Fault monitoring and early warning method based on intelligent boom-type roadheader
By monitoring and providing early warnings for the seals of intelligent cantilever tunneling machines in multiple dimensions, the problem of high failure rates and safety hazards caused by neglecting the condition of the seals has been solved, achieving efficient and reliable fault warnings and safety assurance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA COAL (TIANJIN) UNDERGROUND ENG INTELLIGENCE RES INST CO LTD
- Filing Date
- 2023-05-24
- Publication Date
- 2026-06-02
AI Technical Summary
Existing cantilever tunneling machines neglect the condition of seals in fault monitoring, resulting in high failure rates, increased operating costs, safety hazards, and low efficiency.
By collecting, monitoring, and analyzing data on various seals of the intelligent cantilever tunneling machine, including deformation degree, aging degree, offset, and leakage prediction index, multi-dimensional monitoring and early warning of the seals can be achieved.
It improves the reliability and accuracy of fault monitoring, reduces operating costs, avoids unexpected downtime, and enhances the efficiency and safety of tunneling operations.
Smart Images
Figure CN116927795B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of fault monitoring technology for cantilever tunneling machines, specifically a fault monitoring and early warning method based on intelligent cantilever tunneling machines. Background Technology
[0002] Intelligent cantilever tunneling machines are combined units based on cantilever tunneling machines, incorporating intelligent and automated technologies to achieve cutting, loading and transportation, self-propelled operation, and dust suppression via spraying. Because cantilever tunneling machines operate in harsh environments for extended periods with limited maintenance conditions, their failure rate is relatively high. Therefore, fault monitoring and early warning systems based on intelligent cantilever tunneling machines are particularly important.
[0003] Due to the special nature of seals, their condition has a significant impact on the quality of mechanical equipment. However, current fault monitoring methods for cantilever tunneling machines neglect to monitor the condition of seals, which poses certain risks and defects. This results in the inability to detect and address seal abnormalities during operation, leading to frequent unexpected and emergency shutdowns. This significantly increases operating costs, poses certain safety hazards to tunneling work, and drastically reduces the efficiency of tunneling operations. Summary of the Invention
[0004] The purpose of this invention is to provide a fault monitoring and early warning method based on an intelligent cantilever tunneling machine to solve the problems mentioned in the background art.
[0005] The objective of this invention can be achieved through the following technical solution: a fault monitoring and early warning method based on an intelligent cantilever tunneling machine, comprising the following steps:
[0006] 10. Basic Data Acquisition: The acquisition module collects data on each sealing component of the intelligent cantilever tunneling machine.
[0007] 20. Defect Monitoring and Analysis: The integrity monitoring module monitors the deformation and aging of each seal of the intelligent cantilever tunneling machine, and analyzes the defect degree of each seal of the intelligent cantilever tunneling machine to obtain the defect degree of each seal of the intelligent cantilever tunneling machine.
[0008] 30. Extrusion monitoring and analysis: The average offset and radius change of each seal of the intelligent cantilever tunneling machine are monitored by the boundary anomaly monitoring module, and the extrusion degree of each seal of the intelligent cantilever tunneling machine is analyzed to obtain the extrusion degree of each seal of the intelligent cantilever tunneling machine.
[0009] 40. Data Processing: The processing module analyzes the leakage prediction index corresponding to each seal to obtain the leakage prediction index corresponding to each seal.
[0010] 50. Early Warning Prompt: The early warning module receives the results from the processing module, analyzes the status of each seal of the intelligent cantilever tunneling machine, obtains the status of each normal seal and each abnormal seal, analyzes the early warning level of each abnormal seal, and makes corresponding early warning prompts based on the different early warning levels of each abnormal seal.
[0011] Preferably, the monitoring of the deformation and aging degree of each seal corresponding to the intelligent cantilever tunneling machine is carried out through the following steps:
[0012] 201: Obtain the initial installation thickness H of each seal. i , i is the number of each seal corresponding to the intelligent cantilever tunneling machine, i = 1, 2, 3, ..., n, where n is a positive integer;
[0013] 202: The thickness of each seal is monitored using an ultrasonic thickness gauge to obtain the thickness h of each seal at the current time point for the intelligent cantilever tunneling machine. i ;
[0014] 203: X-rays are sent to each seal of the intelligent cantilever tunneling machine through an X-ray detector. The emitted rays penetrate each seal and are recorded by X-ray film, thereby obtaining X-ray films of each seal.
[0015] 204: The obtained X-ray film is placed in a darkroom for processing to obtain structural X-ray films of each seal. The grayscale value regions of each seal are extracted from the structural X-ray films of each seal. Based on the reference grayscale value of each seal, the reference grayscale value regions of each seal are extracted from the structural X-ray films of each seal. At the same time, the regions of reference grayscale values of each seal are used to form the contour regions of each seal, which serve as the monitoring contour maps of each seal.
[0016] 205: Obtain the original contour map corresponding to each seal and compare it with the monitoring contour map of the corresponding seal to obtain the overlapping area of the contour map of each seal.
[0017] 206: Use a non-metallic ultrasonic flaw detector to send ultrasonic waves to each seal to obtain the corresponding defect echo map. Analyze the defect echo map and take all bright spots or dark spots in the defect echo map as defect signals. Record the shape of the defect signal. If the defect signal is linear, the defect type is determined to be a crack. If the defect signal is round or elliptical, the defect type is determined to be a pore. Count the number of times the defect signal appears to obtain the number of cracks and pores corresponding to each seal. Record the distance from the start point to the end point of the defect signal corresponding to each crack as the crack length corresponding to each crack. Calculate the total crack length using a summation formula.
[0018] Preferably, the analysis of the defect degree of each seal of the intelligent cantilever tunneling machine is carried out through the following steps:
[0019] S1: According to the formula The change d corresponding to each seal is obtained. i ;
[0020] S2: According to the formula Obtain the defect degree QX corresponding to each target seal. i , This represents the area of the original contour map corresponding to the i-th seal. D represents the overlapping area of the contour diagram corresponding to the i-th seal. 标准 L represents the threshold value for the average crack length corresponding to the seal. i N represents the total crack length corresponding to the i-th seal. 标准 p represents the threshold number of cracks corresponding to the seal. i γ1 represents the number of cracks corresponding to the i-th seal, γ2 represents the preset structural change ratio coefficient, and γ3 represents the preset crack number ratio coefficient. 3 γ is the preset total crack length ratio coefficient, and γ4 is the preset porosity ratio coefficient.
[0021] Preferably, the monitoring steps for the average offset and radius change of each seal of the intelligent cantilever tunneling machine are as follows:
[0022] 301: Obtain the original contour map and monitoring contour map corresponding to each seal. Establish a two-dimensional coordinate axis with the center point of the original contour map corresponding to each seal as the origin. Distribute monitoring points evenly along the edges of the original contour map corresponding to each seal, and obtain the coordinates of each monitoring point in the original contour map corresponding to the seal. Record these coordinates as follows: j is the monitoring point number corresponding to each seal, j = 1, 2, 3, ..., k, where k is a positive integer. Monitoring points are evenly distributed along the edge of the monitoring contour map corresponding to each seal in the same manner, and their coordinates are obtained and denoted as (X...). ij ′,Y ij ′);
[0023] 302: Obtain the original radius R corresponding to each seal. i For each seal, a monitoring point is evenly distributed along its contour, corresponding to the center point of the monitoring profile. The center point of each seal is then connected to one of the monitoring points, and the longest connecting line is selected and its length is recorded as _____.
[0024] Preferably, the analysis of the extrusion degree of each seal of the intelligent cantilever tunneling machine is performed as follows:
[0025] SS1: According to the formula The offset between the j-th monitoring point corresponding to the original contour map of each seal and the j-th monitoring point of its corresponding monitoring contour map is calculated.
[0026] SS2: The average offset PY corresponding to each seal is obtained through analysis. i and radius change BJ i ;
[0027] SS3: According to the formula Obtain the extrusion degree JC corresponding to each seal. i μ1 and μ2 are the preset offset weight coefficient and radius change weight coefficient, respectively.
[0028] Preferably, the analysis of the leakage prediction index corresponding to each seal is performed as follows:
[0029] 401: Obtain the monitoring results from the integrity monitoring module and the boundary anomaly monitoring module, including the degree of defect and the degree of extrusion;
[0030] 402: By formula The leakage prediction index SM for each seal was calculated. i σ1 and σ2 are the preset defect conversion factor and extrusion conversion factor, respectively.
[0031] Preferably, the analysis of the state of each seal of the intelligent cantilever tunneling machine is performed as follows:
[0032] The early warning module receives the results from the processing module and obtains the leakage prediction index corresponding to each seal. The leakage prediction index corresponding to each seal is compared with the preset leakage prediction index threshold. If the leakage prediction index corresponding to the seal is less than the preset leakage prediction index threshold, the seal is determined to be in a normal state at the current moment and is marked as a normal seal. If the leakage prediction index corresponding to the seal is greater than the preset leakage prediction index threshold, the seal is determined to be in an abnormal state at the current moment and is marked as an abnormal seal.
[0033] Preferably, the analysis of the warning level corresponding to each abnormal seal is performed as follows:
[0034] Obtain the leakage prediction index corresponding to each abnormal seal and compare it with the preset warning level threshold. When the leakage prediction index corresponding to the abnormal seal is less than or equal to the preset level 3 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 3. When the leakage prediction index corresponding to the abnormal seal is greater than the level 3 warning threshold and less than or equal to the preset level 2 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 2. When the leakage prediction index corresponding to the abnormal seal is greater than the level 2 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 1.
[0035] The beneficial effects of this invention are:
[0036] 1. This invention monitors the deformation and aging of each seal of an intelligent cantilever tunneling machine, providing an intuitive understanding of the structural changes of each seal. This avoids a series of internal structural failures caused by seal defects, not only improving the reliability of fault monitoring and analysis results but also providing accurate and intuitive data for the analysis of leakage prediction indices of each seal.
[0037] 2. This invention provides intuitive monitoring and rational analysis of the radius variation and average offset of each seal of the intelligent cantilever tunneling machine, and records the contour changes of each seal in the mating parts, which greatly ensures the stability of the intelligent cantilever tunneling machine during operation.
[0038] 3. This invention analyzes the leakage prediction index of intelligent cantilever tunneling machines, which plays a crucial role in the condition analysis of seals to a certain extent. It realizes multi-dimensional fault monitoring and analysis of intelligent cantilever tunneling machines, and provides corresponding early warning prompts for seals with different levels of abnormal conditions. This further avoids unexpected shutdowns and malfunction shutdowns, prevents safety accidents, reduces the operating cost of intelligent cantilever tunneling machines, and improves the efficiency of tunneling work. Attached Figure Description
[0039] The invention will now be further described with reference to the accompanying drawings.
[0040] Figure 1 This is a schematic diagram of the method steps of the present invention. Detailed Implementation
[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0042] Please see Figure 1 As shown, this invention is a fault monitoring and early warning method based on an intelligent cantilever tunneling machine, comprising the following steps:
[0043] The data acquisition module collects the initial thickness, original radius, original area, and original outline of each seal of the intelligent cantilever tunneling machine.
[0044] It should be noted that the sealing components for intelligent cantilever tunneling machines are mainly rubber seals.
[0045] The integrity monitoring module monitors the deformation and aging of each seal of the intelligent cantilever tunneling machine. The monitoring steps are as follows:
[0046] Obtain the initial thickness of each seal and denote it as H. i , where i is the number of each seal on the intelligent cantilever tunneling machine, i = 1, 2, 3, ..., n, and n is a positive integer.
[0047] The thickness of each seal was monitored using an ultrasonic thickness gauge, and the thickness of each seal at the current time point was recorded as h. i .
[0048] X-rays are sent to each seal of the intelligent cantilever tunneling machine through an X-ray detector. The emitted rays penetrate each seal and are recorded by X-ray film, thus obtaining X-ray films of each seal.
[0049] In this embodiment of the invention, each sealing component is scanned using an X-ray detector, and a contour map of the sealing component is obtained based on this. The shape of the contour map allows for real-time understanding of the sealing component's condition, reducing the frequency of disassembly and inspection of the sealing components and further improving work efficiency.
[0050] The obtained X-ray films are placed in a darkroom for processing to obtain structural X-ray films of each seal. The grayscale value regions corresponding to each seal are extracted from the structural X-ray films. Based on the reference grayscale value corresponding to each seal, the reference grayscale value regions corresponding to each seal are extracted from the structural X-ray films. At the same time, the regions of reference grayscale values corresponding to each seal are used to form the contour regions corresponding to each seal, which serve as the monitoring contour maps for each seal.
[0051] Obtain the original contour map corresponding to each seal and compare it with the corresponding monitoring contour map to obtain the overlapping area of the contour map corresponding to each seal.
[0052] A non-metallic ultrasonic flaw detector was used to send ultrasonic waves to each seal to obtain the corresponding defect echo map. The defect echo map was analyzed, and all bright or dark spots in the defect echo map were taken as defect signals. The shape of the defect signal was recorded. If the defect signal was linear, the defect type was determined to be a crack. If the defect signal was round or elliptical, the defect type was determined to be a pore. The number of times the defect signal appeared was counted to obtain the number of cracks and pores corresponding to each seal. The distance from the start point to the end point of the defect signal corresponding to each crack was recorded as the crack length corresponding to each crack. The total crack length was calculated by a summation formula.
[0053] Defect monitoring and analysis: The defect degree of each seal of the intelligent cantilever tunneling machine was also analyzed. The analysis process is as follows:
[0054] According to the formula The change d corresponding to each seal is obtained. i The greater the structural change, the greater the change in the current structure of the seal compared to the original structure.
[0055] According to the formula Obtain the defect degree QX corresponding to each seal. i p i N represents the number of cracks corresponding to the i-th seal. 标准 L represents the threshold number of cracks corresponding to the seal. i D represents the total crack length corresponding to the i-th seal. 标准 This represents the threshold value for the average crack length corresponding to the seal. This represents the overlapping area of the contour diagram corresponding to the i-th seal. γ1 represents the total area of the original outline of the structural layer corresponding to the i-th seal. γ1, γ2, γ3, and γ4 represent the preset structural change ratio coefficient, crack number ratio coefficient, total crack length ratio coefficient, and pore number ratio coefficient, respectively. The larger the defect degree QX, the more parts of the internal structure of the seal are missing compared to the original structure.
[0056] The average offset and radius change of each seal of the intelligent cantilever tunneling machine are monitored by the boundary anomaly monitoring module. The monitoring steps are as follows:
[0057] Obtain the original and monitoring contour maps corresponding to each seal. Establish a two-dimensional coordinate axis with the center point of the original contour map corresponding to each seal as the origin. Distribute monitoring points evenly along the edges of the original contour maps corresponding to each seal, and obtain the coordinates of each monitoring point in the original contour map corresponding to the seal. Record these coordinates as follows: j is the monitoring point number corresponding to each seal, j = 1, 2, 3, ..., k, where k is a positive integer. Monitoring points are evenly distributed along the edge of the monitoring contour map corresponding to each seal in the same manner, and their coordinates are obtained and denoted as (X...). ij ′,Y ij ′).
[0058] Obtain the original radius R of each seal. i For each seal, a monitoring point is evenly distributed along its contour, corresponding to the center point of the monitoring profile. The center point of each seal is then connected to one of the monitoring points, and the longest connecting line is selected and its length is recorded as _____.
[0059] The extrusion degree of each seal of the intelligent cantilever tunneling machine was also analyzed, and the analysis process is as follows;
[0060] According to the formula The offset between the j-th monitoring point corresponding to the original contour map of each seal and the j-th monitoring point corresponding to the monitoring contour map is calculated.
[0061] According to the formula The average offset PY corresponding to each seal was calculated. i ,like Then the radius change of each seal is BJ i =c, where c is a constant, if or At that time, through the formula The radius change of each seal was calculated. i .
[0062] According to the formula Obtain the extrusion degree JC corresponding to each seal. i μ1 and μ2 are the preset offset weight coefficient and radius change weight coefficient, respectively.
[0063] By analyzing the average offset and radius change, the extrusion degree of each seal is obtained, providing a reliable basis for accurately judging the condition of the seal.
[0064] The leakage prediction index corresponding to each seal is analyzed by the processing module. The analysis process is as follows:
[0065] Obtain the monitoring results from the integrity monitoring module and the boundary anomaly monitoring module, including the degree of defect and the degree of extrusion;
[0066] Through formula The leakage prediction index SM for each seal was calculated. iσ1 and σ2 are the preset defect conversion factor and extrusion conversion factor, respectively.
[0067] The early warning module receives the results from the processing module and analyzes the status of each seal in the intelligent cantilever tunneling machine to identify normal and abnormal seals. The analysis process is as follows:
[0068] The early warning module receives the results from the processing module and obtains the leakage prediction index corresponding to each seal. The leakage prediction index corresponding to each seal is compared with the preset leakage prediction index threshold. If the leakage prediction index corresponding to the seal is less than the preset leakage prediction index threshold, the seal is determined to be in a normal state at the current moment and is marked as a normal seal. If the leakage prediction index corresponding to the seal is greater than the preset leakage prediction index threshold, the seal is determined to be in an abnormal state at the current moment and is marked as an abnormal seal.
[0069] The warning system analyzes the warning levels corresponding to each abnormal seal and issues corresponding warning prompts based on these levels. The specific analysis process is as follows:
[0070] Obtain the leakage prediction index corresponding to each abnormal seal and compare it with the preset warning level threshold. When the leakage prediction index corresponding to the abnormal seal is less than or equal to the preset level 3 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 3. When the leakage prediction index corresponding to the abnormal seal is greater than the level 3 warning threshold and less than or equal to the preset level 2 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 2. When the leakage prediction index corresponding to the abnormal seal is greater than the level 2 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 1. Issue corresponding warning prompts based on the warning level of the abnormal seal.
[0071] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.
Claims
1. A fault monitoring and early warning method based on an intelligent cantilever tunneling machine, characterized in that, Includes the following steps: Basic data acquisition: The acquisition module collects data on each sealing component of the intelligent cantilever tunneling machine; Early warning prompts: The early warning module receives the results from the processing module, analyzes the status of each seal of the intelligent cantilever tunneling machine, obtains each normal seal and each abnormal seal, analyzes the early warning level corresponding to each abnormal seal, and provides corresponding early warning prompts based on the early warning level of each abnormal seal. Its characteristic is that it further includes: Defect monitoring and analysis: The deformation and aging of each seal of the intelligent cantilever tunneling machine are monitored by the integrity monitoring module, and the defect degree of each seal of the intelligent cantilever tunneling machine is analyzed to obtain the defect degree of each seal of the intelligent cantilever tunneling machine. Extrusion monitoring and analysis: The average offset and radius change of each seal of the intelligent cantilever tunneling machine are monitored by the boundary anomaly monitoring module, and the extrusion degree of each seal of the intelligent cantilever tunneling machine is analyzed to obtain the extrusion degree of each seal of the intelligent cantilever tunneling machine. Data processing: The leakage prediction index corresponding to each seal is analyzed by the processing module to obtain the leakage prediction index corresponding to each seal; The monitoring steps for assessing the deformation and aging of the seals on the intelligent cantilever tunneling machine are as follows: 201: Obtain the initial thickness of each seal and record it as... , i is the number of each seal of the intelligent cantilever tunneling machine, i=1,2,3,...,n, n is a positive integer; 202: The thickness of each seal is monitored using an ultrasonic thickness gauge, and the thickness of each seal at the current time point is recorded as follows: ; 203: X-rays are sent to each seal of the intelligent cantilever tunneling machine through an X-ray detector. The emitted rays penetrate each seal and are recorded by X-ray film, thereby obtaining X-ray films of each seal. 204: The obtained X-ray film is placed in a darkroom for processing to obtain structural X-ray films of each seal. The grayscale value regions of each seal are extracted from the structural X-ray films of each seal. Based on the reference grayscale value of each seal, the reference grayscale value regions of each seal are extracted from the structural X-ray films of each seal. At the same time, the regions of reference grayscale values of each seal are used to form the contour regions of each seal, which serve as the monitoring contour maps of each seal. 205: Obtain the original contour map corresponding to each seal and compare it with the monitoring contour map of the corresponding seal to obtain the overlapping area of the contour map of each seal. 206: Use a non-metallic ultrasonic flaw detector to send ultrasonic waves to each seal to obtain the corresponding defect echo map of each seal. Analyze the defect echo map to obtain the number of cracks, total crack length and number of pores corresponding to each seal.
2. The fault monitoring and early warning method based on an intelligent cantilever tunneling machine according to claim 1, characterized in that, The analysis of the defect degree of each seal of the intelligent cantilever tunneling machine is as follows: S1: According to the formula Obtain the change amount corresponding to each seal. ; S2: According to the formula Obtain the defect degree corresponding to each target seal. , This represents the number of cracks corresponding to the i-th seal. This indicates the threshold number of cracks corresponding to the seal. This represents the total crack length corresponding to the i-th seal. This represents the threshold value for the average crack length corresponding to the seal. This represents the overlapping area of the contour diagram corresponding to the i-th seal. This represents the area of the original contour map corresponding to the i-th seal. These are respectively represented as the preset structural change ratio coefficient, crack number ratio coefficient, total crack length ratio coefficient, and porosity ratio coefficient.
3. The fault monitoring and early warning method based on an intelligent cantilever tunneling machine according to claim 2, characterized in that, The monitoring steps for the average offset and radius change of each seal of the intelligent cantilever tunneling machine are as follows: 301: Obtain the original contour map and monitoring contour map corresponding to each seal. Establish a two-dimensional coordinate axis with the center point of the original contour map corresponding to each seal as the origin. Distribute monitoring points evenly along the edges of the original contour map corresponding to each seal, and obtain the coordinates of each monitoring point in the original contour map corresponding to the seal. Record these coordinates as follows: Let j be the monitoring point number corresponding to each seal. Monitoring points are evenly distributed along the edge of the monitoring profile diagram corresponding to each seal using the same layout method, and their coordinates are obtained and denoted as j. ; 302: Obtain the original radius of each seal and the center point of the monitoring profile of each seal. Distribute monitoring points evenly on the profile of each seal. Connect the center point of each seal to the distributed monitoring points one by one and select the longest connecting line.
4. The fault monitoring and early warning method based on an intelligent cantilever tunneling machine according to claim 3, characterized in that, The analysis of the extrusion degree of each seal of the intelligent cantilever tunneling machine is as follows: SS1: Analysis yields the offset and radius change for each seal. SS2: Analyze the offset between the j-th monitoring point corresponding to the original contour map of each seal and the j-th monitoring point corresponding to the monitoring contour map; SS3: Calculate the extrusion degree of each seal based on the average offset and radius change of each seal.
5. The fault monitoring and early warning method based on an intelligent cantilever tunneling machine according to claim 4, characterized in that, The analysis steps for the leakage prediction index corresponding to each seal are as follows: 401: Obtain the defect degree and extrusion degree corresponding to each seal; 402: The leakage prediction index corresponding to each seal is obtained by analyzing the defect degree and extrusion degree of each seal.
6. The fault monitoring and early warning method based on an intelligent cantilever tunneling machine according to claim 5, characterized in that, The analysis of the state of each seal in the intelligent cantilever tunneling machine is as follows: The early warning module receives the results from the processing module and obtains the leakage prediction index corresponding to each seal. The leakage prediction index corresponding to each seal is compared with the preset leakage prediction index threshold. If the leakage prediction index corresponding to the seal is less than the preset leakage prediction index threshold, the seal is determined to be in a normal state at the current moment and is marked as a normal seal. Otherwise, the seal is determined to be in an abnormal state at the current moment and is marked as an abnormal seal.
7. The fault monitoring and early warning method based on an intelligent cantilever tunneling machine according to claim 6, characterized in that, The analysis of the warning levels corresponding to each abnormal seal is as follows: Obtain the leakage prediction index corresponding to each abnormal seal and compare it with the preset warning level threshold. When the leakage prediction index corresponding to the abnormal seal is less than or equal to the preset level 3 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 3. When the leakage prediction index corresponding to the abnormal seal is greater than the level 3 warning threshold and less than or equal to the preset level 2 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 2. When the leakage prediction index corresponding to the abnormal seal is greater than the level 2 warning threshold, the warning level corresponding to the abnormal seal is determined to be level 1.