A SF6 leakage long-distance detection system and method based on mid-infrared thermal imaging

Abstract

The present invention provides a SF6 leakage long-distance detection system and method based on mid-infrared thermal imaging, which relates to the field of industrial safety detection technology. The present invention first arranges thermometers, mid-infrared thermal imagers and non-dispersive infrared gas analyzers on the surface of the transformer, the flange where the pipeline is connected to the transformer, and the inlet and outlet positions of all connected pipelines to obtain the ambient temperature, equipment surface temperature and gas concentration. By weighted fusion of the collected data, the comprehensive monitoring index is calculated, and compared with the preset index to identify abnormal warning points. Then, further data collection is performed on the identified warning points to obtain environmental humidity and wind speed information, and data preprocessing is performed. Based on the preprocessed temperature difference, gas concentration, humidity and wind speed, a detection model is constructed to generate the leakage probability index of SF6. Finally, by comparing the leakage probability index with the preset leakage threshold, the SF6 leakage status of each warning point is judged.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial safety detection, and in particular to a system and method for long-distance detection of SF6 leakage based on mid-infrared thermal imaging. Background Art

[0002] At present, SF6, as an efficient electrical insulating gas, is widely used in substations, gas-insulated switchgear and other fields. The method of detecting SF6 leakage has evolved from traditional manual monitoring to modern high-tech technology. Traditional methods such as visual inspection and gas concentration monitoring are inefficient and easily affected by human factors. With the increasingly stringent environmental regulations, modern detection technologies have emerged, mainly including non-dispersive infrared gas analyzers, portable gas detectors and optical imaging technology. These methods have higher sensitivity and real-time monitoring capabilities, and can quickly and accurately identify and locate SF6 leaks, thereby effectively reducing its impact on the environment and ensuring the safe operation of power equipment. However, existing leakage detection technology mainly relies on a single sensor at a fixed monitoring point, and the consideration of environmental factors is not comprehensive enough. It is easy to miss detection and false alarms in complex environments, and the response speed is slow, which makes it difficult to meet the needs of real-time monitoring.

[0003] The prior art has the following deficiencies:

[0004] Existing SF6 leakage detection technology mainly relies on single sensor monitoring or operator experience and judgment, which has problems such as insufficient sensitivity and slow response speed. This method often cannot obtain comprehensive environmental and equipment data in real time, resulting in an increased possibility of missed detection or misjudgment. In addition, traditional technologies often find it difficult to take into account multiple influencing factors, such as temperature difference, gas concentration, humidity and dynamic changes in wind speed, making it difficult to accurately assess leakage risks.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a SF6 leakage long-distance detection system and method based on mid-infrared thermal imaging to solve the problems raised in the above background technology.

[0007] A SF6 leakage long-distance detection system based on mid-infrared thermal imaging, comprising:

[0008] The data acquisition module is used to mark the transformer surface, the flange where the pipeline is connected to the transformer, and the inlet and outlet positions of all connected pipelines as detection points in sequence, and to arrange thermometers, mid-infrared thermal imagers, and non-dispersive infrared gas analyzers at the detection points. The surface temperature of the equipment is collected by the mid-infrared thermal imager, and the gas concentration data of the environment is collected by the non-dispersive infrared gas analyzer.

[0009] The comprehensive monitoring module is used to obtain the current ambient temperature through a thermometer, calculate the temperature difference between the ambient temperature and the equipment surface temperature, and perform weighted fusion of the temperature difference and gas concentration data to obtain comprehensive monitoring indicators;

[0010] The early warning point screening module is used to compare the comprehensive monitoring indicators with the preset indicators, mark the locations where the comprehensive monitoring indicators are abnormal as early warning points, and screen out all early warning points;

[0011] The leakage probability index acquisition module is used to collect the ambient humidity and wind speed at the warning point, perform data preprocessing on the temperature difference, gas concentration, humidity and wind speed data at the warning point, build a detection model based on the preprocessed temperature difference, gas concentration, humidity and wind speed data, and generate the leakage probability index of SF6;

[0012] The leakage status judgment module is used to compare the leakage probability index with the preset leakage threshold to determine whether there is SF6 leakage at each warning point under the current data state.

[0013] Furthermore, the specific steps for obtaining the current ambient temperature, equipment surface temperature and gas concentration data are as follows:

[0014] Get the current temperature through the thermometer The ambient temperature of each detection point is calibrated as The mid-infrared thermal imager outputs a thermal image based on the infrared radiation emitted by the surface of the device. The value of each pixel is the radiation intensity received within a certain wavelength range. The relationship between radiation intensity and temperature is expressed by the formula:

[0015] ;

[0016] in, is the radiation intensity received by the thermal imager from the surface of the device, is the emissivity of the device surface, that is, the ratio of the device surface radiation capacity to the black body radiation capacity, between 0 and 1. is the Stefan-Boltzmann constant, is the absolute temperature of the device;

[0017] By reversing the formula, the surface temperature of the object can be obtained. The formula for obtaining the surface temperature of the device is:

[0018] ;

[0019] in, Indicates The surface temperature of the equipment at each detection point.

[0020] Furthermore, the specific steps for obtaining the current gas concentration data are as follows:

[0021] The infrared light emitted by the non-dispersive infrared gas analyzer passes through the area where the device is located. The detector receives the transmitted light and converts it into an electrical signal, which is then digitally processed to calculate the absorption rate. The gas concentration in the area can be obtained through the absorption rate. The formula for obtaining the gas concentration in the environment is:

[0022] ;

[0023] in, For the The gas concentration at each detection point is expressed in , is the absorption coefficient of the gas, in units of , is the optical path length in units of , is the initial intensity of the incident light, is the light intensity after passing through the ambient gas at the first detection point.

[0024] Furthermore, the specific logic for obtaining comprehensive monitoring indicators is as follows:

[0025] The specific formula for obtaining the temperature difference is:

[0026] ;

[0027] in, For the The temperature difference at each detection point;

[0028] The specific formula for obtaining comprehensive monitoring indicators is:

[0029] ;

[0030] in, Indicates Comprehensive monitoring indicators of each detection point, For the The temperature difference of the detection points is For the The gas concentration at each detection point is is the weight coefficient of temperature difference, is the weight coefficient of gas concentration, and .

[0031] Furthermore, the logic for screening out all warning points is as follows:

[0032] Compare the comprehensive monitoring index of each detection point with the preset index threshold. If the comprehensive detection index of the detection point is higher than the index threshold, the Set the detection point as a warning point and mark the location as , If the comprehensive monitoring index of the detection point is lower than the index threshold, the detection point will be regarded as a safe point.

[0033] Furthermore, the specific logic for generating the leakage probability index of SF6 is as follows:

[0034] The humidity sensor and wind speed sensor collect The ambient humidity and wind speed of each warning point are normalized and scaled to Within the range of and , analyze the temperature difference, gas concentration, humidity and wind speed data of the warning point after preprocessing, and obtain the leakage probability index of SF6 at the warning point based on the formula:

[0035] ;

[0036] in, For the The leakage probability index of SF6 at each warning point, For the The temperature difference of the warning points For the The gas concentration at each warning point is For the The humidity of the environment where the warning point is located, For the The wind speed of the environment where the warning point is located, , , and is the weight coefficient, and .

[0037] Furthermore, the specific logic for determining whether there is SF6 leakage under the current data state is:

[0038] The first SF6 leakage probability index of each warning point Compared with the preset leakage threshold, if the leakage probability index of the warning point is higher than the preset leakage threshold, it is judged that there is SF6 leakage at the warning point; if the leakage probability index of the warning point is lower than the preset leakage threshold, the leakage probability index of the warning point will continue to be detected within the next ten minutes until all leakage probability indices are lower than the preset leakage threshold, then it is judged that there is no SF6 leakage at the warning point.

[0039] The present invention further provides a SF6 leakage long-distance detection method based on mid-infrared thermal imaging, the SF6 leakage long-distance detection method is performed by the above-mentioned SF6 leakage long-distance detection system, and the specific steps include:

[0040] Step 1: Mark the transformer surface, the flange where the pipeline is connected to the transformer, and the inlet and outlet positions of all connecting pipelines as detection points in sequence, and set up thermometers, mid-infrared thermal imagers, and non-dispersive infrared gas analyzers at the detection points. The surface temperature of the equipment is collected by the mid-infrared thermal imager, and the gas concentration data of the environment is collected by the non-dispersive infrared gas analyzer.

[0041] Step 2: Obtain the current ambient temperature through a thermometer, calculate the temperature difference between the ambient temperature and the equipment surface temperature, perform weighted fusion on the temperature difference and gas concentration data, and obtain comprehensive monitoring indicators;

[0042] Step 3: Compare the comprehensive monitoring indicators with the preset indicators, mark the locations where the comprehensive monitoring indicators are abnormal as warning points, and screen out all warning points;

[0043] Step 4: Collect the ambient humidity and wind speed at the warning point, perform data preprocessing on the temperature difference, gas concentration, humidity and wind speed data at the warning point, build a detection model based on the preprocessed temperature difference, gas concentration, humidity and wind speed data, and generate the SF6 leakage probability index;

[0044] Step 5: Compare the leakage probability index with the preset leakage threshold to determine whether there is SF6 leakage at each warning point under the current data state.

[0045] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0046] The present invention preliminarily detects areas where leakage may exist by acquiring temperature difference and gas concentration data, and marks these locations as early warning points in advance, and then calculates the probability of leakage at each early warning point in combination with the dynamic data of ambient humidity and wind speed, which can effectively improve the accuracy and real-time performance of SF6 leakage detection. By comparing the set comprehensive detection index with the preset threshold, potential leakage points can be quickly identified, and early warnings can be issued in time. The locations where the early warnings are issued are then monitored in real time to predict the probability of leakage, thereby ensuring that areas where leakage may occur can be found in time. Compared with traditional detection methods, the present invention not only has higher sensitivity and response speed, but also improves the reliability of the overall detection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0048] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0050] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0051] Example:

[0052] See also Figure 1 The present invention provides a SF6 leakage long-distance detection system based on mid-infrared thermal imaging, comprising:

[0053] The data acquisition module is used to mark the transformer surface, the flange where the pipeline is connected to the transformer, and the inlet and outlet positions of all connected pipelines as detection points in sequence, and to arrange thermometers, mid-infrared thermal imagers, and non-dispersive infrared gas analyzers at the detection points. The surface temperature of the equipment is collected by the mid-infrared thermal imager, and the gas concentration data of the environment is collected by the non-dispersive infrared gas analyzer.

[0054] In this embodiment, the specific steps for obtaining the current ambient temperature, device surface temperature and gas concentration data are as follows:

[0055] The ambient temperature of the current 𝑖th detection point is obtained through a thermometer and calibrated as The mid-infrared thermal imager outputs a thermal image based on the infrared radiation emitted by the surface of the device. The value of each pixel is the radiation intensity received within a certain wavelength range. The relationship between radiation intensity and temperature is expressed by the formula:

[0056] ;

[0057] in, is the radiation intensity received by the thermal imager from the surface of the device, is the emissivity of the device surface, that is, the ratio of the device surface radiation capacity to the black body radiation capacity, between 0 and 1. is the Stefan-Boltzmann constant, is the absolute temperature of the device;

[0058] By reversing the formula, the surface temperature of the object can be obtained. The formula for obtaining the surface temperature of the device is:

[0059] ;

[0060] in, Indicates The surface temperature of the equipment at each detection point.

[0061] Mid-infrared thermal imaging technology can measure the temperature of the equipment surface in a non-contact manner, which is very important for environments such as high-voltage equipment and gas storage tanks. Reducing contact can not only avoid potential damage to the equipment, but also help improve personnel safety. In addition, mid-infrared thermal imaging can obtain the temperature distribution on the equipment surface in real time, detect temperature anomalies in time, and help quickly identify possible leaks or equipment failures.

[0062] Leakage of SF6 gas usually causes changes in the surface temperature of the equipment, especially near the leakage point. By detecting the temperature of the equipment surface, the difference with the ambient temperature can be detected, thereby identifying potential leakage areas. In addition, an abnormal increase or decrease in the surface temperature of the equipment may be an early signal of equipment failure. Regular monitoring of the surface temperature can help timely detect aging of the insulation layer, overheating of the equipment or other potential problems, and avoid SF6 leakage caused by failure.

[0063] In this embodiment, the specific steps for obtaining the current gas concentration data are:

[0064] The infrared light emitted by the non-dispersive infrared gas analyzer passes through the area where the device is located. The detector receives the transmitted light and converts it into an electrical signal, which is then digitally processed to calculate the absorption rate. The gas concentration in the area can be obtained through the absorption rate. The formula for obtaining the gas concentration in the environment is:

[0065] ;

[0066] in, For the The gas concentration at each detection point is expressed in , is the absorption coefficient of the gas, in units of , is the optical path length in units of , is the initial intensity of the incident light, is the light intensity after passing through the ambient gas at the first detection point.

[0067] The non-dispersive infrared gas analyzer has the advantages of high sensitivity, real-time monitoring capability, low maintenance requirements and environmental friendliness in detecting SF6 gas concentration. The analyzer only focuses on specific wavelengths, which can reduce interference from other gases, detect gas changes in a timely manner, and improve more accurate measurement results. When a leak occurs in the equipment, the gas concentration will change significantly. By detecting the gas concentration, potential leak points can be quickly identified.

[0068] The comprehensive monitoring module is used to obtain the current ambient temperature through a thermometer, calculate the temperature difference between the ambient temperature and the equipment surface temperature, and perform weighted fusion of the temperature difference and gas concentration data to obtain comprehensive monitoring indicators;

[0069] In this embodiment, the specific logic for obtaining the comprehensive monitoring indicators is:

[0070] The specific formula for obtaining the temperature difference is:

[0071] ;

[0072] in, For the The temperature difference at each detection point;

[0073] The specific formula for obtaining comprehensive monitoring indicators is:

[0074] ;

[0075] in, Indicates Comprehensive monitoring indicators of each detection point, For the The temperature difference of the detection points is For the The gas concentration at each detection point is is the weight coefficient of temperature difference, is the weight coefficient of gas concentration, and .

[0076] The temperature difference is directly proportional to the comprehensive index. Increase, indicating that the equipment may be abnormal or leaking, resulting in comprehensive monitoring indicators Similarly, the gas concentration The increase will also lead to Increase, indicating that the risk of gas leakage increases. Therefore, the gas concentration is also in direct proportion to the comprehensive index. This formula forms a comprehensive monitoring index through a weighted combination of temperature difference and gas concentration, which can effectively reflect the overall status of the detection point. In addition, This means that in this comprehensive monitoring indicator, gas concentration is more important than temperature difference. Directly measured gas concentration can usually reflect the leakage situation more accurately, while temperature difference may be affected by other factors. This constraint ensures that the comprehensive monitoring indicator is a normalized indicator, ensuring that the total contribution of the weighted combination of the two factors is 100%.

[0077] The early warning point screening module is used to compare the comprehensive monitoring indicators with the preset indicators, mark the locations where the comprehensive monitoring indicators are abnormal as early warning points, and screen out all early warning points;

[0078] In this embodiment, the logic for screening out all warning points is as follows:

[0079] Compare the comprehensive monitoring index of each detection point with the preset index threshold. If the comprehensive detection index of the detection point is higher than the index threshold, the Set the detection point as a warning point and mark the location as , If the comprehensive monitoring index of the detection point is lower than the index threshold, the detection point will be regarded as a safe point.

[0080] The leakage probability index acquisition module is used to collect the ambient humidity and wind speed at the warning point, perform data preprocessing on the temperature difference, gas concentration, humidity and wind speed data at the warning point, build a detection model based on the preprocessed temperature difference, gas concentration, humidity and wind speed data, and generate the leakage probability index of SF6;

[0081] In this embodiment, the specific logic for generating the SF6 leakage probability index is as follows:

[0082] The humidity sensor and wind speed sensor collect The ambient humidity and wind speed of each warning point are normalized and scaled to Within the range of and , analyze the temperature difference, gas concentration, humidity and wind speed data of the warning point after preprocessing, and obtain the leakage probability index of SF6 at the warning point based on the formula:

[0083] ;

[0084] in, For the The leakage probability index of SF6 at each warning point, For the The temperature difference of the warning points For the The gas concentration at each warning point is For the The humidity of the environment where the warning point is located, For the The wind speed of the environment where the warning point is located, , , and is the weight coefficient, and .

[0085] SF6 is a gas whose physical properties may be affected by ambient humidity. High humidity may affect the diffusion rate of the gas and the accuracy of concentration measurements. Under high humidity conditions, moisture may cause condensation, which may affect the insulation performance of the equipment and the accuracy of the measuring equipment. Knowing the ambient humidity can help analyze whether the change in gas concentration is related to humidity. When judging SF6 leakage, changes in ambient humidity may affect the readings of equipment surface temperature and gas concentration. Recording humidity data can help correct the impact of other monitoring indicators.

[0086] Wind speed has a direct impact on the diffusion and dilution of gas. Under high wind speed conditions, leaked SF6 gas may be diluted quickly, resulting in lower readings of concentration detection instruments, making it difficult to detect leaks in a timely manner. Understanding wind speed can help analyze the changing pattern of gas concentration at the detection point. When the wind speed is high, a higher gas concentration may be required to detect a leak, so wind speed data helps adjust the detection sensitivity and alarm threshold. Therefore, collecting ambient humidity and wind speed is crucial for determining SF6 leaks. These data not only help improve the accuracy and reliability of leak detection, but also help to comprehensively evaluate the operating status of the equipment and the impact of environmental factors on the monitoring results.

[0087] By normalizing, different types of data are converted to the same dimension, so that different types of data can be directly compared and integrated. When the temperature difference increases, it usually means that there is an abnormality or potential leakage in the equipment. The increase will directly lead to Increase, that is, it is directly proportional to the leakage probability index; the increase in gas concentration means that there is more SF6 gas near this point, and the possibility of leakage increases. Therefore, The increase will also lead to The increase of is also in direct proportion. The higher the humidity, the lower the leakage probability index. Increase, leading to reduce, thus making This suggests that in high humidity environments, the risk of leakage may be reduced, as humidity may affect the diffusion and concentration of gases. Indicates the effect of wind speed on the probability of leakage. The greater the wind speed, the higher the possibility of gas dilution, resulting in a lower leakage probability index. This means that in an environment with a higher wind speed, the risk of leakage may be reduced. Therefore, the humidity and wind speed of the environment are inversely proportional to the leakage probability index. By setting the weight coefficient, the actual contribution of each factor to the probability of SF6 leakage can be better reflected. Gas concentration is the most direct and important leakage indicator, which directly reflects the amount of leaked gas at the detection point. Therefore, the weight coefficient assigned to gas concentration is the largest. Temperature difference is another important leakage indicator, especially when there is a temperature difference between the leaking gas and the surrounding environment. Although the temperature difference is also important, it may be affected by other environmental factors, so its weight should be slightly smaller than that of gas concentration. Wind speed affects the diffusion speed and direction of the leaking gas and has a certain impact on the sensitivity of detection. Therefore, the weight of wind speed should be higher among environmental factors, but lower than temperature difference and gas concentration. The influence of humidity is relatively small. Although humidity can affect the diffusivity of gas or the accuracy of thermal imaging, its direct impact is usually not as good as the other aforementioned factors, so the weight coefficient assigned is the smallest. This constraint ensures that the leakage probability index is a normalized indicator, ensuring that the total contribution of the weighted combination of the four factors is 100%.

[0088] The leakage status judgment module is used to compare the leakage probability index with the preset leakage threshold to determine whether there is SF6 leakage at each warning point under the current data state.

[0089] In this embodiment, the specific logic for determining whether there is SF6 leakage under the current data state is:

[0090] The first SF6 leakage probability index of each warning point Compared with the preset leakage threshold, if the leakage probability index of the warning point is higher than the preset leakage threshold, it is judged that there is SF6 leakage at the warning point; if the leakage probability index of the warning point is lower than the preset leakage threshold, the leakage probability index of the warning point will continue to be detected within the next ten minutes until all leakage probability indices are lower than the preset leakage threshold, then it is judged that there is no SF6 leakage at the warning point.

[0091] See also Figure 2 The present invention further provides a SF6 leakage long-distance detection method based on mid-infrared thermal imaging, the SF6 leakage long-distance detection method is performed by the above-mentioned SF6 leakage long-distance detection system, and the specific steps include:

[0092] Step 1: Mark the transformer surface, the flange where the pipeline is connected to the transformer, and the inlet and outlet positions of all connecting pipelines as detection points in sequence, and arrange thermometers, mid-infrared thermal imagers, and non-dispersive infrared gas analyzers at the detection points. The surface temperature of the equipment is collected by the mid-infrared thermal imager, and the gas concentration data of the environment is collected by the non-dispersive infrared gas analyzer.

[0093] Step 2: Obtain the current ambient temperature through a thermometer, calculate the temperature difference between the ambient temperature and the equipment surface temperature, perform weighted fusion on the temperature difference and gas concentration data, and obtain comprehensive monitoring indicators;

[0094] Step 3: Compare the comprehensive monitoring indicators with the preset indicators, mark the locations where the comprehensive monitoring indicators are abnormal as warning points, and screen out all warning points;

[0095] Step 4: Collect the ambient humidity and wind speed at the warning point, perform data preprocessing on the temperature difference, gas concentration, humidity and wind speed data at the warning point, build a detection model based on the preprocessed temperature difference, gas concentration, humidity and wind speed data, and generate the SF6 leakage probability index;

[0096] Step 5: Compare the leakage probability index with the preset leakage threshold to determine whether there is SF6 leakage at each warning point under the current data state.

[0097] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0098] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A SF6 leakage long-distance detection system based on mid-infrared thermal imaging, characterized in that: include: The data acquisition module is used to mark the transformer surface, the flange where the pipeline is connected to the transformer, and the inlet and outlet positions of all connected pipelines as detection points in sequence, and to arrange thermometers, mid-infrared thermal imagers, and non-dispersive infrared gas analyzers at the detection points. The surface temperature of the equipment is collected by the mid-infrared thermal imager, and the gas concentration data of the environment is collected by the non-dispersive infrared gas analyzer. The comprehensive monitoring module is used to obtain the current ambient temperature through a thermometer, calculate the temperature difference between the ambient temperature and the equipment surface temperature, and perform weighted fusion of the temperature difference and gas concentration data to obtain comprehensive monitoring indicators; The early warning point screening module is used to compare the comprehensive monitoring indicators with the preset indicators, mark the locations where the comprehensive monitoring indicators are abnormal as early warning points, and screen out all early warning points; The leakage probability index acquisition module is used to collect the ambient humidity and wind speed at the warning point, perform data preprocessing on the temperature difference, gas concentration, humidity and wind speed data at the warning point, build a detection model based on the preprocessed temperature difference, gas concentration, humidity and wind speed data, and generate the leakage probability index of SF6; The leakage status judgment module is used to compare the leakage probability index with the preset leakage threshold to determine whether there is SF6 leakage at each warning point under the current data state; The ambient temperature of the current i-th detection point is obtained through a thermometer and calibrated as The mid-infrared thermal imager outputs a thermal image based on the infrared radiation emitted by the surface of the device. The value of each pixel is the radiation intensity received within a certain wavelength range. The relationship between radiation intensity and temperature is expressed by the formula: I=∈·σ·T 4 Where I is the radiation intensity received by the thermal imager from the device surface, ∈ is the emissivity of the device surface, that is, the ratio of the device surface radiation capacity to the black body radiation capacity, which is between 0 and 1, σ is the Stefan-Boltzmann constant, and T is the absolute temperature of the device; By inversely solving the formula, the surface temperature of the object is obtained. The formula for obtaining the surface temperature of the device is: in, Indicates the surface temperature of the equipment at the i-th detection point; The specific formula for obtaining the temperature difference is: Among them, △T i is the temperature difference at the i-th detection point; The specific formula for obtaining comprehensive monitoring indicators is: D i =ω T *△T i +oh C *C i Among them, D i represents the comprehensive monitoring index of the i-th detection point, △T i is the temperature difference of the i-th detection point, C i is the gas concentration at the i-th detection point, ω T is the weight coefficient of temperature difference, ω C is the weight coefficient of gas concentration, ω C >ω T >0 and ω T +ω C =1; The humidity sensor and wind speed sensor are used to collect the ambient humidity and wind speed of the i0th warning point. The temperature difference, gas concentration, humidity and wind speed data of each warning point are normalized and scaled to the range of [0, 1]. The humidity and wind speed of the pre-processed environment are calibrated as and The temperature difference, gas concentration, humidity and wind speed data of the warning point after preprocessing are analyzed, and the formula for obtaining the SF6 leakage probability index of the warning point is: in, is the SF6 leakage probability index of the i0th warning point, is the temperature difference of the i0th warning point, is the gas concentration at the i0th warning point, is the humidity of the environment where the i0th warning point is located, is the wind speed of the environment where the i0th warning point is located, k1, k2, k3 and k4 are weight coefficients, k2>k1>k4>k3>0 and k2+k1+k4+k3=1.

2. The SF6 leakage long-distance detection system based on mid-infrared thermal imaging according to claim 1 is characterized in that: The specific steps for obtaining the current gas concentration data are: The infrared light emitted by the non-dispersive infrared gas analyzer passes through the area where the device is located. The detector receives the transmitted light and converts it into an electrical signal, which is then digitally processed to calculate the absorption rate. The gas concentration in the area can be obtained through the absorption rate. The formula for obtaining the gas concentration in the environment is: Among them, C i is the gas concentration at the ith detection point, in kg / m 3 , α is the absorption coefficient of the gas, in m 2 / kg, L is the optical path length in meters, I0 is the initial intensity of the incident light, I i is the light intensity after passing through the ambient gas at the i-th detection point.

3. The SF6 leakage long-distance detection system based on mid-infrared thermal imaging according to claim 2 is characterized in that: The logic for screening out all warning points is: The comprehensive monitoring index of each detection point is compared with the preset index threshold. If the comprehensive detection index of the i-th detection point is higher than the index threshold, the i-th detection point is set as a warning point and the position is marked as i0. If the comprehensive monitoring index of the i-th detection point is lower than the index threshold, the i-th detection point is regarded as a safe point.

4. The SF6 leakage long-distance detection system based on mid-infrared thermal imaging according to claim 3 is characterized in that: The specific logic for judging whether there is SF6 leakage under the current data state is: The leakage probability index of SF6 at the i0th warning point is Compared with the preset leakage threshold, if the leakage probability index of the warning point is higher than the preset leakage threshold, it is judged that there is SF6 leakage at the warning point; if the leakage probability index of the warning point is lower than the preset leakage threshold, the leakage probability index of the warning point will continue to be detected within the next ten minutes until all leakage probability indices are lower than the preset leakage threshold, then it is judged that there is no SF6 leakage at the warning point.

5. A method for long-distance detection of SF6 leakage based on mid-infrared thermal imaging, characterized in that: The SF6 leakage remote detection method is performed by the SF6 leakage remote detection system according to any one of claims 1 to 4, and the specific steps include: Step 1: Mark the transformer surface, the flange where the pipeline is connected to the transformer, and the inlet and outlet positions of all connecting pipelines as detection points in sequence, and set up thermometers, mid-infrared thermal imagers, and non-dispersive infrared gas analyzers at the detection points. The surface temperature of the equipment is collected by the mid-infrared thermal imager, and the gas concentration data of the environment is collected by the non-dispersive infrared gas analyzer. Step 2: Obtain the current ambient temperature through a thermometer, calculate the temperature difference between the ambient temperature and the equipment surface temperature, perform weighted fusion on the temperature difference and gas concentration data, and obtain comprehensive monitoring indicators; Step 3: Compare the comprehensive monitoring indicators with the preset indicators, mark the locations where the comprehensive monitoring indicators are abnormal as warning points, and screen out all warning points; Step 4: Collect the ambient humidity and wind speed at the warning point, perform data preprocessing on the temperature difference, gas concentration, humidity and wind speed data at the warning point, build a detection model based on the preprocessed temperature difference, gas concentration, humidity and wind speed data, and generate the SF6 leakage probability index; Step 5: Compare the leakage probability index with the preset leakage threshold to determine whether there is SF6 leakage at each warning point under the current data state.

Images