A gas detection system based on an ultrasonic detection device and a drone

Abstract

The application discloses a kind of gas detection systems based on ultrasonic detection device and unmanned plane, it is related to unmanned plane gas detection field, the steps of the method include: the distance of unmanned plane and ground, gas pipeline depth, the flight speed of unmanned plane, standard sound wave propagation speed, spectrum length, sound wave propagation time, leakage area image, pipeline node are collected by data acquisition module;Seismic road surface damage threat data and pipeline leakage threat data are combined to obtain gas leakage threat value;According to gas leakage threat value and personnel risk, assess gas leakage risk level and issue an alarm;Path decision instruction is issued according to risk level.The application improves gas detection efficiency and reduces labor costs while ensuring personnel safety in the event of an earthquake.

Description

Technical Field

[0001] This invention relates to the field of gas detection in unmanned aerial vehicles (UAVs), specifically a gas detection system based on an ultrasonic detection device and an UAV. Background Technology

[0002] Gas leaks are a common but dangerous problem that can lead to fires, explosions, personal injury, and environmental pollution. Therefore, early detection and handling of gas leaks are crucial. Traditional gas leak detection methods typically rely on manual inspections or fixed sensor networks. The advent of ultrasonic sensors has provided a new approach to gas detection. Currently, ultrasonic sensors have been successfully applied in many fields, including distance measurement, object detection, and material inspection, demonstrating great potential for detecting gas leaks and fluid flow.

[0003] For example, patent CN112197176B discloses a gas leak detection system, which includes an ultrasonic flow meter, a solenoid valve and an alarm subsystem. The ultrasonic flow meter detects the flow velocity data in the gas pipeline, and then determines whether there is a leak and the level of gas leak based on the flow velocity data.

[0004] However, the above methods have certain limitations, including limited coverage, long response time, and inability to cover complex or dangerous terrain or facilities. Therefore, a gas detection method that considers real-time response and safety is needed. The rapid development of UAV technology has provided new possibilities for gas detection. UAVs can carry various sensors to quickly and accurately monitor large areas, especially hard-to-reach places. Therefore, this invention proposes a gas detection system based on an ultrasonic detection device and a UAV. Summary of the Invention

[0005] The purpose of this invention is to provide a gas detection system based on an ultrasonic detection device and a drone, so as to solve the problems in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a gas detection system based on an ultrasonic detection device and a drone, comprising:

[0007] The data acquisition module is used to collect data on the distance between the UAV and the ground, the depth of the gas pipeline, the UAV's flight speed, the standard speed of sound, the spectral length, the sound wave propagation time, the image of the leak area, and the number of pipeline sections during the UAV's flight. The threat calculation module is used to run a gas leak threat value calculation strategy, calculate earthquake road damage threat data and pipeline leak threat data, and combine the earthquake road damage threat data and pipeline leak threat data to calculate the gas leak threat value S1. The personnel identification module is used to determine whether there is a personnel risk in the leak area based on the leak area image. The hazard classification module is used to assess the gas leak hazard level based on the gas leak threat value S1 and the personnel risk, and also includes a voice broadcasting device for issuing alarms to residents in the hazard area. The remedial route decision module is used to record repair and rescue routes and issue route decision instructions based on the risk level.

[0008] A further improvement of the present invention is that the threat calculation module includes an environmental interference unit, a gas leak threat value acquisition unit, and a damage location unit. The environmental interference unit is used to calculate the drone's offset distance through wind direction and wind speed data. The gas leak threat value acquisition unit includes a baseline establishment subunit, a leak event feature extraction subunit, a comprehensive threat value calculation subunit, and an anomaly detection subunit.

[0009] A further improvement of this invention is that the baseline establishment subunit includes establishing a dataset of normal gas pipeline transportation environment information as the baseline feature values ​​of the detection system. These baseline feature values ​​include, under safe conditions, acquiring the distance Dis1 between the drone and the ground when the drone hovers above the pipeline using a laser sensor, recording the spectral length Dspe1 and the standard sound wave propagation speed v1 during this period, and obtaining the ratio Dis1 / Dspe1 of the spectral length to the distance under the standard sound wave propagation speed v1. The leakage event feature extraction subunit includes, when a change in the spectral band is detected, extracting the first half of the spectral band, recording the sound wave transmitting node nd1, the sound wave receiving node nd2, and the spectral change node nd3 on the spectral band, and recording the spectral length Dspe2 from node nd1 to node nd3, obtaining the propagation time TIME from node nd1 to node nd2, the distance Dis2 between the drone and the ground during drone flight, and the drone's flight speed v2, thus obtaining the gas leakage range. Therefore, the average propagation speed of sound waves in the gas can be obtained. The gas leakage concentration Con can be represented by the difference between the average propagation speed of sound in the gas, v3, and the standard propagation speed of sound, v1, where Con = |v3 - v1|. The pipeline leakage threat value Gas = Con · Dran can then be obtained.

[0010] A further improvement of this invention is that the comprehensive threat value calculation subunit includes combined pipeline leakage threat data and seismic pavement damage threat data. The seismic pavement damage threat data is obtained by calculating the seismic pavement damage threat value Equake. The number of pipeline sections num is obtained in advance, and the length dataset (L1, L2, ..., L) of each pipeline section is recorded. num ), deep datasets (H1, H2, ..., H num Diameter dataset (D1, D2, ..., D) num ), where L i H is the length of the i-th pipe section. i Let D be the depth of the i-th section of the pipe. i Given the diameter of the i-th pipe section, the pipe stress value is obtained. Where, λ j Let represent the average damage rate of the pipeline under a magnitude j earthquake obtained through an empirical formula. Assuming that the number of gas pipeline failures under seismic action follows a Poisson distribution, then the earthquake-induced road surface damage threat value is... gra represents the total magnitude of the earthquake, used to calculate the gas leak threat level. in The weights representing the threat value of pipeline leaks The weights representing the threat value of earthquake-induced road surface damage.

[0011] A further improvement of this invention is that the anomaly detection subunit is used to compare the gas leak threat value with the gas leak threat value threshold to determine the risk level.

[0012] A further improvement of the present invention is that the damage location unit uses a positioning system carried by the UAV to locate the risk area where there is a gas leak, and obtains the location information of the gas leak area.

[0013] A further improvement of this invention is that the personnel identification module includes setting a resident flow value S2, collecting resident feature datasets and building feature datasets, collecting image information of the leaked area, extracting features from the leaked area image information, and classifying it. Specifically, this includes setting a warning feature binary classifier, and collecting a resident feature dataset (x1, x2, ..., x...) through historical image data. m ) and building feature dataset (y1, y2, ..., y n), m represents the number of resident feature datasets, n represents the number of building feature datasets. The feature datasets are trained using logistic regression, and the training results are input into the warning feature binary classifier. The image information of the leaked area is used to extract features through the warning feature binary classifier, dividing the leaked area into mountainous and plain areas. When the leaked area is a plain, resident feature data is extracted; when the leaked area is a mountainous area, building feature data is extracted. If either resident feature data or building feature data exists, S2 = 1 is output; otherwise, S2 = 0 is output.

[0014] A further improvement of this invention is that the hazard classification module includes setting gas leak risk thresholds Trisk1, Trisk2, Trisk3, and Trisk4, and setting risk levels including minor leak risk, low leak risk, medium leak risk, high leak risk, and emergency leak risk; the formula for judging minor leak risk is as follows: The formula for judging low leakage risk is as follows: The leakage risk assessment formula is F3 = {(Trisk2 < S1 ≤ Trisk3) ∩ S2 = 0}; the high leakage risk assessment formula is F4 = {(Trisk3 < S1 ≤ Trisk4) ∩ S2 = 0}; the emergency leakage risk assessment formula is... If formula F4 or F5 is true, an alarm will be issued to residents in the danger zone via a voice broadcast device.

[0015] A further improvement of this invention is that the remedial path decision module records the passable area during the flight of the UAV to obtain a remedial path planning network, acquires DEM imagery of the remedial path planning network, and obtains a dataset of all remedial paths from the starting point to the remedial point. in Let represent the elevation of the q-th elevation point on the p-th path; the risk level and location information of the gas leak area obtained by the threat calculation module are mapped as leak nodes in the remediation path planning network. These leak nodes follow a rule of increasing leak risk, including level 1, level 2, level 3, level 4, and level 5 leak nodes; when the risk level is determined to be a minor leak risk, a decision is made on whether to proceed with repairs based on the actual situation; when the risk level is determined to be low or medium leak risk, the selection of the remediation path avoids all leak nodes and satisfies... in This represents the elevation of the point with the highest elevation on the p-th path. Let represent the elevation of the minimum elevation point of the p-th path; when the risk level is determined to be high leakage risk, the selection of the remedial path avoids level 3, level 4, and level 5 leakage nodes and satisfies . When the risk level is determined to be an emergency leakage risk, the selection of the remediation path follows the shortest path principle.

[0016] Compared with the prior art, the beneficial effects of the present invention are:

[0017] 1. This invention first uses a combination of ultrasonic devices and drones to acquire data such as the distance to the ground, the depth of the gas pipeline, and the flight speed of the drone. It then uses these data, along with the damage threat value during an earthquake, to assess the gas leak hazard level. This approach considers earthquake risks and ensures the safety of workers while improving gas detection efficiency and reducing labor costs.

[0018] 2. The personnel identification module uses two different terrain feature selection methods to determine whether there is a personnel risk in the leak area. Based on the risk level, it issues an alarm for leak areas with personnel risk. The personnel identification module can promptly issue alarms to residents in dangerous areas. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the workflow of a gas detection system based on an ultrasonic detection device and a drone according to the present invention.

[0020] Figure 2 This is a framework diagram of a gas detection system based on an ultrasonic detection device and a drone according to the present invention. Detailed Implementation

[0021] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0022] Example 1

[0023] Figure 1 and Figure 2 The present invention discloses a gas detection system based on an ultrasonic detection device and a drone, and presents a flowchart and a system framework diagram, including:

[0024] The data acquisition module is used to collect data on the distance between the UAV and the ground, the depth of the gas pipeline, the UAV's flight speed, the standard speed of sound, the spectral length, the sound wave propagation time, the image of the leak area, and the number of pipeline sections during the UAV's flight. The threat calculation module is used to run a gas leak threat value calculation strategy, calculate earthquake road damage threat data and pipeline leak threat data, and combine the earthquake road damage threat data and pipeline leak threat data to calculate the gas leak threat value S1. The personnel identification module is used to determine whether there is a personnel risk in the leak area based on the leak area image. The hazard classification module is used to assess the gas leak hazard level based on the gas leak threat value S1 and the personnel risk, and also includes a voice broadcasting device for issuing alarms to residents in the hazard area. The remedial route decision module is used to record repair and rescue routes and issue route decision instructions based on the risk level.

[0025] The threat calculation module includes an environmental interference unit, a gas leak threat value acquisition unit, and a damage location unit. The environmental interference unit is used to calculate the drone's offset distance using wind direction and wind speed data. The gas leak threat value acquisition unit includes a baseline establishment subunit, a leak event feature extraction subunit, a comprehensive threat value calculation subunit, and an anomaly detection subunit.

[0026] The baseline establishment subunit includes establishing a dataset of normal gas pipeline transportation environment information as the baseline feature values ​​for the detection system. These baseline feature values ​​include, under safe conditions, acquiring the distance Dis1 between the drone and the ground when the drone hovers over the pipeline using a laser sensor, recording the spectral length Dspe1 and the standard sound wave propagation speed v1 during this period. Since the frequency of sound waves does not change under the same conditions, the ratio of spectral length to distance Dis1 / Dspe1 under the standard sound wave propagation speed v1 can be obtained. The leak event feature extraction subunit includes, when a frequency is detected... When the spectral band changes, the first half of the spectral band is extracted. The sound wave transmitting node nd1, sound wave receiving node nd2, and spectral change node nd3 are recorded on this spectral band. The spectral length Dspe2 from node nd1 to node nd3 is also recorded. The propagation time TIME from node nd1 to node nd2, the distance between the drone and the ground Dis2 during the drone's flight, and the drone's flight speed v2 are obtained. The propagation distance of the sound wave in the air is then (Dis1 / Dspe1)Dspe2. Since the drone also moves during the sound wave transmission, the gas leak range... Therefore, the average propagation speed of sound waves in the gas... The gas leak concentration Con can be represented by the difference between the average propagation speed of sound in the gas, v3, and the standard propagation speed of sound, v1, where Con = |v3 - v1|. The pipeline leak threat value Gas = Con · Dran can then be obtained. The comprehensive threat value calculation subunit includes combining pipeline leak threat data and seismic pavement damage threat data. The seismic pavement damage threat data is obtained by calculating the seismic pavement damage threat value Equake. The number of pipe sections num is pre-determined, and the length dataset (L1, L2, ..., L...) of each pipe section is recorded. num ), deep datasets (H1, H2, ..., H num Diameter dataset (D1, D2, ..., D) num ), where L i H is the length of the i-th pipe section. i Let D be the depth of the i-th section of the pipe. i Given the diameter of the i-th pipe section, the pipe stress value is obtained. Where, λ j Let represent the average damage rate of the pipeline under a magnitude j earthquake obtained through an empirical formula. Assuming that the number of gas pipeline failures under seismic action follows a Poisson distribution, then the earthquake-induced road surface damage threat value is... gra represents the total magnitude of the earthquake, used to calculate the gas leak threat level. in The weights representing the threat value of pipeline leaks The weights representing the threat value of earthquake-induced road surface damage.

[0027] The anomaly detection subunit is used to compare the gas leak threat value with the gas leak threat value threshold to determine the risk level.

[0028] The damage location unit uses a positioning system mounted on a drone to locate the risk area where there is a gas leak, and obtains the location information of the gas leak area.

[0029] Gas leaks are often accompanied by explosions and fires, resulting in personal injuries. Therefore, the personnel identification module includes setting a resident flow value S2, collecting resident feature datasets and building feature datasets, acquiring image information of the leak area, extracting features from the leak area image information, and classifying it. Specifically, this includes setting a warning feature binary classifier, collecting a resident feature dataset (x1, x2, ..., x...) using historical image data. m ) and building feature dataset (y1, y2, ..., y n), m represents the number of resident feature datasets, n represents the number of building feature datasets. The feature datasets are trained using logistic regression, and the training results are input into the warning feature binary classifier. The image information of the leaked area is used to extract features through the warning feature binary classifier, dividing the leaked area into mountainous and plain areas. When the leaked area is a plain, resident feature data is extracted; when the leaked area is a mountainous area, building feature data is extracted. If either resident feature data or building feature data exists, S2 = 1 is output; otherwise, S2 = 0 is output.

[0030] The hazard classification module includes setting gas leak risk thresholds Trisk1, Trisk2, Trisk3, and Trisk4, and defining risk levels as minor leak risk, low leak risk, medium leak risk, high leak risk, and emergency leak risk; the formula for judging minor leak risk is as follows: The formula for judging low leakage risk is as follows: The leakage risk assessment formula is F3 = {(Trisk2 < S1 ≤ Trisk3) ∩ S2 = 0}; the high leakage risk assessment formula is F4 = {(Trisk3 < S1 ≤ Trisk4) ∩ S2 = 0}; the emergency leakage risk assessment formula is... If formula F4 or F5 is true, an alarm will be issued to residents in the danger zone via a voice broadcast device.

[0031] During repair and search and rescue operations, manpower costs and the safety of rescue personnel should be considered. Therefore, the remediation path decision-making module should comprehensively consider the leakage risk level and road conditions. By recording passable areas during drone flight, a remediation path planning network is obtained, and DEM images of the remediation path planning network are acquired to obtain a dataset of all remediation paths from the starting point to the remediation point. in Let represent the elevation of the q-th elevation point on the p-th path. The risk level and location information of the gas leak area obtained by the threat calculation module are mapped as leak nodes in the remediation path planning network. These leak nodes follow a rule of increasing leak risk, including Level 1, Level 2, Level 3, Level 4, and Level 5 leak nodes. When the risk level is determined to be a minor leak risk, a decision is made on whether to proceed with repairs based on the actual situation. When the risk level is determined to be low or medium leak risk, the selection of the remediation path must avoid all leak nodes and meet the requirement of saving manpower. Therefore, the path with the smallest difference between the highest and lowest elevation points among all available paths is selected. in This represents the elevation of the point with the highest elevation on the p-th path. Let represent the elevation of the minimum elevation point of the p-th path; when the risk level is determined to be high leakage risk, the selection of the remedial path avoids level 3, level 4, and level 5 leakage nodes and satisfies . When the risk level is determined to be an emergency leakage risk, the selection of the remediation path follows the shortest path principle.

[0032] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0033] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0034] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0035] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0036] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A gas detection system based on an ultrasonic detection device and a drone, characterized in that: include: The data acquisition module is used to collect data on the distance between the UAV and the ground, the depth of the gas pipeline, the UAV's flight speed, the standard speed of sound, the spectral length, the sound wave propagation time, images of the leak area, and the number of pipeline sections during the UAV's flight. The threat calculation module is used to run a gas leak threat value calculation strategy, calculate earthquake-induced road damage threat data and pipeline leak threat data, and combine these two data to calculate the gas leak threat value. ; The personnel identification module is used to determine whether there is a personnel risk in the leak area based on the image of the leak area; the hazard classification module is used to classify the gas leak threat value. It also includes a personnel risk assessment module to evaluate the hazard level of gas leaks, a voice broadcasting device to issue warnings to residents in dangerous areas, and a remedial route decision module to record repair and rescue routes and issue route decision instructions based on the risk level. The threat calculation module includes a gas leak threat value acquisition unit and a damage location unit. The gas leak threat value acquisition unit includes a baseline establishment subunit, a leak event feature extraction subunit, a comprehensive threat value calculation subunit, and an anomaly detection subunit. The baseline establishment subunit includes establishing a dataset of normal gas pipeline transportation environment information as the baseline feature values ​​for the detection system. These baseline feature values ​​include the distance between the drone and the ground, obtained by a laser sensor when the drone hovers over the pipeline under safe conditions. Record the spectral length during this period. Standard speed of sound propagation The speed of sound propagation at standard sound wave speed is obtained. Under the condition of the ratio of spectral length to distance The leakage event feature extraction subunit includes, when a change in the spectral band is detected, extracting the first half of the spectral band and recording the sound wave transmission node on the spectral band. Sound wave receiving node and spectral change nodes and record nodes To node spectral length Get nodes To node transmission time The distance between the drone and the ground during drone flight The flight speed of drones To obtain the gas leak range From this, the average propagation speed of sound waves in the gas can be obtained. Then the concentration of gas leak It can be determined by the average propagation speed of sound waves in the gas. and standard sound wave propagation speed The difference represents, The threat value of pipeline leakage can be obtained. ; The integrated threat value calculation subunit includes combined pipeline leakage threat data and seismic pavement damage threat data. The seismic pavement damage threat data is used to calculate the seismic pavement damage threat value. The number of pipe sections is obtained in advance. Data set recording the length of each pipe section Deep datasets Diameter dataset ,in, For the first The length of the pipe section, For the first The depth of the pipe section, For the first The pipe stress value is obtained by adjusting the pipe diameter. ,in, Indicates that the pipeline is in The average damage rate obtained through empirical formulas under magnitude 4.5 earthquakes, assuming the number of gas pipeline failures under seismic action follows a Poisson distribution, then the earthquake-induced road damage threat value... , Indicates the total magnitude of the earthquake and calculates the gas leak threat value. ,in The weights representing the threat value of pipeline leaks The weights representing the threat value of earthquake-induced road surface damage.

2. The gas detection system based on an ultrasonic detection device and a drone according to claim 1, characterized in that: The anomaly detection subunit is used to compare the gas leak threat value with the gas leak threat value threshold to determine the risk level.

3. A gas detection system based on an ultrasonic detection device and a drone according to claim 2, characterized in that: The damage location unit uses a positioning system mounted on a drone to locate the risk area where there is a gas leak, and obtains the location information of the gas leak area.

4. A gas detection system based on an ultrasonic detection device and a drone according to claim 3, characterized in that: The personnel identification module includes setting resident mobility values. The process involves collecting resident feature datasets and building feature datasets, acquiring image information of the leaked area, extracting features from the leaked area image information, and classifying them. Specifically, this includes setting up a warning feature binary classifier and collecting resident feature datasets from historical image data. and building feature dataset , Indicates the number of resident feature datasets. The number of building feature datasets is represented. These datasets are trained using logistic regression, and the training results are input into the early warning feature binary classifier. Image information of the leaked area is used for feature extraction via the early warning feature binary classifier, dividing the leaked area into mountainous and plain areas. When the leaked area is a plain, resident feature data is extracted; when the leaked area is a mountainous area, building feature data is extracted. If either resident or building feature data exists, the result is output. If resident characteristic data is not available or building characteristic data is available, then output: .

5. A gas detection system based on an ultrasonic detection device and a drone according to claim 4, characterized in that: The hazard classification module includes setting a gas leak risk threshold. , , , The risk levels are defined as minor leakage risk, low leakage risk, medium leakage risk, high leakage risk, and emergency leakage risk; the formula for judging minor leakage risk is as follows: The low leakage risk assessment formula is as follows: The leakage risk assessment formula is as follows: The high leakage risk assessment formula is as follows: The formula for assessing the emergency leakage risk is as follows: If the judgment formula or If established, an alarm will be issued to residents in the danger zone via a voice broadcast device.

6. A gas detection system based on an ultrasonic detection device and a drone according to claim 5, characterized in that: The remedial path decision module records passable areas during UAV flight to obtain a remedial path planning network, acquires DEM imagery of the remedial path planning network, and obtains a dataset of all remedial paths from the starting point to the remedial point. ,in This represents the elevation of the q-th elevation point along the p-th path; The risk level and location information of the gas leak area obtained by the threat calculation module are mapped as leak nodes in the remediation path planning network. These leak nodes follow a rule of increasing leak risk, including Level 1, Level 2, Level 3, Level 4, and Level 5 leak nodes. When the risk level is determined to be a minor leak risk, a decision is made on whether to proceed with repairs based on the actual situation. When the risk level is determined to be low or medium leak risk, the selected remediation path avoids all leak nodes and meets the following conditions. ,in This represents the elevation of the point with the highest elevation on the p-th path. Let represent the elevation of the minimum elevation point on the p-th path; When the risk level is determined to be high leakage risk, the selection of the remediation path avoids level 3, level 4, and level 5 leakage nodes and satisfies the following conditions: ; When the risk level is determined to be an emergency leakage risk, the selection of the remediation path follows the shortest path principle.

Images