Unmanned aerial vehicle pipeline inspection risk intelligent identification method and edge protection calculation system

Abstract

The invention relates to the technical field of unmanned aerial vehicle pipeline inspection, in particular to an unmanned aerial vehicle pipeline inspection risk intelligent recognition method and an edge protection calculation system. The technical problem is that an existing unmanned aerial vehicle pipeline inspection risk intelligent identification method is difficult to clearly observe the surrounding situation of a pipeline at night or in an environment with insufficient light, so that potential risk points and abnormities are difficult to find in time; according to the technical scheme, the unmanned aerial vehicle pipeline inspection risk intelligent identification method and the edge protection calculation system comprise an unmanned aerial vehicle inspection night risk identification and anomaly detection method; compared with a traditional unmanned aerial vehicle pipeline inspection risk intelligent identification method, the situation around the pipeline is difficult to clearly observe at night or in an environment with insufficient light, so that potential risk points and abnormities are difficult to find in time; according to the unmanned aerial vehicle pipeline inspection risk intelligent identification method, the image acquired by the unmanned aerial vehicle can be automatically analyzed through an image processing algorithm, and potential risk points and abnormities can be identified more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle pipeline inspection, and in particular to an intelligent risk identification method and an edge protection computing system for unmanned aerial vehicle pipeline inspection. Background Art

[0002] In the scenario of drone pipeline inspection, drones play a vital role. They need to undertake a variety of key tasks, such as collecting data with load-bearing inspection equipment and using high-definition cameras to take pictures to obtain detailed conditions of the pipeline.

[0003] The existing UAV pipeline inspection risk intelligence method lacks effective night vision function at night or in low-light conditions, which greatly limits its field of view and makes it difficult to clearly observe the surrounding conditions of the pipeline, resulting in potential risk points and anomalies being difficult to detect in a timely manner. At the same time, due to poor visibility at night, the UAV may need to make multiple round trips or extend the inspection time to confirm abnormal situations, reducing the real-time and efficiency of the inspection.

[0004] In view of the problem that the existing UAV pipeline inspection risk intelligence method lacks effective night vision function and makes it difficult to clearly observe the situation around the pipeline, resulting in potential risk points and anomalies being difficult to be discovered in time, the UAV pipeline inspection risk intelligence method can automatically analyze the images collected by the drone through image processing algorithms, enhance image details through algorithm processing, improve detection accuracy at night or in low light environments, more accurately identify potential risk points and anomalies, reduce reliance on manual judgment, reduce labor costs, and also avoid misjudgment or missed judgments that may be caused by human factors. Summary of the invention

[0005] In order to overcome the risk of existing UAV pipeline inspection intelligence methods at night or in low-light environments, due to the lack of effective night vision function, its field of view is greatly limited, making it difficult to clearly observe the surrounding conditions of the pipeline, resulting in potential risk points and abnormalities being difficult to be discovered in time. At the same time, due to poor visibility at night, the UAV may need to make multiple round trips or extend the inspection time to confirm abnormal situations, reducing the real-time and efficiency of the inspection.

[0006] The technical solution of the present invention is: a risk intelligence method for unmanned aerial vehicle pipeline inspection, comprising the following steps:

[0007] S11: First, deploy the drone night vision inspection system to ensure safe operation of drones in low-light environments;

[0008] S12: Plan the intelligent inspection path and intelligently plan the drone inspection route;

[0009] S13: Identify and detect risks and anomalies that occur during drone inspections;

[0010] S14: The data collected during the drone inspection operation is transmitted to the master control terminal in real time for feedback;

[0011] S15: Perform regular maintenance and optimization of equipment systems.

[0012] Preferably, when deploying the UAV night vision inspection system, the following steps are included:

[0013] S21: According to the characteristics of the inspection area, select a UAV platform with good flight stability and load-bearing capacity;

[0014] S22: Install night vision equipment such as infrared thermal imagers on the drone to ensure clear observation of the pipeline and surrounding environment at night or in low light conditions;

[0015] S23: Equipped with an efficient solar battery system, it provides a continuous power supply for the drone, ensuring long-term and stable execution of inspection tasks.

[0016] Preferably, when planning the intelligent inspection path, the following method is included:

[0017] S31: Use GIS to collect map data of the inspection area, including information such as terrain and pipeline layout;

[0018] S32: Based on map data and drone performance parameters, the algorithm automatically plans the optimal inspection route to ensure full coverage and maximum efficiency;

[0019] S33: During the inspection process, the inspection route is dynamically adjusted based on the real-time data sent back by the drone, such as battery level, flight status, etc.

[0020] Preferably, the following steps are included when performing nighttime risk identification and anomaly detection on drone inspections:

[0021] S41: Start the night vision equipment of the drone to collect infrared thermal imaging data of the pipeline and its surrounding environment;

[0022] S42: Analyze the collected images using image processing algorithms to identify potential risks such as abnormal hot spots and leakage signs;

[0023] S43: Once an abnormality is detected, an alarm message is immediately sent to the ground control center via wireless communication, along with detailed information such as the abnormal location and image.

[0024] Preferably, through real-time monitoring and data analysis, including analysis of data obtained by airborne night vision equipment, the early warning capability of potential dangers is enhanced, and time is gained for taking countermeasures in advance. At night, airborne night vision equipment can detect possible danger signals earlier, providing a valuable time window for taking timely preventive measures.

[0025] Preferably, when remotely transmitting and processing data in real time, the following steps are included:

[0026] S51: During the inspection process, the drone transmits the collected data to the ground control center in real time;

[0027] S52: After receiving the data, the ground control center uses advanced data processing software and algorithms to quickly analyze and generate inspection reports;

[0028] S53: Feedback the analysis results and inspection reports to relevant personnel so that timely response measures can be taken.

[0029] As a preference, the following aspects are included when maintaining and optimizing the system:

[0030] A11: Real-time monitoring of the operating status of the drone and solar battery system to ensure stable operation of the system;

[0031] A12: Regularly evaluate the effectiveness of drone inspections, including inspection coverage, anomaly recognition accuracy, and other indicators;

[0032] A13: Based on the evaluation results and actual application feedback, optimize and adjust the system configuration, inspection path, image processing algorithm, etc. to improve inspection efficiency and accuracy.

[0033] Edge protection computing system, including:

[0034] Data collection module: used to collect the data required for drone inspection in real time;

[0035] Data processing and analysis module: used to perform real-time analysis on the drone inspection data collected by the data acquisition module;

[0036] Decision making and execution module: used to make decisions based on the data processing and analysis module.

[0037] Preferably, the data acquisition module includes multiple sets of high-definition cameras and infrared thermal imagers, which are used to collect data on the pipeline and its surrounding environment in real time through various sensors carried by the drone, providing a basis for subsequent risk identification and analysis.

[0038] Preferably, the various sensors carried by the drone, including airborne night vision equipment, can obtain real-time and accurate data on the temperature, pressure, vibration and other parameters of the pipeline during the day and night, as well as abnormal conditions such as cracks and corrosion. Especially at night, the airborne night vision equipment can keenly capture subtle changes that are difficult for conventional sensors to detect, greatly improving the timeliness and accuracy of monitoring.

[0039] Preferably, the data processing and analysis module is used to receive the raw data from the data acquisition module, and use image recognition, temperature analysis, machine learning and other algorithms to process and analyze the data, so as to quickly identify potential risks around the pipeline, such as leakage points, abnormal heating areas, etc. At the same time, the data processing and analysis module is also responsible for organizing the analysis results into an easy-to-understand form to provide support for subsequent decision-making.

[0040] Preferably, the decision-making and execution module is used to formulate corresponding processing strategies or early warning measures based on the output results of the data processing and analysis module. When a pipeline leak is found, an alarm message can be automatically sent to the ground control center, or the emergency response program of the drone can be started for a more detailed inspection. At the same time, the decision-making and execution module is also responsible for communicating with the ground control center, receiving and executing instructions from the control center.

[0041] Beneficial effects of the present invention:

[0042] 1. Compared with the traditional UAV pipeline inspection risk intelligence method, at night or in low-light environments, due to the lack of effective night vision function, its field of view is greatly limited, making it difficult to clearly observe the surrounding conditions of the pipeline, resulting in potential risk points and abnormalities being difficult to be discovered in time. At the same time, due to poor visibility at night, the UAV may need to make multiple round trips or extend the inspection time to confirm abnormal conditions, reducing the real-time and efficiency of the inspection. The UAV pipeline inspection risk intelligence method can automatically analyze the images collected by the UAV through image processing algorithms, enhance image details through algorithm processing, improve detection accuracy at night or in low-light environments, more accurately identify potential risk points and abnormalities, reduce dependence on manual judgment, reduce labor costs, and also avoid misjudgments or missed judgments that may be caused by human factors;

[0043] 2. Through real-time monitoring and data analysis, including analysis of data obtained by airborne night vision equipment, the early warning capability of potential dangers is enhanced, and time is gained for taking countermeasures in advance. Airborne night vision equipment can detect possible danger signals earlier at night, providing a valuable time window for taking preventive measures in a timely manner;

[0044] 3. The various sensors carried by drones, including airborne night vision equipment, can obtain real-time and accurate information on pipeline parameters such as temperature, pressure, vibration, and abnormal conditions such as cracks and corrosion during the day and night. Especially at night, airborne night vision equipment can keenly capture subtle changes that are difficult for conventional sensors to detect, greatly improving the timeliness and accuracy of monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 What is shown is a schematic diagram of the workflow of the UAV pipeline inspection risk intelligence method of the present invention;

[0046] Figure 2 What is shown is a schematic diagram of the deployment workflow of the drone night vision inspection system of the drone pipeline inspection risk intelligence method of the present invention;

[0047] Figure 3 Shown is a schematic diagram of the workflow of drone pipeline inspection risk intelligence method, drone inspection night risk identification and anomaly detection of the present invention. DETAILED DESCRIPTION

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] See also Figure 1-3 The present invention provides an embodiment: a risk intelligence method for unmanned aerial vehicle pipeline inspection, comprising the following steps:

[0050] S11: First, deploy the drone night vision inspection system to ensure safe operation of drones in low-light environments;

[0051] S12: Plan the intelligent inspection path and intelligently plan the drone inspection route;

[0052] S13: Identify and detect risks and anomalies that occur during drone inspections;

[0053] S14: The data collected during the drone inspection operation is transmitted to the master control terminal in real time for feedback;

[0054] S15: Perform regular maintenance and optimization of equipment systems.

[0055] Preferably, when deploying the UAV night vision inspection system, the following steps are included:

[0056] S21: According to the characteristics of the inspection area, select a UAV platform with good flight stability and load-bearing capacity;

[0057] S22: Install night vision equipment such as infrared thermal imagers on the drone to ensure clear observation of the pipeline and surrounding environment at night or in low light conditions;

[0058] S23: Equipped with an efficient solar battery system, it provides a continuous power supply for the drone, ensuring long-term and stable execution of inspection tasks.

[0059] Preferably, when planning the intelligent inspection path, the following method is included:

[0060] S31: Use GIS to collect map data of the inspection area, including information such as terrain and pipeline layout;

[0061] S32: Based on map data and drone performance parameters, the algorithm automatically plans the optimal inspection route to ensure full coverage and maximum efficiency;

[0062] S33: During the inspection process, the inspection route is dynamically adjusted based on the real-time data sent back by the drone, such as battery level, flight status, etc.

[0063] Preferably, the following steps are included when performing nighttime risk identification and anomaly detection on drone inspections:

[0064] S41: Start the night vision equipment of the drone to collect infrared thermal imaging data of the pipeline and its surrounding environment;

[0065] S42: Analyze the collected images using image processing algorithms to identify potential risks such as abnormal hot spots and leakage signs;

[0066] S43: Once an abnormality is detected, an alarm message is immediately sent to the ground control center via wireless communication, along with detailed information such as the abnormal location and image.

[0067] Preferably, through real-time monitoring and data analysis, including analysis of data obtained by airborne night vision equipment, the early warning capability of potential dangers is enhanced, and time is gained for taking countermeasures in advance. At night, airborne night vision equipment can detect possible danger signals earlier, providing a valuable time window for taking timely preventive measures.

[0068] Preferably, when remotely transmitting and processing data in real time, the following steps are included:

[0069] S51: During the inspection process, the drone transmits the collected data to the ground control center in real time;

[0070] S52: After receiving the data, the ground control center uses advanced data processing software and algorithms to quickly analyze and generate inspection reports;

[0071] S53: Feedback the analysis results and inspection reports to relevant personnel so that timely response measures can be taken.

[0072] As a preference, the following aspects are included when maintaining and optimizing the system:

[0073] A11: Real-time monitoring of the operating status of the drone and solar battery system to ensure stable operation of the system;

[0074] A12: Regularly evaluate the effectiveness of drone inspections, including inspection coverage, anomaly recognition accuracy, and other indicators;

[0075] A13: Based on the evaluation results and actual application feedback, optimize and adjust the system configuration, inspection path, image processing algorithm, etc. to improve inspection efficiency and accuracy.

[0076] Edge protection computing system, including:

[0077] Data collection module: used to collect the data required for drone inspection in real time;

[0078] Data processing and analysis module: used to perform real-time analysis on the drone inspection data collected by the data acquisition module;

[0079] Decision making and execution module: used to make decisions based on the data processing and analysis module.

[0080] Preferably, the data acquisition module includes multiple sets of high-definition cameras and infrared thermal imagers, which are used to collect data on the pipeline and its surrounding environment in real time through various sensors carried by the drone, providing a basis for subsequent risk identification and analysis.

[0081] Preferably, the various sensors carried by the drone, including airborne night vision equipment, can obtain real-time and accurate data on the temperature, pressure, vibration and other parameters of the pipeline during the day and night, as well as abnormal conditions such as cracks and corrosion. Especially at night, the airborne night vision equipment can keenly capture subtle changes that are difficult for conventional sensors to detect, greatly improving the timeliness and accuracy of monitoring.

[0082] Preferably, the data processing and analysis module is used to receive the raw data from the data acquisition module, and use image recognition, temperature analysis, machine learning and other algorithms to process and analyze the data, so as to quickly identify potential risks around the pipeline, such as leakage points, abnormal heating areas, etc. At the same time, the data processing and analysis module is also responsible for organizing the analysis results into an easy-to-understand form to provide support for subsequent decision-making.

[0083] Preferably, the decision-making and execution module is used to formulate corresponding processing strategies or early warning measures based on the output results of the data processing and analysis module. When a pipeline leak is found, an alarm message can be automatically sent to the ground control center, or the emergency response program of the drone can be started for a more detailed inspection. At the same time, the decision-making and execution module is also responsible for communicating with the ground control center, receiving and executing instructions from the control center.

[0084] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. Unmanned aerial vehicle pipeline inspection risk intelligence method; its characteristics are: The following steps are included: S11: First, deploy the drone night vision inspection system to ensure safe operation of drones in low-light environments; S12: Plan the intelligent inspection path and intelligently plan the drone inspection route; S13: Identify and detect risks and anomalies that occur during drone inspections; S14: The data collected during the drone inspection operation is transmitted to the master control terminal in real time for feedback; S15: Perform regular maintenance and optimization of equipment systems.

2. The UAV pipeline inspection risk intelligence method according to claim 1 is characterized by: When deploying the drone night vision inspection system, the following steps are included: S21: According to the characteristics of the inspection area, select a UAV platform with good flight stability and load-bearing capacity; S22: Install night vision equipment such as infrared thermal imagers on the drone to ensure clear observation of the pipeline and surrounding environment at night or in low light conditions; S23: Equipped with an efficient solar battery system, it provides a continuous power supply for the drone, ensuring long-term and stable execution of inspection tasks.

3. The risk intelligence method for pipeline inspection by unmanned aerial vehicle according to claim 2 is characterized by: When planning the intelligent inspection path, the following methods are included: S31: Use GIS to collect map data of the inspection area, including information such as terrain and pipeline layout; S32: Based on map data and drone performance parameters, the algorithm automatically plans the optimal inspection route to ensure full coverage and maximum efficiency; S33: During the inspection process, the inspection route is dynamically adjusted based on the real-time data sent back by the drone, such as battery level, flight status, etc.

4. The risk intelligence method for pipeline inspection by unmanned aerial vehicle according to claim 3 is characterized by: When performing nighttime risk identification and anomaly detection on drone inspections, the following steps are included: S41: Start the night vision equipment of the drone to collect infrared thermal imaging data of the pipeline and its surrounding environment; S42: Analyze the collected images using image processing algorithms to identify potential risks such as abnormal hot spots and leakage signs; S43: Once an abnormality is detected, an alarm message is immediately sent to the ground control center via wireless communication, along with detailed information such as the abnormal location and image.

5. The risk intelligence method for pipeline inspection by unmanned aerial vehicle according to claim 4 is characterized by: When data is transmitted remotely and processed in real time, the following steps are included: S51: During the inspection process, the drone transmits the collected data to the ground control center in real time; S52: After receiving the data, the ground control center uses advanced data processing software and algorithms to quickly analyze and generate inspection reports; S53: Feedback the analysis results and inspection reports to relevant personnel so that timely response measures can be taken.

6. The risk intelligence method for pipeline inspection by drone according to claim 5 is characterized by: When maintaining and optimizing the system, the following aspects are included: A11: Real-time monitoring of the operating status of the drone and solar battery system to ensure stable operation of the system; A12: Regularly evaluate the effectiveness of drone inspections, including inspection coverage, anomaly recognition accuracy, and other indicators; A13: Based on the evaluation results and actual application feedback, optimize and adjust the system configuration, inspection path, image processing algorithm, etc. to improve inspection efficiency and accuracy.

7. An edge protection computing system, characterized in that: Included are: Data collection module: used to collect the data required for drone inspection in real time; Data processing and analysis module: used to perform real-time analysis on the drone inspection data collected by the data acquisition module; Decision making and execution module: used to make decisions based on the data processing and analysis module.

8. The edge protection computing system according to claim 7, characterized in that: The data acquisition module includes multiple sets of high-definition cameras and infrared thermal imagers, which are used to collect real-time data on the pipeline and its surrounding environment through various sensors carried by drones, providing a basis for subsequent risk identification and analysis.

9. The edge protection computing system according to claim 8, characterized in that: The data processing and analysis module is used to receive the raw data from the data acquisition module, and use image recognition, temperature analysis, machine learning and other algorithms to process and analyze the data in order to quickly identify potential risks around the pipeline, such as leakage points, abnormal heating areas, etc. At the same time, the data processing and analysis module is also responsible for organizing the analysis results into an easy-to-understand form to provide support for subsequent decision-making.

10. The edge protection computing system according to claim 9, characterized in that: The decision-making and execution module is used to formulate corresponding processing strategies or early warning measures based on the output results of the data processing and analysis module. When a pipeline leak is found, it can automatically send an alarm message to the ground control center, or start the emergency response program of the drone for a more detailed inspection. At the same time, the decision-making and execution module is also responsible for communicating with the ground control center, receiving and executing instructions from the control center.

Images