Gas pipeline hidden danger early warning method and system based on unmanned aerial vehicle

Abstract

The invention provides a gas pipeline hidden danger early-warning method and system based on an unmanned aerial vehicle, and relates to the field of gas pipeline hidden danger early-warning, and the method comprises the steps: carrying out the regional grid division of a gas pipeline, and collecting the inspection data of each gas grid region; based on the inspection data and a gas hidden danger threshold value, according to the fitting curve slope, extracting a gas grid region with a gas hidden danger risk in all gas grid regions, and obtaining a hidden danger type initial weight and a first hidden danger value corresponding to the gas hidden danger region; equally dividing the gas hidden danger area according to the length of a pipeline; calculating a second hidden danger value of the gas hidden danger area based on a dynamic time planning algorithm and the segmented fitting curve corresponding to each gas hidden danger sub-area; and obtaining a final hidden danger value of the hidden danger area, and performing hidden danger early warning according to the final hidden danger value and the reference hidden danger grade classification. According to the invention, the timeliness and accuracy of gas pipeline hidden danger detection can be improved.

Description

Technical Field

[0001] The present invention relates to the field of hidden danger warning of gas pipelines, and particularly to a method and system for hidden danger warning of gas pipelines based on unmanned aerial vehicles (UAVs). Background Art

[0002] Traditional gas inspection methods often rely on manual labor. However, manual inspections have disadvantages such as slow inspection speed, low frequency, small coverage area, high labor costs, and being easily affected by weather. In particular, it is difficult to inspect pipelines in harsh areas. Moreover, when there are hidden dangers in the area, there are also certain safety risks for the inspection personnel themselves. Due to the fact that UAV inspections can overcome the influence of terrain and have the characteristics of low cost, flexibility, and convenience, it has gradually become a trend in inspections in recent years.

[0003] Chinese Patent with Publication No. CN110008845B discloses a method and device for detecting hidden danger points of gas pipelines. The method includes: obtaining a remote sensing image of an area to be detected, and identifying hidden danger targets based on the remote sensing image of the area to be detected; importing gas pipeline information of the area to be detected; marking a hidden danger identification area according to the gas pipeline information of the area to be detected; determining whether the hidden danger targets fall into the hidden danger identification area, and determining the hidden danger targets that fall into the hidden danger identification area as hidden danger points; calculating the minimum distance between the hidden danger points and the gas pipelines in the hidden danger identification area; and determining the hidden danger level of the hidden danger points according to the minimum distance between the hidden danger points and the gas pipelines in the hidden danger identification area. However, the above method cannot perform dynamic warning based on changes in various parameters within the inspection area, nor can it quantify hidden dangers. In the face of a complex and changing pipeline operation environment, it is difficult to accurately identify all abnormal states, and ultimately it cannot comprehensively reflect the hidden danger state. Therefore, it is very necessary to provide a method and system for hidden danger warning of gas pipelines based on UAVs to improve the timeliness and accuracy of gas pipeline hidden danger detection. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for hidden danger warning of gas pipelines based on UAVs. By dividing the gas pipelines into regional grids and collecting inspection data of each grid area, it is possible to effectively extract the areas with gas hidden danger risks, thereby improving the timeliness and accuracy of gas pipeline hidden danger detection.

[0005] The present invention provides a method for hidden danger warning of gas pipelines based on UAVs, the method including:

[0006] Dividing the gas pipelines into regional grids, obtaining a plurality of gas grid areas, and collecting inspection data of each gas grid area;

[0007] Based on the inspection data and the gas hazard threshold, obtain the slope of the fitting curve, and extract the gas grid areas with gas hazard risks in all gas grid areas according to the slope of the fitting curve, and mark the gas grid areas with gas hazard risks as gas hazard areas;

[0008] According to the inspection data corresponding to the gas hazard areas and the improved analytic hierarchy process, obtain the initial weight of the hazard type and the first hazard value corresponding to the gas hazard areas, and perform curve fitting on each type of data in the inspection data to obtain the fitting curve corresponding to each type of data in the inspection data;

[0009] Divide the gas hazard areas equally according to the pipeline length to obtain multiple gas hazard sub-areas, and at the same time divide the fitting curves corresponding to each type of data in the inspection data equally in corresponding quantities to obtain segmented fitting curves, so that the gas hazard sub-areas and the segmented fitting curves correspond one by one;

[0010] Based on the dynamic time warping algorithm and the segmented fitting curves corresponding to each gas hazard sub-area, obtain similar hazard segmented areas, and calculate the second hazard value of the gas hazard areas according to the number of similar hazard segmented areas, the acquisition time interval between adjacent similar hazard segmented areas, and the first hazard value;

[0011] Collect data for each segmented sub-area in the similar hazard segmented areas to obtain the fitting curve of the sub-area at the current moment. Based on the inspection data collected at the current moment, the initial weight of the hazard type, and the dynamic weight algorithm, obtain the dynamically updated weight of the area at the current moment. According to the second hazard value and the dynamically updated weight at the current moment, obtain the final hazard value of the hazard area, and perform hazard warning according to the final hazard value and the reference hazard level classification.

[0012] On the basis of the above technical solutions, preferably, the collection of the inspection data for each time period in each gas grid area specifically includes:

[0013] Deploy drones in each gas grid area to collect inspection data for the gas grid area. Among them, the inspection data includes methane leakage concentration, pipeline color, pipeline infrared temperature, the number of buildings around the gas pipeline, and the number of third-party construction tools, etc.

[0014] On the basis of the above technical solutions, preferably, the deployment of drones in each gas grid area to perform cyclic detection on the inspection data of the gas grid area specifically includes:

[0015] According to the coordinate information of the buried pipe points of the gas pipeline in each gas grid area, set the inspection route of the drone to be from pipe point to pipe point, and collect inspection data and pipeline images along the gas pipeline;

[0016] When the UAV turns, accelerates or decelerates, according to the real-time attitude of the UAV, make an angular adjustment in the opposite direction to the camera carried by the UAV to ensure that the camera always shoots perpendicular to the ground;

[0017] According to the endurance of the UAV, set the UAV for bilateral cruise or unilateral detection, control the UAV to patrol according to the inspection route, and transmit the inspection data and pipeline images collected during a single inspection back to the terminal device.

[0018] More preferably, based on the inspection data and the gas hazard threshold, obtain the slope of the fitted curve, and extract the gas grid areas with gas hazard risks in all gas grid areas according to the slope of the fitted curve. Specifically, it includes:

[0019] Obtain the time series corresponding to each type of parameter for each gas grid area collected by the UAV;

[0020] Based on the curve fitting algorithm and the time series, fit a curve corresponding to the time series;

[0021] Calculate the absolute value of the slope of the fitted curve corresponding to each type of data in each gas grid area, and judge whether the absolute value of the slope of the fitted curve is greater than the gas hazard threshold of the corresponding data type;

[0022] If the absolute value of the slope of the fitted curve of a certain type of parameter in the gas grid area is greater than the gas hazard threshold, mark the gas grid area where the parameter data source is located as a gas hazard area.

[0023] More preferably, evenly divide the gas hazard area according to the pipeline length to obtain multiple gas hazard sub-areas, and at the same time evenly divide the fitted curves corresponding to each type of data in the inspection data by the corresponding number. Specifically, it includes:

[0024] Evenly segment the gas hazard area according to the length of the gas pipeline in the gas hazard area to obtain multiple gas hazard sub-areas with the same length. At the same time, evenly divide the fitted curves of each type of parameter by the number of corresponding sub-areas, so that the gas hazard sub-areas and the segmented fitted curves correspond one by one;

[0025] Based on the dynamic programming algorithm, calculate the similarity distance between the fitted curves corresponding to any two gas hazard sub-areas of the same type of parameter, and judge whether the similarity distance is less than the similarity distance threshold;

[0026] If the similarity distance is less than the similarity distance threshold, mark the gas hazard sub-areas corresponding to the two segmented curves as similar hazard sub-areas.

[0027] More preferably, the expression of the second hidden danger value is:

[0028]

[0029] where H 2 represents the second hidden danger value, norm[] represents the normalization function, H 1 represents the first hidden danger value, m represents the number of gas hidden danger sub-regions in the gas hidden danger area, r represents the number of hidden danger indicators monitored by the UAV, n i,j represents the number of similar gas hidden danger sub-regions when in the i-th gas hidden danger sub-region and the corresponding parameter is the j-th hidden danger indicator, t i,j,k represents the time interval between the k-th and the k + 1-th similar hidden danger regions when in the i-th gas hidden danger sub-region and the corresponding parameter is the j-th hidden danger indicator, represents the average time interval of similar hidden danger regions when in the i-th gas hidden danger sub-region and the corresponding parameter is the j-th hidden danger indicator.

[0030] More preferably, the expression of the predicted hidden danger value is:

[0031]

[0032] where W t,j represents the dynamic weight value of the j-th hidden danger indicator at the t-th moment, x t,j represents the state weight of the j-th hidden danger indicator at the t-th moment, w t,j represents the constant weight of the j-th hidden danger indicator at the t-th moment, α represents the state variable weight balance coefficient, H 3 represents the final hidden danger value, n represents the total number of hidden danger indicators, H 2 represents the second hidden danger value.

[0033] In the second aspect of the present application, a gas pipeline hidden danger early warning system based on a UAV is provided. The gas pipeline hidden danger early warning system includes an information collection module, a data processing module, and a hidden danger early warning module, where

[0034] the information collection module is used to divide the gas pipeline into regional grids, obtain a plurality of gas grid regions, and collect inspection data of each gas grid region;

[0035] The data processing module is used to obtain the slope of the fitting curve based on the inspection data and the gas hazard threshold, and extract the gas grid areas with gas hazard risks in all gas grid areas according to the slope of the fitting curve, and mark the gas grid areas with gas hazard risks as gas hazard areas; according to the inspection data corresponding to the gas hazard areas and the improved analytic hierarchy process, obtain the initial weight of the hazard type and the first hazard value corresponding to the gas hazard areas, and perform curve fitting on each type of data in the inspection data to obtain the fitting curve corresponding to each type of data in the inspection data; divide the gas hazard areas equally according to the pipeline length to obtain multiple gas hazard sub-areas, and at the same time divide the fitting curves corresponding to each type of data in the inspection data into corresponding equal parts to obtain segmented fitting curves, so that the gas hazard sub-areas and the segmented fitting curves correspond one by one; based on the dynamic time warping algorithm and the segmented fitting curves corresponding to each gas hazard sub-area, obtain similar hazard segmented areas, and calculate the second hazard value of the gas hazard areas according to the number of similar hazard segmented areas, the acquisition time interval of adjacent similar hazard segmented areas, and the first hazard value;

[0036] The hazard warning module is used to collect data for each segmented sub-area in the similar hazard segmented areas to obtain the fitting curve of the sub-area at the current moment, and based on the inspection data collected at the current moment, the initial weight of the hazard type and the dynamic weight algorithm, obtain the dynamically updated weight of the area at the current moment, and obtain the final hazard value of the hazard area according to the second hazard value and the dynamically updated weight at the current moment, and perform hazard warning according to the final hazard value and the reference hazard level classification.

[0037] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.

[0038] In the fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the steps of a method for warning hidden dangers of gas pipelines based on unmanned aerial vehicles.

[0039] The method and system for warning hidden dangers of gas pipelines based on unmanned aerial vehicles provided by the present invention have the following beneficial effects compared with the prior art:

[0040] (1) By dividing the gas pipeline into regional grids and collecting the inspection data of each grid area, potential gas hazard areas can be quickly identified. Moreover, based on the analysis method combining inspection data with gas hazard thresholds, areas with gas hazard risks can be effectively extracted, thereby improving the timeliness and accuracy of gas pipeline hazard detection. At the same time, by further dividing the gas hazard areas into sub-areas with the same length and fitting the hazard curve based on time series, dynamic monitoring of hazard changes can be achieved, and similar hazard areas can be identified using the dynamic time warping algorithm, enhancing the ability to track hazards. By combining dynamic weights based on the calculation of the second hazard value, a predicted hazard value for the gas hazard area can be effectively generated, thus realizing early warning of potential gas risks and systematically improving the efficiency of gas hazard management.

[0041] (2) By evenly segmenting the gas hazard areas according to the pipeline length, multiple gas hazard sub-areas with the same length are obtained, improving the spatial resolution of hazard assessment and avoiding the missed or misjudged hazard risks caused by uneven area sizes. Moreover, by collecting the hazard type sequences of each gas hazard sub-area at different time periods, the dynamic changes of hazards can be systematically reflected, providing a basis in the time dimension for risk assessment, making hazard identification more comprehensive. At the same time, based on the dynamic programming algorithm, the similarity distance of the hazard type sequences is calculated, providing a quantitative means for judging the similarity of hazard areas. And by accurately calculating the similarity, the correlation between different hazard areas can be better understood, supporting targeted risk management. Marking similar hazard areas helps decision-makers quickly identify areas with common risk characteristics, thereby taking unified monitoring and management measures, improving the efficiency and effectiveness of hazard handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0043] Figure 1 It is a schematic flowchart of a method for warning gas pipeline hazards based on an unmanned aerial vehicle provided by the present invention;

[0044] Figure 2 It is a schematic structural diagram of a gas pipeline hazard warning system provided by the present invention;

[0045] Figure 3 It is a schematic structural diagram of an electronic device provided by the present invention.

[0046] Explanation of the accompanying reference numerals: 1. Gas pipeline hidden danger warning system; 11. Information acquisition module; 12. Data processing module; 13. Hidden danger warning module; 2. Electronic equipment; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. DETAILED DESCRIPTION

[0047] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The present invention discloses a gas pipeline hidden danger early warning method based on drone, referring to Figure 1 The method includes steps S1 to S6.

[0049] Step S1, divide the gas pipeline into regional grids, obtain multiple gas grid areas, and collect inspection data of each gas grid area.

[0050] In this step, drones are deployed in each gas grid area to perform cyclic detection on the inspection data of the gas grid area, where the inspection data includes methane leakage concentration, pipeline color, infrared temperature, the number of buildings in the gas grid area, and the number of third-party construction machinery and tools.

[0051] This step also includes steps S11 to S13.

[0052] Step S11, according to the coordinate information of the buried pipe points of the gas pipeline in each gas grid area, the inspection route of the drone is set from pipe point to pipe point, and inspection data and pipeline images are collected along the gas pipeline.

[0053] In this step, the inspection route of the drone is generated using aerial photography software or algorithms based on the coordinate information of the buried pipe points of the gas pipeline. The route should be optimized based on the straight path between the pipe points to ensure that the drone can cover all pipeline locations in the shortest time, and install a variety of sensors and detection equipment on the drone, such as cameras, infrared thermal imagers, laser methane sensors, and environmental data sensors, so that inspection data can be collected in real time during flight. The setting of the sensor should ensure that environmental data at different heights and locations can be collected. Install a GPS module on the drone to monitor the location, speed, altitude and other information of the drone in real time to optimize the flight path and ensure the accurate execution of the inspection task. During each inspection, ensure that the system automatically records the collected environmental data and pipeline images, and performs preliminary data analysis after the data is transmitted to the terminal device to identify possible hidden dangers or abnormal conditions in advance.

[0054] Step S12, when the drone turns, accelerates or decelerates, the angle of the camera carried by the drone is adjusted in the opposite direction according to the real-time posture of the drone to ensure that the camera is always perpendicular to the ground for shooting.

[0055] Step S13, according to the endurance of the drone, set the drone to bilateral cruising or unilateral detection, control the drone to inspect along the inspection route, and transmit the inspection data and pipeline images collected in a single inspection back to the terminal device.

[0056] In this step, the drone's flight time and range data are obtained by consulting the drone's technical parameters or actual testing. For drones with long flight capabilities, they can be set to perform pipeline inspections in a bilateral cruise mode. That is, the drone flies back and forth along the pipeline to comprehensively collect inspection data and pipeline images in each area. For drones with weaker flight capabilities, they can be set to use a unilateral detection mode. That is, the drone only flies in one direction for inspection and completes a one-way pipeline coverage. According to the division of pipeline areas and the drone's inspection mode, the path optimization algorithm is used to calculate the shortest drone flight path to ensure that the drone covers as many pipeline areas as possible within a limited flight time. During the actual flight of the drone, its battery power and flight status are monitored in real time. Once it is found that the battery is insufficient or other abnormal conditions are encountered, the drone's inspection mode should be adjusted in time, such as changing from bilateral to unilateral, to ensure safe return.

[0057] Step S2, based on the inspection data and the gas hidden danger threshold, obtain the slope of the fitting curve, and extract the gas grid areas with gas hidden danger risks from all gas grid areas according to the slope of the fitting curve, and mark the gas grid areas with gas hidden danger risks as gas hidden danger areas.

[0058] This step also includes steps S21 to S24.

[0059] Step S21: According to the data collected by the drone for each gas grid area, obtain the time series corresponding to each type of parameter.

[0060] In this step, obtain the inspection data collected by the drone during the inspection of the gas pipeline, including information such as timestamp, geographical location, gas concentration, temperature, and humidity. Classify these inspection data according to different index types, such as methane concentration, carbon dioxide concentration, pipeline temperature, and pipeline humidity. For each type of environmental index, extract the corresponding timestamp and index value. Use the timestamp as the abscissa and the environmental index value as the ordinate to plot a scatter plot on a two-dimensional plane. Use a suitable visualization tool, such as Matplotlib in Python or the plot function in MATLAB, to generate the time-environment scatter plot of each type of environmental index.

[0061] Step S22: Based on the curve fitting algorithm and the time series, fit the curve corresponding to the time series.

[0062] In this step, according to the data distribution of the time-environment scatter plot, select a suitable curve fitting algorithm (such as polynomial fitting, spline fitting, and exponential fitting, etc.), evaluate the fitting effects of various curve fitting algorithms, and select the algorithm that can best fit the scatter plot data. Check whether there are outliers or noise data in the time-environment scatter plot. If necessary, perform data cleaning and perform normalization or other preprocessing operations on the data according to the requirements of the curve fitting algorithm. Use the timestamp as the independent variable (x-axis) and the environmental index value as the dependent variable (y-axis), and use the selected curve fitting algorithm for calculation. For each type of environmental index, perform curve fitting independently to obtain the corresponding time-environment index curve. The curve fitting can be implemented using functions such as scipy.optimize.curve_fit in Python or polyfit in MATLAB.

[0063] Step S23: Calculate the absolute value of the slope of the fitting curve corresponding to each type of data in each gas grid area, and determine whether the absolute value of the slope of the fitting curve is greater than the gas hazard threshold corresponding to the data type.

[0064] Step S24: If the absolute value of the slope of the fitting curve of a certain type of parameter in the gas grid area is greater than the gas hazard threshold, mark the gas grid area where the parameter data source is located as a gas hazard area.

[0065] Step S3: According to the inspection data corresponding to the gas hazard area and the improved analytic hierarchy process, obtain the initial weight of the hazard type corresponding to the gas hazard area and the first hazard value, and perform curve fitting on each type of data in the inspection data to obtain the fitting curve corresponding to each type of data in the inspection data.

[0066] In this embodiment, first, a comparison matrix S is established.

[0067]

[0068] Among them, when s ij = 0, the j-th index (factor) is more important; when s ij = 1, both are equally important; when s ij = 2, the i-th index (factor) is more important.

[0069]

[0070] c ij = lgb ij

[0071]

[0072] Among them, r i represents the importance ranking index, r represents the sum of the elements in each row of the S matrix, B represents the judgment matrix, b ij represents the element of the judgment matrix b, c represents the transfer matrix, c ij represents the element of the transfer matrix C, D represents the optimal transfer matrix, d ij represents the element of the optimal transfer matrix d, e represents the quasi-optimal consistent matrix, e ij represents the element of the quasi-optimal consistent matrix e.

[0073] According to the eigenvector W obtained from e,

[0074]

[0075] Finally, W = (w 1 , w 2, w 3 ,....w r ) is the initial weight vector of each type of index data.

[0076] Step S4: Divide the gas hazard area equally according to the pipeline length to obtain multiple gas hazard sub-areas. At the same time, divide the fitting curve corresponding to each type of data in the inspection data equally according to the corresponding number to obtain a segmented fitting curve, so that the gas hazard sub-areas and the segmented fitting curves correspond one by one.

[0077] In this step, steps S41 to S43 are also included.

[0078] Step S41: Uniformly segment the gas hazard area according to the length of the gas pipeline in the gas hazard area to obtain multiple gas hazard sub-areas with the same length. At the same time, divide each type of parameter fitting curve equally according to the number of corresponding sub-areas, so that the gas hazard sub-areas and the segmented fitting curves correspond one by one.

[0079] In this step, relevant information that has been identified as a gas hazard area is obtained from the previous step, including pipeline position coordinates, pipeline length, etc. The gas hazard areas that need further analysis are determined. According to the pipeline length of each gas hazard area, it is evenly divided into multiple sub-areas with the same length. The segmentation can be carried out in a way of a fixed length (such as 50 meters) or a fixed number (such as 10). The starting and ending coordinates of each gas hazard sub-area are recorded for subsequent data collection. For each gas hazard sub-area, relevant hazard type data are collected at different time periods. The hazard types can include risk factors corresponding to the degree of pipeline corrosion, changes in the surrounding environment, third-party construction activities, etc. The hazard type sequence of each gas hazard sub-area within each time period is recorded to prepare for subsequent similarity analysis.

[0080] Step S42: Calculate the similarity distance between the fitting curves corresponding to any two gas hazard sub-areas of the same type of parameters based on the dynamic programming algorithm, and determine whether the similarity distance is less than the similarity distance threshold.

[0081] In this step, the hazard type sequence data of each gas hazard sub-area at different time periods are obtained from step S41, and a suitable similarity measurement method is selected, such as the Levenshtein distance or the edit distance. For any two hazard type sequences A and B, the dynamic programming algorithm is used to calculate their similarity distance. The basic idea of the dynamic programming algorithm is to construct a two-dimensional table, and each cell in the table records the minimum edit distance between A[i] and B[j]. By filling the table, the similarity distance between the two sequences A and B can be finally obtained. The calculated similarity distance is compared with the pre-set similarity distance threshold. If the similarity distance is less than the threshold, it is considered that the gas hazard sub-areas corresponding to the two hazard type sequences are similar. On the contrary, if the similarity distance is greater than the threshold, it is considered that the gas hazard sub-areas corresponding to the two hazard type sequences are not similar.

[0082] Step S43: If the similarity distance is less than the similarity distance threshold, the gas hazard sub-areas corresponding to the two segmented curves are marked as similar hazard sub-areas.

[0083] By evenly segmenting the gas hazard area according to the pipeline length, multiple gas hazard sub-areas with the same length are obtained, which improves the spatial resolution of hazard assessment and avoids the missed or misjudged hazard risks caused by uneven area sizes. Moreover, collecting the hazard type sequences of each gas hazard sub-area at different time periods can systematically reflect the dynamic changes of hazards, providing a basis in the time dimension for risk assessment, making hazard identification more comprehensive. At the same time, calculating the similarity distance of the hazard type sequences based on the dynamic programming algorithm provides a quantitative means for judging the similarity of hazard areas. And by accurately calculating the similarity, the correlation between different hazard areas can be better understood, supporting targeted risk management. Marking similar hazard areas helps decision-makers quickly identify areas with common risk characteristics, so as to take unified monitoring and management measures, improving the efficiency and effectiveness of hazard handling.

[0084] Step S5: Based on the dynamic time warping algorithm and the piecewise fitting curves corresponding to each gas hazard sub-area, obtain similar hazard segmented areas, and calculate the second hazard value of the gas hazard area according to the number of similar hazard segmented areas, the acquisition time interval between adjacent similar hazard segmented areas, and the first hazard value.

[0085] In this step, the expression of the second hazard value is:

[0086]

[0087] where, H 2 represents the second hazard value, norm[] represents the normalization function, H 1 represents the first hazard value, m represents the number of gas hazard sub-areas in the gas hazard area, r represents the number of hazard indicators monitored by the unmanned aerial vehicle, n i,j represents the number of similar gas hazard sub-areas when in the i-th gas hazard sub-area and corresponding parameter is the j-th hazard indicator, t i,j,k represents the time interval between the k-th and the k + 1-th similar hazard areas when in the i-th gas hazard sub-area and corresponding parameter is the j-th hazard indicator, represents the average time interval of similar hazard areas when in the i-th gas hazard sub-area and corresponding parameter is the j-th hazard indicator.

[0088] Step S6: Collect data for each segmented sub-area in the similar hazard segmented area to obtain the fitting curve of the sub-area at the current moment. Based on the inspection data collected at the current moment, the initial weight of the hazard type, and the dynamic weight algorithm, obtain the dynamically updated weight of the area at the current moment. According to the second hazard value and the dynamically updated weight at the current moment, obtain the final hazard value of the hazard area, and issue a hazard warning according to the final hazard value and the reference hazard level classification.

[0089] In this step, the expression for predicting the hidden danger value is:

[0090]

[0091] where, W t,j represents the dynamic weight value of the j-th hidden danger index at the t-th moment, x t,j represents the state weight of the j-th hidden danger index at the t-th moment, w t,j represents the constant weight of the j-th hidden danger index at the t-th moment, α represents the state variable weight balance coefficient, H 3 represents the predicted hidden danger value, n represents the total number of hidden danger indexes, H 2 represents the second hidden danger value.

[0092] By dividing the gas pipeline into regional grids and collecting the inspection data of each grid area, potential gas hidden danger areas can be quickly identified. And based on the analysis method combining the inspection data with the gas hidden danger threshold, the areas with gas hidden danger risks can be effectively extracted, thereby improving the timeliness and accuracy of gas pipeline hidden danger detection. At the same time, by further dividing the gas hidden danger area into sub-areas with the same length and fitting the hidden danger curve based on the time series, the dynamic monitoring of the hidden danger change can be realized, and the dynamic time programming algorithm is used to identify similar hidden danger areas, enhancing the tracking ability of the hidden danger. On the basis of calculating the second hidden danger value and combining the dynamic weight, the predicted hidden danger value of the gas hidden danger area can be effectively generated, so as to realize the early warning of potential gas risks and systematically improve the efficiency of gas hidden danger management.

[0093] Based on the above method, an embodiment of the present application discloses a gas pipeline hidden danger early warning system based on an unmanned aerial vehicle. Referring to Figure 2 , the gas pipeline hidden danger early warning system 1 includes an information collection module 11, a data processing module 12, and a hidden danger early warning module 13, where,

[0094] The information collection module 11 is used to divide the gas pipeline into regional grids, obtain a plurality of gas grid areas, and collect the inspection data of each gas grid area;

[0095] The data processing module 12 is used to obtain the slope of the fitting curve based on the inspection data and the gas hazard threshold, and extract the gas grid areas with gas hazard risks in all gas grid areas according to the slope of the fitting curve, and mark the gas grid areas with gas hazard risks as gas hazard areas; according to the inspection data corresponding to the gas hazard areas and the improved analytic hierarchy process, obtain the initial weights of the hazard types and the first hazard value corresponding to the gas hazard areas, and perform curve fitting on each type of data in the inspection data to obtain the fitting curves corresponding to each type of data in the inspection data; divide the gas hazard areas equally according to the pipeline length to obtain multiple gas hazard sub-areas, and at the same time divide the fitting curves corresponding to each type of data in the inspection data equally in the corresponding number to obtain segmented fitting curves, so that the gas hazard sub-areas and the segmented fitting curves correspond one by one; based on the dynamic time warping algorithm and the segmented fitting curves corresponding to each gas hazard sub-area, obtain similar hazard segmented areas, and calculate the second hazard value of the gas hazard area according to the number of similar hazard segmented areas, the acquisition time interval between adjacent similar hazard segmented areas, and the first hazard value;

[0096] The hazard warning module 13 is used to collect data for each segmented sub-area in the similar hazard segmented areas to obtain the fitting curve of the sub-area at the current moment, and obtain the dynamically updated weight of the area at the current moment based on the inspection data collected at the current moment, the initial weights of the hazard types, and the dynamic weight algorithm, and obtain the final hazard value of the hazard area according to the second hazard value and the dynamically updated weight at the current moment, and perform hazard warning according to the final hazard value and the reference hazard level classification.

[0097] In one example, the information collection module 11 is used to deploy drones in each gas grid area to collect inspection data of the gas grid area. Among them, the inspection data includes methane leakage concentration, pipeline color, pipeline infrared temperature, the number of buildings around the gas pipeline, and the number of third-party construction tools, etc.

[0098] In one example, the information collection module 11 is used to set the inspection route of the drone from pipe point to pipe point according to the coordinate information of the pipe points where the gas pipelines are buried in each gas grid area, and collect inspection data and pipeline images along the gas pipeline; when the drone turns, accelerates or decelerates, make an angle adjustment in the opposite direction to the camera carried by the drone according to the real-time attitude of the drone to ensure that the camera always shoots perpendicular to the ground; according to the endurance of the drone, set the drone to perform bilateral cruise or unilateral detection, control the drone to perform inspection according to the inspection route, and transmit the inspection data and pipeline images collected in a single inspection back to the terminal device.

[0099] In one example, the data processing module 12 is used to obtain the time series corresponding to each type of parameter according to the data collected by the drone for each gas grid area; fit a curve corresponding to the time series based on the curve fitting algorithm and the time series; calculate the absolute value of the slope of the fitting curve corresponding to each type of data in each gas grid area, and determine whether the absolute value of the slope of the fitting curve is greater than the gas hazard threshold corresponding to the data type; if the absolute value of the slope of the fitting curve of a certain type of parameter in the gas grid area is greater than the gas hazard threshold, mark the gas grid area where the parameter data source is located as a gas hazard area.

[0100] In one example, the data processing module 12 is used to evenly segment the gas hazard areas according to the length of the gas pipeline in the gas hazard areas, obtain multiple gas hazard sub-areas with the same length, and at the same time evenly divide each type of parameter fitting curve according to the number of sub-areas, so that the gas hazard sub-areas and the segmented fitting curves correspond one by one; calculate the similarity distance between the fitting curves corresponding to any two gas hazard sub-areas of the same type of parameter based on the dynamic programming algorithm, and determine whether the similarity distance is less than the similarity distance threshold; if the similarity distance is less than the similarity distance threshold, mark the gas hazard sub-areas corresponding to the two segmented curves as similar hazard sub-areas.

[0101] In one example, the expression of the second hazard value is:

[0102]

[0103] where H 2 represents the second hazard value, norm[] represents the normalization function, H 1 represents the first hazard value, m represents the number of gas hazard sub-areas in the gas hazard area, r represents the number of hazard indicators monitored by the drone, n i,j represents the number of similar gas hazard sub-areas when in the i-th gas hazard sub-area and the corresponding parameter is the j-th hazard indicator, t i,j,k represents the time interval between the k-th and the k + 1-th similar hazard areas when in the i-th gas hazard sub-area and the corresponding parameter is the j-th hazard indicator, represents the average time interval of the similar hazard areas when in the i-th gas hazard sub-area and the corresponding parameter is the j-th hazard indicator.

[0104] In one example, the expression of the predicted hazard value is:

[0105]

[0106] where W t,j represents the dynamic weight value of the j-th hazard indicator at the t-th moment, x t,j represents the state weight of the j-th hazard indicator at the t-th moment, w t,jLet \(w_{j}\) denote the constant weight of the \(j\)-th potential hazard index at the \(t\)-th moment, \(\alpha\) denote the state variable weight balance coefficient, and \(H\) 3 denote the predicted potential hazard value, \(n\) denote the total number of potential hazard indices, and \(H\) 2 denote the second potential hazard value.

[0107] Please refer to Figure 3 , which provides a schematic structural diagram of an electronic device for an embodiment of the present application. As Figure 3 shown, the electronic device 2 may include: at least one processor 21, at least one network interface 24, a user interface 23, a memory 25, and at least one communication bus 22.

[0108] Among them, the communication bus 22 is used to realize the connection and communication between these components.

[0109] Among them, the user interface 23 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 23 may further include a standard wired interface and a wireless interface.

[0110] Among them, the network interface 24 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0111] Among them, the processor 21 may include one or more processing cores. The processor 21 connects various parts within the entire server through various interfaces and lines, and executes various functions of the server and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 25, and by calling data stored in the memory 25. Optionally, the processor 21 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 21 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 21 and may be implemented separately by a single chip.

[0112] Among them, the memory 25 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 25 includes a non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 25 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 25 may also be at least one storage device located far from the aforementioned processor 21. As Figure 3 shown, in the memory 25 as a computer storage medium, it may include an operating system, a network communication module, a user interface module, and an application program of a method for early warning of potential hazards in gas pipelines based on an unmanned aerial vehicle.

[0113] In Figure 3 the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and obtain the data input by the user; while the processor 21 can be used to call the application program of a method for early warning of potential hazards in gas pipelines stored in the memory 25. When executed by one or more processors, the electronic device is enabled to execute one or more methods as in the above embodiments.

[0114] A computer-readable storage medium stores instructions. When executed by one or more processors, the computer is enabled to execute one or more methods as in the above embodiments.

[0115] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0116] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0117] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in electrical or other forms.

[0118] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0120] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0121] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the public disclosure of the practical truth. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional techniques in the technical field not recorded in the present disclosure.

[0122] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A gas pipeline hidden danger early warning method based on drone, characterized in that: The method comprises: Divide the gas pipeline into regional grids, obtain multiple gas grid areas, and collect inspection data for each gas grid area; Based on the inspection data and the gas hidden danger threshold, the slope of the fitting curve is obtained, and the gas grid areas with gas hidden danger risks are extracted from all gas grid areas according to the slope of the fitting curve, and the gas grid areas with gas hidden danger risks are marked as gas hidden danger areas; According to the inspection data corresponding to the gas hazard area and the improved hierarchical analysis method, the initial weight of the hazard type and the first hazard value corresponding to the gas hazard area are obtained, and curve fitting is performed on each type of data in the inspection data to obtain a fitting curve corresponding to each type of data in the inspection data; The gas hazard area is equally divided according to the pipeline length to obtain a plurality of gas hazard sub-areas, and the fitting curve corresponding to each type of data in the inspection data is equally divided by a corresponding number to obtain a segmented fitting curve, so that the gas hazard sub-areas and the segmented fitting curves correspond one to one; Based on the dynamic time planning algorithm and the segmented fitting curve corresponding to each gas hazard sub-area, similar hazard segmented areas are obtained, and according to the number of similar hazard segmented areas, the collection time interval of adjacent similar hazard segmented areas and the first hazard value, the second hazard value of the gas hazard area is calculated; Data is collected for each segmented sub-area in the similar hidden danger segmented area to obtain a fitting curve of the sub-area at the current moment, and the dynamically updated weight of the area at the current moment is obtained based on the inspection data collected at the current moment, the initial weight of the hidden danger type and the dynamic weight algorithm. According to the second hidden danger value and the dynamically updated weight at the current moment, the final hidden danger value of the hidden danger area is obtained, and hidden danger warning is performed according to the final hidden danger value and the reference hidden danger level classification.

2. The method according to claim 1, characterized in that The collection of inspection data of each gas grid area specifically includes: Drones are deployed in each gas grid area to collect inspection data for the gas grid area, where the inspection data includes methane leakage concentration, pipeline color, pipeline infrared temperature, the number of buildings around the gas pipeline, and the number of third-party construction machinery and tools.

3. The method according to claim 2, characterized in that The method of deploying a drone in each gas grid area to collect pipeline parameters in the gas grid area specifically includes: According to the coordinate information of the buried pipe points of the gas pipeline in each gas grid area, the inspection route of the drone is set from pipe point to pipe point, and the inspection data and pipeline image collection are performed along the gas pipeline; When the drone turns, accelerates or decelerates, the camera carried by the drone is adjusted in the opposite direction according to the real-time posture of the drone to ensure that the camera is always perpendicular to the ground for shooting; According to the endurance of the UAV, the UAV is set to bilateral cruising or unilateral detection, the UAV is controlled to inspect along the inspection route, and the inspection data and pipeline images collected in a single inspection are transmitted back to the terminal device.

4. The method according to claim 2, characterized in that The step of obtaining the slope of the fitting curve based on the inspection data and the gas hidden danger threshold, and extracting the gas grid areas with gas hidden danger risks in all gas grid areas according to the slope of the fitting curve, specifically includes: The time series corresponding to each type of parameter is obtained based on the UAV data collected in each gas grid area; Based on a curve fitting algorithm and a time series, fitting a curve corresponding to the time series; Calculate the absolute value of the slope of the fitting curve corresponding to each type of data in each gas grid area, and determine whether the absolute value of the slope of the fitting curve is greater than the gas hazard threshold of the corresponding data type; If the absolute value of the slope of a certain type of parameter fitting curve in the gas grid area is greater than the gas hazard threshold, the gas grid area where the parameter data is sourced is marked as a gas hazard area.

5. The method according to claim 1, characterized in that The gas hazard area is equally divided according to the pipeline length to obtain a plurality of gas hazard sub-areas, and the fitting curve corresponding to each type of data in the inspection data is equally divided by a corresponding number, specifically including: The gas hazard area is evenly segmented according to the length of the gas pipeline in the gas hazard area to obtain multiple gas hazard sub-areas with the same length, and each type of parameter fitting curve is evenly divided into the number of corresponding sub-areas, so that the gas hazard sub-areas and the segmented fitting curves correspond one to one; Calculate the similarity distance of the fitting curves corresponding to any two gas hazard sub-areas with the same parameters based on the dynamic programming algorithm, and determine whether the similarity distance is less than a similarity distance threshold; If the similarity distance is less than a similarity distance threshold, the gas hazard sub-regions corresponding to the two segmented curves are marked as similar hazard sub-regions.

6. The method according to claim 1, characterized in that The expression of the second hidden danger value is: Among them, H2 represents the second hidden danger value, norm[] represents the normalization function, H1 represents the first hidden danger value, m represents the number of gas hidden danger sub-areas in the gas hidden danger area, r represents the number of hidden danger parameter types in the inspection data collected by the drone, and n i,j It represents the number of similar gas hazard sub-areas when it is in the i-th gas hazard sub-area and the corresponding parameter is the j-th hazard parameter type, t i,j,k It represents the time interval between the kth and k+1th adjacent similar hazard sub-areas when the i-th gas hazard sub-area and the corresponding parameter is the j-th hazard index. It represents the average time interval between two similar hidden danger sub-areas when the area is in the i-th gas hidden danger sub-area and the corresponding parameter is the j-th hidden danger index.

7. The method according to claim 1, characterized in that The expression of the final hidden danger value is: Among them, W t,j represents the dynamic weight value of the jth hidden danger parameter at the tth moment, x t,j represents the data of the jth hidden danger parameter in the inspection data collected at the tth time, w t,j represents the fixed weight of the jth hidden danger parameter at the tth moment, α represents the state variable weight balance coefficient, H3 represents the final hidden danger value, n represents the number of hidden danger parameter types, and H2 represents the second hidden danger value.

8. A gas pipeline hidden danger early warning system based on drones, characterized in that: The gas pipeline hidden danger early warning system (1) comprises an information collection module (11), a data processing module (12) and a hidden danger early warning module (13), wherein: The information collection module (11) is used to divide the gas pipeline into regional grids, obtain multiple gas grid areas, and collect inspection data of each gas grid area; The data processing module (12) is used to obtain the slope of the fitting curve based on the inspection data and the gas hazard threshold, and extract the gas grid areas with gas hazard risks from all gas grid areas according to the slope of the fitting curve, and mark the gas grid areas with gas hazard risks as gas hazard areas; according to the inspection data corresponding to the gas hazard area and the improved hierarchical analysis method, obtain the initial weight of the hazard type and the first hazard value corresponding to the gas hazard area, and perform curve fitting on each type of data in the inspection data to obtain the fitting curve corresponding to each type of data in the inspection data; divide the gas hazard area equally according to the pipeline length to obtain a plurality of gas hazard sub-areas, and at the same time divide the fitting curve corresponding to each type of data in the inspection data by a corresponding number to obtain a segmented fitting curve, so that the gas hazard sub-areas and the segmented fitting curve correspond to each other one by one; based on the dynamic time planning algorithm and the segmented fitting curve corresponding to each gas hazard sub-area, obtain similar hazard segmented areas, and calculate the second hazard value of the gas hazard area according to the number of similar hazard segmented areas, the collection time interval of adjacent similar hazard segmented areas and the first hazard value; The hidden danger warning module (13) is used to collect data from each segmented sub-area in the similar hidden danger segmented area, obtain a fitting curve of the sub-area at the current moment, obtain the dynamically updated weight of the area at the current moment based on the inspection data collected at the current moment, the initial weight of the hidden danger type and the dynamic weight algorithm, obtain the final hidden danger value of the hidden danger area according to the second hidden danger value and the dynamically updated weight at the current moment, and perform hidden danger warning according to the final hidden danger value and the reference hidden danger level classification.

9. An electronic device, characterized in that: The electronic device (2) comprises a processor (21), a memory (25), a user interface (23) and a network interface (24), wherein the memory (25) is used to store instructions, the user interface (23) and the network interface (24) are used to communicate with other devices, and the processor (21) is used to execute the instructions stored in the memory (25) so that the electronic device (2) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images