Oil and gas pipeline monitoring method and monitoring system based on image recognition
By setting up a collection equipment group along the oil and gas pipeline and realizing group collaboration, using the data processing center to optimize the monitoring frequency and position of the acquisition equipment, the problems of high image recognition error and calculation cost of oil and gas pipelines in the prior art are solved, and efficient and accurate image recognition and detection are achieved.
Patent Information
- Application Number
- CN202510127091.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-30
- Publication Date
- 2025-06-06
AI Technical Summary
The prior art has errors in the process of oil and gas pipeline image recognition, resulting in increased computing costs and reduced detection efficiency. How to improve image recognition accuracy and detection efficiency without increasing computing resources has become an urgent problem.
By setting up a collection equipment group along the oil and gas pipeline and realizing the group collaboration function of the acquisition equipment, the data processing center is used to perform preliminary analysis and adjustment of the image data, and the monitoring frequency and position of the acquisition equipment are optimized to improve the accuracy and efficiency of image recognition.
On the premise of ensuring real-time performance, accurately capture abnormal points, optimize image recognition algorithms, improve the accuracy and detection efficiency of oil and gas pipeline image recognition, and reduce calculation costs.
Smart Images
Figure CN120101045A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image recognition technology, and specifically to an oil and gas pipeline monitoring method and monitoring system based on image recognition. Background Art
[0002] In recent years, with the rapid development of cities, towns and supporting facilities, the situation of long-distance oil and gas pipelines passing through densely populated areas and environmentally sensitive areas has become increasingly prominent, and the safety inspection of oil and gas pipelines is extremely important.
[0003] Traditional methods of oil and gas pipeline inspection include manual surveys. However, with the increase in the length of oil and gas pipelines and the complex terrain and changing environment along the pipelines, manual inspection is inefficient and poses safety hazards. Therefore, in recent years, the safety inspection of oil and gas pipelines has gradually transitioned to automated inspection. For example, drones are used to capture images of the pipeline surface, and then image recognition technology is used for analysis. This has effectively improved inspection efficiency and accuracy, reduced manual risks, and ensured the safe operation of the pipeline.
[0004] However, in the existing technology, due to factors such as long pipelines, complex and changeable environments along the pipelines, and weather changes, errors may occur in the collection and recognition process of pipeline images. In order to eliminate or reduce these errors, more computing resources are often required in the image processing process, which not only increases the computational cost of image recognition, but also affects the timeliness of real-time detection and reduces the overall detection efficiency. Therefore, how to improve the recognition accuracy and detection efficiency of oil and gas pipeline images while keeping the overall computing power unchanged has become a problem that needs to be solved urgently.
[0005] Therefore, it is necessary to provide an oil and gas pipeline monitoring method and monitoring system based on image recognition to solve the above problems.
[0006] It should be noted that the above information disclosed in this background technology section is only for understanding the background technology of the present application concept, and therefore, it may contain information that does not constitute the prior art. Summary of the invention
[0007] Based on the above-mentioned problems existing in the prior art, the problem to be solved by the present application is: to provide an oil and gas pipeline monitoring method and monitoring system based on image recognition, which saves computing power resources and improves image processing efficiency through collaborative adjustment of acquisition equipment.
[0008] The technical solution adopted by the present application to solve the technical problem is: an oil and gas pipeline monitoring method based on image recognition, comprising: A collection device group is set up along the pipeline, each collection device has a data exchange channel, and a group collaboration function of the collection devices is realized to collect images of the oil and gas pipeline and generate a first image data set; The data processing center receives the first image data set uploaded by the acquisition device, performs a preliminary analysis on the data set, identifies the distribution of abnormal points, and adjusts the group collaboration process of the acquisition device; An execution signal is sent to the collection device. The execution signal contains adjustment instructions, instructing each collection device to reposition and adjust the monitoring frequency according to the distribution of abnormal points and the latest monitoring results. At the same time, the collection device verifies the received execution signal.
[0009] During the implementation of the technical solution of the present application, by configuring the group collaboration function of the acquisition equipment and adjusting the group collaboration process of the acquisition equipment according to the distribution of abnormal points, the abnormal points can be accurately captured and the image recognition algorithm can be optimized while ensuring real-time performance.
[0010] Furthermore, the implementation of the group collaboration function includes the following steps: Number the acquisition devices so that each acquisition device has a unique identification code, so as to accurately identify the device identity during data exchange, and synchronize data through the identification code to ensure that the image data collected by each device is consistent in time; Use TCP / IP protocol as the transmission control protocol between acquisition devices, and generate ACK signal after the acquisition device completes data transmission to confirm successful data transmission; An ACK signal conversion mechanism is established to convert the ACK signal into the image acquisition status identifier of the corresponding area of the acquisition device. While confirming the completion of the transmission through the ACK signal, the image acquisition status identifier of the corresponding area of the acquisition device is obtained.
[0011] Furthermore, the ACK signal conversion mechanism refers to the rule for mapping the ACK signal to the image acquisition state. The image acquisition state is the distribution of abnormal points on the pipeline surface in the current area. The distribution of abnormal points in the image is converted into the signal strength of the ACK signal. The abnormal area is quickly located through information exchange between acquisition devices, and the area with more abnormal points is marked as the adjustment area in time.
[0012] Furthermore, the distribution of abnormal points on the pipeline surface image is proportional to the signal strength of the ACK signal, that is, the denser the distribution of abnormal points on the pipeline surface image, the higher the ACK signal strength, and conversely, the sparser the distribution of abnormal points, the lower the ACK signal strength.
[0013] Further, preliminary analysis of the data set is performed to identify the distribution of abnormal points, and the group collaboration process of the collection equipment is adjusted, further including: Preprocessing the first image data set to remove noise and interference in the image to ensure data purity, and optimizing the image through edge detection technology to more accurately identify abnormal points; Use deep learning algorithms to extract features from preprocessed images, extract abnormal features from images, and classify the extracted abnormal features; According to the classification results, the distribution of abnormal points is quantified, and the group collaboration process of the acquisition equipment is adjusted according to the quantification results.
[0014] Furthermore, the distribution of abnormal points is quantified using a distance-weighted method. By calculating the distance weight of each abnormal point from all other abnormal points, a comprehensive abnormality degree index is calculated, and then the acquisition equipment is optimized according to the calculated abnormality degree index.
[0015] Furthermore, the calculation of the abnormality index includes: first calculating the distance between every two abnormal points, which is the Euclidean distance, and then taking a weighted average of these distance values. Considering that points with closer distances have a greater impact on the abnormality level, a different weight coefficient is assigned to each distance value, where the weight value adopts Gaussian weighting.
[0016] Furthermore, the optimization configuration of the acquisition device specifically involves adjusting the signal strength of the ACK signal. The stronger the signal strength, the denser the abnormal distribution of the pipeline image at that location, and the corresponding acquisition device needs to be adjusted.
[0017] Furthermore, the acquisition device verifies the received execution signal by adopting a change rate judgment method to determine whether the intensity change rate of the ACK signal received for the first time and the ACK signal expected to be generated after the execution signal is implemented is less than a preset threshold. If it is less than the preset threshold, execution begins; if it is greater than or equal to the preset threshold, a recheck signal is returned until the adjustment is completed.
[0018] An oil and gas pipeline monitoring system based on image recognition, comprising: A collection equipment group deployment module is used to set up a collection equipment group along the pipeline, each collection equipment has a data exchange channel, realizes the group collaboration function of the collection equipment, collects images of the oil and gas pipeline, and generates a first image data set; A data analysis and processing module is used for the data processing center to receive the first image data set uploaded by the acquisition device, perform preliminary analysis on the data set, identify the distribution of abnormal points, and adjust the group collaboration process of the acquisition device; The adjustment and verification module is used to send an execution signal to the collection device. The execution signal contains an adjustment instruction, instructing each collection device to reposition and adjust the monitoring frequency according to the distribution of abnormal points and the latest monitoring results. At the same time, the collection device verifies the received execution signal.
[0019] The beneficial effect of the present application is as follows: the present application provides an oil and gas pipeline monitoring method and monitoring system based on image recognition, which configures the group collaboration function of the acquisition equipment and adjusts the group collaboration process of the acquisition equipment according to the distribution of abnormal points, thereby accurately capturing abnormal points and optimizing the image recognition algorithm while ensuring real-time performance.
[0020] In addition to the above-described purposes, features and advantages, the present application also has other purposes, features and advantages. The present application will be further described in detail with reference to the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 This is an overall schematic diagram of an oil and gas pipeline monitoring method based on image recognition in this application; Figure 2 This is a schematic diagram of the module structure of an oil and gas pipeline monitoring system based on image recognition in this application. DETAILED DESCRIPTION
[0022] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0024] Embodiment 1: Figure 1 As shown, the present application provides an oil and gas pipeline monitoring method based on image recognition, which is applied to the monitoring of oil and gas pipelines. The surface image of the oil and gas pipeline is collected, and the collected image data is transmitted to the corresponding processing center after transmission. Then, the image data is analyzed by the processing center to judge the state of the oil and gas pipeline, and reduce the risks of pipeline failure, leakage, etc. caused by corrosion, cracks, wear, deformation, etc. The method includes the following steps: Step 01: Set up a collection device group along the pipeline, each collection device has a data exchange channel, realize the group collaboration function of the collection devices, collect images of the oil and gas pipeline, and generate a first image data set; In the prior art, a variety of devices can be used to collect surface images of oil and gas pipelines, such as ultrasonic imagers, high-precision imagers, etc. In this embodiment, the collection device is a drone, which carries an image collection device and can collect images of the oil and gas pipeline along the pipeline according to a preset route. In addition, in this embodiment, a collection device group is composed of multiple drones, and the pipeline surface image is collected in different areas, thereby improving the collection efficiency; In order to realize information exchange between collection devices, each collection device has a data exchange channel. In this embodiment, the data exchange channel is a wireless transmission channel, which is used to realize information exchange between drones, thereby realizing the group collaboration function of the collection devices. The realization of the group collaboration function includes the following steps: Step 101: Numbering the acquisition devices so that each acquisition device has a unique identification code, so as to accurately identify the device identity during data exchange, and synchronize data through the identification code to ensure that the image data collected by each device is consistent in time; Since the collection device group contains multiple collection devices, in order to facilitate management and scheduling, the collection devices need to be numbered so that each device has a unique identifier, which is convenient for identification during data exchange and subsequent tracing, positioning and other operations, so as to realize information exchange between collection devices and quickly locate abnormal areas; Step 102: Use the TCP / IP protocol as the transmission control protocol between the acquisition devices, and generate an ACK signal after the acquisition device completes the data transmission to confirm that the data transmission is successful; In order to facilitate the transmission of image data and various signals, it is necessary to establish a stable communication network between acquisition devices, use TCP / IP protocol as the transmission control protocol between acquisition devices, and generate ACK signal after data transmission is completed to ensure the reliability and integrity of data transmission. TCP / IP protocol is a protocol cluster that can realize information transmission between multiple different networks. Through this protocol, acquisition devices can exchange data efficiently and stably. After the acquisition device completes data transmission, it will generate ACK signal. ACK signal is a transmission control character in the data communication process, indicating that the transmitted data has been received normally, thereby ensuring the accuracy and consistency of data transmission and avoiding information errors caused by data loss or confusion; Step 103: Establish an ACK signal conversion mechanism to convert the ACK signal into an image acquisition status identifier of the corresponding area of the acquisition device, and simultaneously confirm the completion of the transmission through the ACK signal and obtain the image acquisition status identifier of the corresponding area of the acquisition device; In the prior art, the ACK signal is only a confirmation signal to confirm whether the data is successfully transmitted, and has no other practical application functions. In this embodiment, by establishing an ACK signal conversion mechanism, the ACK signal is converted into an image acquisition status identifier of the corresponding area of the acquisition device, and the ACK signal in the transmission process can be used to monitor the image acquisition status along the oil and gas pipeline in real time, and abnormal situations can be discovered and handled in time; Among them, the ACK signal conversion mechanism refers to the rule for mapping the ACK signal with the image acquisition status. The image acquisition status is the distribution of abnormal points on the pipeline surface image in the current area. The distribution of abnormal points in the image is converted into the signal strength of the ACK signal. The abnormal area is quickly located through information exchange between acquisition devices, and the area with more abnormal points is marked as the adjustment area in time. By adjusting the acquisition parameters in the area, the image acquisition effect is optimized and the data accuracy is improved, so there is no need to repeatedly identify abnormal points in the subsequent image analysis process, thereby improving the overall data processing efficiency.
[0025] Specifically, the distribution of abnormal points on the pipeline surface image is proportional to the signal strength of the ACK signal, that is, the denser the distribution of abnormal points on the pipeline surface image, the higher the ACK signal strength, and conversely, the sparser the distribution of abnormal points, the lower the ACK signal strength. Through this mapping relationship, the system can accurately reflect the surface state of the pipeline and ensure timely identification and processing of abnormal areas. For example, when the first acquisition device sends data to the second acquisition device, it will generate an ACK signal after completion. After mapping the ACK signal through the ACK signal conversion mechanism, the second acquisition device will determine the distribution of pipeline fault points in the area collected by the first acquisition device according to the strength of the received ACK signal. When the ACK signal strength is large, it is determined that the distribution of fault points in the area collected by the first acquisition device is dense. At this time, the second acquisition device will send an adjustment instruction to the data processing center. After verification, the data processing center will send the adjustment instruction to the first acquisition device to adjust the monitoring parameters, such as improving the resolution of the collected image, increasing the sampling frequency, and reducing the monitoring range. The second acquisition device can also directly send the adjustment instruction to the first acquisition device, and the first acquisition device directly adjusts the monitoring parameters.
[0026] Step 02: The data processing center receives the first image data set uploaded by the acquisition device, performs a preliminary analysis on the data set, identifies the distribution of abnormal points, and adjusts the group collaboration process of the acquisition device; The data processing center refers to a general module with functions such as data reception, data processing, and data analysis, which is used to receive the first image data set uploaded by the acquisition device, and perform preliminary analysis on the first image data set to determine the distribution of abnormal points in the oil and gas pipeline, and then adjust the group collaboration process of the acquisition device according to the density of the abnormal points. Specifically, the process further includes the following steps: Step 201: preprocessing the first image data set to remove noise and interference in the image to ensure data purity, and optimizing the image through edge detection technology to more accurately identify abnormal points; the first image data set directly acquired by the acquisition device may contain noise and unnecessary details, which may affect the accuracy of data analysis. By preprocessing the image, such as applying a filter and an edge enhancement algorithm, the edge detection technology can enhance the sudden change part of the pipeline surface in the image, thereby helping to more accurately locate the abnormal point; Step 202: Use a deep learning algorithm to extract features from the preprocessed image, extract abnormal features from the image, and classify the extracted abnormal features; the abnormal features include cracks, corrosion or deformation on the pipeline surface, and use the trained AI model to classify the extracted features to distinguish between normal and abnormal states. In this way, the accuracy of abnormal point recognition can be further improved. The extracted abnormal features can be classified by support vector machine (SVM), decision tree or neural network classification technology, which can be specifically referred to the prior art and will not be described in detail in this embodiment; Step 203: According to the classification result, the distribution of the abnormal points is quantified, and the group collaboration process of the acquisition equipment is adjusted according to the quantification result.
[0027] In the above steps, each acquisition device in the acquisition device group has a data exchange channel, thereby realizing the group collaboration function of the acquisition devices, and through the ACK signal conversion mechanism, the ACK signal is converted into the image acquisition status mark of the corresponding area of the acquisition device, so as to obtain the pipeline information in the interaction process of the acquisition device. Since in the above process, the image acquisition status mark represented by the ACK signal is only preliminarily confirmed, and no detailed analysis of the pipeline image is performed, after the distribution of the abnormal points is quantified, more refined adjustments can be implemented according to the quantification results. Specifically, the distribution of the abnormal points is quantified using a distance weighted method, by calculating the distance weight of each abnormal point from all other abnormal points, and then calculating a comprehensive abnormality index, and according to the index value, the deployment position and monitoring frequency of the acquisition device are adjusted, so that the equipment is more focused on high-risk areas, thereby optimizing the overall monitoring efficiency; The calculation of the abnormality index includes: first calculating the distance between each two abnormal points, which is the Euclidean distance, and then performing weighted averaging on these distance values. Considering that points with closer distances have a greater impact on the degree of abnormality, different weight coefficients are assigned to each distance value, wherein the weight value adopts Gaussian weighting, and the closer the distance, the greater the weight value. The calculation process of Gaussian weighting can refer to the prior art and the corresponding formula, and will not be described in this embodiment. Then, the distance values are accumulated according to different weight coefficients to obtain a comprehensive weight index of each abnormal point; Then, according to the calculated abnormality index, the acquisition equipment is optimized and configured, specifically, the signal strength of the ACK signal is adjusted. The stronger the signal strength, the denser the abnormal distribution of the pipeline image at that location, and the corresponding acquisition equipment needs to be adjusted. Therefore, during the interaction of the acquisition equipment, the abnormal distribution situation is judged according to the strength of the ACK signal.
[0028] Step 03: Send an execution signal to the collection device. The execution signal contains adjustment instructions, instructing each collection device to reposition and adjust the monitoring frequency according to the distribution of abnormal points and the latest monitoring results. At the same time, the collection device verifies the received execution signal; In order to control the acquisition device, it is necessary to send an execution signal to it through the data processing center. The execution signal includes an adjustment instruction to instruct the acquisition device to make adjustments. At the same time, after receiving the execution signal, the acquisition device needs to be verified to prevent the data processing center from making misjudgments. The verification process is implemented using the change rate judgment method. Specifically, it is determined whether the intensity change rate of the ACK signal received for the first time and the ACK signal expected to be generated after the execution signal is implemented is less than the preset threshold. If it is less than the preset threshold, the execution is started. If it is greater than or equal to the preset threshold, the re-check signal is returned until the adjustment is completed. For example, the intensity of the ACK signal received for the first time is 100dbm, and the expected ACK signal intensity after adjustment is 130dbm, with a change rate of 30%, which is less than the preset threshold of 50%. The adjustment is started, and the acquisition device will optimize its monitoring position and frequency according to the latest instructions. In this way, not only the accuracy of the data can be ensured, but also abnormal situations can be responded to in real time, thereby improving the dynamic adaptability of the monitoring system.
[0029] Embodiment 2: Figure 2 As shown, the present application proposes an oil and gas pipeline monitoring system based on image recognition, which runs the oil and gas pipeline monitoring method based on image recognition in Example 1. The system includes: A collection equipment group deployment module is used to set up a collection equipment group along the pipeline, each collection equipment has a data exchange channel, realizes the group collaboration function of the collection equipment, collects images of the oil and gas pipeline, and generates a first image data set; A data analysis and processing module is used for the data processing center to receive the first image data set uploaded by the acquisition device, perform preliminary analysis on the data set, identify the distribution of abnormal points, and adjust the group collaboration process of the acquisition device; The adjustment and verification module is used to send an execution signal to the collection device. The execution signal contains an adjustment instruction, instructing each collection device to reposition and adjust the monitoring frequency according to the distribution of abnormal points and the latest monitoring results. At the same time, the collection device verifies the received execution signal.
[0030] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. An oil and gas pipeline monitoring method based on image recognition, characterized in that: include: A collection device group is set up along the pipeline, each collection device has a data exchange channel, and a group collaboration function of the collection devices is realized to collect images of the oil and gas pipeline and generate a first image data set; The data processing center receives the first image data set uploaded by the acquisition device, performs a preliminary analysis on the data set, identifies the distribution of abnormal points, and adjusts the group collaboration process of the acquisition device; An execution signal is sent to the collection device. The execution signal contains adjustment instructions, instructing each collection device to reposition and adjust the monitoring frequency according to the distribution of abnormal points and the latest monitoring results. At the same time, the collection device verifies the received execution signal.
2. The oil and gas pipeline monitoring method based on image recognition according to claim 1 is characterized in that: The implementation of group collaboration function includes the following steps: Number the acquisition devices so that each acquisition device has a unique identification code, so as to accurately identify the device identity during data exchange, and synchronize data through the identification code to ensure that the image data collected by each device is consistent in time; Use TCP / IP protocol as the transmission control protocol between acquisition devices, and generate ACK signal after the acquisition device completes data transmission to confirm successful data transmission; An ACK signal conversion mechanism is established to convert the ACK signal into the image acquisition status identifier of the corresponding area of the acquisition device. While confirming the completion of the transmission through the ACK signal, the image acquisition status identifier of the corresponding area of the acquisition device is obtained.
3. The oil and gas pipeline monitoring method based on image recognition according to claim 2 is characterized in that: The ACK signal conversion mechanism refers to the rules for mapping the ACK signal to the image acquisition status. The image acquisition status is the distribution of abnormal points on the pipeline surface in the current area. The distribution of abnormal points in the image is converted into the signal strength of the ACK signal. The abnormal area can be quickly located through information exchange between acquisition devices, and the area with more abnormal points can be marked as the adjustment area in time.
4. The oil and gas pipeline monitoring method based on image recognition according to claim 3 is characterized in that: The distribution of abnormal points on the pipeline surface image is proportional to the signal strength of the ACK signal, that is, the denser the distribution of abnormal points on the pipeline surface image, the higher the ACK signal strength; conversely, the sparser the distribution of abnormal points, the lower the ACK signal strength.
5. The oil and gas pipeline monitoring method based on image recognition according to claim 4 is characterized in that: Conduct preliminary analysis of the data set, identify the distribution of outliers, and adjust the group collaboration process of the collection equipment, further including: Preprocessing the first image data set to remove noise and interference in the image to ensure data purity, and optimizing the image through edge detection technology to more accurately identify abnormal points; Use deep learning algorithms to extract features from preprocessed images, extract abnormal features from images, and classify the extracted abnormal features; According to the classification results, the distribution of abnormal points is quantified, and the group collaboration process of the acquisition equipment is adjusted according to the quantification results.
6. The oil and gas pipeline monitoring method based on image recognition according to claim 5 is characterized in that: The distance weighted method is used to quantify the distribution of abnormal points. By calculating the distance weight of each abnormal point from all other abnormal points, a comprehensive abnormality degree index is calculated, and then the acquisition equipment is optimized according to the calculated abnormality degree index.
7. The oil and gas pipeline monitoring method based on image recognition according to claim 6 is characterized by: The calculation of the anomaly index includes: first calculating the distance between every two anomaly points, which is the Euclidean distance, and then taking a weighted average of these distance values. Considering that points with closer distances have a greater impact on the degree of anomaly, different weight coefficients are assigned to each distance value, where the weight value adopts Gaussian weighting.
8. The oil and gas pipeline monitoring method based on image recognition according to claim 6 is characterized in that: The optimization configuration of the acquisition device specifically involves adjusting the signal strength of the ACK signal. The stronger the signal strength, the denser the distribution of pipeline image anomalies at that location, and the corresponding acquisition device needs to be adjusted.
9. The oil and gas pipeline monitoring method based on image recognition according to claim 8 is characterized in that: The acquisition device verifies the received execution signal by using the change rate judgment method to determine whether the intensity change rate of the ACK signal received for the first time and the ACK signal expected to be generated after the execution signal is implemented is less than the preset threshold. If it is less than the preset threshold, execution begins; if it is greater than or equal to the preset threshold, a recheck signal is returned until the adjustment is completed.
10. An oil and gas pipeline monitoring system based on image recognition, used to implement the oil and gas pipeline monitoring method based on image recognition according to any one of claims 1 to 9, characterized in that: include: A collection equipment group deployment module is used to set up a collection equipment group along the pipeline, each collection equipment has a data exchange channel, realizes the group collaboration function of the collection equipment, collects images of the oil and gas pipeline, and generates a first image data set; A data analysis and processing module is used for the data processing center to receive the first image data set uploaded by the acquisition device, perform preliminary analysis on the data set, identify the distribution of abnormal points, and adjust the group collaboration process of the acquisition device; The adjustment and verification module is used to send an execution signal to the collection device. The execution signal contains an adjustment instruction, instructing each collection device to reposition and adjust the monitoring frequency according to the distribution of abnormal points and the latest monitoring results. At the same time, the collection device verifies the received execution signal.