CN117765311A - Circuit image processing method and device and computer equipment - Google Patents

Abstract

The present application relates to a line image processing method, apparatus, computer device, storage medium, and computer program product. The method comprises the following steps: acquiring a line monitoring image, and determining the target category to which the line monitoring image belongs according to the image content; inputting the line monitoring image into a line fault detection model corresponding to a preset target class to obtain a line detection result; and determining a fault position and a fault type according to the line detection result, and reporting the line detection result to a maintenance center corresponding to the fault position and the fault type. By adopting the method, the intelligent detection and positioning of the line faults in the power system can be realized by combining the image analysis and the machine learning technology, and the maintenance efficiency and accuracy are improved.

Description

A circuit image processing method, device and computer equipment

Technical field

The present application relates to the technical field of power system monitoring, and in particular to a line image processing method, device, computer equipment, storage medium and computer program product.

Background technique

Line image and video monitoring technology has been developing rapidly in recent years and is widely used in the power and communications industries. It relies on the collection of a large amount of image and video data, and transforms the data into valuable information through image processing and machine learning technology to achieve real-time monitoring of line status, anomaly detection, fault diagnosis and prediction, etc.

However, in practical applications, we face some problems. First, due to the wide distribution range of the lines and complex weather conditions, it is difficult to collect line image data. Secondly, the state parameters of the lines are many and complex, and the detection requirements of different state parameters are also different. It is difficult to carry out comprehensive and effective monitoring; at the same time, the judgment and positioning of line anomalies require a high degree of accuracy, and traditional image processing methods are prone to misjudgments or missed judgments due to noise, light source, and resolution factors; finally, the amount of line image data is large , the need to quickly analyze and extract valuable information has become a challenge faced by data processing technology.

Traditional power system fault detection usually requires manual intervention to analyze and diagnose a large number of line images, which is time-consuming and labor-intensive. When a fault occurs, the real-time response and maintenance of traditional systems may be limited, making it difficult to handle the fault quickly. In addition, traditional methods may have certain limitations in the accuracy of fault identification, making it difficult to accurately determine the fault location and type. When a fault occurs, there is a lack of historical information reference, making it difficult to fully understand the environment and conditions when the fault occurred. The working environment of power systems is complex and changeable, and traditional methods are difficult to adapt to fault detection needs under various environmental conditions.

Contents of the invention

Based on this, it is necessary to provide a circuit image processing method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical problems.

In a first aspect, this application provides a line image processing method, which method includes:

Obtain a line monitoring image and determine the target category to which the line monitoring image belongs based on the image content;

Input the line monitoring image into the preset line fault detection model corresponding to the target category to obtain the line detection result;

The fault location and fault type are determined according to the line detection results, and the line detection results are reported to the maintenance center corresponding to the fault location and fault type.

In one embodiment, determining the target category to which the line monitoring image belongs based on the image content includes:

Identify the image content of the line detection image, determine the line installation environment and/or shooting weather conditions;

Determine the segmentation method and rules of line monitoring images according to the line erection environment and/or the shooting weather conditions;

In one embodiment, the method further includes:

Load a line image material set, which contains a large number of faulty line images marked with fault locations and fault types, as well as normal line images;

Divide the line image material set into line image material subsets corresponding to multiple categories according to the line installation environment and/or shooting weather conditions;

Use subsets of line image materials corresponding to different categories to train the initial image recognition model and generate line fault detection models corresponding to different categories.

In one embodiment, after reporting the line detection result to the maintenance inspection center corresponding to the fault location and fault type, the method further includes:

Receive the real fault location and real fault type fed back by the maintenance inspection center, and mark the line monitoring image;

The line fault detection model corresponding to the target category is trained based on the marked line monitoring images.

In one embodiment, after determining the fault location and fault type based on the line detection results, the method further includes:

Obtain historical line monitoring images containing the fault location near the shooting time;

Determine the time of line change based on historical line monitoring images;

Send historical line monitoring images corresponding to each line change moment to the maintenance inspection center.

In one embodiment, the method further includes:

Summarize line detection results and count fault locations and fault types;

According to the status parameters of the line corresponding to the fault location and fault type, a reference plan for line material selection and line erection planning is generated.

In a second aspect, this application also provides a circuit image processing device, which includes:

The image processing module is used to obtain line monitoring image data and process the obtained image data;

The image analysis module is used to select and run the line detection model, analyze the input line monitoring image data, and output the line detection results;

The communication module is used to report the line detection results to the maintenance center corresponding to the fault location and fault type.

In a third aspect, this application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

Obtain a line monitoring image and determine the target category to which the line monitoring image belongs based on the image content;

Input the line monitoring image into the preset line fault detection model corresponding to the target category to obtain the line detection result;

The fault location and fault type are determined according to the line detection results, and the line detection results are reported to the maintenance center corresponding to the fault location and fault type.

In a fourth aspect, this application also provides a computer-readable storage medium. The computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by the processor, the following steps are implemented:

Obtain a line monitoring image and determine the target category to which the line monitoring image belongs based on the image content;

Input the line monitoring image into the preset line fault detection model corresponding to the target category to obtain the line detection result;

The fault location and fault type are determined according to the line detection results, and the line detection results are reported to the maintenance center corresponding to the fault location and fault type.

In a fifth aspect, this application also provides a computer program product. The computer program product includes a computer program that implements the following steps when executed by a processor:

Obtain a line monitoring image and determine the target category to which the line monitoring image belongs based on the image content;

Input the line monitoring image into the preset line fault detection model corresponding to the target category to obtain the line detection result;

The fault location and fault type are determined according to the line detection results, and the line detection results are reported to the maintenance center corresponding to the fault location and fault type.

The above-mentioned line image processing methods, devices, computer equipment, storage media and computer program products determine the target category to which the image belongs by performing content analysis on the line monitoring images. It improves the system's ability to understand line images and provides a basis for target categories for subsequent fault detection. Input the image into the line fault detection model corresponding to the preset target category to obtain the line detection results. Automated line fault detection is achieved through pre-trained models, improving detection accuracy and efficiency. Determine the fault location and fault type based on the line detection results, and report the results to the maintenance center corresponding to the fault location and fault type. It realizes automatic identification and location of faults and reports the results in a timely manner, improving the response speed and accuracy of fault management. Through the machine learning model, automatic detection of faults in line images is achieved, reducing the burden of manual analysis. Fault information can be reported to the maintenance center in real time, which helps timely response and maintenance. Improved accuracy of line fault location and type through image content analysis and machine learning models. Automatic fault location and type positioning is achieved, providing a basis for subsequent maintenance decisions. Sending historical images to the maintenance center helps maintenance personnel gain a more comprehensive understanding of the environment and conditions when the failure occurred. Overall, this line image processing method achieves intelligent detection and location of line faults in the power system by combining image analysis and machine learning technology, improving maintenance efficiency and accuracy.

Description of drawings

Figure 1 is a schematic flow chart of a line image processing method in one embodiment;

Figure 2 is a schematic flow chart of a line image processing method in one embodiment;

Figure 3 is a schematic flow chart of a line image processing method in one embodiment;

Figure 4 is a schematic flow chart of a line image processing method in one embodiment;

Figure 5 is a schematic flowchart of a line image processing method in one embodiment;

Figure 6 is a schematic flowchart of a line image processing method in one embodiment;

Figure 7 is a schematic structural diagram of a line image processing device in one embodiment;

Figure 8 is a schematic structural diagram of the computer equipment of the circuit image processing device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

The line image processing method provided by the embodiment of the present application can be applied in the field of power system monitoring and maintenance to ensure the stable operation of the power network, reduce the occurrence of faults, and improve maintenance efficiency. This line image processing method can be executed by the computing equipment of the power system maintenance center.

In one embodiment, as shown in Figure 1, a line image processing method is provided. The method includes:

Step 102: Obtain the line monitoring image and determine the target category to which the line monitoring image belongs based on the image content;

Among them, obtaining line monitoring images refers to obtaining static or dynamic image data from relevant areas of the power system through appropriate equipment or sensors, such as surveillance cameras, high-resolution sensors, etc. Determining the target category to which the image belongs based on the image content refers to identifying and classifying objects or scenes in line monitoring images through image processing and analysis technology to determine the specific target category to which the image belongs.

In implementation, specially designed equipment, such as surveillance cameras or other sensors, are used to capture images of lines and related equipment in the power system, which may include visual information from various angles and perspectives. And use image processing algorithms to analyze and interpret the captured line monitoring images to identify objects, structures or features present in the images and classify them into predefined target categories.

In this step, the system first collects line monitoring images, then uses advanced image processing technology to identify key features in the images, and finally determines the target category to which the image belongs. This step provides basic information for subsequent fault detection and maintenance, helping the system to more accurately understand the current status of the power system.

Step 104: Input the line monitoring image into the line fault detection model corresponding to the preset target category to obtain the line detection result;

Among them, inputting line monitoring images refers to passing previously acquired line monitoring images to subsequent processing steps for further analysis and diagnosis. The line fault detection model corresponding to the preset target category refers to a pre-built and trained model that can perform fault detection and analysis on line monitoring images of a specific target category. Obtaining line detection results refers to processing the input line monitoring images through the model to generate information about faults or problems in the images.

In implementation, previously acquired line monitoring images are introduced into the system through data transmission or input interfaces to provide input data for subsequent line fault detection processes. For the previously determined target categories, the system designs, trains and optimizes a model in advance, which can effectively identify possible faults or anomalies in line monitoring images. Use the preset line fault detection model to analyze and calculate the input line monitoring images, and finally generate detection results about the line status, which may include information such as the location and type of the fault.

In this step, the system uses a pre-trained line fault detection model to process the acquired line monitoring images to obtain detailed information about the line status. This information will provide a basis for subsequent fault location and maintenance, and help the system realize automated monitoring and fault diagnosis of the power system.

Step 106: Determine the fault location and fault type based on the line detection results, and report the line detection results to the maintenance center corresponding to the fault location and fault type.

Among them, determining the fault location and fault type based on the line detection results means using the previously obtained line detection results and analyzing the information in the results to accurately locate the fault location in the power line and determine the specific type of the fault. Reporting the line detection results means sending the information obtained from the line detection to the designated target location for further processing or taking corresponding actions. To the maintenance and inspection center corresponding to the fault location and fault type means sending the line detection results to the central maintenance and inspection center corresponding to the fault location and type for further processing and response.

In implementation, by analyzing the line detection results, the system can accurately confirm the location of the fault in the power system, identify the type of fault, and provide detailed fault location and diagnostic information for subsequent maintenance work. Key information such as fault location and fault type determined based on line detection results will be sent to a specialized maintenance and inspection center through communication channels or network transmission mechanisms for maintenance and management. The obtained line detection results are directly transmitted to the professional maintenance center that matches the confirmed fault location and fault type to facilitate timely maintenance work and fault handling.

In this step, the system determines the location and type of the fault through detailed analysis of the line detection results, and reports this key information to a specialized maintenance center for targeted and timely maintenance and fault handling. This helps minimize the impact of potential faults in the power system on overall system stability and reliability.

In the above line image processing method, the target category to which the image belongs is determined by performing content analysis on the line monitoring image. It improves the system's ability to understand line images and provides a basis for target categories for subsequent fault detection. Input the image into the line fault detection model corresponding to the preset target category to obtain the line detection results. Automated line fault detection is achieved through pre-trained models, improving detection accuracy and efficiency. Determine the fault location and fault type based on the line detection results, and report the results to the maintenance center corresponding to the fault location and fault type. It realizes automatic identification and location of faults and reports the results in a timely manner, improving the response speed and accuracy of fault management.

Through the machine learning model, automatic detection of faults in line images is achieved, reducing the burden of manual analysis. Fault information can be reported to the maintenance center in real time, which helps timely response and maintenance. Improved accuracy of line fault location and type through image content analysis and machine learning models. Automatic fault location and type positioning is achieved, providing a basis for subsequent maintenance decisions. Sending historical images to the maintenance center helps maintenance personnel gain a more comprehensive understanding of the environment and conditions when the failure occurred. Overall, this line image processing method achieves intelligent detection and location of line faults in the power system by combining image analysis and machine learning technology, improving maintenance efficiency and accuracy.

In one embodiment, as shown in Figure 2, the target category to which the line monitoring image belongs is determined based on the image content, including:

Step 1021, identify the image content of the line detection image, determine the line installation environment and/or shooting weather conditions;

Among them, identifying the image content of the line detection image refers to using image processing and analysis technology to identify objects, structures or features contained in the line detection image to obtain detailed information about the image content. Determining the line installation environment and/or shooting weather conditions refers to determining the environmental conditions of the line monitoring images taken based on the identified image content, including the surrounding environment of the line and the weather conditions at the time of shooting.

In implementation, through advanced image processing of line monitoring images, the system is able to identify various elements in the image, such as power lines, equipment, vegetation or other relevant features, to obtain a detailed description of the line status. Based on the analysis of the image content, the system can infer the environment in which the line is set up, such as urban, rural or mountainous areas, as well as the weather conditions when the image was taken, such as sunny, rainy or snowy days.

In this step, the system performs image processing and content analysis on the line detection image to identify elements and features in the image, and based on this information, infers the environment in which the line was set up and the weather conditions at the time of shooting. Such information contributes to a more comprehensive understanding of line monitoring images, providing more context for subsequent fault detection and maintenance decisions.

Step 1022, determine the segmentation method and rules of the line monitoring image according to the line installation environment and/or shooting weather conditions;

Among them, based on the line setting environment and/or shooting weather conditions means that based on the previously determined line setting environment and the weather conditions at the time of shooting, the system infers the specific conditions that may exist in the line monitoring image, such as light intensity, visibility, etc. Determining the segmentation methods and rules for line monitoring images refers to formulating specific methods and rules for image segmentation based on previously acquired environmental and weather information to decompose the image into smaller areas or blocks for more refined analysis and processing . The specific steps and process of segmenting the image are to cut or divide the acquired line monitoring image into small image areas for subsequent analysis and processing; the specific steps of segmenting the image include determining the method and rules of segmentation, such as Divide the mesh or divide it into specific areas, and save the divided image as an independent image file or data.

During implementation, by analyzing the line setting environment and shooting weather conditions, the system can understand the various environmental factors that the image may be affected by, thereby better adapting to the image processing strategy. For different line setting environments and shooting weather conditions, the system can use specific image segmentation strategies to decompose large images into appropriate parts to improve the efficiency and accuracy of subsequent processing.

In this step, the system combines information about the line setting environment and shooting weather conditions to design and implement image segmentation methods and rules suitable for specific conditions. Such a segmentation strategy helps optimize the processing of line monitoring images to better adapt to different environments and weather conditions, and improve the robustness and accuracy of processing.

It should be noted that in this embodiment, the line image classification can also be performed in combination with the line load parameters. During the image content analysis process, the line load parameters, such as current, voltage, power, etc., are simultaneously obtained. The image content features and load parameter features are fused to form a comprehensive feature vector. Combined with the line installation environment and weather conditions, the relationship between the load parameters of the line and the image content is analyzed. According to the changes in load parameters, dynamic segmentation methods and rules are formulated to adapt to the characteristics of line images under different load conditions.

The scheme for classifying line images based on load parameters is as follows:

Fusion of line load parameter information and image content features to form a more comprehensive feature representation;

Update the line image classification model. Taking into account the fused features, you can choose to use models such as deep neural networks to learn more complex feature relationships;

In the preprocessing stage of line images, the image segmentation method is dynamically adjusted based on real-time load parameter information to ensure that the model can better adapt to images under different load conditions.

By combining the load parameters of the line, the system can more comprehensively understand the working status of the line and adjust the image processing and classification strategy according to different load conditions, thereby improving the accuracy and adaptability of line image classification. This solution can more comprehensively consider the actual working environment of the line in power system monitoring, making the system more intelligent and robust.

In one embodiment, as shown in Figure 3, the method further includes:

Step 202, load the line image material set. The line image material set contains a large number of faulty line images marked with fault locations and fault types, as well as normal line images;

Among them, loading the line image material set refers to loading the pre-prepared line image material set into the system so that the system can use these images for model training and learning. The line image material set contains faulty line images marked with fault location and fault type. This means that the material set contains line images that have been marked with actual fault location and fault type information. These images are used to train the model to identify faults. Normal line images refer to the loaded line image material set, which also includes line images under normal operating conditions, and are used for model training to identify normal conditions.

In the implementation, the material set containing various line images is loaded into the storage or memory of the system to provide the required input data for subsequent machine learning model training. In the loaded material set, there are a large number of line images. The fault locations and fault types in these images have been annotated by professionals, providing supervised training data for the model. In addition to including fault images, the material set also includes line images without faults to ensure that the model can distinguish between normal and abnormal conditions and improve the generalization ability of the model.

In this step, the system provides training data for the subsequent machine learning model by loading a line image material set containing rich information. The material set contains images of faulty lines marked with actual fault information, as well as images of normal lines, which helps the training model to accurately identify fault conditions in the power system.

Step 204: Divide the line image material set into line image material subsets corresponding to multiple categories according to the line installation environment and/or shooting weather conditions;

Among them, the line image material set refers to a collection of line images used for training and learning, including marked fault line images and normal line images. According to the route setting environment and/or shooting weather conditions, it means to classify or group the images based on the shooting environment and weather conditions of the route images, so as to conduct more targeted model training. Line image material subsets corresponding to multiple categories refer to dividing the images into multiple subsets based on different environmental and weather conditions based on the entire line image material set, and each subset corresponds to a specific type of condition.

In implementation, a dataset consisting of a variety of line images is used to provide the machine learning model with the diverse data required for training. According to the specific environmental conditions and shooting weather conditions of the line images, the images in the material set are classified into categories to provide more refined training data. The line image material set is subdivided into multiple small collections, each collection representing an image category under a specific line setting environment and/or shooting weather conditions, in order to train the model in a more targeted manner.

In this step, the system divides the entire line image material set into multiple subsets based on the installation environment of the line image and the shooting weather conditions. This classification helps the model better understand line images under different conditions and improves the model's adaptability to diverse environments.

Step 206: Use subsets of line image materials corresponding to different categories to train an initial image recognition model and generate line fault detection models corresponding to different categories.

The line image material subsets corresponding to different categories refer to each subset obtained in step 204, and each subset represents an image category under a specific line construction environment and/or shooting weather conditions. Training the initial image recognition model refers to using machine learning technology to build an initial image recognition model by training line images to identify key features and patterns in the image. Generating line fault detection models corresponding to different categories means generating line fault detection models suitable for different categories of conditions based on the initial image recognition model through further training and adjustment.

In the implementation, small sets are formed according to different environmental and weather conditions, and each small set contains line images corresponding to specific conditions. Using subsets of line image materials corresponding to different categories, through training algorithms and optimization of model parameters, an initial image recognition model is established so that it can understand line images under different environments and weather conditions. Using the initial image recognition model, further model training and optimization are performed on the subset of line image materials corresponding to each category to generate a line fault detection model for specific environments and weather conditions.

In this step, the system uses the divided line image material subsets corresponding to different categories to establish an initial image recognition model through the machine learning training process. Then, by further training and adjusting this initial model, line fault detection models suitable for different conditions are generated to improve the sensitivity and accuracy of the model to diverse conditions.

In one embodiment, as shown in Figure 4, after the line detection results are reported to the maintenance center corresponding to the fault location and fault type, it also includes:

Step 302: Receive the real fault location and real fault type fed back by the maintenance inspection center, and mark the line monitoring image;

Among them, receiving feedback from the maintenance and inspection center refers to obtaining actual information about the line fault from the maintenance and inspection center, including the real fault location and the real fault type. The real fault location and real fault type refer to the accurate information about line faults provided by the maintenance inspection center. The real fault location represents the exact location where the fault occurs, and the real fault type represents the specific type of fault that occurred. Marking line monitoring images refers to marking the corresponding line monitoring images based on the real fault location and real fault type fed back by the maintenance inspection center to display the actual location and type of the fault.

During implementation, the system obtains actual fault information through the communication channel with the maintenance and inspection center, which is confirmed and calibrated by professionals. The maintenance center provides feedback on the exact location and type of line fault, which is derived from on-site inspection and analysis. The real fault information obtained from the maintenance inspection center is associated with the corresponding line monitoring image, and the location and type of the actual fault are indicated on the image through marking, annotation or other means.

In this step, the system receives actual fault information from the maintenance center, and then associates this information with the corresponding line monitoring images so that the real fault location and fault type are marked on the image. This helps the system perform subsequent model evaluation and improvement, improving the accuracy of the model for real fault conditions.

Step 304: Train a line fault detection model corresponding to the target category based on the marked line monitoring images.

The marked line monitoring image refers to marking the line monitoring image according to the real fault location and the real fault type fed back by the maintenance inspection center in step 302 to display the actual location and type of the fault. The line fault detection model corresponding to the target category refers to the line fault detection model corresponding to different categories generated in step 206, and is used to identify line faults under specific environmental and weather conditions. Training the model refers to using the marked line monitoring images to further train the line fault detection model corresponding to the target category through the optimization of the training algorithm and model parameters.

During implementation, the system has established a series of specialized line fault detection models for different categories of environmental and weather conditions, with each model used to handle fault detection under specific conditions. Line monitoring images with real fault information are used to iteratively train the corresponding line fault detection model to improve the fault identification accuracy of the model in real environments. Labeled line monitoring images are manually or automatically labeled images with real fault information, which can be used for model training.

In this step, the system uses the marked line monitoring images to further train the line fault detection model under specific environmental and weather conditions by adjusting the training algorithm and model parameters. This helps the model better adapt to the diversity in real environments and improves the reliability of fault detection.

In one of the embodiments, as shown in Figure 5, after determining the fault location and fault type based on the line detection results, it also includes:

Step 402: Obtain historical line monitoring images containing fault locations near the shooting time;

Wherein, obtaining the shooting time that is close refers to obtaining relevant information or data in a time period that is close to or adjacent to the current shooting time. Historical line monitoring images containing fault locations refer to historical line monitoring images with previous fault locations, which are used to analyze and study the context and trends of fault occurrences.

In the implementation, around the shooting time of the current line monitoring image, other relevant information close to the time is obtained for comparison and analysis. Obtain line monitoring images containing previous fault locations that were captured in a historical time period close to the current shooting moment. These images can be used to understand the historical background and changes of the fault.

In this step, the system obtains historical line monitoring images that are similar to the current shooting time. These images contain information about the location of previous faults. This helps the system analyze the historical evolution and trends of faults, providing more comprehensive information to support fault detection and maintenance decisions.

Step 404: Determine the line change time based on historical line monitoring images;

Among them, historical line monitoring images refer to images with line status at past time points, which are used to understand changes in lines at different times. Determining the line change moment refers to analyzing the historical line monitoring images to determine the time point when a substantial change or failure occurs in the line status.

In implementation, images containing line status information at previous points in time can be used to analyze trends and characteristics of lines over time. Using image processing and analysis technology, the system can identify the time when line status changes in historical line monitoring images to locate the moment when problems may occur.

In this step, the system uses historical line monitoring images and analyzes the image content to determine the time point when the line status changes substantially, that is, the line change moment. This helps understand line evolution trends and provides more context for fault diagnosis.

Step 406: Send historical line monitoring images corresponding to each line change moment to the maintenance inspection center.

The historical line monitoring image corresponding to the time when the line changes refers to the historical line monitoring image corresponding to the specific time when the line changes determined in step 404. Sending to the maintenance inspection center means sending the historical line monitoring images corresponding to the line change moments to the maintenance inspection center through communication channels so that professionals can conduct further inspection and analysis.

In implementation, for each determined line change moment, the system prepares and extracts corresponding historical line monitoring images for subsequent analysis and processing. Using communication protocols or network connections, the system transmits historical line monitoring images at each line change moment to the maintenance center to assist maintenance personnel in more comprehensively understanding the evolution of line status.

In this step, the system sends the historical line monitoring images corresponding to each determined line change moment to the maintenance center so that professionals can conduct detailed inspection and analysis in terms of fault diagnosis and maintenance. This helps provide more comprehensive information to support the decision-making and operations of the maintenance inspection center.

In one embodiment, as shown in Figure 6, the method further includes:

Step 502: Summarize the line detection results and count fault locations and fault types;

Among them, summarizing line detection results refers to collecting and integrating line detection results obtained from different line monitoring images to form comprehensive fault information. Statistical fault location and fault type refers to analyzing the summarized line detection results, calculating and summarizing the fault location and fault type, and forming a statistical report.

In the implementation, the detection results from line monitoring images at various time points and under different conditions are centralized and summarized in order to have a comprehensive understanding of the fault status of the entire line system. Based on the detection results of line monitoring images, the system performs statistics and calculations on the location of the fault and the specific type of fault, providing maintenance personnel with detailed fault information.

In this step, the system integrates and summarizes the detection results from line monitoring images under different times and conditions, and then makes statistics on fault locations and fault types. This helps generate comprehensive fault statistics reports, providing maintenance personnel with a clear overview of faults so that appropriate maintenance and repair measures can be taken.

Step 504: Generate a reference plan for line material selection and line erection planning based on the fault location and the status parameters of the line corresponding to the fault type.

Among them, the line status parameters corresponding to the fault location and fault type refer to obtaining the line status parameters related to each fault location and fault type, including current, voltage, temperature, etc. Generating a reference plan refers to using the line status parameters corresponding to the fault location and fault type to formulate recommended plans for material selection and line erection planning for maintenance and repair work.

In implementation, for each fault event, the system collects and analyzes various status parameters of the line corresponding to the fault location and fault type to fully understand the working status of the line. Based on the analysis of line status parameters, the system generates reference solutions for each fault location and fault type, including material selection and erection planning, to guide subsequent maintenance and repair operations.

In this step, the system provides detailed information about the working status of the line based on the line status parameters corresponding to the fault location and fault type, and generates corresponding reference plans to support maintenance personnel in line material selection and erection planning. This helps improve the accuracy and efficiency of maintenance decisions.

The following are examples of line material selection and line erection planning in this step:

Suppose a fault occurs at a cable connection point on a power transmission tower, and the fault type is damage to the cable insulation. The system obtains the following line status parameters based on the fault location and fault type: cable temperature rises and current fluctuates greatly. The reference solutions provided for this situation mainly focus on material selection. For example, considering the large current fluctuations, copper wires with better conductivity and stability are selected to meet the needs of current transmission. Or use high-temperature insulation materials that are resistant to electrical breakdown to adapt to rising cable temperatures.

Suppose a line connects a city and a suburb and has multiple points of failure. By analyzing the line status parameters corresponding to the fault location and type, the system learned that the current demand in the urban part is higher, while the suburban part may be affected by different weather conditions. The reference solutions provided for this situation mainly focus on line erection planning, such as using higher-capacity transmission lines in urban parts to meet current needs, and selecting insulation materials with anti-pollution and weather resistance to reduce the impact of weather conditions on lines. Impact. Consider using more stable transmission lines in suburban areas and choosing insulation materials suitable for different weather conditions to improve line reliability.

These two examples illustrate the process of line material selection and line erection planning based on the line status parameters corresponding to the fault location and type. Specific solutions will vary based on fault conditions and actual requirements. This comprehensive approach helps improve the maintainability and stability of the line.

It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

Based on the same inventive concept, embodiments of the present application also provide a line image processing device for implementing the above-mentioned line image processing method. The implementation scheme for solving the problem provided by this device is similar to the implementation scheme recorded in the above method. Therefore, for the specific limitations in the embodiments of one or more circuit image processing apparatuses provided below, please refer to the above description of the circuit image processing method. Limitations will not be repeated here.

In one embodiment, as shown in Figure 7, a line image processing device is provided, including: an image processing module 602, an image analysis module 604 and a communication module 606, wherein:

The image processing module 602 is used to obtain line monitoring image data and process the obtained image data.

The image analysis module 604 is used to select and run the line detection model, analyze the input line monitoring image data, and output the line detection results.

The communication module 606 is used to report the line detection results to the maintenance center corresponding to the fault location and fault type.

In one embodiment, the image analysis module 604 is also used to identify the image content of the line detection image, determine the line installation environment and/or shooting weather conditions;

Determine the segmentation methods and rules for line monitoring images based on the line installation environment and/or shooting weather conditions.

In one embodiment, the image analysis module 604 is also used to load a line image material set. The line image material set contains a large number of faulty line images marked with fault locations and fault types, as well as normal line images;

In one embodiment, the image processing module 602 is further used to divide the line image material set into line image material subsets corresponding to multiple categories according to the line setting environment and/or shooting weather conditions;

In one embodiment, the image analysis module 604 is also used to train an initial image recognition model using subsets of line image materials corresponding to different categories, and generate line fault detection models corresponding to different categories.

In one embodiment, the communication module 606 is also used to receive the real fault location and the real fault type fed back by the maintenance center,

In one embodiment, the image analysis module 604 is further used to label the line monitoring images, and to train the line fault detection model corresponding to the target category based on the labeled line monitoring images.

In one embodiment, the image processing module 602 is further used to obtain a historical line monitoring image containing a fault location close to the shooting time;

In one embodiment, the image analysis module 604 is also used to determine the line change moment based on historical line monitoring images;

In one embodiment, the communication module 606 is also used to send historical line monitoring images corresponding to each line change moment to the maintenance center.

In one embodiment, the image analysis module 604 is also used to summarize line detection results, count fault locations and fault types, and generate reference plans for line material selection and line erection planning based on the status parameters of the lines corresponding to the fault locations and fault types. .

Each module in the above-mentioned line image processing device can be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be shown in Figure 8 . The computer device includes a processor, a memory, an input/output interface (Input/Output, referred to as I/O), and a communication interface. Among them, the processor, memory and input/output interface are connected through the system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The database of the computer device is used to store line image processing data. The input/output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. The computer program implements a circuit image processing method when executed by a processor.

Those skilled in the art can understand that the structure shown in Figure 8 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.

In one embodiment, a computer device is also provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the steps in the above method embodiments.

In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the steps in the above method embodiments.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

In one embodiment, a computer program product is provided, including a computer program that implements the steps in each of the above method embodiments when executed by a processor.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage. In the media, when executed, the computer program may include the processes of the above method embodiments. Any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random) Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene memory, etc. Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration and not a limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM). The databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto. The processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to this.

The technical features of the above embodiments can be combined in any way. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, all possible combinations should be used. It is considered to be within the scope of this manual.

The above-described embodiments only express several implementation modes of the present application, and their descriptions are relatively specific and detailed, but should not be construed as limiting the patent scope of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all fall within the protection scope of the present application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims (10)

1. A circuit image processing method, characterized in that the method includes: Obtain a line monitoring image and determine the target category to which the line monitoring image belongs based on the image content; Input the line monitoring image into the preset line fault detection model corresponding to the target category to obtain the line detection result; The fault location and fault type are determined according to the line detection results, and the line detection results are reported to the maintenance center corresponding to the fault location and fault type. 2. The line image processing method according to claim 1, characterized in that determining the target category to which the line monitoring image belongs according to the image content includes: Identify the image content of the line detection image, determine the line installation environment and/or shooting weather conditions; According to the line installation environment and/or the shooting weather conditions, the segmentation method and rules of the line monitoring images are determined. 3. The line image processing method according to claim 2, characterized in that the method further includes: Load a line image material set, which contains a large number of faulty line images marked with fault locations and fault types, as well as normal line images; Divide the line image material set into line image material subsets corresponding to multiple categories according to the line installation environment and/or shooting weather conditions; Use subsets of line image materials corresponding to different categories to train the initial image recognition model and generate line fault detection models corresponding to different categories. 4. The line image processing method according to claim 1, characterized in that after reporting the line detection result to the maintenance inspection center corresponding to the fault location and fault type, it further includes: Receive the real fault location and real fault type fed back by the maintenance inspection center, and mark the line monitoring image; The line fault detection model corresponding to the target category is trained based on the marked line monitoring images. 5. The line image processing method according to claim 4, characterized in that after determining the fault location and fault type according to the line detection results, it further includes: Obtain historical line monitoring images containing the fault location near the shooting time; Determine the line change moment based on historical line monitoring images; Send historical line monitoring images corresponding to each line change moment to the maintenance inspection center. 6. The line image processing method according to claim 1, characterized in that the method further includes: Summarize line detection results and count fault locations and fault types; According to the status parameters of the line corresponding to the fault location and fault type, a reference plan for line material selection and line erection planning is generated. 7. A circuit image processing device, characterized in that the device includes: The image processing module is used to obtain line monitoring image data and process the obtained image data; The image analysis module is used to select and run the line detection model, analyze the input line monitoring image data, and output the line detection results; The communication module is used to report the line detection results to the maintenance center corresponding to the fault location and fault type. 8. A computer device, comprising a memory and a processor, the memory stores a computer program, wherein the method of any one of claims 1 to 6 is implemented when the processor executes the computer program. step. 9. A computer-readable storage medium with a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented. 10. A computer program product, comprising a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 6.