Unmanned intelligent inspection system for gas leakage

Abstract

The invention discloses a gas leakage unmanned intelligent inspection system, which relates to the technical field of unmanned inspection, and comprises an environment monitoring sensor module, a gas leakage positioning module, a risk assessment module, an autonomous navigation positioning module, an inspection planning module, a remote interaction module and a monitoring early warning module. By evaluating the risk and harm of gas leakage, making a tour inspection plan and planning an optimal tour inspection route and combining with multi-sensor fusion-based autonomous positioning navigation, autonomous tour inspection can be realized, gas leakage early warning is issued in time through a remote interaction module, corresponding measures are taken, the harm of gas leakage accidents is reduced, and the safety of gas leakage accidents is improved. The problems of large workload, low efficiency, leak detection and the like of a manual gas pipeline inspection mode are solved, and the method is an effective mode for replacing manual inspection.

Description

[0001] This application is a divisional application. The application number of the original application is 202211138157.1, the application date is September 19, 2022, and the name of the invention is "An explosion-proof inspection unmanned vehicle and inspection method for gas leak monitoring." Technical Field

[0002] The invention belongs to the field of unmanned inspection, and in particular relates to an unmanned intelligent inspection system for gas leakage. Background Art

[0003] At present, gas leak monitoring mainly adopts manual inspection. The inspection method in which inspectors carry gas detectors has the disadvantages of large workload and low efficiency, and the inspection environment is complex and the inspection work is dangerous. Inspection unmanned vehicles are a solution to replace manual inspection. The advantages of using inspection unmanned vehicles in gas leak monitoring are: inspection unmanned vehicles can enter various complex and dangerous areas; use a variety of sensors to inspect the site, and can provide timely warnings when abnormalities are found, and human-computer interaction is convenient. At the same time, the inspection efficiency is high and the comprehensive inspection cost is low, which has obvious advantages over manual inspection.

[0004] At present, unmanned inspection vehicles are unable to independently plan the best inspection route and accurately locate gas leaks. They are not intelligent enough to adapt to increasingly complex inspection tasks and give full play to the advantages of unmanned inspection. Summary of the invention

[0005] The purpose of the present invention is to solve the problems in the prior art and to provide an unmanned intelligent inspection system for gas leaks, which can realize autonomous planning of inspections and has a high degree of intelligence, thereby helping to improve inspection efficiency and reduce costs.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An explosion-proof inspection unmanned vehicle for gas leakage monitoring, comprising:

[0008] Environmental monitoring sensor module, used to monitor the gas pipeline operating environment and pipeline gas leakage;

[0009] A gas leak locating module is used to detect gas leaks and locate gas leak points by detecting the acoustic wave signals generated when a gas pipeline leaks;

[0010] The risk assessment module is used to evaluate the factors and correlations related to the gas leakage risk in the gas pipeline inspection area, establish a system hierarchy, calculate the risk coefficient of regional gas leakage, and then evaluate the consequences and losses of gas leakage according to the gas leakage hazards in each area;

[0011] The autonomous navigation and positioning module senses the surrounding environment through multi-source sensor fusion to establish an accurate map for autonomous navigation and positioning, and conducts autonomous inspections according to the planned inspection routes;

[0012] Inspection planning module, which calculates the priority of gas pipeline inspection areas, formulates inspection plans, and plans the best inspection routes;

[0013] The monitoring and early warning module is used to record the monitored environmental information and establish a database. When abnormal environmental air indicators are detected, the gas leakage point is located and the early warning information and on-site situation records are reported to the remote monitoring station.

[0014] Furthermore, it also includes a remote interaction module for uploading the environmental data and inspection videos collected during the inspection process to the server.

[0015] Furthermore, the environmental monitoring sensor module is provided with a methane sensor, a temperature and humidity sensor, a smoke sensor, an oxygen sensor, a carbon dioxide sensor, a carbon monoxide sensor, a sulfur hexafluoride sensor, a hydrogen sulfide sensor and a dust sensor.

[0016] Furthermore, the gas leakage locating module is provided with an ultrasonic sensor array.

[0017] Furthermore, the sensor fusion module in the autonomous navigation and positioning module uses laser radar, camera, RTK and IMU to perform multi-source sensor fusion.

[0018] A patrol method of the explosion-proof patrol unmanned vehicle for gas leakage monitoring comprises:

[0019] The ultrasonic sensor array performs signal-to-noise separation on the received sound wave signals, and uses the MCSVM intelligent algorithm to distinguish between on-site noise and the sound wave signals generated by gas leaks. Combined with the sensors in the environmental monitoring module, it detects gas leaks in the gas pipeline and locates the gas leak point.

[0020] Divide the inspection areas into different areas, use the analytic hierarchy process to analyze the gas leakage risk factors in each area, assess the hazards and losses of gas leakage, formulate inspection plans, and plan inspection routes;

[0021] Multi-source sensor fusion perceives the surrounding environment, builds accurate maps to achieve autonomous navigation and positioning, and conducts autonomous inspections according to the planned inspection routes;

[0022] During the inspection, the environmental information is monitored and a database is established. When abnormal ambient air indicators are detected, the gas leak point is located, and the warning information and on-site situation records are reported to the remote monitoring station, and sound and light alarm information is generated at the same time;

[0023] Read sensor data along the gas pipeline and inside the pipeline, upload the inspection video to the server, and complete special inspection tasks through remote control.

[0024] Furthermore, the ultrasonic sensor array uses VMD variational mode decomposition and wavelet threshold denoising algorithm to separate the signal from the received sound wave signal:

[0025] Perform VMD decomposition on the acoustic wave signal to solve the correlation between the original waveform and each eigenmode component;

[0026] The components with larger correlation coefficients are retained, and the components with correlation coefficients less than the threshold are processed by wavelet threshold denoising algorithm based on the best mother wavelet;

[0027] The retained components and the denoised modal components are reconstructed to achieve signal-to-noise separation of the waveform signal.

[0028] Furthermore, the relative delay of the ultrasonic sensor array signal is calculated based on the peak detection method of the acoustic wave signal to locate the gas leakage point:

[0029] Perform endpoint detection on the acoustic wave signal, divide the waveform time domain signal into windows, and calculate the average energy and volatility of the waveform signal within the window;

[0030] Calculate the increment of average energy and volatility between windows. When the preset threshold is reached, take the zero-crossing point before the first waveform peak in the window as the endpoint of the sound wave. The energy and volatility thresholds are sampled as dynamic thresholds. The calculation method is to calculate the average energy and volatility of the waveform in a period of time before and after the current window.

[0031] The waveform peak features are extracted during the continuous segment of the sound wave. When the signals of the ultrasonic sensor array meet multiple feature matches, the waveform delay is calculated and the sound source position is solved based on the relative delay.

[0032] Furthermore, gas leakage risk factors include environmental factors, intrusion factors, design factors and accidental factors.

[0033] Furthermore, the inspection route planning method is:

[0034] Use the analytic hierarchy process to analyze the relationship between various gas leakage risk factors and establish a system hierarchy;

[0035] Construct a comparison matrix between factors in the same level relative to factors in the upper level, and calculate the weights of factors in the same level;

[0036] According to the gas pipeline operation records, combined with the pipeline operation standards, the index of each factor is obtained;

[0037] Calculate the risk factor of regional gas leakage based on the relevance of different factors to gas leakage;

[0038] Combined with the hazards of accidents caused by gas leakage in the area, the hazard coefficient of regional gas leakage is obtained;

[0039] According to the gas area hazard coefficient, formulate an inspection plan and plan the inspection route.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention provides an unmanned intelligent inspection system for gas leakage, which adopts a combination of multiple environmental monitoring sensors and ultrasonic sensor array acoustic wave positioning methods to realize gas leakage detection and locate leakage points, thereby reducing the missed detection rate; by evaluating the risk and harm of gas leakage, an inspection plan is formulated and the optimal inspection route is planned, and combined with autonomous positioning and navigation based on multi-sensor fusion, autonomous inspection can be realized without manual duty; through a remote interactive module, a gas leakage warning is issued in time and corresponding measures are taken, thereby reducing the harm of gas leakage accidents, having a high degree of intelligence, being conducive to improving inspection efficiency and reducing costs, solving the problems of heavy workload, low efficiency, missed detection, etc. in the manual inspection method of gas pipelines, and being an effective way to replace manual inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 This is a structural block diagram of the gas leak monitoring and inspection unmanned vehicle system of the present invention.

[0044] Figure 2 It is a structural block diagram of the gas leak acoustic wave positioning of the present invention.

[0045] Figure 3 This is a structural block diagram of the gas leakage risk assessment and inspection route planning of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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 is further described in detail below in conjunction with the accompanying drawings:

[0049] See also Figure 1 The present invention provides an explosion-proof patrol unmanned vehicle for gas leakage monitoring, including an environmental monitoring sensor module, a gas leakage positioning module, an autonomous navigation positioning module, a risk assessment module, a patrol planning module, a monitoring and early warning module and a remote interaction module.

[0050] Environmental monitoring sensor module, used to monitor the gas pipeline operating environment and pipeline gas leakage;

[0051] The gas leak location module detects gas leaks and locates the gas leak point by detecting the acoustic wave signal generated when a gas pipeline leaks;

[0052] The risk assessment module is used to evaluate the factors and correlations related to the gas leakage risk in the gas pipeline inspection area, establish a system hierarchy, calculate the risk coefficient of regional gas leakage, and then evaluate the consequences and losses of gas leakage according to the gas leakage hazards in each area;

[0053] The autonomous navigation and positioning module senses the surrounding environment through multi-source sensor fusion to establish an accurate map for autonomous navigation and positioning, and conducts autonomous inspections according to the planned inspection routes;

[0054] Inspection planning module, which calculates the priority of gas pipeline inspection areas, formulates inspection plans, and plans the best inspection routes;

[0055] Remote interaction module, used to upload environmental data and inspection videos collected during the inspection process to the server;

[0056] The monitoring and early warning module is used to record the monitored environmental information and establish a database. When abnormal environmental air indicators are detected, the gas leakage point is located, the early warning information and on-site situation records are reported to the remote monitoring station, and sound and light alarm information is generated at the same time.

[0057] The environmental monitoring sensors carried on the inspection unmanned vehicle include methane sensors, temperature and humidity sensors, smoke sensors, oxygen sensors, carbon dioxide sensors, carbon monoxide sensors, sulfur hexafluoride sensors, hydrogen sulfide sensors, and dust sensors. They can monitor the air indicators of the gas pipeline operating environment, pipeline gas leakage types, and leaked gas concentrations, and provide a reference for gas leakage point positioning and risk assessment.

[0058] Reference Figure 2 The gas leak location module of the inspection unmanned vehicle is equipped with an ultrasonic sensor array, which locates the gas leak point by identifying the sound wave signal generated when the gas pipeline leaks. First, the sound wave signal monitored by the ultrasonic sensor array is separated from the noise, and then the leak is identified, the sound wave delay is estimated, and the leak point location is solved.

[0059] The acoustic signal noise separation first performs VMD decomposition on the acoustic signal to obtain the intrinsic mode components of different frequency bands; then solves the correlation between the original waveform and each intrinsic mode component; retains the components with correlation coefficient greater than 0.5, and uses the wavelet threshold denoising algorithm based on the optimal mother wavelet to process the components with correlation coefficient less than the threshold.

[0060] The wavelet threshold denoising algorithm based on the best mother wavelet selects the best wavelet basis function for wavelet transform by analyzing the acoustic time domain waveforms of no leakage events and continuous leakage events; the transformed signal is processed using the threshold function to remove abnormal high-frequency coefficients; for the problem that the threshold function is discontinuous and the denoising effect of wavelet coefficients less than the threshold is not ideal, an exponential threshold estimator is used, and for wavelet coefficients less than the threshold, the adjustment factor is used as the coefficient of the threshold estimator. The modal components after denoising and the retained related components are reconstructed to achieve signal-to-noise separation of the waveform signal.

[0061] The MCSVM intelligent algorithm is used to identify the pre-processed acoustic signal, distinguish the on-site interference signal and the acoustic signal generated by the gas leak, and combine with the high-sensitivity gas sensor in the environmental monitoring module to reduce the false recognition rate of gas leaks.

[0062] After the acoustic signal is separated from the signal-to-noise and the gas leakage signal is identified, a method based on the peak detection of the acoustic signal is used to estimate the acoustic delay of the ultrasonic sensor array. This method does not require Fourier transform operations on the sound source signal and has a small amount of calculation.

[0063] The acoustic wave delay estimation first detects the endpoint of the acoustic wave signal, divides the waveform time domain signal into windows, and takes 1 / 2 overlap between windows to calculate the average energy and volatility of the waveform signal in the window, and then calculates the increment of the average energy and volatility between windows. When the predetermined threshold is reached, the zero-crossing point before the first waveform peak in the window is taken as the acoustic wave endpoint. In order to further improve the anti-noise ability of the endpoint detection method, the energy and fluctuation threshold are calculated based on the average energy and volatility of the waveform in a period of time before and after the current window. After the sound source endpoint is identified using energy and fluctuation indicators, the information frame contains three parts, namely the environmental background, the sound wave arrival stage, and the sound wave duration. The waveform peak features are extracted during the sound wave duration. When the signals of the sensor array meet multiple feature matches, the waveform delay is calculated, and the sound source position is solved based on the relative delay.

[0064] Reference Figure 3 The risk assessment module of the inspection unmanned vehicle divides the area into different areas according to the differences in the inspection areas. By analyzing the analysis factors of each area, it evaluates the hazards and losses of gas leakage, and provides a basis for the inspection plan and inspection route planning of the inspection unmanned vehicle.

[0065] The factors related to gas leakage risk can be divided into four categories according to the characteristics of each risk factor: environmental factors, intrusion factors, design factors and accidental factors. Environmental factors mainly consider the terrain structure, soil indicators and air quality of the area where the gas pipeline is located; intrusion factors mainly consider the number of human activities and the possibility and severity of damage to the fuel pipeline; design factors mainly consider the number and type of gas pipeline protection layers, system operation years and fault-tolerant redundant design; accidental factors mainly consider operating conditions, construction and maintenance operations.

[0066] Use the analytic hierarchy process to analyze the relationship between various factors in the system and establish the system hierarchy; construct a comparison matrix between factors in the same level relative to the upper level factors, and calculate the weight of each factor in the same level; evaluate according to the gas pipeline operation records and the pipeline operation standards to obtain the index of each factor; calculate the risk coefficient of regional gas leakage according to the degree of relevance of different factors to gas leakage; then, combine the accident hazards caused by gas leakage in the area to obtain the hazard coefficient of regional gas leakage; then, formulate an inspection plan and plan the inspection route according to the gas regional hazard coefficient.

[0067] The autonomous navigation and positioning module of the inspection unmanned vehicle uses laser radar, camera, RTK and IMU. Through multi-source sensor fusion, it senses the surrounding environment and establishes an accurate map to achieve autonomous navigation and positioning, and conducts autonomous inspections according to the planned inspection routes. The monitoring and early warning module monitors environmental information and establishes a database. When abnormal ambient air indicators are detected, the gas leak point is located, and the early warning information and on-site situation records are reported to the remote monitoring station, and sound and light alarm information is generated to remind other personnel on site.

[0068] The inspection unmanned vehicle reads the sensor data installed along and inside the gas pipeline through wireless communication, uploads the data and inspection video to the server, and when manual takeover is required, the administrator can remotely control the unmanned vehicle to perform special inspection tasks through information returned by sensors such as the visible light camera on the unmanned vehicle.

[0069] The explosion-proof patrol unmanned vehicle for gas leakage monitoring of the present invention is equipped with a variety of environmental monitoring sensors to monitor the operating environment of the gas pipeline and the gas leakage of the pipeline; the gas leakage positioning module is equipped with an ultrasonic sensor array to identify the sound waves generated by the gas leakage, and combines the environmental monitoring sensor to detect the concentration of the leaked gas to avoid false alarms of gas leakage and realize the positioning of the leakage point; the risk assessment module analyzes the gas leakage risk factors and calculates the risk coefficient of regional gas leakage, and formulates the inspection plan and plans the inspection route through the inspection planning module; the autonomous navigation and positioning module realizes autonomous navigation and positioning through multi-source sensor fusion, and realizes autonomous inspection through the planned route; after the gas leakage is detected, the monitoring and early warning module reports the early warning information and the on-site situation record to the remote monitoring station, and generates sound and light alarm information to remind other personnel on the scene.

[0070] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An unmanned intelligent inspection system for gas leaks, characterized in that: It includes a gas leak positioning module, a risk assessment module and an inspection planning module connected in sequence, the risk assessment module is also connected to the environmental monitoring sensor module, the environmental monitoring sensor module, the monitoring and early warning module, and the inspection planning module are connected in sequence; Environmental monitoring sensor module, used to monitor the gas pipeline operating environment and pipeline gas leakage, providing a reference for gas leakage point location and risk assessment; A gas leak locating module is used to detect gas leaks and locate gas leak points by detecting the acoustic wave signals generated when a gas pipeline leaks; The risk assessment module is used to evaluate the factors and correlations related to the gas leakage risk in the gas pipeline inspection area, establish a system hierarchy, calculate the risk coefficient of regional gas leakage, and then obtain the regional gas leakage hazard coefficient based on the gas leakage hazard situation in each area, and evaluate the consequences and losses of gas leakage; The monitoring and early warning module is used to record the monitored operating environment information and establish a database. When abnormal ambient air indicators are detected, the gas leakage point is located, the early warning information and on-site situation records are reported to the remote monitoring station, and sound and light alarm information is generated at the same time; The inspection planning module is used to formulate inspection plans and plan the optimal inspection routes by evaluating the risk factor and hazard factor of gas leakage.

2. The unmanned intelligent inspection system for gas leaks according to claim 1 is characterized in that: It also includes an autonomous navigation and positioning module connected to the inspection planning module, which is used to sense the surrounding environment through multi-source sensor fusion to establish an accurate map for autonomous navigation and positioning, and to conduct autonomous inspections according to the planned inspection routes.

3. The unmanned intelligent inspection system for gas leaks according to claim 2 is characterized in that: The autonomous navigation and positioning module includes a sensor fusion module, which is used to perform multi-source sensor fusion through lidar, camera, RTK and IMU.

4. The unmanned intelligent inspection system for gas leaks according to claim 1 is characterized in that: It also includes a remote interaction module that is respectively connected to the inspection planning module, the risk assessment module, and the monitoring and early warning module, and is used to upload the environmental data and inspection videos collected during the inspection process to the server.

5. The unmanned intelligent inspection system for gas leaks according to claim 1 is characterized in that: The environmental monitoring sensor module is installed on the inspection unmanned vehicle and includes methane sensors, temperature and humidity sensors, smoke sensors, oxygen sensors, carbon dioxide sensors, carbon monoxide sensors, sulfur hexafluoride sensors, hydrogen sulfide sensors and dust sensors.

6. The unmanned intelligent inspection system for gas leaks according to claim 1 is characterized in that: The gas leak locating module is equipped with an ultrasonic sensor array. It performs signal-to-noise separation on the acoustic wave signals monitored by the ultrasonic sensor array, and then performs leak identification, acoustic wave delay estimation and leak point location calculation.

7. The unmanned intelligent inspection system for gas leaks according to claim 6 is characterized in that: The specific method of signal-to-noise separation is: perform VMD decomposition on the acoustic wave signal to obtain the intrinsic mode components of different frequency bands, and solve the correlation between the original waveform and each intrinsic mode component; retain the components with correlation coefficients greater than the threshold, and use the wavelet threshold denoising algorithm based on the optimal mother wavelet to process the components with correlation coefficients less than the threshold; The retained components and the denoised modal components are reconstructed to achieve signal-to-noise separation of the waveform signal.

Images