal mechanization, in which intelligent coal mining is the key. As the core equipment for coal mining, the reliability and safety of coal mining machines are directly related to the normal operation of comprehensive mining operations and the safety and efficiency of coal mine production. The operating environment of coal mining machines is complex, and harsh conditions such as heavy loads, frequent starts and narrow spaces lead to difficulties in status monitoring and frequent failures. Therefore, in view of coal mining conditions, conducting research on active perception of coal mining machine status, data processing, indicator analysis and health assessment is an important means to achieve health management of coal mining machines throughout their life cycle, and is also a basic guarantee for ensuring the status monitoring and diagnosis of key mine equipment and realizing safe, efficient and intelligent development of coal mines.

[0003] In the existing technology, it is not easy to identify the key factors that affect the operating status of the coal mining machine, it is not easy to accurately locate potential problems, and reduce the possibility of failures from the root. It is also not easy to combine the trend of changes in health status, and it is not easy to issue early warning signals in time and dynamically adjust the operating strategy. It cannot effectively avoid accidents and improve the safety and reliability of equipment operation. At the same time, it is not easy to achieve accurate prediction of the future health status of the coal mining machine, and it is not easy to identify failure trends in advance to avoid passive maintenance and sudden shutdowns, thereby increasing energy consumption and maintenance costs.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the problems in the related technology, the present invention proposes a method and system for monitoring and diagnosing the status of key mine equipment to overcome the above-mentioned technical problems existing in the existing related technology.

[0006] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a method for monitoring and diagnosing the condition of key equipment in a mine is provided, the method comprising the following steps: S1. Acquire the real-time operating parameters of the coal mining machine in the mine, pre-process the real-time operating parameters of the coal mining machine, and extract the operating characteristic parameters of the coal mining machine; S2. diagnose and analyze the extracted coal mining machine operation characteristic parameters using a factor diagnosis algorithm to identify key factors affecting the coal mining machine operation status; S3. Based on key factors, a coal mining machine fault prediction model is established, and the coal mining machine fault prediction model is used to predict the health status of the coal mining machine at future moments, and the change trend of the health status of the coal mining machine is identified; S4. According to the changing trend of the health status of the coal mining machine, combined with the operating conditions and safety thresholds of the coal mining machine, an early warning signal is issued, the operating status of the coal mining machine is monitored in real time, and the operating strategy of the coal mining machine is dynamically adjusted.

[0007] Furthermore, obtaining the real-time operating parameters of the coal mining machine in the mine, preprocessing the real-time operating parameters of the coal mining machine, and extracting the operating characteristic parameters of the coal mining machine include the following steps: S11, performing data decomposition on the acquired real-time operating parameters of the coal mining machine, and using signal separation technology to filter high-frequency noise in the real-time operating parameters to obtain the real-time operating parameters of the coal mining machine after denoising; S12, using dynamic mode decomposition technology to decompose the denoised real-time operating parameters of the coal mining machine, extract each operating mode component, and smooth the extracted mode components; S13, calculating the correlation index between the extracted operation mode components and the original coal mining machine operation parameters, screening out the characteristic components with high correlation, and eliminating the operation mode components with low correlation; S14. Integrate the screened high-correlation pattern components to form a complete coal mining machine operation characteristic data set, and extract the coal mining machine operation characteristic parameters.

[0008] Furthermore, the factor diagnosis algorithm is used to diagnose and analyze the extracted coal mining machine operation characteristic parameters, and the key factors affecting the coal mining machine operation state are identified, including the following steps: S21, preset the key factor search range and feature selection range of the coal mining machine operation status diagnosis model; S22, randomly generating a number of key factor combinations and feature subset combinations into a number of key factor schemes, and all key factor schemes constitute a parameter group for diagnostic analysis; S23, using each key factor scheme to train the coal mining machine operation status diagnosis model, calculate its fitness value, and record the diagnostic performance results of the current key factor scheme; S24, performing a local search on the area near the key factor solution with the highest fitness value in the parameter group, and updating and recording the key factor combination and feature subset with the highest fitness value; S25. Randomly distribute the remaining key factor solutions to other key factor combinations and feature subsets in the global range, recalculate their fitness values, and update the global optimal key factor solution as the key factor affecting the operating status of the coal mining machine.

[0009] Further, performing a local search on the area near the key factor solution with the highest fitness value in the parameter group, and updating and recording the key factor combination and feature subset with the highest fitness value includes the following steps: S241, presetting a local search range, taking the current optimal key factor solution as the center, setting a disturbance range for each dimension of the key factor, calculating the local search area of ​​each key factor solution, and forming a multi-dimensional search space; S242, randomly generating a number of new key factor solutions within the local search range, and retraining the coal mining machine operation status diagnosis model using the new key factor solutions, and calculating the fitness value of each new key factor solution; S243. Compare the fitness values ​​of the new key factor solution and the current optimal solution within the local search range. If the new solution is better than the current optimal solution, update it to the optimal solution and record its key factor combination and feature subset; otherwise, keep the status quo.

[0010] Furthermore, based on the key factors, a coal mining machine fault prediction model is established, and the coal mining machine fault prediction model is used to predict the health status of the coal mining machine at future moments. Identifying the change trend of the health status of the coal mining machine includes the following steps: S31, input a set of key factors affecting the operating state of the coal mining machine as basic input data of the fault prediction model; S32, decomposing the input key factor set into a number of pattern components using variational pattern decomposition technology to extract multidimensional feature information; S33, dividing each pattern component into a training set and a test set, and performing normalization processing on the training set and the test set; S34, constructing a deep learning prediction model for each pattern component, and performing model training on the training set of each pattern component to generate future eigenvalues ​​of each pattern component; S35, combining the future eigenvalues ​​of all mode components to form a complete dynamic trajectory of key factor sets, and generating a change trajectory of key factors of the coal mining machine at future moments; S36. Based on the changing trajectory of key factors of the coal mining machine, a coal mining machine fault prediction model is established to predict the health status of the coal mining machine at future moments and identify the changing trend of the health status of the coal mining machine.

[0011] According to another aspect of the present invention, a key mine equipment condition monitoring and diagnosis system is provided, the condition monitoring and diagnosis system comprising: The data acquisition module is used to obtain the real-time operating parameters of the coal mining machine in the mine, pre-process the real-time operating parameters of the coal mining machine, and extract the operating characteristic parameters of the coal mining machine; A factor diagnosis module is used to diagnose and analyze the extracted coal mining machine operation characteristic parameters using a factor diagnosis algorithm to identify key factors affecting the coal mining machine operation status; A model building module is used to build a coal mining machine fault prediction model based on key factors, and use the coal mining machine fault prediction model to predict the health status of the coal mining machine at future moments, and identify the change trend of the health status of the coal mining machine; The monitoring and early warning module is used to send out early warning signals according to the changing trend of the health status of the coal mining machine, combined with the operating conditions and safety thresholds of the coal mining machine, monitor the operating status of the coal mining machine in real time, and dynamically adjust the operating strategy of the coal mining machine.

[0012] The beneficial effects of the present invention are: 1. The present invention combines the health status change trend and safety threshold, timely issues early warning signals and dynamically adjusts the operation strategy, effectively avoids accidents, improves the safety and reliability of equipment operation, and establishes a prediction model based on key factors to further enhance the scientificity and accuracy of health status assessment, provide technical support for the health management of the coal mining machine throughout its life cycle, dynamically adjusts the operation strategy, and combines the health status prediction results and working conditions to optimize the coal mining machine's operating efficiency, while reducing energy consumption and maintenance costs, and helping to efficiently mine coal mines.

[0013] 2. The present invention utilizes a factor diagnosis algorithm to identify key factors that affect the operating status of the coal mining machine, which helps to accurately locate potential problems and reduce the possibility of failures from the root. By identifying the core factors that affect the operating status of the coal mining machine, targeted maintenance measures can be taken at an early stage to reduce the frequency of equipment failures, thereby improving economic benefits and extending the service life of the coal mining machine.

[0014] 3. The present invention uses a coal mining machine fault prediction model to accurately predict the future health status of the coal mining machine, identify fault trends in advance, avoid passive maintenance and sudden shutdowns, and thus achieve comprehensive perception of the coal mining machine's operating status and accurate prediction of its future health status. It not only improves the intelligence and reliability of key mine equipment status monitoring and diagnosis, but also provides scientific support for the efficient operation and safe production of the equipment, while significantly reducing the failure rate and operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 is a flow chart of a method for monitoring and diagnosing the condition of key equipment in a mine according to an embodiment of the present invention; Figure 2The present invention is a block diagram of a key mine equipment status monitoring and diagnosis system according to an embodiment of the present invention.

[0017] In the figure: 1. Data acquisition module; 2. Factor diagnosis module; 3. Model building module; 4. Monitoring and early warning module. DETAILED DESCRIPTION

[0018] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments. They can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention.

[0019] According to an embodiment of the present invention, a method and system for monitoring and diagnosing the status of key equipment in a mine are provided.

[0020] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the method for monitoring and diagnosing the condition of key equipment in a mine according to an embodiment of the present invention, the method for monitoring and diagnosing the condition includes the following steps: S1. Acquire the real-time operating parameters of the coal mining machine in the mine, pre-process the real-time operating parameters of the coal mining machine, and extract the operating characteristic parameters of the coal mining machine; Specifically, the real-time operating parameters include: mechanical operating parameters, electrical parameters, environmental parameters, position and posture parameters, etc.

[0021] Specifically, the operating characteristic parameters include: power characteristic parameters, vibration characteristic values, current / voltage characteristic parameters, environmental load characteristics, displacement characteristics, power factor, vibration characteristic values, etc.

[0022] S2. diagnose and analyze the extracted coal mining machine operation characteristic parameters using a factor diagnosis algorithm to identify key factors affecting the coal mining machine operation status; Specifically, the key factors include: vibration characteristics, torque fluctuations, temperature changes, and wear characteristics of the mechanical system. Current, voltage, power factor, and frequency characteristics of the electrical system. Environmental conditions include dust concentration, humidity, temperature, and external vibration. Operating conditions include drum speed, coal mining load, and trajectory stability.

[0023] S3. Based on key factors, a coal mining machine fault prediction model is established, and the coal mining machine fault prediction model is used to predict the health status of the coal mining machine at future moments, and the change trend of the health status of the coal mining machine is identified; S4. According to the changing trend of the health status of the coal mining machine, combined with the operating conditions and safety thresholds of the coal mining machine, an early warning signal is issued, the operating status of the coal mining machine is monitored in real time, and the operating strategy of the coal mining machine is dynamically adjusted.

[0024] It should be explained that the real-time operating parameters of each subsystem during the operation of the coal mining machine, including vibration signals, current, voltage, temperature, speed, etc., are continuously collected; the health status assessment value of the coal mining machine is updated in real time in combination with the fault prediction model; the changing trend of the health status of the coal mining machine is analyzed; the current equipment health status is reflected through health scores or status classifications (such as excellent, sub-healthy, fault warning); and safety thresholds are set according to the operating conditions of the coal mining machine, equipment design standards and historical data: Normal range: The shearer operates within the design range and no adjustment is required.

[0025] Warning range: Key parameters are close to the threshold and the device may be in a sub-healthy state.

[0026] Warning scope: Key parameters exceed the threshold, and there is a potential operational risk.

[0027] Shutdown scope: Key parameters are seriously out of limit and immediate shutdown and inspection are required.

[0028] Compare the change trend of the coal mining machine health status assessment value and the real-time parameter to detect whether there are abnormal fluctuations or threshold value exceeds the limit; apply real-time diagnostic algorithms (such as trend analysis, outlier detection, etc.) to identify potential failure risks; trigger different levels of early warning signals based on the detection results: Level 1 warning: The health status has slightly deteriorated, reminding the operator to pay attention to the equipment status.

[0029] Level 2 warning: The health status has deteriorated significantly, indicating that maintenance is needed in advance.

[0030] Level 3 warning: The health status is seriously abnormal, an alarm signal is issued and shutdown is recommended.

[0031] Operators and managers are reminded through sound and light alarms, remote monitoring platforms or SMS notifications. According to the early warning signals and operating status, the operating parameters of the coal mining machine are dynamically adjusted in combination with the operating conditions: Load adjustment: When the equipment load is too high, reduce the shearer workload or reduce the drum cutting depth.

[0032] Speed ​​adjustment: adjust the roller speed and conveyor speed according to the motor temperature or vibration status.

[0033] Operation mode optimization: Switch the operation mode of the coal mining machine according to the health status, such as switching from high load mode to low load mode.

[0034] Intermittent operation strategy: When the equipment temperature approaches the safety threshold, intermittent operation is adopted to reduce the temperature rise rate.

[0035] According to the adjustment strategy, the equipment operating parameters, such as cutting depth, roller speed, conveyor speed, etc., are dynamically modified through the control system; control instructions can be issued through PLC (Programmable Logic Controller) or industrial automation system to ensure real-time and efficient adjustments. After adjustment, the operating parameters and health status are monitored in real time to verify the adjustment effect: if the health status improves, maintain the current adjustment; if the effect is not ideal, further optimize the adjustment strategy or issue a higher level of warning.

[0036] In this optional embodiment, the real-time operating parameters of the coal mining machine are obtained, and the real-time operating parameters of the coal mining machine are preprocessed to extract the operating characteristic parameters of the coal mining machine, including the following steps: S11, performing data decomposition on the acquired real-time operating parameters of the coal mining machine, and using signal separation technology to filter high-frequency noise in the real-time operating parameters to obtain the real-time operating parameters of the coal mining machine after denoising; Specifically, signal separation technology refers to the technology of separating useful signals from noise signals in the real-time operating parameters of coal mining machines, thereby removing noise interference. Its core goal is to extract key information signals in equipment operation while filtering out high-frequency noise that may affect data analysis.

[0037] S12, using dynamic mode decomposition technology to decompose the denoised real-time operating parameters of the coal mining machine, extract each operating mode component, and smooth the extracted mode components; Specifically, dynamic mode decomposition technology is a data-driven analysis method used to extract the main dynamic modes (operating modes) from the time series data of complex systems and decompose and predict the characteristic components.

[0038] S13, calculating the correlation index between the extracted operation mode components and the original coal mining machine operation parameters, screening out the characteristic components with high correlation, and eliminating the operation mode components with low correlation; S14. Integrate the screened high-correlation pattern components to form a complete coal mining machine operation characteristic data set, and extract the coal mining machine operation characteristic parameters.

[0039] In this optional embodiment, the extracted coal mining machine operation characteristic parameters are diagnosed and analyzed using a factor diagnosis algorithm to identify key factors affecting the coal mining machine operation state, including the following steps: S21, preset the key factor search range and feature selection range of the coal mining machine operation status diagnosis model; S22, randomly generating a number of key factor combinations and feature subset combinations into a number of key factor schemes, and all key factor schemes constitute a parameter group for diagnostic analysis; S23, using each key factor scheme to train the coal mining machine operation status diagnosis model, calculate its fitness value, and record the diagnostic performance results of the current key factor scheme; S24, performing a local search on the area near the key factor solution with the highest fitness value in the parameter group, and updating and recording the key factor combination and feature subset with the highest fitness value; S25. Randomly distribute the remaining key factor solutions to other key factor combinations and feature subsets in the global range, recalculate their fitness values, and update the global optimal key factor solution as the key factor affecting the operating status of the coal mining machine.

[0040] Specifically, the factor diagnosis algorithm is the bee algorithm, which is a new cluster intelligent search algorithm that finds the optimal solution to the problem by simulating the foraging behavior of bees in nature.

[0041] In this optional embodiment, performing a local search on the area near the key factor solution with the highest fitness value in the parameter group, and updating and recording the key factor combination and feature subset with the highest fitness value includes the following steps: S241, preset a local search range (i.e., nearest neighbor search), take the current optimal key factor solution as the center, set a disturbance range for each dimension of the key factor, calculate the local search area of ​​each key factor solution, and form a multi-dimensional search space; S242, randomly generating a number of new key factor solutions within the local search range, and retraining the coal mining machine operation status diagnosis model using the new key factor solutions, and calculating the fitness value of each new key factor solution; S243. Compare the fitness values ​​of the new key factor solution and the current optimal solution within the local search range. If the new solution is better than the current optimal solution, update it to the optimal solution and record its key factor combination and feature subset; otherwise, keep the status quo.

[0042] In this optional embodiment, the formula for calculating the local search area of ​​each key factor solution is: ; In the formula, S Represents a multidimensional search space; m a Indicates the optimal key factor solution. a The value of the key factor; N Indicates the total number of key factors; Δ m a Indicates the optimal key factor solution. a The disturbance range of the key factors.

[0043] In this optional embodiment, based on key factors, a coal mining machine fault prediction model is established, and the coal mining machine fault prediction model is used to predict the health status of the coal mining machine at a future moment, and identifying the change trend of the health status of the coal mining machine includes the following steps: S31, input a set of key factors affecting the operating state of the coal mining machine as basic input data of the fault prediction model; S32, decomposing the input key factor set (i.e., variational mode decomposition), using variational mode decomposition technology to decompose the key factor set into a number of mode components (i.e., intrinsic mode functions), and extracting multi-dimensional feature information; S33, dividing each pattern component into a training set and a test set, and performing normalization processing on the training set and the test set; S34, constructing a deep learning prediction model (i.e., a long short-term memory neural network model) for each pattern component, and performing model training on the training set of each pattern component to generate future eigenvalues ​​of each pattern component; S35, combining the future eigenvalues ​​of all mode components to form a complete dynamic trajectory of key factor sets, and generating a change trajectory of key factors of the coal mining machine at future moments; S36. Based on the changing trajectory of key factors of the coal mining machine, a coal mining machine fault prediction model is established to predict the health status of the coal mining machine at future moments and identify the changing trend of the health status of the coal mining machine.

[0044] In this optional embodiment, the input key factor set is decomposed, and the key factor set is decomposed into a number of pattern components using variational mode decomposition technology. Extracting multidimensional feature information includes the following steps: S321. Setting initial parameters of variational mode decomposition according to the time series characteristics and frequency characteristics of the key factor set; S322. Decomposing the key factor set into a number of mode components by using variational mode decomposition technology, each mode component reflects different frequency characteristics in the key factor set, and retains its original characteristic information; S323. Perform feature analysis on each pattern component to extract multi-dimensional feature information related to key factors.

[0045] In this optional embodiment, the key factor set is decomposed into a number of mode components by using the variational mode decomposition technique, each mode component reflects a different frequency characteristic in the key factor set, and retaining its original characteristic information includes the following steps: S3221, initializing the number of pattern components and the initial frequency range, determining the number of components according to the characteristic distribution of the key factor set, and setting the initial center frequency of each component; S3222, extracting the frequency characteristics of each mode component by using Hilbert transform, and aligning the frequency of the components by using spectrum shifting technology; S3223, setting a variational optimization objective function to minimize the bandwidth of each mode component, while constraining the sum of all mode components to reconstruct a set of key factors; S3224, using Lagrange multiplier method and alternating direction multiplier method for optimization iteration, and gradually completing the mode component decomposition of the key factor set by optimizing component values ​​and center frequencies; S3225. Extract the mode components after decomposition, verify each component, evaluate its frequency characteristics and reconstruction error with the original key factor set, and retain its original characteristic information.

[0046] In this optional embodiment, the formula of the variational optimization objective function is: ; In the formula, u k ( t ) indicates the k The mode components are in time t The time domain signal on ; express u k ( t )’s Hilbert transform; ω k Indicates k The center frequency of each mode component; ∂ t Indicates time t The derivation of Indicates that the k The spectrum of the mode component is shifted to the complex exponential term of the zero-frequency band; M represents the total number of mode components; j Represents an imaginary unit (imaginary unit j Used to separate the phase and amplitude information of a signal, thereby more accurately analyzing the frequency characteristics of the signal).

[0047] According to another embodiment of the present invention, Figure 2 As shown, a key mine equipment condition monitoring and diagnosis system is also provided, and the condition monitoring and diagnosis system includes: Data acquisition module 1, used to acquire the real-time operating parameters of the coal mining machine in the mine, pre-process the real-time operating parameters of the coal mining machine, and extract the operating characteristic parameters of the coal mining machine; Factor diagnosis module 2, used to diagnose and analyze the extracted coal mining machine operation characteristic parameters using factor diagnosis algorithm, and identify key factors affecting the coal mining machine operation status; Model building module 3 is used to build a coal mining machine fault prediction model based on key factors, and use the coal mining machine fault prediction model to predict the health status of the coal mining machine at future moments, and identify the change trend of the health status of the coal mining machine; The monitoring and early warning module 4 is used to send out early warning signals according to the changing trend of the health status of the coal mining machine, combined with the operating conditions and safety thresholds of the coal mining machine, monitor the operating status of the coal mining machine in real time, and dynamically adjust the operating strategy of the coal mining machine.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring and diagnosing the condition of key equipment in a mine, characterized in that: The condition monitoring and diagnostic method comprises the following steps: S1. Acquire the real-time operating parameters of the coal mining machine in the mine, pre-process the real-time operating parameters of the coal mining machine, and extract the operating characteristic parameters of the coal mining machine; S2. diagnose and analyze the extracted coal mining machine operation characteristic parameters using a factor diagnosis algorithm to identify key factors affecting the coal mining machine operation status; S3. Based on key factors, a coal mining machine fault prediction model is established, and the coal mining machine fault prediction model is used to predict the health status of the coal mining machine at future moments, and the change trend of the health status of the coal mining machine is identified; S4. According to the changing trend of the health status of the coal mining machine, combined with the operating conditions and safety thresholds of the coal mining machine, an early warning signal is issued, the operating status of the coal mining machine is monitored in real time, and the operating strategy of the coal mining machine is dynamically adjusted.

2. A method for monitoring and diagnosing the condition of key mine equipment according to claim 1, characterized in that: The method of obtaining the real-time operating parameters of the coal mining machine, preprocessing the real-time operating parameters of the coal mining machine, and extracting the operating characteristic parameters of the coal mining machine includes the following steps: S11, performing data decomposition on the acquired real-time operating parameters of the coal mining machine, and using signal separation technology to filter high-frequency noise in the real-time operating parameters to obtain the real-time operating parameters of the coal mining machine after denoising; S12, using dynamic mode decomposition technology to decompose the denoised real-time operating parameters of the coal mining machine, extract each operating mode component, and smooth the extracted mode components; S13, calculating the correlation index between the extracted operation mode components and the original coal mining machine operation parameters, screening out the characteristic components with high correlation, and eliminating the operation mode components with low correlation; S14. Integrate the screened high-correlation pattern components to form a complete coal mining machine operation characteristic data set, and extract the coal mining machine operation characteristic parameters.

3. A method for monitoring and diagnosing the condition of key mine equipment according to claim 1, characterized in that: The method of using the factor diagnosis algorithm to diagnose and analyze the extracted coal mining machine operation characteristic parameters and identifying the key factors affecting the coal mining machine operation state includes the following steps: S21, preset the key factor search range and feature selection range of the coal mining machine operation status diagnosis model; S22, randomly generating a number of key factor combinations and feature subset combinations into a number of key factor schemes, and all key factor schemes constitute a parameter group for diagnostic analysis; S23, using each key factor scheme to train the coal mining machine operation status diagnosis model, calculate its fitness value, and record the diagnostic performance results of the current key factor scheme; S24, performing a local search on the area near the key factor solution with the highest fitness value in the parameter group, and updating and recording the key factor combination and feature subset with the highest fitness value; S25. Randomly distribute the remaining key factor solutions to other key factor combinations and feature subsets in the global range, recalculate their fitness values, and update the global optimal key factor solution as the key factor affecting the operating status of the coal mining machine.

4. A method for monitoring and diagnosing the condition of key mine equipment according to claim 3, characterized in that: The local search of the area near the key factor solution with the highest fitness value in the parameter group, and updating and recording the key factor combination and feature subset with the highest fitness value comprises the following steps: S241, presetting a local search range, taking the current optimal key factor solution as the center, setting a disturbance range for each dimension of the key factor, calculating the local search area of ​​each key factor solution, and forming a multi-dimensional search space; S242, randomly generating a number of new key factor solutions within the local search range, and retraining the coal mining machine operation status diagnosis model using the new key factor solutions, and calculating the fitness value of each new key factor solution; S243. Compare the fitness values ​​of the new key factor solution and the current optimal solution within the local search range. If the new solution is better than the current optimal solution, update it to the optimal solution and record its key factor combination and feature subset; otherwise, keep the status quo.

5. A method for monitoring and diagnosing the condition of key mine equipment according to claim 4, characterized in that: The formula for calculating the local search area of ​​each key factor solution is: ； In the formula, S Represents a multidimensional search space; m a Indicates the optimal key factor solution. a The value of the key factor; N Indicates the total number of key factors; Δ m a Indicates the optimal key factor solution. a The disturbance range of the key factors.

6. A method for monitoring and diagnosing the condition of key mine equipment according to claim 1, characterized in that: The method of establishing a coal mining machine fault prediction model based on key factors, using the coal mining machine fault prediction model to predict the health status of the coal mining machine at a future moment, and identifying the change trend of the health status of the coal mining machine includes the following steps: S31, input a set of key factors affecting the operating state of the coal mining machine as basic input data of the fault prediction model; S32, decomposing the input key factor set into a number of pattern components using variational pattern decomposition technology to extract multidimensional feature information; S33, dividing each pattern component into a training set and a test set, and performing normalization processing on the training set and the test set; S34, constructing a deep learning prediction model for each pattern component, and performing model training on the training set of each pattern component to generate future eigenvalues ​​of each pattern component; S35, combining the future eigenvalues ​​of all mode components to form a complete dynamic trajectory of key factor sets, and generating a change trajectory of key factors of the coal mining machine at future moments; S36. Based on the changing trajectory of key factors of the coal mining machine, a coal mining machine fault prediction model is established to predict the health status of the coal mining machine at future moments and identify the changing trend of the health status of the coal mining machine.

7. A method for monitoring and diagnosing the condition of key mine equipment according to claim 6, characterized in that: Decomposing the input key factor set, using variational mode decomposition technology to decompose the key factor set into a number of mode components, and extracting multidimensional feature information includes the following steps: S321. Setting initial parameters of variational mode decomposition according to the time series characteristics and frequency characteristics of the key factor set; S322. Decomposing the key factor set into a number of mode components by using variational mode decomposition technology, each mode component reflects different frequency characteristics in the key factor set, and retains its original characteristic information; S323. Perform feature analysis on each pattern component to extract multi-dimensional feature information related to key factors.

8. A method for monitoring and diagnosing the condition of key mine equipment according to claim 7, characterized in that: The method of decomposing the key factor set into a number of mode components by using the variational mode decomposition technique, each mode component reflects different frequency characteristics in the key factor set, and retaining its original characteristic information includes the following steps: S3221, initializing the number of pattern components and the initial frequency range, determining the number of components according to the characteristic distribution of the key factor set, and setting the initial center frequency of each component; S3222, extracting the frequency characteristics of each mode component by using Hilbert transform, and aligning the frequency of the components by using spectrum shifting technology; S3223, setting a variational optimization objective function to minimize the bandwidth of each mode component, while constraining the sum of all mode components to reconstruct a set of key factors; S3224, using Lagrange multiplier method and alternating direction multiplier method for optimization iteration, and gradually completing the mode component decomposition of the key factor set by optimizing component values ​​and center frequencies; S3225. Extract the mode components after decomposition, verify each component, evaluate its frequency characteristics and reconstruction error with the original key factor set, and retain its original characteristic information.

9. A method for monitoring and diagnosing the condition of key mine equipment according to claim 8, characterized in that: The formula of the variational optimization objective function is: ； In the formula, u k ( t ) indicates the k The mode components are in time t The time domain signal on ; express u k ( t )’s Hilbert transform; ω k Indicates k The center frequency of each mode component; ∂ t Indicates time t The derivation of Indicates that the k The spectrum of the mode component is shifted to the complex exponential term of the zero-frequency band; M represents the total number of mode components; j Represents an imaginary unit.

10. A system for monitoring and diagnosing the condition of key equipment in a mine, used to implement the method for monitoring and diagnosing the condition of key equipment in a mine according to any one of claims 1 to 9, characterized in that: The condition monitoring and diagnostic system includes: The data acquisition module is used to obtain the real-time operating parameters of the coal mining machine in the mine, pre-process the real-time operating parameters of the coal mining machine, and extract the operating characteristic parameters of the coal mining machine; A factor diagnosis module is used to diagnose and analyze the extracted coal mining machine operation characteristic parameters using a factor diagnosis algorithm to identify key factors affecting the coal mining machine operation status; A model building module is used to build a coal mining machine fault prediction model based on key factors, and use the coal mining machine fault prediction model to predict the health status of the coal mining machine at future moments, and identify the change trend of the health status of the coal mining machine; The monitoring and early warning module is used to send out early warning signals according to the changing trend of the health status of the coal mining machine, combined with the operating conditions and safety thresholds of the coal mining machine, monitor the operating status of the coal mining machine in real time, and dynamically adjust the operating strategy of the coal mining machine.

Images