Pipeline anomaly detection method, electronic equipment, storage medium and program product
By obtaining environmental information and sensor data in the pipeline area, and using an abnormality recognition model to detect pipeline abnormalities, the problem of low manual inspection efficiency is solved, and pipeline abnormality detection is achieved in a timely discovery and accurate response.
Patent Information
- Application Number
- CN202510595766.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-09
- Publication Date
- 2025-08-26
AI Technical Summary
In the prior art, pipeline abnormality detection mainly relies on manual inspection, which is inefficient and difficult to detect emergencies in a timely manner, resulting in the inability to effectively control the risks.
By obtaining the environmental information of the area where the pipeline is located, including area images and multi-type sensor data, the abnormality identification model is used to determine the pipeline abnormality, and an alarm prompt information is sent when an abnormality is detected.
Improve the efficiency and accuracy of pipeline abnormality detection, reduce misjudgment and misjudgment, and ensure that relevant personnel can respond to abnormal situations in a timely manner.
Smart Images
Figure CN120541566A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of pipeline technology, and in particular to a pipeline anomaly detection method, electronic equipment, storage medium, and program product. Background Art
[0002] With the rapid development of society and the acceleration of industrialization, pipelines, as the "blood vessels" for transporting energy and resources, play an indispensable role in the oil and natural gas sectors. However, due to the long-term underground burial of pipelines or exposure to complex environments, they can be damaged by infrastructure construction equipment, complex environments, and human interference, seriously threatening pipeline safety.
[0003] Prior art pipeline anomaly detection primarily relies on manual inspections. Inspectors must walk or drive along the pipeline section by section, resulting in low efficiency and difficulty quickly covering large areas. Furthermore, the labor and time costs are high. Furthermore, if emergencies occur, manual inspections are difficult to detect and respond to in a timely manner, resulting in an inability to effectively control risks.
[0004] Therefore, how to improve the detection efficiency of pipeline anomalies is an urgent problem to be solved. Summary of the Invention
[0005] The purpose of this application is to provide a pipeline anomaly detection method, electronic equipment, storage medium and program product, aiming to solve the problem of how to improve the detection efficiency of pipeline anomalies.
[0006] In a first aspect, a pipeline anomaly detection method is provided, comprising: obtaining environmental information of an area to be detected in which the pipeline is located; the environmental information comprising: an area image and sensor data of the area to be detected; the sensor data comprising: temperature data, smoke data, rainfall data, and wind data; the pipeline is used to transmit flammable fluid; based on the environmental information, determining a pipeline anomaly identification result for the area to be detected; and sending an alarm prompt message when the anomaly identification result indicates that an anomaly exists around the pipeline.
[0007] The method provided by the embodiments of this application has the following beneficial effects: By integrating regional images and multi-type sensor data, not only can changes in the pipeline's surrounding environment be detected promptly, improving the efficiency of pipeline anomaly detection, but the images can also intuitively show whether the pipeline's appearance is damaged or deformed. Sensor data can reflect the potential impact of environmental factors on the pipeline. Multi-dimensional information fusion improves the accuracy of anomaly identification and reduces false positives and missed detections. When the anomaly identification results indicate an anomaly and an alarm message is sent to prompt, relevant personnel can respond quickly based on the alarm message.
[0008] In some embodiments, determining the abnormality recognition result of the pipeline based on the environmental information includes: inputting the environmental information into the abnormality recognition model, and determining the regional information of the area to be detected based on the environmental information through the abnormality recognition model, where the regional information includes at least one of the following: object information of the target object in the area to be detected, pipeline status information, and meteorological information of the area to be detected; and determining the abnormality recognition result of the pipeline based on the regional information.
[0009] In some embodiments, based on the area information, the abnormality recognition result of the pipeline is determined, including: when the object information of the target object in the area to be detected meets the first preset condition, determining that the abnormality recognition result indicates that there is an abnormality around the pipeline; the first preset condition includes at least one of the following: there is smoke and flames in the area to be detected; the temperature of the area to be detected is greater than the temperature threshold; the length of time that pedestrians stay in the area to be detected is greater than the time threshold; there are abnormal behaviors of pedestrians in the area to be detected; the abnormal behavior is used to indicate destructive behavior of pedestrians on the pipeline; mechanical equipment enters the area to be detected; the mechanical equipment in the area to be detected is in working condition.
[0010] In some embodiments, determining the abnormality identification result of the pipeline based on the area information includes: when the pipeline status information in the area to be detected meets a second preset condition, determining that the abnormality identification result indicates that there is an abnormality around the pipeline; the second preset condition includes at least one of the following: the pipeline in the area to be detected is exposed and / or corroded and / or broken; there is a pipeline leakage in the area to be detected.
[0011] In some embodiments, the abnormality identification result of the pipeline is determined based on the regional information, including: when the meteorological information of the area to be detected meets the third preset condition, determining that the abnormality identification result indicates that there is an abnormality around the pipeline; the third preset condition includes: a natural disaster occurs in the area to be detected.
[0012] In some embodiments, determining a pipeline anomaly recognition result of an area to be detected based on environmental information includes: determining a first pipeline anomaly recognition result of the area to be detected based on sensor data of the area to be detected; determining a second pipeline anomaly recognition result of the area to be detected based on an area image of the area to be detected; and performing weighted summation of the first pipeline anomaly recognition result and the second pipeline anomaly recognition result to determine the pipeline anomaly recognition result.
[0013] In some embodiments, the anomaly recognition model is trained in the following manner: obtaining a training data set, the training data set including: environmental information samples and target area information corresponding to the environmental information samples; inputting the environmental information samples into the initial anomaly recognition model, and determining the predicted area information based on the environmental information samples by the initial anomaly recognition model; training the initial anomaly recognition model based on the predicted area information and the target area information to obtain a trained anomaly recognition model.
[0014] In the second aspect, a pipeline anomaly detection device is also provided, including: an acquisition unit for acquiring environmental information of the area to be detected where the pipeline is located; the environmental information includes: an area image and sensor data of the area to be detected; the sensor data includes: temperature data, smoke data, rainfall data and wind data; the pipeline is used to transmit combustible fluid; a processing unit is used to determine the pipeline anomaly identification result of the area to be detected based on the environmental information; when the anomaly identification result indicates that there is an anomaly around the pipeline, an alarm prompt information is sent.
[0015] In some embodiments, determining the abnormality recognition result of the pipeline based on the environmental information includes: inputting the environmental information into the abnormality recognition model, and determining the regional information of the area to be detected based on the environmental information through the abnormality recognition model, where the regional information includes at least one of the following: object information of the target object in the area to be detected, pipeline status information, and meteorological information of the area to be detected; and determining the abnormality recognition result of the pipeline based on the regional information.
[0016] In some embodiments, based on the area information, the abnormality recognition result of the pipeline is determined, including: when the object information of the target object in the area to be detected meets the first preset condition, determining that the abnormality recognition result indicates that there is an abnormality around the pipeline; the first preset condition includes at least one of the following: there is smoke and flames in the area to be detected; the temperature of the area to be detected is greater than the temperature threshold; the length of time that pedestrians stay in the area to be detected is greater than the time threshold; there are abnormal behaviors of pedestrians in the area to be detected; the abnormal behavior is used to indicate destructive behavior of pedestrians on the pipeline; mechanical equipment enters the area to be detected; the mechanical equipment in the area to be detected is in working condition.
[0017] In some embodiments, determining the abnormality identification result of the pipeline based on the area information includes: when the pipeline status information in the area to be detected meets a second preset condition, determining that the abnormality identification result indicates that there is an abnormality around the pipeline; the second preset condition includes at least one of the following: the pipeline in the area to be detected is exposed and / or corroded and / or broken; there is a pipeline leakage in the area to be detected.
[0018] In some embodiments, the abnormality identification result of the pipeline is determined based on the regional information, including: when the meteorological information of the area to be detected meets the third preset condition, determining that the abnormality identification result indicates that there is an abnormality around the pipeline; the third preset condition includes: a natural disaster occurs in the area to be detected.
[0019] In some embodiments, determining a pipeline anomaly recognition result of an area to be detected based on environmental information includes: determining a first pipeline anomaly recognition result of the area to be detected based on sensor data of the area to be detected; determining a second pipeline anomaly recognition result of the area to be detected based on an area image of the area to be detected; and performing weighted summation of the first pipeline anomaly recognition result and the second pipeline anomaly recognition result to determine the pipeline anomaly recognition result.
[0020] In some embodiments, the anomaly recognition model is trained in the following manner: obtaining a training data set, the training data set including: environmental information samples and target area information corresponding to the environmental information samples; inputting the environmental information samples into the initial anomaly recognition model, and determining the predicted area information based on the environmental information samples by the initial anomaly recognition model; training the initial anomaly recognition model based on the predicted area information and the target area information to obtain a trained anomaly recognition model.
[0021] In a third aspect, the present application provides an electronic device comprising: a processor and a memory configured to store processor-executable instructions; wherein the processor is configured to execute the instructions to implement any one of the optional pipeline anomaly detection methods in the first aspect above.
[0022] In a fourth aspect, the present application provides a computer-readable storage medium having instructions stored thereon. When the instructions in the computer-readable storage medium are executed by a device, the device is enabled to execute any one of the optional pipeline anomaly detection methods in the first aspect described above.
[0023] In a fifth aspect, the present application provides a computer program product comprising computer instructions, which, when executed on a processor of a device, enable the device to execute any one of the pipeline anomaly detection methods optionally described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0025] Figure 1 A schematic diagram of the structure of a pipeline anomaly detection system provided in an embodiment of the present application;
[0026] Figure 2 A schematic diagram of a unified architecture of an anomaly recognition algorithm provided in an embodiment of the present application;
[0027] Figure 3A schematic diagram of a unified architecture of an intelligent recognition platform provided in an embodiment of the present application;
[0028] Figure 4 A schematic diagram of the architecture of a unified access system provided in an embodiment of the present application;
[0029] Figure 5 A flow chart of a pipeline anomaly detection method provided in an embodiment of the present application;
[0030] Figure 6 A flow chart of another pipeline anomaly detection method provided in an embodiment of the present application;
[0031] Figure 7 A flow chart of another pipeline anomaly detection method provided in an embodiment of the present application;
[0032] Figure 8 A schematic structural diagram of a pipeline anomaly detection device provided in an embodiment of the present application;
[0033] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0034] In the embodiments of the present application, the terms "first," "second," "third," "fourth," "fifth," and "sixth" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, a feature specified as "first," "second," "third," "fourth," "fifth," and "sixth" may explicitly or implicitly include one or more of the features.
[0035] In the embodiments of the present application, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.
[0036] “A and / or B” includes the following three combinations: A only, B only, and a combination of A and B.
[0037] With the rapid development of society and the acceleration of industrialization, pipelines, as the "blood vessels" for transporting energy and resources, play an indispensable role in the oil and natural gas sectors. However, due to the long-term underground burial of pipelines or exposure to complex environments, they can be damaged by infrastructure construction equipment, complex environments, and human interference, seriously threatening pipeline safety.
[0038] Prior art pipeline anomaly detection primarily relies on manual inspections. Inspectors must walk or drive along the pipeline section by section, resulting in low efficiency and difficulty quickly covering large areas. Furthermore, the labor and time costs are high. Furthermore, if emergencies occur, manual inspections are difficult to detect and respond to in a timely manner, resulting in an inability to effectively control risks.
[0039] Therefore, how to improve the detection efficiency of pipeline anomalies is an urgent problem to be solved.
[0040] Based on this, the present application provides a pipeline anomaly detection method, electronic device, storage medium and program product, including: obtaining environmental information of the area to be detected where the pipeline is located; the environmental information includes: regional images and sensor data of the area to be detected; the sensor data includes: temperature data, smoke data, rainfall data and wind data; the pipeline is used to transmit flammable fluids; based on the environmental information, determining the pipeline anomaly recognition result of the area to be detected; when the anomaly recognition result indicates that there is an anomaly around the pipeline, sending an alarm prompt message. By integrating regional images and multi-type sensor data, not only can changes in the environment around the pipeline be detected in a timely manner, improving the efficiency of pipeline anomaly detection, but the image can also intuitively show whether the pipeline appearance is damaged or deformed, the sensor data can reflect the potential impact of environmental factors on the pipeline, and multi-dimensional information fusion improves the accuracy of anomaly recognition and reduces misjudgments and missed judgments. When the anomaly recognition result shows that there is an anomaly and sends an alarm message to prompt, relevant personnel can respond quickly according to the alarm message.
[0041] The pipeline anomaly detection method, electronic device, storage medium and program product provided by this application are introduced below with reference to the accompanying drawings.
[0042] like Figure 1 As shown, the present application proposes a pipeline anomaly detection system, including: a camera 10, a sensor 20 and a server 30.
[0043] As a possible implementation, the camera 10 is used to obtain an image of the area to be inspected where the pipeline is located.
[0044] The sensor 20 is used to obtain sensor data of the area to be inspected where the pipeline is located. The sensors include at least a temperature sensor, a smoke sensor, a rain sensor, and a wind sensor. Therefore, the sensor data includes at least temperature data, smoke data, rain data, and wind data.
[0045] The server 30 obtains the regional image and sensor data of the area to be detected, and determines the pipeline abnormality recognition result of the area to be detected based on the regional image and sensor data of the area to be detected, and determines whether to issue an alarm prompt.
[0046] In one possible implementation, the pipeline anomaly detection system may further include an edge device. The edge device is configured to determine an anomaly identification result for the pipeline in the area to be detected based on the regional image and sensor data of the area to be detected, and transmit the anomaly identification result to a server. If the anomaly identification result indicates an anomaly around the pipeline, the server transmits an alarm prompt message.
[0047] It should be noted that when performing regional image acquisition, edge devices from different manufacturers may use different algorithms to determine the abnormality recognition results of the pipelines in the inspection area based on the regional images and sensor data. If the edge devices use their own unique recognition algorithms to determine the abnormality recognition results of the pipelines, it will lead to poor system compatibility.
[0048] As a possible implementation method, the pipeline anomaly detection system of the embodiment of the present application uses a unified recognition algorithm to ensure that various devices can understand and interact with each other at the data level, achieving seamless docking and collaborative work.
[0049] In one possible implementation, Figure 2 The technical architecture of the unified recognition algorithm, as shown in Figure 1, includes: First, the pipeline anomaly detection algorithm and model are determined. This step can be completed on a cloud server or the server of the pipeline anomaly detection system. The updated algorithm and model are then embedded and deployed in edge devices using Hypertext Transfer Protocol (HTTP). The edge devices then determine pipeline anomaly recognition results for the target area based on area images captured by cameras and sensor data collected by sensors.
[0050] like Figure 2 As shown (sensors are not shown), there are n edge devices and n cameras, and the edge devices and cameras correspond one to one.
[0051] It should be noted that the camera can obtain video data of the area to be detected, and the area to be detected needs to include multiple cameras to ensure full coverage of the area to be detected. These videos from different sources are stored in the server's memory in a scattered manner. In order to facilitate user viewing, these different sources are integrated into a unified intelligent recognition platform to centrally manage and schedule video data.
[0052] However, with the continuous development of technology, cameras produced at different times may use different technologies, resulting in differences in data formats. Cameras of different brands may adopt unique data formats or communication protocols. Therefore, the data formats of multiple cameras in a detection area may be different. Therefore, the data formats of cameras can be unified to achieve a unified intelligent recognition platform.
[0053] As a possible implementation, Figure 3 As shown, the intelligent recognition platform can be unified and implemented through service hooking and data transfer based on streaming media services. The whole process is to first connect the camera group and the back-end service of the intelligent recognition platform, establish the binding hook between the camera (public network and local area network) and the video background data, and the camera needs to support the international 281811 protocol. Then, the back-end service and the streaming media service are connected. The camera sends the video stream information to the streaming media service through the hook protocol. The streaming media service organizes the video stream information in a unified format to obtain the platform stream data and sends the platform stream data to the back-end service. The back-end service then encapsulates the platform stream data in http format to the front-end page, and the front-end page displays the video captured by the camera.
[0054] It should be noted that the processing process of the sensor data can refer to the above description and will not be repeated here.
[0055] As another possible implementation method, the alarm information also needs to be connected to the intelligent identification platform for display, and the access of the alarm information can be achieved through the communication technology system of intelligent monitoring equipment.
[0056] In one possible implementation, when the edge device corresponding to the device (including the camera and sensor) identifies an abnormality in the pipeline through an abnormality recognition algorithm, it sends a Transmission Control Protocol (TCP) message to the back-end service of the intelligent recognition platform. The TCP message carries alarm information, which includes text information and image information.
[0057] TCP messages are transmitted as hexadecimal packets, divided into header and body information. The first 14 bytes (2 hexadecimal digits, i.e., 14 * 2 = 28 bits of data) are the header information, followed by the body information. After receiving the TCP message, the backend service processes it and returns a response data in the same format (response header and response body).
[0058] It should be understood that the intelligent recognition platform unifies data from different cameras and can uniformly store, encode, decode, and transmit video streams from various channels, enabling the sharing and centralized control of video resources. Users can view and manage all relevant video surveillance footage on a single platform, improving the efficiency and convenience of video management.
[0059] It should be noted that since alarm information is associated with the video and sensor data captured by the camera, it is difficult to quickly and accurately associate the regional image and sensor data corresponding to the alarm information when an alarm event occurs. This results in the staff being unable to obtain on-site video footage as a reference in a timely manner when handling the alarm event, which may affect the judgment and processing efficiency of the alarm event. Therefore, this application proposes an intelligent monitoring and management (IMS) system that can connect alarm information and environmental information to the IMS system according to certain standards and interface specifications, and associate the alarm information with the environmental information.
[0060] like Figure 4 As shown in the figure, as a possible implementation method, the front-end interface of the intelligent recognition platform for interacting with users is integrated into the IMS system. First, the front-end interface code of the intelligent recognition platform is embedded into the interface framework of the IMS system, and then the data interface between the intelligent recognition platform and the IMS system is connected.
[0061] As another possible implementation method, the streaming media service and background service of the intelligent recognition platform are integrated into the IMS system.
[0062] It should be understood that centralized processing, storage, and distribution of environmental and alarm information is achieved. By integrating this information into the IMS system, the system can correlate and analyze environmental information and alarms. When an alarm is received, relevant video footage and sensor data can be quickly retrieved, providing managers with an intuitive understanding of the on-site situation, facilitating timely decision-making and appropriate measures. This also facilitates unified management of all environmental and alarm information within the system, improving system security and reliability.
[0063] It should be noted that the pipeline anomaly identification system of this application can also support the following functions:
[0064] (1) Communication management functions include status monitoring and connection quality management. Status monitoring supports real-time detection and display of digital certificates and session status of cameras and sensors, ensuring normal operation and communication security of cameras and sensors. Connection quality management provides detailed connection quality information, such as latency and bandwidth utilization, to help users evaluate communication status.
[0065] (2) Video viewing and playback functions include: support for real-time monitoring and historical playback. Real-time monitoring: Displays the video information captured by the device in real time on the front-end page. Historical playback: Provides historical video replay function, allowing users to select a specific time period for precise playback.
[0066] (3) The camera's real-time monitoring and control functions include: online status monitoring, connection quality information, PTZ control, and map positioning. Online status monitoring: displays the camera's online or offline status and monitors disconnections caused by network fluctuations. Connection quality information: provides information on the connection quality between the camera and the server. PTZ control: supports full-scale control of PTZ-enabled cameras, including rotation, zoom, etc., and the ability to set preset points. Map positioning: displays the camera's installation location on a map, allowing for an intuitive view of the camera's distribution.
[0067] (4) Sensor monitoring functions include: real-time monitoring, intelligent control, weather information display, and alarms. Real-time monitoring: Use monitoring equipment to monitor sensor status, performance, or operation in real time. Intelligent control: Intervene and adjust sensor operation status in real time through intelligent methods. Weather information display: Displays real-time weather information of the sensor area, including temperature, humidity, wind speed, etc. Alarm function: Monitors device sensor power, hardware information, location information, network information, and provides alarms.
[0068] (5) Real-time alarm monitoring functions include: intelligent identification, alarm information transmission, and alarm recording and query. Intelligent identification: The device is embedded with an intelligent identification program to monitor abnormal situations such as man-made damage or natural disasters in real time. Alarm information transmission: Real-time alarm information and images are transmitted to the platform for manual identification and processing. Alarm recording and query: Records the alarm events of the device and provides event query and statistics functions. Real-time monitoring of abnormal situations such as man-made damage or natural disasters, recording alarm events, and providing query functions.
[0069] It should be understood that the pipeline anomaly identification system adopts an integrated design. Through pipeline anomaly identification algorithms, real-time warning and response mechanisms, modularity and scalability, an anomaly detection system is constructed. By capturing regional images and using sensor data to provide multi-dimensional meteorological information, abnormal conditions around the pipeline can be more comprehensively perceived.
[0070] In some embodiments, the execution entity of the pipeline anomaly detection method of the present application can be a pipeline anomaly detection system, or it can be a server of the pipeline anomaly detection system, where the server can be a server cluster composed of multiple servers, or a single server, or a computer, or a processor or processing chip in a server or computer, or any other device or equipment with an existing pipeline anomaly detection function. The embodiments of the present application are not limited to this.
[0071] like Figure 5 As shown, the pipeline anomaly detection method provided by this application includes:
[0072] S501: Obtain environmental information of the area to be inspected where the pipeline is located.
[0073] The environmental information includes: an image of the area to be inspected and sensor data; the sensor data includes: temperature data, smoke data, rainfall data, and wind data. The pipeline is used to transport flammable fluids.
[0074] As a possible implementation manner, a regional image of the area to be detected is acquired by a camera, and the camera transmits the acquired regional image of the area to be detected to a server via a wired network (such as Ethernet) or a wireless network.
[0075] The camera can be installed at a suitable location around the area to be inspected to ensure that the area where the pipeline is located is covered. The camera can be fixed-angle or rotatable to obtain images from different angles.
[0076] As a possible implementation method, the temperature sensor, smoke sensor, rain sensor and wind sensor obtain temperature data, smoke data, rain data and wind data of the area to be detected, and transmit the temperature data, smoke data, rain data and wind data to the server through a wired network (such as Ethernet) or a wireless network.
[0077] S502: Determine pipeline anomaly recognition results in the area to be detected based on environmental information.
[0078] As a possible implementation, pipeline anomaly detection can be determined based on thresholds. Based on historical data on the pipeline's material, preset thresholds can be set for sensor data such as temperature, smoke, rainfall, and wind speed. For example, temperatures on normal days typically fluctuate within a certain range. When the temperature exceeds a certain upper threshold, it may indicate a potential fire in the area being detected. Smoke data exceeding the trace value typically seen in a normal environment may indicate a fire or other abnormality.
[0079] The acquired sensor data is compared with a set threshold. If any sensor data exceeds the threshold, the pipeline anomaly identification result is considered to be abnormal. Regional images can be analyzed according to a preset algorithm. For example, if image analysis detects obvious fractures or deformations on the pipeline surface, and if they reach a certain level, an abnormality is determined.
[0080] Another possible implementation method is to use a knowledge rule base to determine pipeline anomaly identification results. First, a knowledge rule base is established based on the rules governing the relationship between pipeline anomaly identification results and environmental information. For example, empirically, when wind speeds reach a certain level and persist for a period of time, combined with a significant change in soil moisture around the pipeline due to increased rainfall, abnormalities such as displacement or deformation may occur in the pipeline. The acquired environmental information is input into the knowledge rule base, and reasoning and judgment are performed based on the rules within the knowledge rule base. Through a comprehensive analysis of multiple environmental information factors, it is determined whether a pipeline anomaly exists, as well as the possible type and cause of the anomaly.
[0081] S503: When the abnormality identification result indicates that there is an abnormality around the pipeline, an alarm prompt message is sent.
[0082] As a possible implementation, an email server is configured to connect the IMS system to a text messaging platform. When an anomaly is detected around the pipeline, the system generates a detailed email with a description of the anomaly, images of the area to be inspected, and sensor data. Pre-defined recipient email addresses are added to the email list to initiate the delivery of the alarm email.
[0083] As another possible implementation, the alarm information is converted into a voice signal, and then the voice alarm information is played through a speaker or voice playback device connected to the system, so that on-site personnel can hear the alarm prompt in time.
[0084] Another possible implementation involves connecting audible and visual alarm devices: Install audible and visual alarm devices, such as warning lights and sirens, in the area to be inspected and connect them to the pipeline anomaly detection system via a hardware interface or communication protocol. When the system detects an anomaly, a control signal triggers the audible and visual alarm devices, emitting strong flashing lights and audible alarms to attract the attention of inspectors or pedestrians.
[0085] You can also set the sound and light alarm parameters according to the on-site environment and actual needs, such as the flashing frequency of the warning light, the volume and tone of the siren, etc. Different sound and light alarm modes can be set for different types or levels of abnormalities, so that on-site personnel can quickly distinguish the severity of the abnormal situation.
[0086] Another possible implementation method is to use pop-up windows on the server's display page. When an anomaly is detected around the pipeline, a modal pop-up window appears in the center of the page. This pop-up window prevents the user from interacting with the rest of the page until the user confirms or closes the pop-up window. Alternatively, the pop-up window can appear in a corner of the page, such as the upper right corner.
[0087] You can also set a fixed notification bar at a certain location on the page (at the top or bottom). When an alarm message is received, the notification bar will automatically expand and display the alarm content. The notification bar can use different colors to distinguish different alarm levels, such as red for severe alarms and yellow for general alarms. Users can click on the information in the notification bar to view detailed information and can also manually close the notification bar when no longer needed.
[0088] You can also set a dedicated alarm icon on the page. When a pipeline anomaly occurs, the icon will begin flashing or animating to attract the user's attention. Hovering the mouse over the icon will display a brief alarm message, such as "X pipeline anomalies." Clicking the icon will jump to a detailed alarm information page, showing the specific anomaly and related data.
[0089] This integration of regional images and multi-type sensor data not only allows for timely detection of changes in the pipeline's surrounding environment, improving the efficiency of pipeline anomaly detection, but also provides a visual representation of the pipeline's appearance, flames, pedestrians, construction machinery, and destructive behavior. Sensor data can reflect the potential impact of environmental factors on the pipeline. Multi-dimensional information fusion improves anomaly identification accuracy and reduces misjudgments and missed detections. When anomaly identification results indicate an anomaly and an alarm is issued, relevant personnel can respond quickly based on the alarm information.
[0090] In some embodiments, as Figure 6 As shown, the above S502 includes: including:
[0091] S601: Input environmental information into an anomaly recognition model, and use the anomaly recognition model to determine area information of an area to be detected based on the environmental information.
[0092] The area information includes at least one of the following: object information of a target object in the area to be detected, pipeline status information, and meteorological information of the area to be detected.
[0093] Target objects include flames or smoke, pedestrians, and mechanical equipment. Target object information includes: the size, location, and color of the flame or smoke; the location and posture of pedestrians; and the type, operating status, and location of mechanical equipment.
[0094] Pipeline status information includes: whether the pipeline is broken, whether the pipeline is exposed, and the color of the soil around the pipeline.
[0095] As a possible implementation method, after obtaining the environmental information, the environmental information is preprocessed to obtain the preprocessed environmental information, and then the environmental information is subjected to feature extraction, and the extracted features are input into the trained anomaly recognition model, and the model obtains the regional information of the area to be detected.
[0096] In some embodiments, the anomaly recognition model is a YOLOv5 model based on the PyTorch framework.
[0097] It should be understood that because the YOLOv5 model can detect images in a relatively short time, it can promptly detect anomalies and respond quickly to pipeline inspection areas that require real-time monitoring. The YOLOv5 model can also simultaneously detect multiple targets in an image. Whether it is environmental anomalies such as flames and smoke, or pipeline-related targets such as pedestrians and mechanical equipment, it can accurately identify them in the same image, providing comprehensive anomaly information.
[0098] The YOLOv5 model, based on the PyTorch framework, has good compatibility across different hardware platforms and operating systems, making it easy to deploy in practical applications. For example, it can be installed on monitoring devices or servers to identify anomalies in pipeline areas to be inspected.
[0099] S602: Determine the abnormality recognition result of the pipeline according to the regional information.
[0100] As a possible implementation manner, when the object information of the target object in the area to be detected meets a first preset condition, it is determined that the abnormality recognition result indicates that an abnormality exists around the pipeline.
[0101] In a possible implementation, after obtaining the object information, trajectory analysis is combined to determine the length of time a pedestrian stays, the movement trajectory of mechanical equipment, etc.
[0102] The first preset condition includes at least one of the following: the presence of smoke and flames in the area to be detected; the temperature in the area to be detected is greater than the temperature threshold; the length of time pedestrians stay in the area to be detected is greater than the time threshold; pedestrians in the area to be detected have abnormal behavior; abnormal behavior is used to indicate destructive behavior of pedestrians on the pipeline; mechanical equipment enters the area to be detected; the mechanical equipment in the area to be detected is in working condition.
[0103] As another possible implementation, when the pipeline status information in the area to be detected meets the second preset condition, it is determined that the abnormality recognition result indicates that an abnormality exists around the pipeline.
[0104] In a possible implementation, when the color of soil around the pipeline is greater than a preset color depth, it is determined that the pipeline has a leak.
[0105] The second preset condition includes at least one of the following: the pipeline in the area to be inspected is exposed and / or corroded and / or broken; there is a pipeline leakage in the area to be inspected.
[0106] As another possible implementation, when the meteorological information of the area to be detected meets a third preset condition, it is determined that the abnormality identification result indicates that an abnormality exists around the pipeline. The third preset condition includes: a natural disaster occurs in the area to be detected.
[0107] In some embodiments, the anomaly recognition model is trained in the following manner: obtaining a training data set, the training data set including: environmental information samples and target area information corresponding to the environmental information samples; inputting the environmental information samples into the initial anomaly recognition model, and determining the predicted area information based on the environmental information samples by the initial anomaly recognition model; training the initial anomaly recognition model based on the predicted area information and the target area information to obtain a trained anomaly recognition model.
[0108] As a possible implementation method, during the model training process, the model performance is evaluated based on indicators such as recognition accuracy, recall rate, and F1 score, and necessary model optimization is performed based on the evaluation results.
[0109] It should be understood that environmental information covers multiple data such as regional images, temperature, and smoke. The anomaly recognition model comprehensively processes this information and can more accurately determine whether the pipeline is abnormal. Compared with single information judgment, it greatly improves the accuracy of anomaly recognition and reduces false alarms and missed alarms.
[0110] The model can capture subtle abnormal changes in the early stages of pipeline operation. These subtle signals, after being analyzed and processed by the model, can provide early warning of potential failures or leakage risks, buying valuable time for taking measures.
[0111] In some embodiments, as Figure 7 As shown, the above S502 includes:
[0112] S701: Determine a first pipeline abnormality recognition result in the area to be detected based on sensor data in the area to be detected.
[0113] As one possible implementation, for each type of sensor data, a threshold is determined based on the distribution of sensor data during normal pipeline operation. The sensor data is then compared with the threshold to obtain a first pipeline anomaly identification result. For example, for a temperature sensor, if the temperature exceeds the threshold, it is determined that the pipeline may be anomaly.
[0114] S702: Determine a second pipeline abnormality recognition result in the area to be detected based on the area image of the area to be detected.
[0115] As a possible implementation method, the region image is input into an anomaly recognition model, such as a convolutional neural network (CNN). The model automatically learns the features in the region image to obtain the second pipeline anomaly recognition results.
[0116] S703 : Perform weighted summation on the first pipeline abnormality recognition result and the second pipeline abnormality recognition result to determine a pipeline abnormality recognition result.
[0117] It should be noted that because sensor detection and image detection each have their own advantages and disadvantages, using either method alone may result in false positives or missed detections. To improve the accuracy and reliability of the recognition results, the two results are weighted and summed. The sensor detection result is assigned a first weight, and the image detection result is assigned a second weight, with the sum of the first and second weights being 1. The first and second weights can be pre-set.
[0118] For example, a sensor can still obtain stable sensor data even when the environment changes, while image detection may be affected by environmental factors such as light and weather. In particular, at night, images are not clear, which can cause fluctuations in detection results. In this case, the sensor is more stable, so the first weight can be set to 1 and the second weight can be set to 0.
[0119] In an environment with stable lighting, since the accuracy of image data is higher than the accuracy of sensor data, the first weight can be set to 0 and the second weight can be set to 1.
[0120] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, the pipeline anomaly detection device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easy for those skilled in the art to realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0121] In the embodiments of the present application, the functional modules of the pipeline anomaly detection device can be divided according to the above method. For example, the pipeline anomaly detection device can include functional modules corresponding to the functional divisions, or two or more functions can be integrated into a single processing module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the module division in the embodiments of the present application is schematic and is only a logical functional division. In actual implementation, other division methods may be used.
[0122] Figure 8 This is a schematic diagram of the structure of a pipeline anomaly detection device provided in an embodiment of the present application. Figure 8 The pipeline anomaly detection device 800 includes: an acquisition unit 810 and a processing unit 820.
[0123] The acquisition unit 810 is used to obtain environmental information of the area to be detected where the pipeline is located; the environmental information includes: regional images and sensor data of the area to be detected; the sensor data includes: temperature data, smoke data, rainfall data and wind data; the pipeline is used to transmit combustible fluids.
[0124] The processing unit 820 is used to determine the pipeline anomaly recognition result of the area to be detected based on the environmental information; when the anomaly recognition result indicates that there is an anomaly around the pipeline, send an alarm prompt information.
[0125] In some embodiments, the processing unit 820 is specifically used to input environmental information into the anomaly recognition model, and determine the regional information of the area to be detected based on the environmental information through the anomaly recognition model, where the regional information includes at least one of the following: object information of the target object in the area to be detected, pipeline status information, and meteorological information of the area to be detected; based on the regional information, determine the abnormality recognition result of the pipeline.
[0126] In some embodiments, the processing unit 820 is specifically used to determine that the abnormality recognition result indicates that there is an abnormality around the pipeline when the object information of the target object in the area to be detected meets the first preset condition; the first preset condition includes at least one of the following: there is smoke and flames in the area to be detected; the temperature of the area to be detected is greater than the temperature threshold; the length of time that pedestrians stay in the area to be detected is greater than the time threshold; there are abnormal behaviors of pedestrians in the area to be detected; the abnormal behavior is used to indicate destructive behavior of pedestrians on the pipeline; mechanical equipment enters the area to be detected; the mechanical equipment in the area to be detected is in working condition.
[0127] In some embodiments, the processing unit 820 is specifically configured to determine that the abnormality identification result indicates that an abnormality exists around the pipeline when the pipeline status information in the area to be detected meets a second preset condition; the second preset condition includes at least one of the following: the pipeline in the area to be detected is exposed and / or corroded and / or broken; there is a pipeline leak in the area to be detected.
[0128] In some embodiments, the processing unit 820 is specifically configured to determine that the abnormality identification result indicates that an abnormality exists around the pipeline when the meteorological information of the area to be detected meets a third preset condition; the third preset condition includes: a natural disaster occurs in the area to be detected.
[0129] In some embodiments, the processing unit 820 is specifically used to determine a first pipeline abnormality recognition result of the area to be detected based on the sensor data of the area to be detected; determine a second pipeline abnormality recognition result of the area to be detected based on the regional image of the area to be detected; and perform weighted summation of the first pipeline abnormality recognition result and the second pipeline abnormality recognition result to determine the pipeline abnormality recognition result.
[0130] In some embodiments, the processing unit 820 is also used to obtain a training data set, which includes: environmental information samples and target area information corresponding to the environmental information samples; inputting the environmental information samples into the initial anomaly recognition model, and determining the predicted area information based on the environmental information samples through the initial anomaly recognition model; training the initial anomaly recognition model based on the predicted area information and the target area information to obtain a trained anomaly recognition model.
[0131] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 9 As shown, the electronic device 900 includes but is not limited to: a processor 901 and a memory 902.
[0132] The memory 902 is used to store executable instructions of the processor 901. It is understandable that the processor 901 is configured to execute instructions to implement the pipeline anomaly detection method in the above embodiment.
[0133] It should be noted that those skilled in the art can understand that Figure 9 The electronic device structure shown in the figure does not limit the electronic device, and the electronic device may include Figure 9 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.
[0134] The processor 901 is the control center of the electronic device. It uses various interfaces and lines to connect the various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 902 and calling data stored in the memory 902, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 901 may include one or more processing units. Optionally, the processor 901 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 901.
[0135] The memory 902 can be used to store software programs and various data. The memory 902 may mainly include a program storage area and a data storage area. The program storage area may store an operating system, application programs required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 902 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.
[0136] In an exemplary embodiment, a computer-readable storage medium including instructions is further provided, such as a memory 902 including instructions. The above instructions can be executed by the processor 901 of the electronic device 900 to implement the method in the above embodiment.
[0137] In actual implementation, Figure 8 The acquisition unit 810 and the processing unit 820 in the embodiment can be composed of Figure 9 The processor 901 in the embodiment calls the computer program stored in the memory 902. The specific execution process can be referred to the description of the method part in the above embodiment, which will not be repeated here.
[0138] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0139] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, which can be executed by the processor 901 of the electronic device to implement the method in the above embodiment.
[0140] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned method embodiment are implemented and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.
[0141] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete the full classification or partial functions described above.
[0142] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0143] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0144] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0145] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.
[0146] In the description of the embodiments of the present application, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.
[0147] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
Claims
1. A pipeline anomaly detection method, characterized in that: The method comprises: Acquiring environmental information of the area to be inspected where the pipeline is located; the environmental information includes: an area image of the area to be inspected and sensor data; the sensor data includes: temperature data, smoke data, rainfall data, and wind data; the pipeline is used to transport combustible fluid; Determining pipeline anomaly recognition results in the area to be detected based on the environmental information; When the abnormality identification result indicates that there is an abnormality around the pipeline, an alarm prompt message is sent.
2. The pipeline anomaly detection method according to claim 1, characterized in that: The determining of the abnormality identification result of the pipeline according to the environmental information includes: Inputting the environmental information into an anomaly recognition model, and determining regional information of the area to be detected based on the environmental information through the anomaly recognition model, wherein the regional information includes at least one of the following: object information of a target object in the area to be detected, pipeline status information, and meteorological information of the area to be detected; An abnormality identification result of the pipeline is determined based on the area information.
3. The pipeline anomaly detection method according to claim 2, characterized in that: Determining the abnormality identification result of the pipeline according to the area information includes: If the object information of the target object in the area to be detected meets a first preset condition, determining that the abnormality recognition result indicates that an abnormality exists around the pipeline; The first preset condition includes at least one of the following: There is smoke and flame in the area to be detected; The temperature of the area to be detected is greater than a temperature threshold; The length of time that pedestrians stay in the area to be detected is greater than a time threshold; There is abnormal behavior of pedestrians in the detection area; the abnormal behavior is used to indicate that the pedestrians have destructive behavior on the pipeline; Mechanical equipment enters the area to be inspected; The mechanical equipment in the area to be detected is in working condition.
4. The pipeline anomaly detection method according to claim 2, characterized in that: Determining the abnormality identification result of the pipeline according to the area information includes: If the pipeline status information in the area to be detected meets a second preset condition, determining that the abnormality recognition result indicates that an abnormality exists around the pipeline; The second preset condition includes at least one of the following: The pipelines in the area to be inspected are exposed and / or corroded and / or broken; There is a pipeline leakage in the area to be detected.
5. The pipeline anomaly detection method according to claim 2, characterized in that: Determining the abnormality identification result of the pipeline according to the area information includes: When the meteorological information of the area to be detected meets a third preset condition, determining that the abnormality recognition result indicates that an abnormality exists around the pipeline; The third preset condition includes: A natural disaster occurs in the area to be detected.
6. The pipeline anomaly detection method according to claim 1, characterized in that: Determining the pipeline anomaly recognition result of the to-be-detected area according to the environmental information includes: Determining a first pipeline abnormality recognition result in the area to be detected based on the sensor data in the area to be detected; determining a second pipeline abnormality recognition result of the area to be detected based on the area image of the area to be detected; A weighted sum is performed on the first pipeline abnormality identification result and the second pipeline abnormality identification result to determine the pipeline abnormality identification result.
7. The pipeline anomaly detection method according to claim 2, characterized in that: The anomaly recognition model is trained in the following way: Acquire a training data set, the training data set including: an environmental information sample and target area information corresponding to the environmental information sample; Inputting the environmental information sample into an initial anomaly recognition model, and determining prediction area information based on the environmental information sample by the initial anomaly recognition model; The initial anomaly recognition model is trained according to the predicted region information and the target region information to obtain a trained anomaly recognition model.
8. An electronic device, characterized in that: include: a processor and a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 7.
9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 7.
10. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are run on an electronic device, the electronic device is caused to perform the method according to any one of claims 1 to 7.