A gas leak detection method, device and equipment based on thermal imaging technology

Abstract

The present invention provides a gas leak detection method, device, and equipment based on thermal imaging technology. These methods identify a target area in a thermal image of chemical equipment and determine the target area. The method also acquires the target area in real time, generates data points, and fits the data points to a fitted curve. Reference points are determined, and anomaly curves are determined based on the monotonicity of the fitted curve between two adjacent reference points. The method also calculates the average rate of change, generates a set of average rates of change, and determines the maximum rate of change. An evaluation coefficient is determined based on the fitted curve, the anomaly curve, and the maximum rate of change, and the presence of a gas leak is determined. This method improves the accuracy of gas leak detection and avoids the loss of work efficiency caused by misjudgments. Through real-time monitoring and highly automated analysis, the method effectively identifies abnormal gas leak conditions, reduces false alarms, and improves the safety monitoring efficiency of chemical equipment. Thermal imaging technology enables continuous, contactless monitoring of equipment, ensuring safe and real-time operation.

Description

Technical Field

[0001] The present invention relates to the technical field of gas leakage detection, and in particular to a gas leakage detection method, device and equipment based on thermal imaging technology. Background Art

[0002] Thermal imaging technology refers to the use of infrared detectors and optical imaging lenses to receive the infrared radiation energy distribution pattern of the target being measured and reflect it on the photosensitive element of the infrared detector, thereby obtaining a thermal imaging image. This thermal imaging image corresponds to the heat distribution field on the surface of the object, and the different colors on the thermal imaging image represent the different temperatures of the object being measured.

[0003] Gas leakage refers to the abnormal escape of waste gases (such as carbon monoxide, carbon dioxide, etc.) generated by combustion or harmful gases produced in other chemical processes from certain parts of the equipment or pipelines into the surrounding environment during the operation of chemical equipment due to equipment aging, poor sealing, pipeline damage or operational errors. This type of leakage may not only lead to a decrease in production efficiency, but also pose a serious threat to the health of operators and even cause major safety accidents such as fire or explosion.

[0004] In the existing technology, most of the methods for determining whether there is a gas leak are to determine the area in the thermal imaging image where the temperature exceeds a preset value. However, in actual situations, the reaction conditions include heat exchange between the high-temperature chemical equipment itself and the environment, which will also cause the ambient temperature to rise, and then cause the area in the thermal imaging image where the temperature exceeds the preset value to increase. In this case, the judgment result of the gas leak may be erroneous, and after receiving the erroneous warning information, the staff will need to shut down the chemical equipment and handle the chemical equipment, affecting the overall work efficiency. Summary of the Invention

[0005] The purpose of the present invention is to provide a gas leakage detection method, device and equipment based on thermal imaging technology, which can improve the accuracy of judging gas leakage and avoid the decrease in work efficiency caused by misjudgment.

[0006] According to one object of the present invention, the present invention provides a gas leak detection method based on thermal imaging technology, comprising the following steps:

[0007] S1. Acquire a thermal imaging image of a chemical plant, determine a target area based on temperature values ​​corresponding to pixels in the thermal imaging image, determine the area of ​​a minimum circumscribed rectangle of the target area, and use the area as the target area;

[0008] S2. Obtain the target area in real time within the preset monitoring period and generate data points (t a , S a ), S aThe time interval between the start point of the monitoring period is t a The target area at the time of φ is obtained, and the data points are fitted to obtain a fitting curve f(x);

[0009] S3. Taking the maximum and minimum points on the fitting curve as reference points, and taking the starting point and the end point of the fitting curve as reference points, and determining the monotonicity of the fitting curve between two adjacent reference points, and when the fitting curve monotonically increases between two adjacent reference points, taking it as an abnormal curve h(x);

[0010] S4. Calculate the average rate of change [0, T] is the value range of the abnormal curve, generating the average change rate set C jh =(C1, C2, ..., C n ), C n Indicates the average rate of change corresponding to the nth abnormal curve and determines the maximum rate of change C max =max(C jh );

[0011] S3. Determine an evaluation coefficient K based on the fitting curve, the abnormal curve, and the maximum change rate, and determine that there is a gas leak when the evaluation coefficient K≥K', and send an early warning message to remind staff, where K' represents a preset evaluation coefficient threshold.

[0012] Furthermore, in step S3, the process of determining the evaluation coefficient K according to the fitting curve, the abnormal curve and the maximum change rate specifically includes:

[0013] The evaluation coefficient K is calculated by the formula, which specifically includes:

[0014]

[0015] Among them, ε represents the preset correction coefficient, T i represents the i-th abnormal curve h i (x) duration, t sta Indicates the starting point of the monitoring period, t end Indicates the end of the monitoring period.

[0016] Furthermore, in step S1, when the target area S≥S', subsequent steps are not executed and it is determined that there is a gas leak, and an early warning message is sent to remind the staff, where S' represents a preset target area threshold.

[0017] Furthermore, in step S3, a reference point number threshold m is set. When the number of reference points is less than or equal to m-2, the following steps are performed:

[0018] determining the monotonicity of the fitted curve;

[0019] When the fitting curve increases monotonically, the calculated area difference ΔS=S'-f(t end ), when the area difference ΔS≤ΔS', it is determined that there is a gas leak and an early warning message is sent to remind the staff, ΔS' represents a preset area difference threshold;

[0020] When the fitting curve decreases monotonically, it is determined that there is no gas leakage;

[0021] When the fitting curve does not have monotonicity, a preset judgment step is performed to determine whether there is a gas leak.

[0022] Furthermore, the judging step specifically includes:

[0023] Determine the maximum area S max = max(f(x)), and calculate the evaluation difference SPG = S'-S max When the evaluation difference SPG≤ΔS', it is determined that there is a gas leak and an early warning message is sent to remind the staff.

[0024] Furthermore, in step S4, the process of determining the maximum change rate further includes the following steps:

[0025] Calculate the rate of change difference ΔC b =C b -C max , and when the change rate difference is greater than or equal to ΔC b =≥C', it is marked as an abnormal difference, and C' represents the preset difference threshold;

[0026] Calculate the abnormal ratio R = Byc / Btot, where Byc represents the total number of abnormal differences and Btot represents the total number of rate of change differences. When the abnormal ratio R ≥ 0.8, remove the maximum rate of change, determine the maximum rate of change again, and repeat the above steps until the corresponding abnormal ratio R is < 0.8 after removing the maximum rate of change.

[0027] Furthermore, in step S1, the process of determining the target area according to the temperature values ​​corresponding to the pixels in the thermal imaging image specifically includes:

[0028] Determine the temperature value corresponding to the pixel point in the thermal imaging image, and when the temperature value corresponding to the pixel point is greater than or equal to a preset temperature value threshold, mark the pixel point as a target pixel point, mark all target pixel points in the thermal imaging image, and use the area formed by all target pixel points as the target area.

[0029] Furthermore, in step S1, the thermal imaging image of the chemical equipment is acquired based on a thermal imager, and the thermal imager is located at a preset position.

[0030] According to a second aspect of an embodiment of the present invention, a gas leakage detection device based on thermal imaging technology is provided, comprising:

[0031] a target area determination module, configured to obtain a thermal imaging image of the chemical equipment, determine a target area based on the temperature values ​​corresponding to the pixels in the thermal imaging image, and determine the area of ​​the minimum circumscribed rectangle of the target area as the target area;

[0032] The data point generation and curve fitting module is used to obtain the target area in real time within the preset monitoring period and generate data points (t a , S a ), S a The time interval between the start point of the monitoring period is t a The target area at the time of φ is obtained, and the data points are fitted to obtain a fitting curve f(x);

[0033] an abnormal curve calculation module, which uses the maximum and minimum points on the fitting curve as reference points, and uses the starting point and end point of the fitting curve as reference points, and determines the monotonicity of the fitting curve between two adjacent reference points, and when the fitting curve monotonically increases between two adjacent reference points, it is regarded as an abnormal curve h(x);

[0034] Change rate calculation module, calculates the average change rate [0, T] is the value range of the abnormal curve, generating the average change rate set C jh =(C1, C2, ..., C n ), C n Indicates the average rate of change corresponding to the nth abnormal curve and determines the maximum rate of change C max =max(C jh );

[0035] The evaluation coefficient and gas leakage judgment module determines the evaluation coefficient K according to the fitting curve, the abnormal curve and the maximum change rate, and determines that there is a gas leakage when the evaluation coefficient K≥K', and sends an early warning message to remind the staff, where K' represents a preset evaluation coefficient threshold.

[0036] According to a third aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps of the gas leakage detection method based on thermal imaging technology provided in the first aspect of the present disclosure are implemented.

[0037] The technical solution of the present invention first determines the target area, that is, the area to be monitored. When the thermal imager is imaging, it is a thermal imaging image of the entire area. By determining the target area, the amount of data that needs to be processed later can be reduced, the overall processing efficiency can be improved, and computing resources can be saved. Then, the area of ​​the minimum circumscribed rectangle of the target area (i.e., the target area) is determined, and data points are generated based on the target area and a fitting curve is determined. This is the basis for subsequent processing. It is worth noting that the fitting curve can reflect the changing trend of the target area. The changing trend of the target area under normal conditions is very different from that under abnormal conditions (i.e., when there is a gas leak). When there is a gas leak, the speed and degree of increase of the target area are greater. Then, the abnormal curve is determined. The abnormal curve is the part of the fitting curve where the target area increases. Considering the change of the abnormal curve, the computing resource requirements during the overall analysis are reduced. Then, the average change rate is calculated and the maximum change rate is determined. The maximum change rate reflects the speed at which the target area increases. The greater the speed at which the target area increases, the higher the risk of gas leakage. Finally, an evaluation coefficient is determined based on the fitting curve, the abnormal curve, and the maximum change rate, and a gas leak is determined. The present invention can improve the accuracy of judging gas leaks and avoid the decrease in work efficiency caused by misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are 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.

[0039] Figure 1 A schematic diagram of a flow chart of an embodiment of the present invention;

[0040] Figure 2 Schematic diagram of the structure of the device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0042] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like to indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention.

[0043] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a communication between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0044] Example 1

[0045] like Figure 1 As shown, a gas leak detection method based on thermal imaging technology includes the following steps:

[0046] S1: Acquire a thermal imaging image of the chemical equipment, determine a target area based on temperature values ​​corresponding to pixels in the thermal imaging image, determine the area of ​​a minimum circumscribed rectangle of the target area, and use the area as the target area;

[0047] S2: Obtain the target area in real time within the preset monitoring period and generate data points (t a , S a ), S a The time interval between the start point of the monitoring period is t a The target area at the time of φ(x) is obtained, and the data points are fitted to obtain a fitting curve f(x);

[0048] S3: taking the maximum point and the minimum point on the fitting curve as reference points, and taking the starting point and the end point of the fitting curve as reference points, and determining the monotonicity of the fitting curve between two adjacent reference points, and when the fitting curve monotonically increases between two adjacent reference points, taking it as an abnormal curve h(x);

[0049] S4: Calculate the average rate of change [0, T] is the value range of the abnormal curve, generating the average change rate set C jh =(C1, C2, ..., C n ), C n Indicates the average rate of change corresponding to the nth abnormal curve and determines the maximum rate of change C max =max(C jh );

[0050] S5: Determine the evaluation coefficient K according to the fitting curve, the abnormal curve and the maximum change rate, and determine that there is a gas leak when the evaluation coefficient K≥K', and send an early warning message to remind the staff, where K' represents a preset evaluation coefficient threshold.

[0051] It should be noted that the target area (i.e., the area to be monitored) is first determined. The thermal imager captures a thermal image of the entire area. Determining the target area can reduce the amount of data required for subsequent processing, improve overall processing efficiency, and save computing resources. The area of ​​the minimum enclosing rectangle of the target area (i.e., the target area) is then determined. Data points are generated based on the target area and a fitting curve is determined. This forms the basis for subsequent processing. It is worth noting that the fitting curve can reflect the changing trend of the target area. The changing trend of the target area under normal conditions differs significantly from that under abnormal conditions (i.e., when a gas leak occurs). When a gas leak occurs, the target area increases at a greater rate and degree. Next, the abnormal curve is determined. The abnormal curve is the portion of the fitting curve where the target area increases. Considering the changes in the abnormal curve reduces the computing resource requirements for the overall analysis. The average rate of change is then calculated and the maximum rate of change is determined. The maximum rate of change reflects the rate of increase of the target area. The greater the rate of increase of the target area, the higher the risk of gas leakage. Finally, the evaluation coefficient is determined based on the fitting curve, the abnormal curve, and the maximum rate of change, and a determination is made as to whether a gas leak exists.

[0052] In another preferred embodiment of the present invention, in step S5, the process of determining the evaluation coefficient K according to the fitting curve, the abnormal curve and the maximum change rate specifically includes:

[0053] The evaluation coefficient K is calculated by the formula, which specifically includes:

[0054]

[0055] Among them, ε represents the preset correction coefficient, T i represents the i-th abnormal curve h i (x) duration, t sta Indicates the starting point of the monitoring period, t end Indicates the end of the monitoring period.

[0056] It is worth noting that the greater the maximum rate of change, the faster the target area increases, which means the greater the possibility of gas leakage. Therefore, the maximum rate of change is proportional to the evaluation coefficient. It is understandable that under normal conditions, there is heat exchange between the chemical equipment in working condition and the environment, and the target area will also increase, but the rate and amplitude of increase should be lower; the relationship between the remaining parameters and the evaluation coefficient is determined by referring to the above ideas, and will not be elaborated on here; ε can be set by experience.

[0057] In another preferred embodiment of the present invention, in step S1, when the target area S≥S', subsequent steps are not executed and it is determined that there is a gas leak, and an early warning message is sent to remind the staff, and S' represents the preset target area threshold.

[0058] It can be understood that by setting the target area threshold S', when the target area is detected to reach or exceed the threshold, the system can immediately determine the presence of a gas leak and quickly issue a warning message. This allows for a timely response in extreme cases (such as severe leaks), avoiding missing the optimal processing opportunity due to computational delays. In some obvious cases, a rapid increase in the target area may indicate a very serious gas leak, and further complex calculations such as fitting curves and abnormal curves may no longer be necessary. Setting a threshold can simplify the processing process and reduce the system's computational burden and resource consumption.

[0059] In another preferred embodiment of the present invention, in step S3, a reference point number threshold m is set, and when the number of reference points is less than or equal to m-2, the following steps are performed:

[0060] determining the monotonicity of the fitted curve;

[0061] When the fitting curve increases monotonically, the calculated area difference ΔS=S'-f(t end ), when the area difference ΔS≤ΔS', it is determined that there is a gas leak and an early warning message is sent to remind the staff, ΔS' represents a preset area difference threshold;

[0062] When the fitting curve decreases monotonically, it is determined that there is no gas leakage;

[0063] When the fitting curve does not have monotonicity, a preset judgment step is performed to determine whether there is a gas leak.

[0064] It should be noted that by setting the reference point number threshold m, when the number of reference points is small, that is, less than or equal to (m-1), the monotonicity of the fitting curve is judged, and corresponding processing steps are taken according to different situations, thereby simplifying the judgment process, avoiding unnecessary complex analysis, and improving the overall detection efficiency; when the number of reference points is small, the fitting curve may not provide enough information for detailed analysis. In this case, directly performing risk assessment based on the monotonicity of the curve and the area difference can improve the sensitivity of the system in specific situations and avoid underreporting; when the number of reference points is small, directly judging the monotonicity of the fitting curve and performing a simplified risk assessment based on the area difference ΔS can reduce the amount of calculation and improve the detection speed, which is particularly important in real-time monitoring systems.

[0065] In another preferred embodiment of the present invention, the determining step specifically includes:

[0066] Determine the maximum area S max = max(f(x)), and calculate the evaluation difference SPG = S'-S max When the evaluation difference SPG≤ΔS', it is determined that there is a gas leak and an early warning message is sent to remind the staff.

[0067] It should be noted that by calculating the maximum area S max The difference between the maximum expansion of the target area and the preset target area threshold can quantify the difference between the expected area and the maximum expansion of the target area. This difference directly reflects whether there is a risk of abnormal expansion, thereby providing a clear quantitative indicator for the assessment of leakage risk. At the same time, this method can capture the peak value of the target area during the entire monitoring cycle, ensuring that even abnormal expansion that occurs in a short period of time can be detected, which helps to avoid underreporting due to area fluctuations.

[0068] In another preferred embodiment of the present invention, in step S4, the process of determining the maximum rate of change further includes the following steps:

[0069] Calculate the rate of change difference ΔC b =C b -C max , and when the rate of change difference is greater than or equal to ΔC b =≥C', it is marked as an abnormal difference, and C' represents the preset difference threshold;

[0070] Calculate the abnormal ratio R = Byc / Btot, where Byc represents the total number of abnormal differences and Btot represents the total number of rate of change differences. When the abnormal ratio R is ≥ 0.8, remove the maximum rate of change, determine the maximum rate of change again, and repeat the above steps until the corresponding abnormal ratio R is < 0.8 after removing the maximum rate of change.

[0071] It is understandable that in complex monitoring data, some abnormally high change rates may be caused by noise or short-term fluctuations rather than real gas leaks. These abnormal change rates may interfere with the overall judgment. The above method can be used to identify and remove these abnormal data points, thereby improving the accuracy of the final assessment results. When determining the maximum change rate, by removing those abnormal change rates that account for too high a proportion, the excessive influence of a single extreme value on the overall judgment can be avoided. This method helps to ensure that the maximum change rate that is ultimately retained is more representative, thereby improving the reliability of gas leak assessment.

[0072] In another preferred embodiment of the present invention, in step S1, the process of determining the target area according to the temperature values ​​corresponding to the pixels in the thermal imaging image specifically includes:

[0073] Determine the temperature value corresponding to the pixel point in the thermal imaging image, and when the temperature value corresponding to the pixel point is greater than or equal to a preset temperature value threshold, mark the pixel point as a target pixel point, mark all target pixel points in the thermal imaging image, and use the area formed by all target pixel points as the target area.

[0074] It is worth noting that by identifying pixels representing high temperatures and determining target areas, it is possible to focus analysis and monitoring of key areas and reduce the computing resources required for overall analysis.

[0075] In another preferred embodiment of the present invention, in step S1, the thermal imaging image of the chemical equipment is acquired based on a thermal imager, and the thermal imager is at a preset position.

[0076] It is worth noting that fixing the thermal imager at a preset position can ensure that the thermal imaging image obtained each time has the same viewing angle and coverage during the entire monitoring cycle, avoiding inconsistent monitoring results due to changes in the instrument position, and ensuring the stability and accuracy of monitoring. The preset position is determined according to actual conditions; by pre-setting the position of the thermal imager, it can ensure that key parts (such as high-temperature parts of chemical equipment or areas prone to leakage) are within the monitoring range, which helps to maximize the monitoring effect of the thermal imager and ensure that key areas are continuously monitored.

[0077] Example 2

[0078] like Figure 2As shown, a gas leak detection device based on thermal imaging technology includes:

[0079] a target area determination module, configured to obtain a thermal imaging image of the chemical equipment, determine a target area based on the temperature values ​​corresponding to the pixels in the thermal imaging image, and determine the area of ​​the minimum circumscribed rectangle of the target area as the target area;

[0080] The data point generation and curve fitting module is used to obtain the target area in real time within the preset monitoring period and generate data points (t a , S a ), S a The time interval between the start point of the monitoring period is t a The target area at the time of φ is obtained, and the data points are fitted to obtain a fitting curve f(x);

[0081] an abnormal curve calculation module, which uses the maximum and minimum points on the fitting curve as reference points, and uses the starting point and end point of the fitting curve as reference points, and determines the monotonicity of the fitting curve between two adjacent reference points, and when the fitting curve monotonically increases between two adjacent reference points, it is regarded as an abnormal curve h(x);

[0082] Change rate calculation module, calculates the average change rate [0, T] is the value range of the abnormal curve, generating the average change rate set C jh =(C1, C2, ..., C n ), C n Indicates the average rate of change corresponding to the nth abnormal curve and determines the maximum rate of change C max =max(C jh );

[0083] The evaluation coefficient and gas leakage judgment module determines the evaluation coefficient K according to the fitting curve, the abnormal curve and the maximum change rate, and determines that there is a gas leakage when the evaluation coefficient K≥K', and sends an early warning message to remind the staff, where K' represents a preset evaluation coefficient threshold.

[0084] In the present invention, the target area, i.e., the area to be monitored, is first determined. The thermal imager captures a thermal image of the entire area. Determining the target area can reduce the amount of data that needs to be processed subsequently, improve overall processing efficiency, and save computing resources. The area of ​​the minimum circumscribed rectangle of the target area (i.e., the target area) is then determined, and data points are generated based on the target area to determine a fitting curve, which forms the basis for subsequent processing. It is worth noting that the fitting curve can reflect the changing trend of the target area. The changing trend of the target area under normal conditions differs significantly from that under abnormal conditions (i.e., when there is a gas leak). When there is a gas leak, the speed and degree of increase of the target area are both greater. Next, an abnormal curve is determined. The abnormal curve is the portion of the fitting curve where the target area increases. Taking into account the changes in the abnormal curve, the computing resource requirements for the overall analysis are reduced. The average rate of change is then calculated and the maximum rate of change is determined. The maximum rate of change reflects the rate of increase of the target area. The greater the rate of increase of the target area, the higher the risk of gas leakage. Finally, an evaluation coefficient is determined based on the fitting curve, the abnormal curve, and the maximum rate of change, and a determination is made as to whether there is a gas leak.

[0085] This invention improves the accuracy of gas leak detection, avoiding the loss of work efficiency caused by misjudgments. Through real-time monitoring and highly automated analysis, it effectively identifies abnormal gas leak conditions, reduces false alarms, and improves the safety monitoring efficiency of chemical equipment. Thermal imaging technology enables continuous, contactless monitoring of equipment, ensuring safe and real-time operation.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A gas leak detection method based on thermal imaging technology, characterized in that: The steps include: S1. Acquire a thermal imaging image of a chemical plant, determine a target area based on temperature values ​​corresponding to pixels in the thermal imaging image, determine the area of ​​a minimum circumscribed rectangle of the target area, and use the area as the target area; S2. Obtain the target area in real time within the preset monitoring period and generate data points (t a , S a ), S a The time interval between the start point of the monitoring period is t a The target area at the time of , and fitting the data points to obtain a fitting curve f (x); S3, taking the maximum point and the minimum point on the fitting curve as reference points, and taking the starting point and the end point of the fitting curve as reference points, and determining the monotonicity of the fitting curve between two adjacent reference points, and when the fitting curve monotonically increases between two adjacent reference points, taking it as an abnormal curve h(x); S4. Calculate the average rate of change , [0, T] is the value range of the abnormal curve, generating the average change rate set C jh = (C1, C2, ..., C n ), C n Indicates the average rate of change corresponding to the nth abnormal curve and determines the maximum rate of change C max =max(C jh ); S5. Determine an evaluation coefficient K based on the fitting curve, the abnormal curve, and the maximum rate of change, and determine that a gas leak exists when the evaluation coefficient K ≥ K', and send an early warning message to alert staff, where K' represents a preset evaluation coefficient threshold; In step S5, the process of determining the evaluation coefficient K according to the fitting curve, the abnormal curve and the maximum change rate specifically includes: The evaluation coefficient K is calculated by the formula, which specifically includes: ； Among them, ε represents the preset correction coefficient, T i represents the i-th abnormal curve h i (x) duration, t sta Indicates the starting point of the monitoring period, t end Indicates the end of the monitoring period.

2. The gas leakage detection method based on thermal imaging technology according to claim 1, characterized in that: In step S1, when the target area S≥S', subsequent steps are not executed and it is determined that there is a gas leak, and an early warning message is sent to remind the staff. S' represents a preset target area threshold.

3. The gas leakage detection method based on thermal imaging technology according to claim 2, characterized in that: In step S3, a reference point number threshold m is set. When the number of reference points is less than or equal to m-2, the following steps are performed: determining the monotonicity of the fitted curve; When the fitting curve increases monotonically, the calculated area difference ΔS=S'-f(t end ), when the area difference ΔS≤ΔS', it is determined that there is a gas leak and an early warning message is sent to remind the staff, ΔS' represents the preset area difference threshold; When the fitting curve decreases monotonically, it is determined that there is no gas leakage; When the fitting curve does not have monotonicity, a preset judgment step is performed to determine whether there is a gas leak.

4. The gas leakage detection method based on thermal imaging technology according to claim 3, characterized in that: The judging step specifically includes: Determine the maximum area S max = max(f(x)), and calculate the evaluation difference SPG = S'-S max When the evaluation difference SPG≤ΔS', it is determined that there is a gas leak and an early warning message is sent to remind the staff.

5. The gas leakage detection method based on thermal imaging technology according to claim 1, characterized in that: In step S4, the process of determining the maximum rate of change further includes the following steps: Calculate the rate of change difference ΔC b =C b -C max , and when the change rate difference is greater than or equal to ΔC b =≥C', it is marked as an abnormal difference, and C' represents the preset difference threshold; Calculate the abnormal ratio R = Byc / Btot, where Byc represents the total number of abnormal differences and Btot represents the total number of rate of change differences. When the abnormal ratio R ≥ 0.8, remove the maximum rate of change, determine the maximum rate of change again, and repeat the above steps until the corresponding abnormal ratio R is < 0.8 after removing the maximum rate of change.

6. The gas leakage detection method based on thermal imaging technology according to claim 1, characterized in that: In step S1, the process of determining the target area according to the temperature values ​​corresponding to the pixels in the thermal imaging image specifically includes: Determine the temperature value corresponding to the pixel point in the thermal imaging image, and when the temperature value corresponding to the pixel point is greater than or equal to a preset temperature value threshold, mark the pixel point as a target pixel point, mark all target pixel points in the thermal imaging image, and use the area formed by all target pixel points as the target area.

7. The gas leakage detection method based on thermal imaging technology according to claim 1, characterized in that: In step S1, the thermal imaging image of the chemical equipment is obtained based on a thermal imager, and the thermal imager is at a preset position.

8. A device for gas leakage detection method based on thermal imaging technology according to any one of claims 1 to 7, characterized in that: include: a target area determination module, configured to obtain a thermal imaging image of the chemical equipment, determine a target area based on the temperature values ​​corresponding to the pixels in the thermal imaging image, and determine the area of ​​the minimum circumscribed rectangle of the target area as the target area; The data point generation and curve fitting module is used to obtain the target area in real time within the preset monitoring period and generate data points (t a , S a ), S a The time interval between the start point of the monitoring period is t a The target area at the time of , and fitting the data points to obtain a fitting curve f (x); an abnormal curve calculation module, which uses the maximum and minimum points on the fitting curve as reference points, and uses the starting point and end point of the fitting curve as reference points, and determines the monotonicity of the fitting curve between two adjacent reference points, and when the fitting curve monotonically increases between two adjacent reference points, it is regarded as an abnormal curve h(x); Change rate calculation module, calculates the average change rate , [0, T] is the value range of the abnormal curve, generating the average change rate set C jh = (C1, C2, ..., C n ), C n Indicates the average rate of change corresponding to the nth abnormal curve and determines the maximum rate of change C max =max(C jh ); The evaluation coefficient and gas leakage judgment module determines the evaluation coefficient K according to the fitting curve, the abnormal curve and the maximum change rate, and determines that there is a gas leakage when the evaluation coefficient K≥K', and sends an early warning message to remind the staff, where K' represents a preset evaluation coefficient threshold.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the gas leak detection method based on thermal imaging technology as claimed in any one of claims 1 to 8 are implemented.

Images