Pipeline inspection method, device and equipment and storage medium

Abstract

The invention discloses a pipeline inspection method, device and equipment and a storage medium. The method comprises the following steps: receiving image information, gas information and infrared information of a pipeline collected by an unmanned aerial vehicle, and image information, gas information and infrared information around the pipeline; according to the image information, abnormal construction conditions around the pipeline are identified, and a first inspection result is generated; according to the gas information, the abnormal gas condition of the pipeline is recognized, and a second inspection result is generated; according to the infrared information, the abnormal infrared condition of the pipeline is identified, and a third inspection result is generated; and analyzing the abnormal leakage condition of the pipeline according to the inspection result. According to the invention, automatic monitoring and analysis of the abnormal condition of the pipeline can be realized, the inspection quality and the inspection efficiency are improved, and the operation risk of inspection personnel is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline inspection, and particularly to a pipeline inspection method, device, equipment and storage medium. Background Art

[0002] In petrochemical enterprises, petroleum and natural gas resources are mainly transported by pipelines. The pipelines are long and often need to cross terrain-complex areas such as swamps, deserts, mountains, forests and populated areas. Over time, some pipelines have rusted and thinned. At the same time, when these pipelines face serious natural disaster threats, illegal tapping and gas theft, and illegal occupation of pipelines by above-ground buildings, there are huge safety hazards. Once a leak occurs, it is extremely easy to cause major property losses. Therefore, it is necessary to inspect the pipelines to ensure that there is no leakage risk.

[0003] Traditional pipeline inspection methods usually take manual inspection as the main means. The inspectors patrol along the pipeline to check the pipeline body below and its surface environment. However, this manual inspection method has the following disadvantages: (1) When using the manual inspection method to detect oil and gas pipelines, the inspectors need to be equipped with a variety of inspection equipment. During regular inspections, only the area below and on the side of the pipeline can be inspected, and the situation above the pipeline cannot be viewed. At the same time, the inspectors must keep their communication tools unblocked to ensure that they can be contacted at any time. The manual inspection process is time-consuming and laborious, and the labor cost is relatively high. (2) In complex terrain areas and in the case of oil and gas leakage, there are also certain safety hazards when the inspectors patrol and inspect the pipelines. (3) Lack of electronic data recording and safety hazards. Without the support of electronic data, it is impossible to effectively supervise and track the pipelines, resulting in safety hazards and supervision loopholes. Summary of the Invention

[0004] The present invention provides a pipeline inspection method, device, equipment and storage medium to solve the technical problems of time-consuming and laborious manual inspection, safety hazards and lack of electronic data recording.

[0005] To solve the above technical problems, an embodiment of the present invention provides a pipeline inspection method, including:

[0006] Receiving inspection data collected by a drone; wherein, the inspection data includes: image information, gas information and infrared information of the pipeline, as well as image information, gas information and infrared information around the pipeline;

[0007] According to each of the image information, identifying abnormal construction situations around the pipeline, and generating a first inspection result according to the abnormal construction situations; wherein, the first inspection result includes: the distribution of engineering vehicles around the pipeline and the distribution of muck piles.

[0008] Identify the abnormal gas conditions of the pipeline based on the respective gas information, and generate a second inspection result according to the abnormal gas conditions; wherein, the second inspection result includes: gas distribution information and gas concentration information around the pipeline;

[0009] Identify the abnormal infrared conditions of the pipeline based on the respective infrared information, and generate a third inspection result according to the abnormal infrared conditions; wherein, the third inspection result includes: the highest temperature information and the lowest temperature information at the pipeline site;

[0010] Analyze the abnormal leakage conditions of the pipeline based on the first inspection result, the second inspection result, and the third inspection result.

[0011] As a preferred solution, the drone collects inspection data in the following manner:

[0012] Fly to a preset pipeline inspection point according to preset route parameters; wherein, the route parameters include: flight starting point, flight ending point, flight altitude, flight speed, waypoint actions, drone camera pitch angle, and number of shots;

[0013] During flight, collect the image information, gas information, and infrared information of the pipeline, as well as the image information, gas information, and infrared information around the pipeline by means of the on-board camera, gas sensor, and external infrared sensor respectively, and transmit the collected image information, gas information, and infrared information back in real time.

[0014] As a preferred solution, the real-time transmission of the collected image information, gas information, and infrared information includes:

[0015] Transmit the collected image information, gas information, and infrared information back in real time through a preset API interface according to the preset MQTT communication protocol.

[0016] As a preferred solution, the drone receives the route parameters in the following manner:

[0017] Receive a control signal through the API interface; wherein, the control signal is a signal based on the GB28181 extended protocol;

[0018] Parse the control signal to obtain the navigation information parameters of the drone.

[0019] As a preferred solution, the identification of abnormal construction conditions around the pipeline according to the respective image information includes:

[0020] Identify the engineering vehicle information and muck pile information around the pipeline by identifying each of the image information according to a preset abnormal construction identification algorithm; wherein, the abnormal construction identification algorithm includes: yolov5 object detection algorithm;

[0021] When any of the following situations occurs, it is determined that there is abnormal construction around the pipeline:

[0022] It is recognized that the engineering vehicle stays within the preset pipeline range, or it is recognized that the area of the muck pile within the pipeline range exceeds the preset area threshold.

[0023] As a preferred solution, the recognition of the abnormal gas situation of the pipeline according to each of the gas information includes:

[0024] Recognize each of the gas information to obtain the gas distribution information and gas concentration information around the pipeline;

[0025] Compare the gas concentration around the pipeline with the preset concentration threshold. When the gas concentration around the pipeline is greater than the concentration threshold, it is determined that the gas concentration around the pipeline is abnormal.

[0026] As a preferred solution, the gas information includes: infrared images of the pipeline and around the pipeline;

[0027] The recognition of the abnormal infrared situation of the pipeline according to each of the infrared information includes:

[0028] Recognize the temperature abnormal points in the infrared image. When the temperature corresponding to the temperature abnormal points on the pipeline is higher than the preset temperature threshold, it is determined that the temperature around the pipeline is abnormal.

[0029] On the basis of the above embodiments, another embodiment of the present invention provides a pipeline inspection device, including: an inspection data acquisition module, a construction abnormality recognition module, a gas abnormality recognition module, an infrared abnormality recognition module, and a pipeline abnormality analysis module;

[0030] The inspection data acquisition module is used to receive the inspection data collected by the drone; wherein, the inspection data includes: image information, gas information, and infrared information of the pipeline, as well as image information, gas information, and infrared information around the pipeline;

[0031] The construction abnormality recognition module is used to recognize the abnormal construction situation around the pipeline according to each of the image information, and generate a first inspection result according to the abnormal construction situation; wherein, the first inspection result includes: the distribution situation of engineering vehicles and the distribution situation of muck piles around the pipeline;

[0032] The gas abnormality recognition module is used to recognize the abnormal gas situation of the pipeline according to each of the gas information, and generate a second inspection result according to the abnormal gas situation; wherein, the second inspection result includes: the gas distribution information and gas concentration information around the pipeline;

[0033] The infrared anomaly recognition module is used to recognize the abnormal infrared conditions of the pipeline based on the infrared information, and generate a third inspection result according to the abnormal infrared conditions; wherein, the third inspection result includes: the highest temperature information and the lowest temperature information at the pipeline site;

[0034] The pipeline anomaly analysis module is used to analyze the abnormal leakage conditions of the pipeline according to the first inspection result, the second inspection result, and the third inspection result.

[0035] Based on the above embodiments, another embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the pipeline inspection method described in the above embodiments of the present invention.

[0036] Based on the above embodiments, another embodiment of the present invention provides a storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the storage medium is located to execute the pipeline inspection method described in the above embodiments of the present invention.

[0037] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0038] In the present invention, image information, gas information, and infrared information of the pipeline and its surrounding areas collected by a drone are received; the abnormal construction conditions around the pipeline are recognized according to the image information, and a first inspection result is generated according to the abnormal construction conditions; the abnormal gas conditions of the pipeline are recognized according to the gas information, and a second inspection result is generated according to the abnormal gas conditions; the abnormal infrared conditions of the pipeline are recognized according to the infrared information, and a third inspection result is generated according to the abnormal infrared conditions; the abnormal leakage conditions of the pipeline are analyzed according to the first inspection result, the second inspection result, and the third inspection result.

[0039] The present invention can use a drone to collect information about the pipeline and its surrounding areas, and then the system automatically performs anomaly detection and recognition on the inspection data collected by the drone to generate inspection results, and further analyzes the abnormal conditions of the pipeline according to the generated inspection results. By using the present invention, manual inspection of the pipeline can be avoided, automatic monitoring and analysis of pipeline abnormal conditions can be realized, the inspection quality and efficiency can be improved, and the operation risk of inspection personnel can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a schematic flowchart of a pipeline inspection method provided by an embodiment of the present invention;

[0041] Figure 2It is a schematic structural diagram of an unmanned aerial vehicle (UAV) pipeline inspection system;

[0042] Figure 3 It is a technical architecture diagram of an unmanned aerial vehicle (UAV) pipeline inspection system;

[0043] Figure 4 It is a schematic structural diagram of a YOLOv5 object detection network;

[0044] Figure 5 It is a schematic structural diagram of a pipeline inspection device provided in an embodiment of the present invention. Detailed implementation manners

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0046] Embodiment 1

[0047] Please refer to Figure 1 , which is a schematic flowchart of a pipeline inspection method provided in an embodiment of the present invention, including the following specific steps:

[0048] S1. Receive the inspection data collected by the UAV; wherein, the inspection data includes: image information, gas information, and infrared information of the pipeline, as well as image information, gas information, and infrared information around the pipeline;

[0049] Preferably, the UAV collects the inspection data in the following manner: fly to a preset pipeline inspection point according to preset route parameters; wherein, the route parameters include: flight starting point, flight ending point, flight altitude, flight speed, waypoint actions, the pitch angle of the UAV camera, and the number of shootings; during the flight, collect the image information, gas information, and infrared information of the pipeline, as well as the image information, gas information, and infrared information around the pipeline respectively according to the carried camera, gas sensor, and infrared sensor, and transmit the collected image information, gas information, and infrared information back in real time.

[0050] Preferably, the real-time transmission of the collected image information, gas information, and infrared information includes: real-time transmission of the collected image information, gas information, and infrared information through a preset API interface according to the preset MQTT communication protocol.

[0051] Preferably, the drone receives route parameters in the following manner: receiving a control signal through the API interface, where the control signal is a signal based on the GB28181 extended protocol; parsing the control signal to obtain the navigation information parameters of the drone.

[0052] Please refer to Figure 2 , which is a schematic structural diagram of the drone pipeline inspection system. The present invention designs and develops an air-ground integrated drone pipeline inspection system, and realizes the automatic pipeline inspection of the drone based on this system. The system mainly consists of the following two parts:

[0053] (1) Drone pipeline inspection hardware: a hangar, a ground station, and a drone set (hereinafter referred to as the drone) equipped with a gimbal camera and a gas sensor.

[0054] (2) Drone pipeline inspection software: including a drone cloud scheduling platform and various AI intelligent algorithms to be used below.

[0055] Through the drone pipeline inspection system, when using the drone for pipeline inspection, the drone communicates with the ground station through its equipped 5G network connection module and uses the 5G IoT card of the enterprise edge settlement for drone navigation control and real-time data transmission. The drone and its equipped infrared dual-light gimbal camera and airborne gas sensor use visible light, infrared images, and gas information to identify and detect temperature abnormal points, gas abnormal points, and construction abnormal points found during the flight.

[0056] The specific inspection and abnormal identification process is as follows:

[0057] (1) Overall system architecture

[0058] a. Technical architecture:

[0059] Please refer to Figure 3 , which is a technical architecture diagram of the drone pipeline inspection system. The air-ground integrated drone pipeline inspection system mainly completes the automatic inspection of production chemical pipelines, the fault identification of pipelines, and the real-time dynamic monitoring of the site through the combination of software and hardware such as a fully autonomous drone charging hangar, a drone equipped with a special camera or a gas detector, a computer network, and artificial intelligence.

[0060] b. Technical route:

[0061] The air-ground integrated drone pipeline inspection system uses the MQTT IoT communication protocol to realize the interaction between the cloud and the terminal, and constructs a route in the cloud and issues control instructions to the drone and the nest to complete the entire system operation process. Its main technical route is as follows:

[0062] During the operation of the pipeline inspection application, the UAV transmits the collected status information, real-time video, and sensor data to the server through the network provided by the IoT card. The control instructions of the operator on the cloud scheduling platform are finally sent to the UAV via the hangar and the ground station. In actual deployment, the ground station can be installed within a range of 5-10 meters near the hangar and is connected by twisted pair (communicating using the TCP / IP protocol, which is error-free, lossless, non-repeating, and arrives in order, and can achieve reliable transmission through mechanisms such as checksum, retransmission control, sequence number identification, sliding window, and acknowledgment). In the entire system, although the hangar and the ground station are two independent hardware entities, they are a virtual whole when communicating externally.

[0063] Among them, the MQTT (Message Queuing Telemetry Transport) is a message protocol based on the publish / subscribe paradigm under the ISO standard (ISO / IEC PRF 20922). The hangar, the ground station, and the UAV cloud scheduling platform communicate in this way. The real-time temperature information and gas information collected by the UAV are also transmitted to the UAV cloud scheduling platform deployed on the enterprise server through this protocol.

[0064] The control signaling (including the route parameter information of the UAV) conforming to the GB28181 extended protocol sent by the UAV cloud scheduling platform issues control signaling directly recognizable by the UAV through the server deployed on the UAV cloud scheduling platform, and finally reaches the UAV via the hangar and the ground station, and then the UAV executes the response action.

[0065] As a flying aerial camera, the UAV needs to transmit its own status information, as well as the control signaling for operating the UAV, the real-time video captured by the camera, and the information of the mounted high-precision gas sensor. The real-time video and gas sensor data captured by the UAV during the patrol are directly transmitted to the UAV cloud scheduling platform through the 5G signal.

[0066] Through the above technical route of the present invention, the latency problem of control signaling and video transmission can be minimized, and data interfaces can be developed according to the requirements of the enterprise platform, with good flexibility and autonomy for secondary development and upgrade optimization. At the same time, it ensures that the input and output data meet the GB28181 video and signaling requirements, providing a broad space for the maintenance and upgrade iteration of future technological progress and demand changes.

[0067] c. Integrated architecture:

[0068] In the integrated air-ground UAV pipeline inspection system, the API interfaces of the hangar, UAV, and UAV cloud scheduling platform are open, supporting the GB / T 28181-2016 national standard video protocol and taking the lead in defining UAV extended signaling, seamlessly compatible with existing systems, and meeting the requirements of application and function integration according to the integrated service mode of the enterprise data resource center. The unified identity authentication with the intelligent factory platform is completed, integrating user login information and account information, enabling seamless login and switching. The UAV inspection application is also integrated into the system menu as a sub-application of the inspection management application. Its inspection tasks are synchronized with those in the intelligent factory inspection management application, and the inspection results and alarm information can be transmitted back to the inspection management application together. In addition, the integration with the SMS platform is completed, and gas or temperature abnormality information and corresponding time and location alarm information can be sent to relevant enterprise personnel via SMS.

[0069] (2) UAV collects inspection data

[0070] Traditional UAVs are just simple passive flying vehicles without a "brain" and do not have the ability of autonomous flight and automatic task execution. Before use, the drone pilot needs to plan in advance the takeoff and landing locations, flight routes, flight distances, and battery life, etc. During the flight, all actions need to be manually controlled by the drone pilot through the remote control.

[0071] In the present invention, with the goal of "making UAVs fully unmanned", the operation control instructions that originally needed to be issued by the drone pilot in real time are stored in the system by presetting route parameters (the route parameters include: flight start point, flight end point, flight altitude, flight speed, waypoint actions, UAV camera pitch angle, number of shots, etc.), and relying on the advantages of high-speed and low-latency communication of the 5G network, the route parameters are uploaded to the UAV terminal before the UAV operation, and then during the UAV flight, its flight images and telemetry data are transmitted back to the edge computing server in real time to achieve cloud-edge collaboration (cloud computing-edge computing), realizing the functions of autonomous driving, autonomous cruising, and active obstacle avoidance of the UAV.

[0072] The UAV becomes an intelligent UAV with Internet of Things communication and decision-making capabilities by carrying an on-board edge computing module equipped with a 5G communication module to achieve autonomous operation. Based on the 5G+AI environment perception technology, a series of sensors such as cameras, ultrasonic sensors, and infrared sensors are used to perceive the surrounding environment, achieving deep integration with the physical environment, and realizing functions such as self-positioning in space, autonomous diagnosis of the fuselage operation state, active obstacle avoidance during automatic flight, and precise landing, etc., to achieve the purpose of safe flight. During the flight, various state data, sensing data of the UAV, as well as the videos and images collected during the operation can be transmitted to the integrated air-ground platform in real time through the 5G network for transfer and analysis.

[0073] The integrated air-ground UAV pipeline inspection system is developed according to the technical route of "remote scheduling - UAV autonomous flight - AI autonomous analysis", that is, the UAV cloud scheduling platform remotely schedules the UAV to fly, and the images, gas, and infrared data obtained during the UAV autonomous flight are transmitted back to the UAV scheduling platform in real time through the enterprise 5G intranet. The AI algorithm deployed on the enterprise algorithm platform retrieves the image, gas, and infrared data to identify anomalies and generate reports in real time. The UAV scheduling platform pushes data such as flight videos, inspection results, and anomaly alarms to the enterprise management platform for daily management of petrochemical pipelines.

[0074] S2. According to each of the image information, identify the abnormal construction situation around the pipeline, and generate a first inspection result according to the abnormal construction situation; wherein, the first inspection result includes: the distribution of engineering vehicles and the distribution of muck piles around the pipeline;

[0075] Preferably, the identifying the abnormal construction situation around the pipeline according to each of the image information includes: identifying each of the image information according to a preset abnormal construction identification algorithm to obtain the information of engineering vehicles and muck piles around the pipeline; wherein, the abnormal construction identification algorithm includes: the yolov5 object detection algorithm; when any of the following situations occurs, it is determined that there is an abnormal construction situation around the pipeline: it is recognized that an engineering vehicle stays within a preset pipeline range, or it is recognized that the area of the muck pile within the pipeline range exceeds a preset area threshold.

[0076] (3) The AI algorithm performs anomaly identification

[0077] The AI recognition algorithm in the present invention is based on a large number of pictures and videos stored in the database as comparison data, providing photos and videos to increase the recognition accuracy on the basis of recognition. Generally speaking, the end user needs to provide 4 first-person view videos of normal flight routes per year for data comparison.

[0078] a. Abnormal construction identification: Based on the abnormal construction identification algorithm deployed on the enterprise algorithm platform, combine the image information collected by the UAV daily with the AI algorithm to identify the engineering vehicles and muck piles around the pipeline from the image information. Then, analyze the abnormal construction situation around the pipeline according to the engineering vehicles and muck piles around the pipeline, and automatically generate a first inspection report. The first inspection report mainly includes event records of engineering vehicles and personnel gathering, and records information such as the location, time, and frequency of the event occurrence. Through the abnormal construction identification algorithm, it is possible to automatically compare and timely discover and locate abnormal pipelines and construction events around the pipeline, and notify the management personnel for handling in a timely manner.

[0079] Among them, the abnormal construction identification algorithm can be: the yolov5 object detection algorithm, please refer to Figure 4, which is a schematic structural diagram of the YOLOv5 object detection network. A drone is used to carry a dual-light pan-tilt camera. Based on the YOLOv5 object detection network, construction vehicles and muck piles are identified near the oil pipeline to monitor whether there is any construction that may damage the pipeline. In a specific embodiment, if an engineering vehicle stays within 10 meters around the pipeline, it will be determined as abnormal construction and an alarm will be triggered. If the area of the muck pile within 10 meters near the pipeline exceeds 25 square meters, it will be determined as abnormal construction and an alarm will be triggered.

[0080] The YOLOv5 is a single-stage object detection algorithm. Some new improvement ideas are added to this algorithm based on YOLOv4, which greatly improves its speed and accuracy. The specific improvements include: Mosaic data augmentation at the input end, adaptive anchor box calculation, and adaptive image scaling operation; Focus structure and CSP structure at the backbone end; SPP and FPN+PAN structures at the Neck end; loss function GIOU_Loss at the output end and DIOU_nms for predicting box screening. In addition, various improvement ideas in YOLOv5 can still be applied to other object detection algorithms. After long-term data accumulation and algorithm iteration, the detection accuracy of engineering vehicles and muck piles can reach over 90%.

[0081] S3. According to each of the gas information, identify the abnormal gas condition of the pipeline, and generate a second inspection result according to the abnormal condition; wherein, the second inspection result includes: gas distribution information and gas concentration information around the pipeline;

[0082] Preferably, the identifying the abnormal gas concentration condition of the pipeline according to each of the gas information includes: identifying each of the gas information to obtain the gas distribution information and gas concentration information around the pipeline; comparing the gas concentration around the pipeline with a preset concentration threshold, and when the gas concentration around the pipeline is greater than the concentration threshold, it is determined that the gas concentration around the pipeline is abnormal.

[0083] b. Pipeline gas anomaly identification: Based on the artificial intelligence gas detection algorithm deployed on the enterprise algorithm platform, real-time identification of abnormal gas by AI from a high-altitude perspective is realized. The gas information detected by the gas detector carried by the drone is combined with the analysis algorithm to complete visualization, and the gas distribution and abnormal gas concentration information of the pipe gallery pipeline are detected in real time, and it is compared with the preset highest threshold for calculation. According to the comparison result, the abnormal gas concentration condition of the pipeline is analyzed. Then, according to the abnormal gas concentration condition of the pipeline, a second inspection report with key analysis results is automatically generated; wherein, the second inspection report mainly describes the location and time information of this inspection, and presents the gas data collected in this inspection in the form of a table in the report.

[0084] S4. Identify the abnormal infrared conditions of the pipeline based on each of the infrared information, and generate a third inspection result according to the abnormal infrared conditions; wherein, the third inspection result includes: the highest temperature information and the lowest temperature information at the pipeline site.

[0085] Preferably, the gas information includes: infrared images of the pipeline and its surrounding area; the identifying the abnormal infrared conditions of the pipeline based on each of the infrared information includes: identifying the temperature abnormal points in the infrared images, and when the temperature corresponding to the temperature abnormal point on the pipeline is higher than a preset temperature threshold, it is determined that the temperature around the pipeline is abnormal.

[0086] c. Pipeline infrared anomaly identification: Based on the pipeline infrared anomaly identification algorithm deployed on the enterprise algorithm platform, realize real-time pipeline infrared AI identification from an aerial perspective.

[0087] Combine the pipeline infrared images captured by the infrared dual-light pan-tilt camera with the infrared anomaly identification algorithm to identify the temperature abnormal points in the infrared images, and analyze the abnormal infrared conditions of the pipeline by comparing the temperature abnormal points in the infrared images. In a specific embodiment, if the temperature measured on the pipeline is higher than the set threshold of 80 degrees Celsius, it is determined that the temperature is abnormal and an alarm is triggered. Then, a third inspection report is automatically generated according to the abnormal infrared conditions; wherein, the third inspection report mainly includes: event records of the highest and lowest temperatures in the picture, and information such as the location and time when the event occurred.

[0088] Through the pipeline infrared anomaly identification algorithm, it is possible to detect and identify the pipeline infrared anomaly information in real time, discover the pipeline infrared anomaly situation in time, quickly locate the pipeline with abnormal temperature, analyze whether the pipeline leaks, and notify relevant personnel for handling.

[0089] In the pipeline infrared anomaly identification algorithm, through semantic segmentation technology, the edge of the pipeline area and the background area in the picture is accurately segmented, the RGB pixel values of the non-pipeline area are set to 0, and the temperature abnormal points are searched in the segmented pipeline area. Specifically: Since the pixel points of different temperatures in the picture are composed of the components corresponding to the pixel values of each point in the RGB three channels, we use a 3*3 temperature conversion matrix to traverse the image with a step size of 1, calculate the temperature value of each 9-point area, and obtain a new numerical picture with temperature after traversing the image. Search for the point with the largest numerical value in the pipeline area, which is the highest temperature point of the pipeline, record the coordinate position of this point in the image, and then compare the temperature value of this point with the set alarm threshold. If it is greater than the alarm threshold, an alarm is issued, indicating that there is a leak at this point, and relevant personnel are notified for handling.

[0090] S5. Analyze the abnormal leakage situation of the pipeline according to the first inspection result, the second inspection result, and the third inspection result.

[0091] The above abnormal construction, pipeline infrared and gas identification can all share data, integrate with the enterprise data resource center, and the analysis results can be queried on the UAV dispatching platform. Relevant personnel can analyze the abnormal leakage situation of the pipeline according to the inspection results and take corresponding measures in time when pipeline leakage occurs.

[0092] As can be seen, the present invention provides a pipeline inspection method, and the following beneficial effects can be achieved through the present invention:

[0093] (1) Improve operation efficiency: The infrared sensor is very sensitive to heat sources and can almost immediately detect temperature changes. By using a UAV equipped with an infrared sensor for UAV inspection, the temperature of an object can be measured without having to go to the pipeline site and come into contact with the object, which can not only ensure the measurement accuracy, improve operation efficiency, but also ensure the safety of users. It has extremely high application value in temperature anomalies, fire warnings, and non-destructive testing during pipeline inspections.

[0094] (2) Quickly locate abnormal situations around the pipeline: During manual inspection, the overall environment around the pipeline cannot be observed, while the UAV inspection has a wide viewing angle and fast positioning. Using AI algorithms can quickly identify abnormal construction, abnormal vehicles and personnel situations around, and real-time transmit enterprise alarms back, making up for the deficiencies of manual inspection.

[0095] (3) Improve the response time to abnormal gas conditions: By using a UAV equipped with a gas sensor for UAV gas detection inspection, the accuracy of the gas sensor in detecting gas concentration can be as high as 90%. The gas sensor can automatically detect gas concentration, avoid harm to the human body caused by excessive gas concentration, and has self-diagnosis and fault detection functions, which can ensure the reliability and stability of the sensor. The sensor is connected to the UAV and does not require complex operation steps, which is convenient and easy to understand.

[0096] (4) Automation and real-time performance: With the help of the high-speed transmission of the enterprise 5G network and the organic combination of the hangar and high-performance UAVs, real-time operation, cruising and observation over an infinite distance can be achieved. Through 4G / 5G network-connected UAV technology, the data transmission delay can be short, breaking through the limitations of the position, ability, response time, etc. of the UAV operator, changing the traditional UAV operation mode that is difficult to operate continuously at a high frequency, and greatly releasing the operation ability of the UAV.

[0097] Embodiment 2

[0098] Please refer to Figure 5 , which is a schematic structural diagram of a pipeline inspection device provided by an embodiment of the present invention. The device includes: an inspection data acquisition module, a construction anomaly identification module, a gas anomaly identification module, an infrared anomaly identification module, and a pipeline anomaly analysis module;

[0099] The inspection data acquisition module is used to receive the inspection data collected by the drone; among them, the inspection data includes: image information, gas information, and infrared information of the pipeline, as well as image information, gas information, and infrared information around the pipeline;

[0100] The construction anomaly identification module is used to identify the abnormal construction conditions around the pipeline according to each piece of the image information, and generate a first inspection result according to the abnormal construction conditions; among them, the first inspection result includes: the distribution of engineering vehicles and the distribution of muck piles around the pipeline;

[0101] The gas anomaly identification module is used to identify the abnormal gas conditions of the pipeline according to each piece of the gas information, and generate a second inspection result according to the abnormal gas conditions; among them, the second inspection result includes: the gas distribution information and the gas concentration information around the pipeline;

[0102] The infrared anomaly identification module is used to identify the abnormal infrared conditions of the pipeline according to each piece of the infrared information, and generate a third inspection result according to the abnormal infrared conditions; among them, the third inspection result includes: the highest temperature information and the lowest temperature information at the pipeline site;

[0103] The pipeline anomaly analysis module is used to analyze the abnormal leakage conditions of the pipeline according to the first inspection result, the second inspection result, and the third inspection result.

[0104] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0105] Those skilled in the art can clearly understand that for the convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the foregoing method embodiments, and will not be described in detail here.

[0106] Embodiment III

[0107] Accordingly, an embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the pipeline inspection method described in the above-mentioned embodiment of the invention is implemented.

[0108] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The device may include, but is not limited to, a processor and a memory.

[0109] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the device, and connects various parts of the entire device through various interfaces and lines.

[0110] Embodiment 4

[0111] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program. When the computer program runs, the device where the storage medium is located is controlled to execute the pipeline inspection method described in the above-mentioned embodiment of the invention.

[0112] The memory may be used to store the computer program. By running or executing the computer program stored in the memory and calling the data stored in the memory, various functions of the device are realized. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function, etc.; the data storage area may store data created according to the use of the mobile phone, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a FlashCard, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0113] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0114] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications are also regarded as the protection scope of the present invention.

Claims

1. A pipeline inspection method, characterized in that, it includes: Receiving the inspection data collected by the drone; wherein, the inspection data includes: image information, gas information and infrared information of the pipeline, as well as image information, gas information and infrared information around the pipeline; According to each of the image information, identifying the abnormal construction situation around the pipeline, and generating a first inspection result according to the abnormal construction situation; wherein, the first inspection result includes: the distribution of engineering vehicles and the distribution of muck piles around the pipeline; According to each of the gas information, identifying the abnormal gas situation of the pipeline, and generating a second inspection result according to the abnormal gas situation; wherein, the second inspection result includes: the gas distribution information and gas concentration information around the pipeline; According to each of the infrared information, identifying the abnormal infrared situation of the pipeline, and generating a third inspection result according to the abnormal infrared situation; wherein, the third inspection result includes: the highest temperature information and the lowest temperature information at the pipeline site; Analyzing the abnormal leakage situation of the pipeline according to the first inspection result, the second inspection result and the third inspection result.

2. The pipeline inspection method according to claim 1, characterized in that, The drone collects inspection data in the following manner: Fly to a preset pipeline inspection point according to preset route parameters; wherein, the route parameters include: flight starting point, flight ending point, flight altitude, flight speed, waypoint actions, drone camera pitch angle, and number of shots; During the flight, according to the on-board camera, gas sensor and external red sensor, respectively collect the image information, gas information and infrared information of the pipeline, as well as the image information, gas information and infrared information around the pipeline, and transmit the collected image information, gas information and infrared information back in real time.

3. The pipeline inspection method according to claim 2, characterized in that, The real-time transmission of the collected image information, gas information and infrared information includes: According to the preset MQTT communication protocol, the collected image information, gas information and infrared information are transmitted back in real time through a preset API interface.

4. The pipeline inspection method according to claim 3, characterized in that, The drone receives the route parameters in the following manner: Receive a control signal through the API interface; wherein, the control signal is a signal based on the GB28181 extended protocol; Parse the control signal to obtain the navigation information parameters of the drone.

5. The pipeline inspection method according to claim 1, characterized in that, The identifying the abnormal construction situation around the pipeline according to each of the image information includes: Identifying each of the image information according to a preset abnormal construction identification algorithm, and identifying the engineering vehicle information and muck pile information around the pipeline; wherein, the abnormal construction identification algorithm includes: yolov5 target detection algorithm; When any of the following situations occurs, it is determined that there is an abnormal construction situation around the pipeline: It is recognized that the engineering vehicle stays within the preset pipeline range, or it is recognized that the area of the muck pile within the pipeline range exceeds the preset area threshold.

6. The pipeline inspection method according to claim 1, characterized in that, identifying the abnormal gas conditions of the pipeline according to the respective gas information includes: identifying the respective gas information to obtain the gas distribution information and gas concentration information around the pipeline; comparing the gas concentration around the pipeline with a preset concentration threshold, and when the gas concentration around the pipeline is greater than the concentration threshold, it is determined that the gas concentration around the pipeline is abnormal.

7. The pipeline inspection method according to claim 1, characterized in that, the gas information includes: infrared images of the pipeline and around the pipeline; identifying the abnormal infrared conditions of the pipeline according to the respective infrared information includes: identifying the temperature abnormal points in the infrared image, and when the temperature corresponding to the temperature abnormal points on the pipeline is higher than a preset temperature threshold, it is determined that the temperature around the pipeline is abnormal.

8. A pipeline inspection device, characterized in that, comprising: an inspection data acquisition module, a construction abnormality identification module, a gas abnormality identification module, an infrared abnormality identification module, and a pipeline abnormality analysis module; the inspection data acquisition module is configured to receive the inspection data collected by the drone; wherein, the inspection data includes: image information, gas information, and infrared information of the pipeline, as well as image information, gas information, and infrared information around the pipeline; the construction abnormality identification module is configured to identify the abnormal construction conditions around the pipeline according to the respective image information, and generate a first inspection result according to the abnormal construction conditions; wherein, the first inspection result includes: the distribution of engineering vehicles and the distribution of muck piles around the pipeline; the gas abnormality identification module is configured to identify the abnormal gas conditions of the pipeline according to the respective gas information, and generate a second inspection result according to the abnormal gas conditions; wherein, the second inspection result includes: the gas distribution information and gas concentration information around the pipeline; the infrared abnormality identification module is configured to identify the abnormal infrared conditions of the pipeline according to the respective infrared information, and generate a third inspection result according to the abnormal infrared conditions; wherein, the third inspection result includes: the highest temperature information and the lowest temperature information at the pipeline site; the pipeline abnormality analysis module is configured to analyze the abnormal leakage conditions of the pipeline according to the first inspection result, the second inspection result, and the third inspection result.

9. An electronic device, characterized in that, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the pipeline inspection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, the storage medium includes a stored computer program, wherein, when the computer program runs, it controls the device where the storage medium is located to execute the pipeline inspection method according to any one of claims 1 to 7.

Images