Gas leakage detection method, device, equipment, storage medium and program product

Abstract

The application provides a gas leakage detection method, device, equipment, storage medium and program product. The method comprises the following steps: obtaining first light intensity attenuation data of a target area, and performing inversion reconstruction processing on the first light intensity attenuation data to obtain a laser concentration field; obtaining flow data in a low peak period in the target area, and determining flow anomaly data in the flow data through an anomaly detection model; obtaining discrete pressure sensor data in the target area, and determining pressure topology low point data based on the discrete pressure sensor data; then, the laser concentration field, the flow anomaly data and the pressure topology low point data are fused to obtain leakage confidence, and an alarm notification and a leakage point position are output when the leakage confidence exceeds a preset threshold, so as to reduce the gas detection blind area and improve the accuracy of the gas leakage detection result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gas leakage inspection, and in particular to a gas leakage detection method, device, equipment, storage medium and program product. BACKGROUND

[0002] Gas leakage is a major hidden danger for urban public safety, and therefore gas detection needs to be performed in residential areas, industrial and commercial users, gas pipe networks and the like to improve urban public safety.

[0003] The prior art is to densely deploy point sensors such as catalytic combustion, electrochemical and thermal conductivity sensors in a detection area, and to realize real-time detection of gas in the detection area through multiple point sensors.

[0004] However, the effective detection radius of a single catalytic combustion sensor in the prior art is 2-5 meters, and therefore 200-500 point sensors need to be deployed in each square kilometer area, which is costly and prone to a large number of blind areas, thereby further reducing the detection accuracy of gas leakage. SUMMARY

[0005] The embodiments of the present application provide a gas leakage detection method, device, equipment, storage medium and program product to reduce the gas detection blind area and improve the accuracy of the gas leakage detection result.

[0006] In a first aspect, the embodiments of the present application provide a gas leakage detection method, comprising:

[0007] obtaining first light intensity attenuation data of a target area, flow data of a low peak period in the target area and discrete pressure sensor data in the target area;

[0008] obtaining a laser concentration field by inverse reconstruction processing of the first light intensity attenuation data, determining flow anomaly data in the flow data through an anomaly detection model, and determining pressure topology low point data based on the discrete pressure sensor data;

[0009] performing fusion processing on the laser concentration field, the flow anomaly data and the pressure topology low point data to obtain a leakage confidence; and outputting an alarm notification and a leakage point position when the leakage confidence exceeds a preset threshold.

[0010] Optionally, the fusion processing of the laser concentration field, the flow anomaly data and the pressure topology low point data to obtain the leakage confidence specifically comprises:

[0011] performing spatio-temporal alignment processing on the laser concentration field, the flow anomaly data and the pressure topology low point data to obtain spatio-temporally aligned laser concentration field, flow anomaly data and pressure topology low point data;

[0012] determine laser evidence according to laser scanning concentration values in the laser concentration field after spatiotemporal alignment; determine flow evidence according to gas meter flow in the flow anomaly data after spatiotemporal alignment; determine pressure evidence according to pressure topology low point data after spatiotemporal alignment;

[0013] When the target region does not meet the preset complex terrain, perform evidence synthesis processing based on the laser evidence, the flow evidence, and the pressure evidence to determine a local leakage confidence of the target region.

[0014] Optionally, after determining the local leakage confidence, perform weighted average processing on laser scanning point positions corresponding to the laser concentration field, gas meter positions corresponding to the flow anomaly data, and pressure sensor positions corresponding to the pressure topology low point data to obtain a leakage point position corresponding to the local leakage confidence.

[0015] Optionally, when the target region meets the preset complex terrain, determine unmanned aerial vehicle leakage evidence based on the unmanned aerial vehicle concentration field;

[0016] Generate a global leakage confidence of the target region according to the unmanned aerial vehicle leakage evidence, the laser evidence, the flow evidence, and the pressure evidence.

[0017] Optionally, when the global leakage confidence exceeds a preset threshold, obtain a leakage point position corresponding to the global leakage confidence of the target region by determining a spatial intersection of a leakage point position indicated by the unmanned aerial vehicle leakage evidence and leakage point positions indicated by the laser evidence, the flow evidence, and the pressure evidence.

[0018] Optionally, the unmanned aerial vehicle concentration field is obtained by inverse reconstruction on second light intensity attenuation data of the target region collected by an unmanned aerial vehicle extension unit; wherein,

[0019] When the unmanned aerial vehicle extension unit collects the second light intensity attenuation data of the target region, the following steps are included:

[0020] Determine a single route scanning width based on terrain constraint information of the target region, a preset flight height, and a preset laser scanning field of view angle;

[0021] Generate an obstacle avoidance route set that meets a preset coverage rate for the target region based on the single route scanning width; and collect the second light intensity attenuation data based on the obstacle avoidance route set.

[0022] In a second aspect, an embodiment of the present application provides a gas leakage detection device, which includes:

[0023] An acquisition module is configured to acquire first light intensity attenuation data of a target region, flow data of a low peak period in the target region, and discrete pressure sensor data in the target region.

[0024] The processing module is used to obtain the laser concentration field by inverting and reconstructing the first light intensity attenuation data; to identify abnormal flow data in the flow data through an anomaly detection model; and to determine the pressure topological low point data based on discrete pressure sensor data.

[0025] The processing module is also used to fuse laser concentration field, abnormal flow data and pressure topology low point data to obtain leakage confidence; when the leakage confidence exceeds a preset threshold, it outputs an alarm notification and the location of the leakage point.

[0026] Optionally, the processing module is also used to perform spatiotemporal alignment processing on the laser concentration field, flow anomaly data and pressure topology low point data to obtain spatiotemporally aligned laser concentration field, flow anomaly data and pressure topology low point data;

[0027] Laser evidence was determined based on the laser scan concentration value in the spatiotemporally aligned laser concentration field; flow evidence was determined based on the gas meter flow rate in the spatiotemporally aligned flow anomaly data; and pressure evidence was determined based on the spatiotemporally aligned pressure topology low point data.

[0028] When the target area does not conform to the preset complex terrain, evidence synthesis processing is performed based on laser evidence, flow evidence, and pressure evidence to determine the local leakage confidence level of the target area.

[0029] Optionally, the processing module is further configured to, after determining the local leakage confidence level, perform weighted averaging on the laser scanning point location corresponding to the laser concentration field, the gas meter location corresponding to the abnormal flow data, and the pressure sensor location corresponding to the low pressure topology data to obtain the leakage point location corresponding to the local leakage confidence level.

[0030] Optionally, the processing module is also used to determine evidence of drone leakage based on the drone concentration field when the target area meets the preset complex terrain.

[0031] Based on drone leakage evidence, laser evidence, flow evidence, and pressure evidence, a global leakage confidence level for the target area is generated.

[0032] Optionally, the processing module is also used to obtain the location of the leak point corresponding to the global leakage confidence level of the target area by determining the spatial intersection of the leak point location indicated by the UAV leakage evidence and the leak point locations indicated by the laser evidence, flow evidence, and pressure evidence when the global leakage confidence level exceeds a preset threshold.

[0033] Optionally, the concentration field of the UAV is obtained by inverting and reconstructing the second light intensity attenuation data of the target area after the UAV extended unit collects the second light intensity attenuation data of the target area; wherein,

[0034] The processing module is also used to determine the scanning width of a single flight path based on the terrain constraint information of the target area, the preset flight altitude, and the preset laser scanning field of view.

[0035] A set of obstacle avoidance routes is generated based on the scanning width of a single route to ensure that the coverage of the target area meets the preset coverage rate; second light intensity attenuation data is collected based on the set of obstacle avoidance routes.

[0036] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0037] The memory stores instructions that the computer executes;

[0038] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0039] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0040] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0041] The gas leak detection method, apparatus, equipment, storage medium, and program product provided in this application embodiment obtains first light intensity attenuation data of a target area and performs inversion reconstruction processing on the first light intensity attenuation data to obtain a laser concentration field; obtains flow rate data during off-peak hours in the target area and identifies abnormal flow rate data in the flow rate data through an anomaly detection model; obtains discrete pressure sensor data in the target area and determines pressure topological low point data based on the discrete pressure sensor data; then, it performs fusion processing on the laser concentration field, abnormal flow rate data, and pressure topological low point data to obtain a leak confidence level, and outputs an alarm notification and leak point location when the leak confidence level exceeds a preset threshold, thereby reducing the gas detection blind zone and improving the accuracy of gas leak detection results. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] Figure 1 A flowchart illustrating the gas leak detection method provided in this application;

[0044] Figure 2Schematic diagram of the gas leak detection system provided in this application Figure 1 ;

[0045] Figure 3 Schematic diagram of the gas leak detection system provided in this application Figure 2 ;

[0046] Figure 4 A schematic diagram of the gas leak detection device provided in this application;

[0047] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0048] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0049] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0050] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse.

[0051] Currently, gas leaks pose a significant threat to urban public safety. Therefore, timely detection of gas leaks is necessary. Detection locations include, but are not limited to: residential areas, industrial and commercial users, gas pipeline networks, gas gate stations and other urban gas infrastructure areas; complex terrain areas such as mountainous areas and rivers; super-large areas such as industrial parks with a floor area of ​​10 km²; areas involved in emergency situations such as pipeline inspections after earthquakes; and underground areas such as underground utility tunnels where GPS (Global Positioning System) signals are missing.

[0052] Existing gas leak detection technologies are divided into contact detection technologies (such as catalytic combustion sensors, electrochemical sensors, and thermal conductivity sensors) and non-contact detection technologies (such as infrared gas imaging and ultrasonic detection).

[0053] For example, in contact detection technology, catalytic combustion sensors are used for detection. The effective detection radius of a single catalytic combustion sensor is only 2-5 meters, and 200-500 sensors need to be deployed per square kilometer. This is costly and has a large number of blind spots, resulting in limited coverage. Furthermore, since catalytic combustion sensors rely on the heat change generated by the combustion of gas on the catalyst surface to detect concentration, this method is suitable for combustible gases such as methane and propane, but it is susceptible to sulfides, leading to poisoning or detection failure, which reduces the safety and reliability of the detection.

[0054] For example, in non-contact detection technologies, infrared gas imaging equipment is used for detection. This method utilizes the absorption characteristics of gases to specific wavelengths of infrared light to generate gas cloud images using a thermal imager. It is suitable for visualizing leaks in industrial plants, but its effective detection distance is less than 100 meters, which limits its detection range. It is also susceptible to weather conditions (such as rain and fog), making it difficult to meet the needs of large-area coverage. In addition, when identifying gas leaks through manual inspections, blind spots in inspection paths are likely to exist in complex pipe networks (such as underground pipe corridors and densely built-up areas). Manual inspections are inefficient, rely on human experience, and have a high rate of missed detections.

[0055] Based on the above scenarios, it can be seen that existing technologies suffer from technical problems such as limited detection range, high false negative rate, low detection efficiency, and poor accuracy.

[0056] The gas leak detection method provided in this application acquires first light intensity attenuation data, flow rate data during off-peak hours, and discrete pressure sensor data within a target area. The first light intensity attenuation data is then inverted and reconstructed to obtain a laser concentration field. Flow rate data is analyzed to identify flow anomalies, and discrete pressure sensor data is analyzed to identify pressure topological low points. Laser evidence is then determined based on the laser scan concentration value in the laser concentration field. Flow evidence is determined based on the gas meter flow rate in the spatiotemporally aligned flow anomaly data. Pressure evidence is determined based on the spatiotemporally aligned pressure topological low point data. When the target area does not conform to a preset complex terrain, the local leak confidence level of the target area is determined based on the aforementioned evidence. When the target area conforms to the preset complex terrain, a second light intensity attenuation data and flight attitude data of the target area are also collected by a UAV extension unit based on an obstacle avoidance flight path set. A UAV concentration field is generated based on the collected second light intensity attenuation data and flight attitude data. UAV leak evidence is determined based on the UAV concentration field. The UAV leak evidence and the local leak confidence level are then weighted and averaged to obtain a global leak confidence level. When the confidence level exceeds a preset threshold, an alarm notification and the leak location are output. This application reduces the blind spot in gas detection and improves the accuracy and reliability of gas leak detection results.

[0057] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0058] Figure 1 A schematic flowchart of the gas leak detection method provided in this application is shown below. Figure 1 As shown, the method includes:

[0059] S101. Acquire the first light intensity attenuation data of the target area, the flow data during off-peak hours in the target area, and the discrete pressure sensor data in the target area.

[0060] Optionally, if the target area (e.g., a station, residential area, or small park) does not conform to the preset complex scenario, Figure 2 Schematic diagram of the gas leak detection system provided in this application Figure 1 ,like Figure 2 As shown, the gas leak detection system for the aforementioned target area includes a laser scanning unit, a gas meter unit, a pressure sensor unit, and a data fusion unit.

[0061] Optionally, when the target area (e.g., mountainous areas, rivers, industrial parks) meets the preset complex scenario, Figure 3Schematic diagram of the gas leak detection system provided in this application Figure 2 ,like Figure 3 As shown, the gas leak detection system for the aforementioned target area includes a laser scanning unit, a gas meter unit, a pressure sensor unit, a drone extension unit, and a data fusion unit.

[0062] In one possible embodiment, based on tunable semiconductor laser absorption spectroscopy, the absorption intensity of methane to a specified wavelength of laser light is measured using a laser scanning unit to obtain first light intensity attenuation data. For example, methane molecules have a strong absorption peak in the near-infrared region (e.g., 1653.7 nm), based on the Lambert-Beer law, i.e. It was determined that after the laser passes through methane gas, the initial intensity attenuation data is related to the methane concentration and optical path length. Determine the first light intensity attenuation data. Among them, The emitted light intensity (W). To receive light intensity (W) For methane at wavelength Absorption coefficient at (ppm⁻¹·m⁻¹) This refers to the methane concentration (ppm). is the optical path length (m).

[0063] Optionally, a gimbal in the laser scanning unit rotates horizontally (0° to 360°) and vertically (-30° to +90°) to perform spatial scanning of the target area. This gimbal is equipped with a laser transmitting / receiving module, and the scanning path during spatial scanning employs a spiral coverage strategy to ensure no blind spots within a fixed radius (e.g., 500 meters). The spiral coverage strategy includes a horizontal step angle, a vertical step angle, and a scanning cycle. The formula for calculating the horizontal step angle is... , The diameter of the laser beam (e.g., 0.1m). Let the scan radius be (e.g., 500m). The formula for calculating the vertical step angle is: , The scanning height is (e.g., 10m). The formula for calculating the scanning cycle is: , Used to indicate horizontal rotational speed. , is used to indicate vertical rotational speed.

[0064] In one possible embodiment, a gas meter unit is used to collect flow data during off-peak hours within the target area.

[0065] In one possible embodiment, a pressure sensor unit is used to collect discrete pressure sensor data from multiple pressure sensors within the target area. Since the pressure drops near the leak point, pressure topology low point data is determined from the discrete pressure sensor data.

[0066] S102. The laser concentration field is obtained by inverting and reconstructing the first light intensity attenuation data; abnormal flow data in the flow data is determined by the anomaly detection model; and the pressure topology low point data is determined based on the discrete pressure sensor data.

[0067] In one possible embodiment, a laser scanning unit scans and acquires multi-path optical data within the target area. The concentration integral value of ) (i.e., Then, the data fusion unit calculates the first light intensity attenuation data based on the concentration integral value. This first light intensity attenuation data is then iteratively optimized (e.g., using the SIRT algorithm) to generate a laser concentration field within a fixed radius (e.g., 500 meters). (e.g., a methane concentration heatmap with a resolution of 0.5m × 0.5m). For example, the formula for iterative optimization is: .

[0068] In one possible embodiment, after obtaining the traffic data, an anomaly detection model is used by a data fusion unit to identify traffic anomalies within the traffic data. The anomaly detection model includes a constant current model and a microflow model, with the constant current model being the most suitable. Off-peak hours From time to time Hourly traffic The flow rate was determined to be in a constant current abnormal state, whereby... For example, the off-peak period is 0:00-6:00, and the peak period is 18:00-20:00. This is based on a microflow model. The average flow rate within period T during off-peak hours Below the minimum reference gas flow rate The flow rate is determined to be a small flow anomaly. If a constant flow or small flow anomaly is detected by the anomaly detection model, then the flow rate is integrated. Estimate the leakage amount, This is the abnormal start time. This is the end time of the anomaly. Anomaly flow data is determined based on the amount of leakage (e.g., continuous flow even when no gas is being used, or flow rate below a preset normal flow rate threshold).

[0069] In one possible embodiment, after obtaining discrete pressure sensor data at multiple locations, kriging interpolation is employed. Discrete pressure sensor data Interpolation is a continuous pressure field , interpolation weights and Minimize the estimated variance , It is a semi-variogram. Then, based on the continuous pressure field, the gradient of the continuous pressure field is calculated. and the gradient magnitude Less than the threshold And pressure value Below the average pressure in the target area Discrete pressure sensor data within the region are identified as pressure topological low point data, i.e. , This represents the standard deviation of the pressure field, used to reflect the normal fluctuation range.

[0070] S103. The laser concentration field, abnormal flow data, and pressure topology low point data are fused to obtain the leakage confidence level; when the leakage confidence level exceeds the preset threshold, an alarm notification and the location of the leakage point are output.

[0071] The gas leak detection method provided in this application fuses laser concentration field, abnormal flow data, and pressure topology low point data to obtain the leak confidence level of the target area. When the leak confidence level exceeds a preset threshold, an alarm is triggered and the location of the leak point is output, thereby expanding the gas detection range and coverage, reducing detection blind spots, and improving the accuracy of gas leak detection results.

[0072] Optionally, the laser concentration field, flow anomaly data, and pressure topology low point data are spatiotemporally aligned to obtain spatiotemporally aligned laser concentration field, flow anomaly data, and pressure topology low point data; laser evidence is determined based on the laser scan concentration value in the spatiotemporally aligned laser concentration field; flow evidence is determined based on the gas meter flow rate in the spatiotemporally aligned flow anomaly data; pressure evidence is determined based on the spatiotemporally aligned pressure topology low point data; when the target area does not conform to the preset complex terrain, evidence synthesis processing is performed based on laser evidence, flow evidence, and pressure evidence to determine the local leakage confidence level of the target area.

[0073] Optionally, after determining the local leakage confidence level, the location of the leak point corresponding to the local leakage confidence level is obtained by performing a weighted average of the laser scanning point location corresponding to the laser concentration field, the gas meter location corresponding to the abnormal flow data, and the pressure sensor location corresponding to the low pressure topology data.

[0074] In one possible embodiment, a data fusion unit adds timestamps to the laser concentration field with a spatial resolution of 0.5m, the abnormal flow data located to a specific user, and the pressure topology low point data with a spatial resolution of 5m to ensure data temporal consistency. Then, the laser scanning point position corresponding to the laser concentration field, the gas meter position corresponding to the specific user corresponding to the abnormal flow data, and the pressure sensor position corresponding to the pressure topology low point data are mapped to a grid coordinate system of a preset size (e.g., the WGS84 grid coordinate system with a grid size of 0.5m × 0.5m) to ensure data spatial consistency and obtain the spatiotemporally aligned laser concentration field, abnormal flow data, and pressure topology low point data.

[0075] In one possible embodiment, the data fusion unit, for any given location (x, y), determines the concentration of laser evidence. Exceeding the preset concentration threshold (e.g., 5000ppm), then determine the weight corresponding to the laser evidence: , If the flow evidence indicates an anomaly in constant or minute flow at that location, then determine the weight corresponding to the flow evidence: , If the pressure evidence indicates that the location is a pressure topological low point, then determine the weight corresponding to the pressure evidence: , .

[0076] In one possible embodiment, when the target area (e.g., a facility, residential area, or small park) does not conform to a preset complex scenario, based on Figure 2 The gas leak detection system shown defines an identification framework Θ = {normal, abnormal}, and determines the basic probability allocation for laser evidence A, flow evidence B, and pressure evidence C. , , For example, their values ​​are shown in Table 1 below:

[0077] Table 1

[0078]

[0079] Based on the above information, three sources of evidence (laser evidence A, flow evidence B, and pressure evidence C) are synthesized using Dempster's combination rules to calculate the local leakage confidence level in the target area. The specific process is as follows:

[0080] (1) Combine laser evidence A and flow evidence B using Dempster's combination rule, i.e., calculate the conflict coefficient based on Dempster's combination rule. ,in, For the focal element of laser evidence A, Let fjörn be the focal element of traffic evidence B, and fjörn's and The intersection is empty, therefore... Substitute the data to get .

[0081] For the target focal element J ( or ),based on calculate The formula is as follows:

[0082] .

[0083] Among them, based on the target focal element J Because it satisfies The combination is Therefore, we get:

[0084] .

[0085] Substituting the data into the above formula, we get 0.8 × 0.7 = 0.56, thus obtaining:

[0086] .

[0087] Based on the target focal element J Because it satisfies The combination is Therefore, we get:

[0088] .

[0089] Substituting the data into the above formula yields: Therefore, we get:

[0090] .

[0091] Since 0.9032 + 0.0968 = 1, the result is verified and meets the basic probability allocation requirements.

[0092] (2) Combined with the pressure evidence C, i.e., based on the formula for calculating the conflict coefficient in step (1), the conflict coefficient calculation formula is obtained:

[0093] .

[0094] in, , , The focal elements are respectively the laser evidence A, flow evidence B, and pressure evidence C, and the focal elements are... and Since the intersection is empty, we get:

[0095] .

[0096] Regarding the above Substitute the data as .

[0097] For the target focal element J ( or ),based on Synthesized The formula is as follows:

[0098] .

[0099] Among them, based on the target focal element J Since the intersection is satisfied The combination is ,therefore:

[0100] .

[0101] Substituting the data into the above formula yields: .

[0102] Then determine .

[0103] Based on the target focal element J Since the intersection is satisfied The combination is ,therefore:

[0104] .

[0105] Substituting the data into the above formula yields: .

[0106] Then determine .

[0107] because Therefore, the result is verified and meets the basic probability allocation requirements.

[0108] (3) The data in Table 2 below are obtained:

[0109] Table 2

[0110]

[0111] In one possible embodiment, if the local leakage confidence level calculated by the data fusion unit exceeds a preset threshold (e.g., 0.9), an alarm notification is output based on the following formula:

[0112] Calculate the location of the leak corresponding to the local leak confidence level. More specifically, by determining the laser scanning point position corresponding to the laser concentration field. Location of gas meter corresponding to abnormal flow data and the pressure sensor location corresponding to the low point data of the pressure topology. A weighted average calculation is performed to obtain the location of the leak corresponding to the local leak confidence level. .in, ,For example, 0.8 0.15 It is 0.05.

[0113] This embodiment ensures the spatiotemporal consistency of multi-source data under non-complex terrain by performing spatiotemporal alignment on multi-dimensional data, avoiding false alarms and response delays caused by data asynchrony in traditional technologies. Furthermore, it synthesizes local leakage confidence based on laser concentration field, abnormal flow data, and pressure topology low point data, reducing detection blind spots and improving the accuracy and reliability of local leakage confidence.

[0114] In this embodiment, when the confidence level of a local leak exceeds a preset threshold, the coordinates of the local leak point are determined by a weighted average of the laser scanning point, the gas meter position, and the pressure sensor position, thereby improving the accuracy and reliability of leak location.

[0115] Optionally, when the target area meets the preset complex terrain, the drone leakage evidence is determined based on the drone concentration field; and the global leakage confidence level of the target area is generated based on the drone leakage evidence, laser evidence, flow evidence and pressure evidence.

[0116] Optionally, the UAV concentration field is obtained by inverting and reconstructing the second light intensity attenuation data of the target area after the UAV extension unit collects the second light intensity attenuation data of the target area; wherein, when the UAV extension unit collects the second light intensity attenuation data of the target area, it includes: determining the scanning width of a single flight path based on the terrain constraint information of the target area, the preset flight altitude, and the preset laser scanning field of view; generating a set of obstacle avoidance flight paths that meet the preset coverage rate of the target area based on the scanning width of the single flight path; and collecting the second light intensity attenuation data based on the set of obstacle avoidance flight paths.

[0117] Optionally, when the target area (e.g., mountainous areas, rivers, industrial parks) meets the preset complex scenario, based on Figure 3 The gas leak detection system shown controls the drone's flight via a drone extension unit, adjusting the drone's altitude accordingly. and laser scanning field of view (Horizontal direction) Calculate the scan width of a single line. Therefore, the set of obstacle avoidance routes is determined based on the obtained scan width. This ensures that, based on the obstacle avoidance route set covering the aforementioned target area, the coverage rate of the target area meets the preset coverage rate, and the spatial intersection of the obstacle avoidance route set and the obstacle set in the target area is an empty set.

[0118] Optionally, after obtaining the set of obstacle avoidance routes, the UAV extension unit represents each route as a sequence of points, i.e. ,in Use waypoints and establish fitness functions. The fitness function is used to perform fitness analysis on each route, and the optimal path is obtained, which minimizes the path length, maximizes the coverage of the target area, and maximizes the obstacle avoidance score. .

[0119] Optionally, the obstacle avoidance routes generated in the above embodiments can be updated and iterated through operations such as selection (roulette wheel), crossover (single point exchange), and mutation (random adjustment of waypoints).

[0120] Optionally, the data fusion unit includes a drone subsystem deployed on the drone extension unit side, a local subsystem deployed on the ground at the locations of the laser scanning unit, pressure sensor unit, and gas meter unit, and a cloud fusion platform deployed in the cloud.

[0121] In one possible embodiment, after obtaining the optimal path, the UAV extension unit controls the UAV's flight based on the obstacle avoidance route corresponding to the optimal path, enabling the UAV to scan the target area in real time during flight and obtain the multi-optical-path integrated concentration. The data includes the drone's position and attitude (e.g., drone altitude, scan angle, GPS, INS (Inertial Navigation System)) and meteorological data. Optical path length , For the drone's altitude, The scanning angle.

[0122] In one possible embodiment, the multi-optical-path integrated concentration is achieved via a drone subsystem (e.g., NVIDIA Jetson AGX). The UAV's position and attitude data (e.g., UAV altitude and scanning angle) (GPS / INS) and meteorological data are used to modify the Lambert-Beer law in the above embodiments as follows: , The atmospheric attenuation coefficient (e.g., fog, rain) affects the laser beam. Based on the modified Lambert-Beer law, the second intensity attenuation data is determined. The concentration field of the UAV is generated by iteratively optimizing the solution based on this second intensity attenuation data. ,Right now:

[0123] .

[0124] in, For the number of iterations, For the first The drone's altitude during the second scan. For the first The drone's angle during the second scan. Evidence of drone leakage was determined based on the drone's concentration field using the drone subsystem. (For example, if the concentration gradient exceeds a preset concentration gradient threshold or the concentration change rate exceeds a preset concentration change rate threshold), and upload the drone evidence to the cloud for global fusion processing through the cloud fusion platform.

[0125] In one possible embodiment, after the local subsystem obtains the first light intensity attenuation data, the flow rate data during off-peak hours, and the discrete pressure sensor data for the target area, it determines laser evidence, flow rate evidence, and pressure evidence based on the first light intensity attenuation data, the flow rate data during off-peak hours, and the discrete pressure sensor data for the target area, and generates local leakage evidence based on the laser evidence, flow rate evidence, and pressure evidence. And upload it to the cloud-based fusion platform.

[0126] In one possible embodiment, drone leakage evidence and local leakage evidence are synthesized using a cloud-based fusion platform based on Dempster rules to obtain the global leakage confidence score for the target area, where the global leakage confidence score = .

[0127] This embodiment enables UAVs to collect data by activating the UAV extension unit in complex terrain, thereby generating a UAV concentration field. Based on the UAV concentration field, data fusion is performed with laser evidence, pressure evidence, and flow evidence to generate a global confidence score. This achieves air-ground collaboration, effectively expands the detection range, and improves the accuracy and reliability of the detection results.

[0128] This embodiment enables UAV data collection when the target area is a pre-defined complex terrain. Based on the flight altitude and field of view, the scanning width is calculated, and a set of obstacle avoidance routes is generated to ensure that the UAV scanning area covers the aforementioned pre-defined complex terrain, reduce detection blind spots, avoid obstacles in the target area, and improve the accuracy and reliability of detection results.

[0129] Optionally, when the global leakage confidence exceeds a preset threshold, the leakage point location corresponding to the global leakage confidence in the target area is obtained by determining the spatial intersection of the leakage point location indicated by the drone leakage evidence and the leakage point locations indicated by the laser evidence, flow evidence, and pressure evidence.

[0130] In one possible embodiment, if the global leak confidence level calculated by the data fusion unit exceeds a preset threshold (e.g., 0.95), an alarm notification is output, and the leak point location corresponding to the local leak confidence level is obtained by weighted averaging the leak evidence from the drone, the laser scanning point location corresponding to the laser concentration field, the gas meter location corresponding to the abnormal flow data, and the pressure sensor location corresponding to the low pressure topology data. .

[0131] This embodiment locates the global leak point by combining and complementing air-to-ground data through the spatial intersection of UAV leak evidence with laser evidence, flow evidence, and pressure evidence. This eliminates the positioning bias of a single data source, enables precise location of the leak point in complex terrain, and improves the accuracy and reliability of the detection results.

[0132] Figure 4 This is a schematic diagram of the gas leak detection device provided in this application, as shown below. Figure 4 As shown, the gas leak detection device 40 provided in this embodiment includes:

[0133] The acquisition module 401 is used to acquire the first light intensity attenuation data of the target area, the flow data during off-peak hours in the target area, and the discrete pressure sensor data in the target area.

[0134] Processing module 402 is used to obtain the laser concentration field by inverting and reconstructing the first light intensity attenuation data; to determine the abnormal flow data in the flow data by using an anomaly detection model; and to determine the pressure topological low point data based on discrete pressure sensor data.

[0135] The processing module 402 is also used to fuse the laser concentration field, abnormal flow data and pressure topology low point data to obtain the leakage confidence level; when the leakage confidence level exceeds the preset threshold, it outputs an alarm notification and the location of the leakage point.

[0136] Optionally, the processing module 402 is also used to perform spatiotemporal alignment processing on the laser concentration field, flow anomaly data and pressure topology low point data to obtain spatiotemporally aligned laser concentration field, flow anomaly data and pressure topology low point data;

[0137] Laser evidence was determined based on the laser scan concentration value in the spatiotemporally aligned laser concentration field; flow evidence was determined based on the gas meter flow rate in the spatiotemporally aligned flow anomaly data; and pressure evidence was determined based on the spatiotemporally aligned pressure topology low point data.

[0138] When the target area does not conform to the preset complex terrain, evidence synthesis processing is performed based on laser evidence, flow evidence, and pressure evidence to determine the local leakage confidence level of the target area.

[0139] Optionally, the processing module 402 is further configured to, after determining the local leakage confidence level, perform weighted averaging on the laser scanning point location corresponding to the laser concentration field, the gas meter location corresponding to the abnormal flow data, and the pressure sensor location corresponding to the low pressure topology data to obtain the leakage point location corresponding to the local leakage confidence level.

[0140] Optionally, the processing module 402 is also used to determine evidence of drone leakage based on the drone concentration field when the target area meets the preset complex terrain.

[0141] Generate a global leakage confidence level for the target area based on drone leakage evidence, laser evidence, flow evidence, and pressure evidence.

[0142] Optionally, the processing module 402 is further configured to, when the global leakage confidence exceeds a preset threshold, determine the location of the leak point indicated by the UAV leakage evidence and the location of the leak point indicated by the laser evidence, flow evidence, and pressure evidence, and obtain the location of the leak point corresponding to the global leakage confidence in the target area.

[0143] Optionally, the concentration field of the UAV is obtained by inverting and reconstructing the second light intensity attenuation data of the target area after the UAV extended unit collects the second light intensity attenuation data of the target area; wherein,

[0144] The processing module 402 is also used to determine the scanning width of a single flight path based on the terrain constraint information of the target area, the preset flight altitude and the preset laser scanning field of view.

[0145] A set of obstacle avoidance routes is generated based on the scanning width of a single route to ensure that the coverage of the target area meets the preset coverage rate; second light intensity attenuation data is collected based on the set of obstacle avoidance routes.

[0146] The gas leak detection device provided in this embodiment can perform the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0147] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0148] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0149] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0150] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0151] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0152] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0153] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0154] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0155] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0156] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0157] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0158] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0159] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0160] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0161] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0162] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for detecting gas leaks, characterized in that, include: Acquire the first light intensity attenuation data of the target area, the flow rate data during off-peak hours in the target area, and the discrete pressure sensor data in the target area; The laser concentration field is obtained by inverting and reconstructing the first light intensity attenuation data; abnormal flow data in the flow data is determined by an anomaly detection model. Determine the pressure topology low point data based on the discrete pressure sensor data; The laser concentration field, the abnormal flow data, and the pressure topology low point data are fused to obtain the leakage confidence level; when the leakage confidence level exceeds a preset threshold, an alarm notification and the location of the leakage point are output. Specifically, the leakage confidence level is obtained by fusing the laser concentration field, the abnormal flow data, and the pressure topological low point data, including: The laser concentration field, the flow anomaly data, and the pressure topology low point data are spatiotemporally aligned to obtain the spatiotemporally aligned laser concentration field, flow anomaly data, and pressure topology low point data. Laser evidence was determined based on the laser scan concentration value in the spatiotemporally aligned laser concentration field; flow evidence was determined based on the gas meter flow rate in the spatiotemporally aligned flow anomaly data; and pressure evidence was determined based on the spatiotemporally aligned pressure topology low point data. When the target area does not conform to the preset complex terrain, evidence synthesis processing is performed based on the laser evidence, flow evidence, and pressure evidence to determine the local leakage confidence level of the target area.

2. The method according to claim 1, characterized in that, Also includes: After determining the local leakage confidence level, the location of the leak point corresponding to the local leakage confidence level is obtained by performing a weighted average of the laser scanning point location corresponding to the laser concentration field, the gas meter location corresponding to the abnormal flow data, and the pressure sensor location corresponding to the low pressure topology data.

3. The method according to claim 1, characterized in that, Also includes: When the target area meets the preset complex terrain, evidence of drone leakage is determined based on the drone concentration field. A global leakage confidence level for the target area is generated based on the drone leakage evidence, the laser evidence, the flow rate evidence, and the pressure evidence.

4. The method according to claim 3, characterized in that, Also includes: When the global leakage confidence exceeds a preset threshold, the leakage point location corresponding to the global leakage confidence of the target area is obtained by determining the spatial intersection of the leakage point location indicated by the UAV leakage evidence and the leakage point locations indicated by the laser evidence, flow evidence, and pressure evidence.

5. The method according to claim 3, characterized in that, The UAV concentration field is obtained by inverting and reconstructing the second light intensity attenuation data of the target area after the UAV's extended unit collects the second light intensity attenuation data of the target area; wherein... When the UAV extension unit collects the second light intensity attenuation data of the target area, it includes: Based on the terrain constraints of the target area, the preset flight altitude, and the preset laser scanning field of view, the scanning width of a single flight path is determined; Based on the scanning width of the single route, a set of obstacle avoidance routes is generated to ensure that the coverage of the target area meets the preset coverage rate; the second light intensity attenuation data is collected based on the set of obstacle avoidance routes.

6. A gas leak detection device, characterized in that, include: The acquisition module is used to acquire the first light intensity attenuation data of the target area, the flow data during off-peak hours in the target area, and the discrete pressure sensor data in the target area. The processing module is used to obtain the laser concentration field by inverting and reconstructing the first light intensity attenuation data; to determine the abnormal flow data in the flow data by using an anomaly detection model; and to determine the pressure topological low point data based on the discrete pressure sensor data. The processing module is also used to fuse the laser concentration field, the abnormal flow data, and the pressure topology low point data to obtain the leakage confidence level; and to output an alarm notification and the location of the leakage point when the leakage confidence level exceeds a preset threshold. Specifically, when the processing module fuses the laser concentration field, the abnormal flow data, and the pressure topological low point data to obtain the leakage confidence level, it is used for: The laser concentration field, the flow anomaly data, and the pressure topology low point data are spatiotemporally aligned to obtain the spatiotemporally aligned laser concentration field, flow anomaly data, and pressure topology low point data. Laser evidence was determined based on the laser scan concentration value in the spatiotemporally aligned laser concentration field; flow evidence was determined based on the gas meter flow rate in the spatiotemporally aligned flow anomaly data; and pressure evidence was determined based on the spatiotemporally aligned pressure topology low point data. When the target area does not conform to the preset complex terrain, evidence synthesis processing is performed based on the laser evidence, flow evidence, and pressure evidence to determine the local leakage confidence level of the target area.

7. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-5.

Images