A method, system, device and storage medium for identifying oil and gas pipeline leakage by unmanned aerial vehicle integrating gas sensor and acoustic camera

Abstract

The present invention proposes a method for identifying oil and gas pipeline leakage using a drone that integrates a gas sensor and an acoustic camera. The drone is equipped with a gas sensor and an acoustic camera to collect information, and the flight path of the drone is planned. The drone flies along the planned path, and the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and the acoustic camera are analyzed and processed, and the leakage rate is calculated through an algorithm, thereby improving the accuracy and reliability of detection.

Description

Technical Field

[0001] The present invention relates to oil and gas pipeline leakage detection, and in particular to an unmanned aerial vehicle oil and gas pipeline leakage identification method, system, device and storage medium integrating a gas sensor and an acoustic camera. Background Art

[0002] Traditional methods for detecting oil and gas pipeline leaks include manual inspections, ground vehicle inspections, and fixed sensor monitoring. These methods have problems such as low efficiency, high cost, and difficulty in covering remote areas. In recent years, with the development of drone technology, the use of drones for oil and gas pipeline inspections has become a new trend. However, existing drone inspection methods often rely on only a single sensor, such as using only a gas sensor or only an acoustic camera, resulting in low detection accuracy and efficiency. Summary of the invention

[0003] The purpose of the present invention is to solve the problem of low leakage detection accuracy in the above-mentioned prior art, and to provide a UAV oil and gas pipeline leakage identification method integrating gas sensors and acoustic cameras to improve the accuracy, reliability and efficiency of leakage detection.

[0004] The present invention is achieved through the following technical solutions:

[0005] The present invention provides a method for identifying oil and gas pipeline leakage using an unmanned aerial vehicle (UAV) by integrating a gas sensor and an acoustic camera, comprising the following steps:

[0006] S1: UAV configuration: The drone is equipped with a gas sensor and an acoustic camera. The gas sensor is used to detect specific gases, and the acoustic camera is used to capture ultrasonic signals.

[0007] S2: Automatic flight path planning: Based on GIS data and the layout of oil and gas pipelines, the flight path of the drone is planned to ensure that all areas that need to be inspected are covered;

[0008] S3: Data collection and processing: The drone flies along the planned path, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and acoustic camera are analyzed and processed to calculate the estimated leakage rate.

[0009] Furthermore, the specific gases include: hydrogen sulfide, methane, ethane, ammonia, and carbon monoxide.

[0010] Furthermore, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures the ultrasonic signal. Based on the data collected by the gas sensor and the acoustic camera, the estimated leakage rate is calculated, including:

[0011] Control the gas sensor to detect the content of specific gas in the environment. If it exceeds the preset threshold, control the acoustic camera to collect ultrasonic signals, form an acoustic image, and obtain the geographical location information of the ultrasonic signal;

[0012] The acoustic image is input into the trained neural network model, and the model outputs a leak rate estimate.

[0013] Furthermore, the acoustic image is input into the trained neural network model, and the model outputs the estimated leakage rate including:

[0014] The acoustic image is input into a sequentially connected convolution module CBS, a feature analysis module FAM, a first CBM module, a second CBM module, a third CBM module, and a fourth CBM module. The outputs of the first, second, third, and fourth CBM modules are recorded as features F1, F2, F3, and F4. The features F1, F2, F3, and F4 are respectively input into the convolution module CBS to obtain features Fc1, Fc2, Fc3, and Fc4. The Fc4 is upsampled to obtain Fu4. Fu4 and Fc3 are fused through a feature fusion module FFM and then upsampled to obtain feature Fu3. Fu3 and Fc2 are fused through a feature fusion module FFM and then upsampled to obtain feature Fu2. Fu2 and Fc1 are fused through the feature fusion module FFM and then input into a sequentially connected pooling layer, a first fully connected layer Fc1, and a second fully connected layer Fc2. The leakage rate estimation value is output through the output layer.

[0015] Furthermore, the convolution module CBS is: CONV+BN+SILU.

[0016] Furthermore, the CBM module is: CONV+BN+Mish.

[0017] Furthermore, the feature analysis module FAM includes:

[0018] F1=concat(CBS(CBS(CBS(Fin))), CBS(CBS(Fin)));

[0019] F2 = maxpooling(Fin);

[0020]

[0021] Among them, the concat() shown represents a cascade operation, the maxpooling() represents maximum pooling, the Fin represents the input features of the feature parsing module FAM, and the FFAM represents the output features of the feature parsing module FAM.

[0022] Furthermore, the feature fusion module is:

[0023] F=Conv(Conv(Fu i+1 )⊕Fc i )⊕Fc i ,i={1,2,3},F represents the fused features, and Conv() represents the convolution operation.

[0024] Furthermore, the method for identifying oil and gas pipeline leakage by using a drone integrating a gas sensor and an acoustic camera also includes:

[0025] S4: Real-time feedback: The analysis results are fed back to the monitoring center in real time so that timely measures can be taken to deal with the leakage. The analysis results include geographic location information and leakage rate estimation.

[0026] Furthermore, the present invention includes an unmanned aerial vehicle oil and gas pipeline leakage identification system integrating a gas sensor and an acoustic camera, including the following modules:

[0027] UAV equipped with configuration module: The UAV is equipped with a gas sensor and an acoustic camera. The gas sensor is used to detect specific gases, and the acoustic camera is used to capture ultrasonic signals.

[0028] Automatic flight path planning module: Based on GIS data and the layout of oil and gas pipelines, the flight path of the drone is planned to ensure that all areas that need to be inspected are covered;

[0029] Data acquisition and processing module: The drone flies along a planned path, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and acoustic camera are analyzed and processed to calculate the estimated leakage rate.

[0030] Furthermore, the present invention also includes an unmanned aerial vehicle oil and gas pipeline leakage identification device that integrates a gas sensor and an acoustic camera, including a processor and a memory; the memory is used to store programs; and the processor executes the above method.

[0031] Furthermore, the present invention includes a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0032] Compared with the prior art, the present invention has the following advantages:

[0033] (1) Multi-sensor fusion: By using gas sensors and acoustic cameras simultaneously, the accuracy and reliability of detection are improved.

[0034] (2) Intelligent analysis: Using advanced data analysis algorithms, it can quickly and accurately locate leak points.

[0035] (3) Efficient inspection: Drones fly autonomously, reducing manpower requirements and improving inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the specific implementation of the present invention or the technical solution in the prior art, the drawings required for describing the specific implementation or the prior art will be briefly introduced below. Obviously, the drawings described below are only one implementation of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flow chart of a method for identifying oil and gas pipeline leaks by using a drone that integrates a gas sensor and an acoustic camera;

[0038] Figure 2 This is the structural diagram of the neural network model. DETAILED DESCRIPTION

[0039] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the technical scheme in the specific implementation mode of the present invention is clearly and completely described below to further illustrate the present invention. Obviously, the specific implementation mode described is only a part of the implementation mode of the present invention, rather than all styles.

[0040] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0041] As attached Figure 1 As shown,

[0042] The present invention provides a method for identifying oil and gas pipeline leakage using an unmanned aerial vehicle (UAV) by integrating a gas sensor and an acoustic camera, comprising the following steps:

[0043] S1: UAV configuration: The drone is equipped with a gas sensor and an acoustic camera. The gas sensor is used to detect specific gases, and the acoustic camera is used to capture ultrasonic signals.

[0044] S2: Automatic flight path planning: Based on GIS data and the layout of oil and gas pipelines, the flight path of the drone is planned to ensure that all areas that need to be inspected are covered;

[0045] S3: Data collection and processing: The drone flies along the planned path, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and acoustic camera are analyzed and processed to calculate the estimated leakage rate.

[0046] Furthermore, the specific gases include: hydrogen sulfide, methane, ethane, ammonia, and carbon monoxide.

[0047] Furthermore, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures the ultrasonic signal. Based on the data collected by the gas sensor and the acoustic camera, the estimated leakage rate is calculated, including:

[0048] Control the gas sensor to detect the content of specific gas in the environment. If it exceeds the preset threshold, control the acoustic camera to collect ultrasonic signals, form an acoustic image, and obtain the geographical location information of the ultrasonic signal;

[0049] The acoustic image is input into the trained neural network model, and the model outputs a leak rate estimate.

[0050] Furthermore, the acoustic image is input into the trained neural network model, and the model outputs the estimated leakage rate including:

[0051] As attached Figure 2 As shown, the acoustic image is input into a sequentially connected convolution module, a feature analysis module FAM, a first CBM module, a second CBM module, a third CBM module, and a fourth CBM module, the outputs of the first, second, third, and fourth CBM modules are recorded as features F1, F2, F3, and F4, the features F1, F2, F3, and F4 are respectively input into the convolution module to obtain features Fc1, Fc2, Fc3, and Fc4, the Fc4 is upsampled to obtain Fu4, Fu4 and Fc3 are fused through a feature fusion module FFM and then upsampled to obtain feature Fu3, Fu3 and Fc2 are fused through a feature fusion module FFM and then upsampled to obtain feature Fu2, Fu2 and Fc1 are fused through a feature fusion module FFM, and then input into a sequentially connected pooling layer, a first fully connected layer Fc1, and a second fully connected layer Fc2, and the leakage rate estimation value is output through the output layer.

[0052] Furthermore, the convolution module is: CONV+BN+SILU.

[0053] Furthermore, the CBM module is: CONV+BN+Mish.

[0054] Furthermore, the feature analysis module FAM includes:

[0055] F1=concat(CBS(CBS(CBS(Fin))), CBS(CBS(Fin)));

[0056] F2 = maxpooling(Fin);

[0057]

[0058] Among them, the concat() shown represents a cascade operation, the maxpooling() represents maximum pooling, the Fin represents the input features of the feature parsing module FAM, and the FFAM represents the output features of the feature parsing module FAM.

[0059] Furthermore, the feature fusion module is:

[0060] F=Conv(Conv(Fu i+1 )⊕Fc i )⊕Fc i ,i={1,2,3},F represents the fused features.

[0061] Furthermore, the method for identifying oil and gas pipeline leakage by using a drone integrating a gas sensor and an acoustic camera also includes:

[0062] S4: Real-time feedback: The analysis results are fed back to the monitoring center in real time so that timely measures can be taken to deal with the leakage. The analysis results include geographic location information and leakage rate estimation.

[0063] Furthermore, the present invention includes an unmanned aerial vehicle oil and gas pipeline leakage identification system integrating a gas sensor and an acoustic camera, including the following modules:

[0064] UAV equipped with configuration module: The UAV is equipped with a gas sensor and an acoustic camera. The gas sensor is used to detect specific gases, and the acoustic camera is used to capture ultrasonic signals.

[0065] Automatic flight path planning module: Based on GIS data and the layout of oil and gas pipelines, the flight path of the drone is planned to ensure that all areas that need to be inspected are covered;

[0066] Data acquisition and processing module: The drone flies along a planned path, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and acoustic camera are analyzed and processed to calculate the estimated leakage rate.

[0067] Furthermore, the present invention also includes an unmanned aerial vehicle oil and gas pipeline leakage identification device that integrates a gas sensor and an acoustic camera, including a processor and a memory; the memory is used to store programs; and the processor executes the above method.

[0068] Furthermore, the present invention includes a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0069] Compared with the prior art, the present invention has the following advantages:

[0070] (1) Multi-sensor fusion: By using gas sensors and acoustic cameras simultaneously, the accuracy and reliability of detection are improved.

[0071] (2) Intelligent Analysis: Using advanced data analysis algorithms, it can quickly and accurately estimate the leakage rate.

[0072] (3) Efficient inspection: Drones fly autonomously, reducing manpower requirements and improving inspection efficiency.

[0073] The above describes the main technical features and basic principles of the present invention and the related advantages. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the concept or basic features of the present invention. Therefore, no matter from which point of view, the above specific embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present invention.

[0074] In addition, it should be understood that although the present specification is described according to various implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation method may also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A method for identifying oil and gas pipeline leakage using an unmanned aerial vehicle (UAV) by integrating a gas sensor and an acoustic camera, characterized in that: The steps include: S1: UAV configuration: The drone is equipped with a gas sensor and an acoustic camera. The gas sensor is used to detect specific gases, and the acoustic camera is used to capture ultrasonic signals. S2: Automatic flight path planning: Based on GIS data and the layout of oil and gas pipelines, the flight path of the drone is planned to ensure that all areas that need to be inspected are covered; S3: Data collection and processing: The drone flies along the planned path, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and the acoustic camera are analyzed and processed to calculate the estimated leakage rate; The gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and the acoustic camera are analyzed and processed to calculate the estimated leakage rate, including: Control the gas sensor to detect the content of specific gas in the environment. If it exceeds the preset threshold, control the acoustic camera to collect ultrasonic signals, form an acoustic image, and obtain the geographical location information of the ultrasonic signal; The acoustic image is input into the trained neural network model, and the model outputs the leakage rate estimation value; The acoustic image is input into the trained neural network model, and the model outputs the leakage rate estimation value including: The acoustic image is input into the sequentially connected convolution module CBS, feature analysis module FAM, first CBM module, second CBM module, third CBM module, and fourth CBM module, and the outputs of the first, second, third, and fourth CBM modules are recorded as features F1, F2, F3, and F4. The features F1, F2, F3, and F4 are respectively input into the convolution module CBS to obtain features Fc1, Fc2, Fc3, and Fc4. The Fc4 is upsampled to obtain Fu4. Fu4 and Fc3 are fused through the feature fusion module FFM and then upsampled to obtain feature Fu3. Fu3 and Fc2 are fused through the feature fusion module FFM and then upsampled to obtain feature Fu2. Fu2 and Fc1 are fused through the feature fusion module FFM, and then input into the sequentially connected pooling layer, the first fully connected layer Fc1, and the second fully connected layer Fc2, and the leakage rate estimation value is output through the output layer; The convolution module is: CONV+BN+SILU; The CBM module is: CONV+BN+Mish; The feature analysis module FAM comprises: F1=concat(CBS(CBS(CBS(Fin))), CBS(CBS(Fin))); F2 = maxpooling(Fin); ； Wherein, the concat() indicates a cascade operation, the maxpooling() indicates maximum value pooling, the Fin indicates the input feature of the feature parsing module FAM, and the FFAM indicates the output feature of the feature parsing module FAM; The feature fusion module is: F=Conv(Conv(Fui+1)⊕Fci)⊕Fci,i={1,2,3}, F represents the fused features.

2. The method for identifying oil and gas pipeline leakage by using a drone integrating a gas sensor and an acoustic camera according to claim 1 is characterized in that: Specific gases include: hydrogen sulfide, methane, ethane, ammonia, carbon monoxide.

3. The method for identifying oil and gas pipeline leakage by using a drone integrating a gas sensor and an acoustic camera according to claim 1, characterized in that: The method further comprises: S4: Real-time feedback: The analysis results are fed back to the monitoring center in real time so that timely measures can be taken to deal with the leakage. The analysis results include geographic location information and leakage rate estimation.

4. A UAV oil and gas pipeline leakage identification system integrating a gas sensor and an acoustic camera, wherein the system implements the method according to any one of claims 1 to 3, characterized in that: Includes the following modules: UAV equipped with configuration module: The UAV is equipped with a gas sensor and an acoustic camera. The gas sensor is used to detect specific gases, and the acoustic camera is used to capture ultrasonic signals. Automatic flight path planning module: Based on GIS data and the layout of oil and gas pipelines, the flight path of the drone is planned to ensure that all areas that need to be inspected are covered; Data acquisition and processing module: The drone flies along a planned path, the gas sensor monitors the changes in gas concentration in the surrounding environment in real time, and the acoustic camera captures ultrasonic signals. The data collected by the gas sensor and acoustic camera are analyzed and processed to calculate the estimated leakage rate.

5. An unmanned aerial vehicle oil and gas pipeline leakage identification device integrating a gas sensor and an acoustic camera, characterized in that: The method comprises a processor and a memory; the memory is used to store a program; the processor executes the program to implement the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 3.

Images