A fire valve fault online diagnosis method and system

Abstract

The present invention relates to the field of image processing technology, and more specifically to a method and system for online diagnosis of fire valve faults, comprising: obtaining a gas concentration characteristic value for each block based on the grayscale values ​​of all pixels in each block, obtaining an airflow vector for each pixel and a main airflow vector for each block, obtaining a gas correlation for each block based on the gas concentration characteristic value, the airflow vector for each pixel in each block, and the main airflow vector for each block; obtaining an airflow trend vector for each block and a regional trend vector for each block based on the main airflow vector and the gas correlation, and obtaining the degree of abnormality for each block; obtaining all abnormal blocks and non-abnormal blocks in an infrared image based on the degree of abnormality for each block, diagnosing fire valve faults based on all abnormal blocks and non-abnormal blocks in the infrared image, and generating an alarm when a fire valve fault occurs. The present invention improves the accuracy of fire valve fault diagnosis and detection by processing infrared images.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a fire valve fault online diagnosis method and system. Background Art

[0002] With the rapid development of industry and engineering, fire valves, as key components for controlling fluid flow, are crucial for ensuring production safety and resource efficiency. Fire valves primarily regulate gas pressure and flow. Failures that result in gas leaks can not only cause serious safety incidents but also stall production and waste resources. Therefore, online diagnostic testing technology for fire valves is of paramount importance in industry and engineering.

[0003] In existing fire valve fault diagnosis technology, infrared thermal cameras are widely used to capture infrared images of fire valves and nearby pipelines. Normally, when a gas leak occurs somewhere in a pipeline, the gas concentration in the pipeline changes, and this change can be diagnosed by differences in grayscale distribution in the infrared image. However, in practice, the problem becomes more complex when fire valves and pipelines are densely packed.

[0004] Specifically, when a leak in one pipe is very close to a leak in another adjacent pipe, if gas leaks simultaneously from both leaks, the direction and trend of the leaked gas will affect each other. This interaction blurs the grayscale distribution differences in the infrared image, making it impossible to accurately detect fire valve failures when directly analyzing and detecting the grayscale distribution differences in the infrared image.

[0005] To address this issue, a more accurate and reliable online fire valve fault diagnosis method and system is needed. This method and system should be able to overcome the interference caused by the mutual influence of leaking gases in densely packed pipelines and accurately identify fire valve fault states, thereby ensuring production safety and resource utilization efficiency in industrial and engineering fields. Summary of the Invention

[0006] The present invention provides a fire valve fault online diagnosis method and system to solve the existing problems.

[0007] The present invention provides a fire valve fault online diagnosis method and system using the following technical solutions:

[0008] An embodiment of the present invention provides a method for online diagnosis of fire valve faults, the method comprising the following steps:

[0009] Collect infrared images of fire valves;

[0010] The infrared image is divided into several blocks. The gas concentration characteristic of each block is obtained based on the grayscale values ​​of all pixels in each block. The airflow vector of each pixel is obtained based on the gradient amplitude and gradient direction of each pixel. The main airflow vector of each block is obtained based on the airflow vectors of all pixels in each block. The gas correlation of each block is obtained based on the gas concentration characteristic of each block, the airflow vectors of the pixels in each block, and the main airflow vector of each block.

[0011] Obtain the airflow trend vector of each block based on the main airflow vector and gas correlation of each block, obtain the adjacent blocks of each block, obtain the regional trend vector of each block based on the airflow trend vector of each block and the airflow trend vectors of its adjacent blocks, and obtain the abnormality degree of each block based on the variance of the gas correlation between each block and all adjacent blocks, the regional trend vector of each block, and the airflow trend vector;

[0012] According to the abnormality degree of each block, all abnormal blocks and non-abnormal blocks in the infrared image are obtained, and the fire valve failure is diagnosed based on all abnormal blocks and non-abnormal blocks in the infrared image, and an alarm is issued when the fire valve fails.

[0013] Furthermore, the gas concentration characteristic value of each block is obtained according to the grayscale values ​​of all pixels in each block, including the following calculation formula:

[0014]

[0015] Where, Represents the mean grayscale value of all pixels in the i-th block, represents the variance of the grayscale values ​​of all pixels in the i-th block, Represents the gas concentration characteristic value of the i-th block.

[0016] Furthermore, the airflow vector of each pixel is obtained according to the gradient amplitude and gradient direction of each pixel, and the main airflow vector of each block is obtained according to the airflow vectors of all pixels in each block, including the following specific steps:

[0017] The gradient amplitude of each pixel is used as the modulus of the airflow vector of each pixel, and the gradient direction of each pixel is used as the direction of the airflow vector of each pixel;

[0018] The airflow vectors of all pixels in each block are summed up, and the result is recorded as the main airflow vector of each block.

[0019] Furthermore, the gas correlation of each block is obtained according to the gas concentration characteristic value of each block, the airflow vector of the pixel points in each block, and the main airflow vector of each block, including the calculation formula as follows:

[0020]

[0021] Where, represents the gas concentration characteristic of the i-th block, represents the airflow vector of the j-th pixel in the i-th block, represents the main vector of the airflow of the i-th block, represents the variance of the angle between the airflow vector of all pixels in the i-th block and the main airflow vector of the i-th block, n represents the number of all pixels in the i-th block, represents the modulus of the vector, represents the gas correlation of the i-th block, Represents the cosine value of the angle between the main airflow vector of the i-th block and the airflow vector of the j-th pixel in the i-th block.

[0022] Furthermore, the method of obtaining the airflow trend vector of each block according to the airflow main vector and gas correlation of each block includes the following specific steps:

[0023] The gas correlation of each block is used as the modulus of the airflow trend vector of each block, and the direction of the main airflow vector of each block is used as the direction of the airflow trend vector of each block, so as to obtain the airflow trend vector of each block.

[0024] Furthermore, the process of obtaining the adjacent blocks of each block and obtaining the regional trend vector of each block according to the airflow trend vector of each block and the airflow trend vectors of the adjacent blocks of each block includes the following specific steps:

[0025] All blocks in the eight neighborhoods of each block are obtained and recorded as the adjacent blocks of each block. The vector data are added according to the airflow trend vectors of each block and the corresponding adjacent blocks to obtain the regional trend vector of each block.

[0026] Furthermore, the abnormality degree of each block is obtained based on the variance of the gas correlation between each block and all adjacent blocks, the regional trend vector of each block, and the airflow trend vector, including the calculation formula as follows:

[0027]

[0028] Where, represents the regional trend vector of the i-th block, represents the airflow trend vector of the vth neighboring block of the i-th block, m represents the number of all neighboring blocks of the i-th block, represents the variance of the gas correlation between the i-th block and all corresponding adjacent blocks, represents the modulus of the vector, Indicates the abnormality of the i-th block, Represents the cosine value of the angle between the regional trend vector of the i-th block and the airflow trend vector of the v-th adjacent block of the i-th block.

[0029] Furthermore, the method of obtaining all abnormal blocks and non-abnormal blocks in the infrared image according to the abnormality degree of each block and diagnosing the fire valve fault according to all abnormal blocks and non-abnormal blocks in the infrared image includes the following specific steps:

[0030] For any block, when the abnormality degree of the block is greater than or equal to the preset threshold T1, the block is judged to be an abnormal block; when the abnormality degree of the block is less than the preset threshold T1, the block is judged to be a non-abnormal block;

[0031] The ratio of the number of all abnormal blocks in the infrared image to the total number of all blocks in the infrared image is calculated and recorded as the proportion of abnormal blocks in the infrared image. When the proportion of abnormal blocks in the infrared image is greater than or equal to the preset threshold value T2, it is determined that the fire valve is faulty; when the proportion of abnormal blocks in the infrared image is less than the preset threshold value T2, it is determined that the fire valve is not faulty.

[0032] Furthermore, the fire valve failure is a gas leakage failure.

[0033] The present invention also provides an online diagnosis system for fire valve faults, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the above steps when executing the computer program.

[0034] The beneficial effects of the technical solution of the present invention are: obtaining the gas concentration characteristic quantity of each block according to the grayscale value of all pixels in each block, obtaining the airflow vector of each pixel according to the gradient amplitude and gradient direction of each pixel, obtaining the main airflow vector of each block according to the airflow vector of all pixels in each block, obtaining the gas correlation of each block according to the gas concentration characteristic quantity of each block, the airflow vector of the pixels in each block and the main airflow vector of each block, eliminating the mutual influence of the flow direction and trend of the leaked gas at multiple leakage points, and preliminarily determining the blocks with abnormalities; obtaining the degree of abnormality of each block according to the variance of the gas correlation of each block and all adjacent blocks, the regional trend vector and the airflow trend vector of each block; obtaining all abnormal blocks and non-abnormal blocks in the infrared image according to the degree of abnormality of each block, diagnosing fire valve faults according to all abnormal blocks and non-abnormal blocks in the infrared image, and giving an alarm when a fire valve fails, thereby improving the accuracy of fire valve fault diagnosis and detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0036] Figure 1 The present invention is a flowchart of the steps of an online diagnosis method for fire valve faults. DETAILED DESCRIPTION

[0037] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, provides a detailed description of the specific implementation, structure, features, and effectiveness of a method and system for online diagnosis of fire valve faults according to the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0039] The specific scheme of the online diagnosis method and system for fire valve faults provided by the present invention is described in detail below with reference to the accompanying drawings.

[0040] See also Figure 1 , which shows a flowchart of a method for online diagnosis of fire valve faults provided by one embodiment of the present invention, the method comprising the following steps:

[0041] Step S001: Collect infrared images of fire valves.

[0042] There are numerous types of fire valves, categorized by their function, structure, and actuation method. Common fire valves include, but are not limited to, alarm valves, signal valves, check valves, safety valves, pressure reducing valves, and test / drain valves. Over time, valve seals can lose their sealing properties due to aging, wear, or corrosion, leading to gas leaks. Alternatively, cracks in the valve body or bonnet—caused by manufacturing defects, poor welding quality, water hammer, or frost cracking—can cause gas leaks.

[0043] It should be noted that in order to analyze whether there is an abnormal gas leakage at the fire valve, it is necessary to collect infrared images of the fire valve for analysis.

[0044] Specifically, an infrared thermal sensing camera is used to capture an infrared thermal sensing image of the fire valve, and the infrared thermal sensing image of the fire valve is preprocessed into grayscale to obtain a preprocessed infrared image of the fire valve.

[0045] At this point, the infrared image of the fire valve is obtained.

[0046] Step S002: Divide the infrared image into several blocks, obtain the gas concentration characteristic of each block according to the grayscale values ​​of all pixels in each block, obtain the airflow vector of each pixel according to the gradient amplitude and gradient direction of each pixel, obtain the main airflow vector of each block according to the airflow vectors of all pixels in each block, and obtain the gas correlation of each block according to the gas concentration characteristic of each block, the airflow vectors of the pixels in each block and the main airflow vector of each block.

[0047] It should be noted that when a fire valve fails, gas leakage occurs at the fault site, causing the gas concentration in the pipeline to change. Therefore, when a fire valve fails, the closer the block in the image is to the fire valve, the greater the difference in the grayscale values ​​of the pixels within the block. That is, the grayscale difference between all pixels in each block can be used to analyze whether each block has an abnormality.

[0048] It should be further explained that since the images collected are infrared images, the ones with high grayscale values ​​after grayscale conversion are gas. Therefore, the higher the mean grayscale value of all pixels in each block, the greater the possibility that the block is a normal block, and vice versa. In addition, because the distribution of gas concentration in each block is relatively uniform when there are no defects or leaks in the fire valve, the variance of the grayscale values ​​of all pixels in each block can be used to analyze whether each block is a normal block.

[0049] Specifically, a threshold value T is preset, wherein this embodiment is described by taking T=100 as an example, and this embodiment does not impose any specific limitation, wherein T can be determined according to specific implementation conditions. The infrared image is equally divided into T blocks.

[0050] The gas concentration characteristic of each block is obtained according to the grayscale values ​​of all pixels in each block, which can be expressed as follows:

[0051]

[0052] Where, Represents the mean grayscale value of all pixels in the i-th block, represents the variance of the grayscale values ​​of all pixels in the i-th block, Represents the gas concentration characteristic value of the i-th block.

[0053] Among them, when the mean of the grayscale values ​​of all pixels in each block is larger, the possibility that the block is a normal block is greater; when the mean of the grayscale values ​​of all pixels in each block is smaller, the possibility that the block is a normal block is smaller; when the variance of the grayscale values ​​of all pixels in each block is smaller, it indicates that the grayscale values ​​of the pixels in the block are relatively close, that is, the smaller the grayscale difference of the block, the greater the possibility that the block is a normal block, that is, the larger the corresponding gas concentration characteristic value; when the variance of the grayscale values ​​of all pixels in each block is larger, it indicates that the grayscale value difference of the pixels in the block is large, the possibility that the block is a normal block is smaller, that is, the corresponding gas concentration characteristic value is smaller.

[0054] At this point, the gas concentration characteristic value of each block is obtained.

[0055] Obtain the gradient magnitude and gradient direction of all pixel points, use the gradient magnitude of each pixel point as the modulus of the airflow vector, and use the gradient direction as the direction of the airflow vector. At this point, the airflow vector of each pixel point is obtained.

[0056] The airflow vectors of all pixels in each block are summed up, and the result is recorded as the main airflow vector of each block.

[0057] It should be noted that when the fire valve is not faulty, the gas flow direction in the pipeline is relatively uniform, that is, the angle between the directions of the airflow vectors of the pixels in each block should be relatively small. When the fire valve fails, due to the influence of external air and pressure, the flow direction of the gas in the pipeline becomes more inconsistent, that is, the gas in the pipeline is relatively chaotic. Therefore, analysis can be performed based on the difference between the airflow vectors of all pixels in each block and the main airflow vector of each block.

[0058] Specifically, the gas correlation of each block is obtained based on the gas concentration characteristic of each block, the airflow vector of each pixel in each block, and the main airflow vector of each block, which can be expressed as follows:

[0059]

[0060] Where, represents the gas concentration characteristic of the i-th block, represents the airflow vector of the j-th pixel in the i-th block, represents the main vector of the airflow of the i-th block, represents the variance of the angle between the airflow vector of all pixels in the i-th block and the main airflow vector of the i-th block, n represents the number of all pixels in the i-th block, represents the modulus of the vector, represents the gas correlation of the i-th block, Represents the cosine value of the angle between the main airflow vector of the i-th block and the airflow vector of the j-th pixel in the i-th block.

[0061] in, represents the mean value of the length of the airflow vectors of all pixels in the ith block mapped onto the main airflow vector of the ith block, It represents the ratio of the mean length of the airflow vectors of all pixels in the i-th block mapped on the airflow main vector of the i-th block to the modulus length of the airflow main vector of the i-th block. When the ratio is larger, that is, closer to 1, it means that the gas flow direction in the i-th block is relatively consistent, and the possibility that the i-th block is a normal block is greater. When the ratio is smaller, that is, closer to 0, it means that the gas flow direction in the i-th block is more inconsistent, that is, more chaotic, and the possibility that the i-th block is an abnormal block is greater, that is, the possibility that there is a fire valve failure is greater.

[0062] At this point, the gas correlation of each block is obtained.

[0063] Step S003: Obtain the airflow trend vector of each block based on the main airflow vector and gas correlation of each block, obtain the adjacent blocks of each block, obtain the regional trend vector of each block based on the airflow trend vector of each block and the airflow trend vector of each adjacent block, and obtain the degree of abnormality of each block based on the variance of the gas correlation between each block and all adjacent blocks, the regional trend vector of each block and the airflow trend vector.

[0064] It should be noted that in the above steps, only the data of all pixels in each block are analyzed. However, when all pixels in a block are at defects, the difference between the airflow vectors of all pixels in this block is relatively small, and the block is also considered to be a normal block. Therefore, blocks in the neighborhood near a block can be selected for joint analysis, and the difference between the vectors of all blocks in the neighborhood can be used to further analyze whether there is a fault.

[0065] It should be further explained that when a fault occurs at the fire valve, there is a pressure difference between the inside and outside of the pipe, which causes the pressure of the gas at the gap to change. That is, there is a difference in the trend between the vectors of the pixel points in the image, and the difference is large, while the trend difference between the vectors of the pixel points in the normal area is small.

[0066] Specifically, the gas correlation of each block is used as the modulus of the airflow trend vector of each block, and the direction of the airflow main vector of each block is used as the direction of the airflow trend vector of each block, so as to obtain the airflow trend vector of each block.

[0067] All blocks in the eight neighborhoods of each block are obtained and recorded as the adjacent blocks of each block. The vector data are added according to the airflow trend vectors of each block and the corresponding adjacent blocks to obtain the regional trend vector of each block.

[0068] According to the variance of the gas correlation between each block and all adjacent blocks, the regional trend vector and the airflow trend vector of each block, the abnormality degree of each block is obtained, which can be specifically expressed as follows:

[0069]

[0070] Where, represents the regional trend vector of the i-th block, represents the airflow trend vector of the vth neighboring block of the i-th block, m represents the number of all neighboring blocks of the i-th block, represents the variance of the gas correlation between the i-th block and all corresponding adjacent blocks, represents the modulus of the vector, Indicates the abnormality of the i-th block, Represents the cosine value of the angle between the regional trend vector of the i-th block and the airflow trend vector of the v-th adjacent block of the i-th block.

[0071] in, represents the difference between the modulus of the regional trend vector of the i-th block and the modulus of the airflow trend vector of the v-th adjacent block of the i-th block, It represents the mean of the difference between the modulus of the regional trend vector of the i-th block and the modulus of the airflow trend vectors of all adjacent blocks of the i-th block. When the mean of the difference between the vector moduli is larger, the block is more abnormal, that is, the possibility of the fire valve being faulty is greater. When the mean of the difference between the vector moduli is smaller, the block is more normal, that is, the possibility of the fire valve being faulty is smaller. This represents the mean cosine of the angle between the regional trend vector of block i and the airflow trend vectors of all its neighboring blocks. A smaller mean cosine of the angle indicates a more normal block, meaning the fire valve is less likely to be faulty. A larger mean cosine of the angle indicates a more abnormal block, meaning the fire valve is more likely to be faulty. A larger variance in the gas correlation between each block and all its neighboring blocks indicates a more heterogeneous gas correlation between that block and its neighboring blocks, meaning the fire valve is more likely to be faulty. A smaller variance in the gas correlation between each block and its neighboring blocks indicates a more homogeneous gas correlation between that block and its neighboring blocks, meaning the fire valve is less likely to be faulty.

[0072] At this point, the abnormality level of each block is obtained.

[0073] Step S004: obtaining all abnormal blocks and non-abnormal blocks in the infrared image according to the abnormality degree of each block, and diagnosing the fire valve fault based on all abnormal blocks and non-abnormal blocks in the infrared image.

[0074] A threshold value T1 is preset. This embodiment uses T1 = 0.8 as an example. This embodiment does not impose any specific limitations on this value, and T1 can be determined based on specific implementation circumstances. For any block, if the abnormality level of the block is greater than or equal to the preset threshold value T1, the block is determined to be an abnormal block; if the abnormality level of the block is less than the preset threshold value T1, the block is determined to be a non-abnormal block.

[0075] At this point, all abnormal blocks and non-abnormal blocks in the infrared image are obtained.

[0076] A threshold value T2 is preset, wherein this embodiment is described by taking T2=0.5 as an example, and this embodiment does not make any specific limitation, wherein T2 may be determined according to specific implementation conditions.

[0077] The ratio of the number of all abnormal blocks in the infrared image to the total number of all blocks in the infrared image is calculated and recorded as the proportion of abnormal blocks in the infrared image. When the proportion of abnormal blocks in the infrared image is greater than or equal to the preset threshold value T2, it is determined that the fire valve is faulty; when the proportion of abnormal blocks in the infrared image is less than the preset threshold value T2, it is determined that the fire valve is not faulty.

[0078] Alarm when fire valve fails.

[0079] This embodiment provides a fire valve fault online diagnosis system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, steps S001 to S004 are implemented.

[0080] 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 principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A fire valve fault online diagnosis method, characterized in that: The method comprises the following steps: Collect infrared images of fire valves; The infrared image is divided into several blocks. The gas concentration characteristic of each block is obtained based on the grayscale values ​​of all pixels in each block. The airflow vector of each pixel is obtained based on the gradient amplitude and gradient direction of each pixel. The main airflow vector of each block is obtained based on the airflow vectors of all pixels in each block. The gas correlation of each block is obtained based on the gas concentration characteristic of each block, the airflow vectors of the pixels in each block, and the main airflow vector of each block. Obtain the airflow trend vector of each block based on the main airflow vector and gas correlation of each block, obtain the adjacent blocks of each block, obtain the regional trend vector of each block based on the airflow trend vector of each block and the airflow trend vectors of its adjacent blocks, and obtain the abnormality degree of each block based on the variance of the gas correlation between each block and all adjacent blocks, the regional trend vector of each block, and the airflow trend vector; According to the abnormality degree of each block, all abnormal blocks and non-abnormal blocks in the infrared image are obtained, and the fire valve fault is diagnosed based on all abnormal blocks and non-abnormal blocks in the infrared image, and an alarm is issued when the fire valve fails; The gas concentration characteristic value of each block is obtained according to the grayscale values ​​of all pixels in each block, and the calculation formula included is as follows: Where, Represents the mean grayscale value of all pixels in the i-th block, represents the variance of the grayscale values ​​of all pixels in the i-th block, represents the gas concentration characteristic of the i-th block; The gas correlation of each block is obtained based on the gas concentration characteristic of each block, the airflow vector of the pixel points in each block, and the main airflow vector of each block. The calculation formula is as follows: Where, represents the gas concentration characteristic of the i-th block, represents the airflow vector of the j-th pixel in the i-th block, represents the main vector of the airflow of the i-th block, represents the variance of the angle between the airflow vector of all pixels in the i-th block and the main airflow vector of the i-th block, n represents the number of all pixels in the i-th block, represents the modulus of the vector, represents the gas correlation of the i-th block, represents the cosine value of the angle between the main airflow vector of the i-th block and the airflow vector of the j-th pixel in the i-th block; The abnormality degree of each block is obtained based on the variance of the gas correlation between each block and all adjacent blocks, the regional trend vector and the airflow trend vector of each block, and the calculation formula included is as follows: Where, represents the regional trend vector of the i-th block, represents the airflow trend vector of the vth adjacent block of the i-th block, m represents the number of all adjacent blocks of the i-th block, represents the variance of the gas correlation between the i-th block and all corresponding adjacent blocks, represents the modulus of the vector, Indicates the abnormality of the i-th block, Represents the cosine value of the angle between the regional trend vector of the i-th block and the airflow trend vector of the v-th adjacent block of the i-th block.

2. A fire valve fault online diagnosis method according to claim 1, characterized in that: The airflow vector of each pixel is obtained according to the gradient amplitude and gradient direction of each pixel, and the main airflow vector of each block is obtained according to the airflow vectors of all pixels in each block. The specific steps include the following: The gradient amplitude of each pixel is used as the modulus of the airflow vector of each pixel, and the gradient direction of each pixel is used as the direction of the airflow vector of each pixel; The airflow vectors of all pixels in each block are summed up, and the result is recorded as the main airflow vector of each block.

3. The online diagnosis method for fire valve fault according to claim 1, characterized in that: The specific steps of obtaining the airflow trend vector of each block according to the airflow main vector and gas correlation of each block are as follows: The gas correlation of each block is used as the modulus of the airflow trend vector of each block, and the direction of the main airflow vector of each block is used as the direction of the airflow trend vector of each block, so as to obtain the airflow trend vector of each block.

4. The online diagnosis method for fire valve fault according to claim 1, characterized in that: The method of obtaining the adjacent blocks of each block and obtaining the regional trend vector of each block according to the airflow trend vector of each block and the airflow trend vectors of the adjacent blocks of each block includes the following specific steps: All blocks in the eight neighborhoods of each block are obtained and recorded as the adjacent blocks of each block. The vector data are added according to the airflow trend vectors of each block and the corresponding adjacent blocks to obtain the regional trend vector of each block.

5. The online diagnosis method for fire valve fault according to claim 1, characterized in that: The method of obtaining all abnormal blocks and non-abnormal blocks in the infrared image according to the abnormality degree of each block and diagnosing the fire valve fault according to all abnormal blocks and non-abnormal blocks in the infrared image includes the following specific steps: For any block, when the abnormality degree of the block is greater than or equal to the preset threshold T1, the block is judged to be an abnormal block; when the abnormality degree of the block is less than the preset threshold T1, the block is judged to be a non-abnormal block; The ratio of the number of all abnormal blocks in the infrared image to the total number of all blocks in the infrared image is calculated and recorded as the proportion of abnormal blocks in the infrared image. When the proportion of abnormal blocks in the infrared image is greater than or equal to the preset threshold value T2, it is determined that the fire valve is faulty; when the proportion of abnormal blocks in the infrared image is less than the preset threshold value T2, it is determined that the fire valve is not faulty.

6. The online diagnosis method for fire valve fault according to claim 1, characterized in that: The fire valve failure is a gas leakage failure.

7. A fire valve fault online diagnosis system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the online diagnosis method for fire valve faults as described in any one of claims 1 to 6 are implemented.

Images