CN117765311A - Circuit image processing method and device and computer equipment - Google Patents
Circuit image processing method and device and computer equipment Download PDFInfo
- Publication number
- CN117765311A CN117765311A CN202311719732.1A CN202311719732A CN117765311A CN 117765311 A CN117765311 A CN 117765311A CN 202311719732 A CN202311719732 A CN 202311719732A CN 117765311 A CN117765311 A CN 117765311A
- Authority
- CN
- China
- Prior art keywords
- line
- fault
- image
- line monitoring
- detection result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 claims abstract description 116
- 238000012544 monitoring process Methods 0.000 claims abstract description 113
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000004590 computer program Methods 0.000 claims abstract description 28
- 238000010191 image analysis Methods 0.000 claims abstract description 13
- 239000000463 material Substances 0.000 claims description 51
- 238000012545 processing Methods 0.000 claims description 40
- 238000012549 training Methods 0.000 claims description 29
- 230000008859 change Effects 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 14
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 abstract description 29
- 238000010801 machine learning Methods 0.000 abstract description 13
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000000875 corresponding effect Effects 0.000 description 68
- 238000004458 analytical method Methods 0.000 description 22
- 238000010586 diagram Methods 0.000 description 9
- 230000007613 environmental effect Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000003709 image segmentation Methods 0.000 description 4
- 230000008439 repair process Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000011810 insulating material Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
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
Technical Field
The present disclosure relates to the field of power system monitoring technology, and in particular, to a line image processing method, an apparatus, a computer device, a storage medium, and a computer program product.
Background
The line image video monitoring technology is a technology which is rapidly developed in recent years, is widely applied in the power and communication industries, relies on a large amount of image and video data acquisition, converts the data into valuable information through image processing and machine learning technologies, and achieves the functions of monitoring line states in real time, detecting anomalies, diagnosing faults, predicting the faults and the like;
However, in practical application, problems are faced, firstly, because the distribution range of the line is wide, the weather condition is complex, and the acquisition of the line image data is difficult; secondly, the state parameters of the circuit are more and complex, the detection requirements of different state parameters are different, and the comprehensive and effective monitoring is difficult; meanwhile, high accuracy is required for judging and positioning the line abnormality, and the traditional image processing method is easy to misjudge or miss judge due to noise, light source and resolution factors; finally, the large amount of line image data requires rapid analysis and extraction of valuable information, which is a challenge for data processing technology.
The traditional power system fault detection generally needs to be manually participated in, and a large number of line images are analyzed and diagnosed, so that time and labor are wasted. In the event of a failure, the real-time response and maintenance of conventional systems may be limited, resulting in difficulties in rapid handling of the failure. In addition, the conventional method may have a certain limitation in accuracy of fault identification, and it is difficult to accurately determine the position and type of the fault, and when the fault occurs, it is difficult to comprehensively understand the environment and conditions when the fault occurs due to lack of reference of historical information. The working environment of the power system is complex and changeable, and the traditional method is difficult to adapt to the fault detection requirements under various environmental conditions.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a line image processing method, apparatus, computer device, computer readable storage medium, and computer program product, in view of the above-described technical problems.
In a first aspect, the present application provides a line image processing method, including:
acquiring a line monitoring image, and determining a target category to which the line monitoring image belongs according to image content;
inputting the line monitoring image into a preset line fault detection model corresponding to the 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.
In one embodiment, the determining, according to the image content, the target category to which the line monitoring image belongs includes:
identifying the image content of the line detection image, and determining a line setting environment and/or shooting weather conditions;
determining a segmentation mode and a rule of a line monitoring image according to the line setting environment and/or the shooting weather condition;
in one embodiment, the method further comprises:
Loading a line image material set, wherein the line image material set comprises a large number of fault line images marked with fault positions and fault types and normal line images;
dividing the line image material set into line image material subsets corresponding to a plurality of categories according to line setting environments and/or shooting weather conditions;
and training an initial image recognition model by utilizing the line image material subsets corresponding to different categories, and generating line fault detection models corresponding to different categories.
In one embodiment, after the reporting the line detection result to the maintenance center corresponding to the fault location and the fault type, the method further includes:
receiving the real fault position and the real fault type fed back by the maintenance center, and marking the line monitoring image;
and training a line fault detection model corresponding to the target class based on the marked line monitoring image.
In one embodiment, after determining the fault location and the fault type according to the line detection result, the method further includes:
acquiring historical line monitoring images including the fault positions, which are close to the shooting time;
determining a line change moment according to the historical line monitoring image;
And sending a historical line monitoring image corresponding to each line change moment to the maintenance center.
In one embodiment, the method further comprises:
summarizing line detection results, and counting fault positions and fault types;
and generating a reference scheme for line material selection and line erection planning according to the state parameters of the line corresponding to the fault position and the fault type.
In a second aspect, the present application further provides a line image processing apparatus, the apparatus including:
the image processing module is used for acquiring line monitoring image data and processing the acquired image data;
the image analysis module is used for selecting and operating a line detection model, analyzing the input line monitoring image data and outputting a line detection result;
and the communication module is used for reporting the line detection result to the maintenance center corresponding to the fault position and the fault type.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring a line monitoring image, and determining a target category to which the line monitoring image belongs according to image content;
Inputting the line monitoring image into a preset line fault detection model corresponding to the 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.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a line monitoring image, and determining a target category to which the line monitoring image belongs according to image content;
inputting the line monitoring image into a preset line fault detection model corresponding to the 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.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
Acquiring a line monitoring image, and determining a target category to which the line monitoring image belongs according to image content;
inputting the line monitoring image into a preset line fault detection model corresponding to the 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.
The line image processing method, the device, the computer equipment, the storage medium and the computer program product determine the target category to which the image belongs by carrying out content analysis on the line monitoring image. The understanding capability of the system to the line image is improved, and a basis of target categories is provided for subsequent fault detection. Inputting the image into a line fault detection model corresponding to a preset target class to obtain a line detection result. Automatic line fault detection is realized through the pre-trained model, and the accuracy and the efficiency of detection are improved. And determining a fault position and a fault type according to the line detection result, and reporting the result to a maintenance center corresponding to the fault position and the fault type. The automatic identification and positioning of faults are realized, the results are reported in time, and the response speed and accuracy of fault management are improved. Through the machine learning model, the automatic detection of faults in the line images is realized, and the burden of manual analysis is reduced. The fault information can be reported to the maintenance center in real time, and timely response and maintenance are facilitated. The accuracy of the position and the type of the line fault is improved through image content analysis and a machine learning model. The automatic fault location and type positioning are realized, and a foundation is provided for subsequent maintenance decisions. And sending the historical image to the maintenance center, so that maintenance personnel can know the environment and conditions when the fault occurs more comprehensively. In general, the line image processing method combines image analysis and machine learning technologies to realize intelligent detection and positioning of line faults in the power system, and improves maintenance efficiency and accuracy.
Drawings
FIG. 1 is a flow diagram of a circuit image processing method according to one embodiment;
FIG. 2 is a flow diagram of a circuit image processing method according to one embodiment;
FIG. 3 is a flow diagram of a circuit image processing method according to one embodiment;
FIG. 4 is a flow diagram of a circuit image processing method according to one embodiment;
FIG. 5 is a flow diagram of a circuit image processing method according to one embodiment;
FIG. 6 is a flow diagram of a circuit image processing method according to one embodiment;
FIG. 7 is a schematic diagram of a circuit image processing apparatus according to an embodiment;
fig. 8 is a schematic diagram of a configuration of a computer device of the circuit image processing apparatus according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The line image processing method provided by the embodiment of the application can be applied to the field of monitoring and maintenance of the power system so as to ensure stable operation of the power network, reduce fault occurrence and improve maintenance efficiency. Such line image processing methods may be performed by a computing device of a power system dimension inspection center.
In one embodiment, as shown in fig. 1, there is provided a line image processing method, including:
102, acquiring a line monitoring image, and determining a target class to which the line monitoring image belongs according to image content;
the line monitoring image is obtained by acquiring static or dynamic image data from a relevant area of the power system through a suitable device or sensor, such as a monitoring camera, a high-resolution sensor and the like. Determining the target class to which the image belongs according to the image content refers to identifying and classifying objects or scenes in the line monitoring image through image processing and analysis technology so as to determine the specific target class to which the image belongs.
In practice, specially designed devices, such as monitoring cameras or other sensors, are used to capture images of lines and related devices in the power system, which may include visual information of various angles and viewing angles. And analyzing and interpreting the captured line monitoring images using image processing algorithms to identify objects, structures or features present in the images and categorize them into predefined target categories.
In this step, the system first collects line monitoring images, then identifies key features in the images by advanced image processing techniques, and finally determines the target class to which the images belong. This step provides basic information for subsequent fault detection and maintenance, helping the system to more accurately understand the current state of the power system.
Step 104, inputting the line monitoring image into a line fault detection model corresponding to a preset target class to obtain a line detection result;
wherein, inputting the line monitoring image refers to transferring the previously acquired line monitoring image to a subsequent processing step for further analysis and diagnosis. The line fault detection model corresponding to the preset target class refers to a model which is built and trained in advance and can perform fault detection and analysis on line monitoring images of specific target classes. Obtaining a line detection result refers to processing an input line monitoring image through a model to generate information about faults or problems in the image.
In practice, the previously acquired line monitoring images are introduced into the system via a data transmission or input interface to provide input data for the subsequent line fault detection process. For the previously determined target class, the system designs, trains and optimizes a model in advance that can effectively identify possible faults or anomalies in the line monitoring image. And analyzing and calculating the input line monitoring image by using a preset line fault detection model, and finally generating a detection result about the line state, wherein the detection result possibly comprises information such as the position and the type of the fault.
In this step, the system processes the acquired line monitoring images using a pre-trained line fault detection model to obtain detailed information about the line status. The information provides a basis for subsequent fault positioning and maintenance, and helps the system to realize automatic monitoring and fault diagnosis of the power system.
And 106, 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.
The determining of the fault location and the fault type according to the line detection result refers to precisely positioning the fault occurrence location in the power line by analyzing information in the result by using the previously obtained line detection result, and determining the specific type of the fault. Reporting the line detection results refers to sending information obtained from the line detection to a designated target site for further processing or taking corresponding action. To a service center corresponding to a fault location and fault type refers to sending the line detection results to a central maintenance and repair center corresponding to the fault location and type for further processing and response.
In the implementation, through analysis of the line detection result, the system can accurately confirm the position of the fault in the power system, identify the type of the fault and provide detailed fault positioning and diagnosis information for subsequent maintenance work. And sending the key information such as the fault position, the fault type and the like determined according to the line detection result to a special maintenance center through a communication channel or a network transmission mechanism so as to maintain and manage. And directly transmitting the acquired line detection result to a professional maintenance center matched with the confirmed fault position and fault type so as to promote timely maintenance work and fault treatment.
In this step, the system determines the location and type of the fault by detailed analysis of the line detection results and reports these key information to a dedicated maintenance center for timely maintenance and fault handling. This helps to minimize the impact of potential faults in the power system on overall system stability and reliability.
In the line image processing method, the object category to which the image belongs is determined by carrying out content analysis on the line monitoring image. The understanding capability of the system to the line image is improved, and a basis of target categories is provided for subsequent fault detection. Inputting the image into a line fault detection model corresponding to a preset target class to obtain a line detection result. Automatic line fault detection is realized through the pre-trained model, and the accuracy and the efficiency of detection are improved. And determining a fault position and a fault type according to the line detection result, and reporting the result to a maintenance center corresponding to the fault position and the fault type. The automatic identification and positioning of faults are realized, the results are reported in time, and the response speed and accuracy of fault management are improved.
Through the machine learning model, the automatic detection of faults in the line images is realized, and the burden of manual analysis is reduced. The fault information can be reported to the maintenance center in real time, and timely response and maintenance are facilitated. The accuracy of the position and the type of the line fault is improved through image content analysis and a machine learning model. The automatic fault location and type positioning are realized, and a foundation is provided for subsequent maintenance decisions. And sending the historical image to the maintenance center, so that maintenance personnel can know the environment and conditions when the fault occurs more comprehensively. In general, the line image processing method combines image analysis and machine learning technologies to realize intelligent detection and positioning of line faults in the power system, and improves maintenance efficiency and accuracy.
In one embodiment, as shown in fig. 2, determining, according to the image content, a target category to which the line monitoring image belongs, includes:
step 1021, identifying the image content of the line detection image, determining the line set-up environment and/or shooting weather conditions;
wherein, the identification of the image content of the line inspection image refers to identifying the object, structure or feature contained in the line inspection image by using image processing and analysis technology to obtain detailed information about the image content. Determining the line set-up environment and/or shooting weather conditions refers to determining the environment conditions shot by the line monitoring image according to the identified image content, including the surrounding environment of the line and the weather conditions during shooting.
In practice, by performing advanced image processing on the line monitoring image, the system is able to identify various elements in the image, such as power lines, equipment, vegetation, or other related features, to obtain a detailed description of the status of the line. Based on the analysis of the image content, the system can infer the setting up environment of the line, such as city, country or mountain area, and the like, and the weather conditions at the time of image capturing, such as sunny days, rainy days or snowy days, and the like.
In this step, the system recognizes elements and features in the image by performing image processing and content analysis on the line inspection image, and deduces the environment of line setup and weather conditions at the time of photographing from these information. Such information facilitates a more comprehensive understanding of the line monitoring image, providing more context information for subsequent fault detection and maintenance decisions.
Step 1022, determining the segmentation mode and rule of the line monitoring image according to the line setting environment and/or the photographed weather condition;
wherein, according to the line set-up environment and/or the photographed weather condition, the system deduces specific conditions such as illumination intensity, visibility, etc. that may exist in the line monitoring image based on the previously determined line set-up environment and the photographed weather condition. Determining the segmentation method and rules of the line monitoring image refers to formulating specific method and rules of image segmentation according to the previously acquired environmental and weather information so as to decompose the image into smaller areas or blocks for finer analysis and processing. The specific steps and processes of the segmentation image are to cut or divide the obtained line monitoring image into small image areas so as to carry out subsequent analysis and processing; the specific steps of the image segmentation include determining the manner and rule of segmentation, such as meshing or segmenting according to specific regions, and storing the segmented image as an independent image file or data.
In practice, by analyzing the line set up environment and the photographed weather conditions, the system can learn about the various environmental factors to which the image may be subjected, thereby better adapting to the image processing strategy. Aiming at different line setting environments and shooting weather conditions, the system can adopt a specific image segmentation strategy to decompose a large image into proper parts so as to improve the efficiency and accuracy of subsequent processing.
In this step, the system combines the information of the line set-up environment and the photographed weather conditions to design and implement the image segmentation method and rule suitable for the specific conditions. The segmentation strategy is beneficial to optimizing the processing of the line monitoring image so as to better adapt to different environments and weather conditions and improve the robustness and accuracy of the processing.
It should be noted that, in this embodiment, the line image classification may also be performed by combining the load parameters of the line, and in the process of analyzing the image content, the load parameters of the line, such as current, voltage, power, etc., are obtained at the same time. And fusing the image content characteristics and the load parameter characteristics to form a comprehensive characteristic vector. And analyzing the relation between the load parameters of the line and the image content by combining the line setting environment and the weather condition. And according to the change condition of the load parameters, a dynamic segmentation mode and a dynamic segmentation rule are formulated so as to adapt to the characteristics of the line images under different load conditions.
The scheme for classifying the line images by combining the load parameters is specifically as follows:
fusing the information of the line load parameters with the image content characteristics to form a more comprehensive characteristic representation;
updating the line image classification model, and considering the fused characteristics, selecting models such as a deep neural network and the like to learn more complex characteristic relations;
in the preprocessing stage of the line image, the segmentation mode of the image is dynamically adjusted according to the real-time load parameter information, so that the model can be better adapted to the images under different load conditions.
By combining the load parameters of the circuit, the system can more comprehensively understand the working state of the circuit and adjust the image processing and classifying strategies according to different load conditions, thereby improving the accuracy and adaptability of the circuit image classification. The scheme can more comprehensively consider the actual working environment of the circuit in the monitoring of the power system, so that the system is more intelligent and robust.
In one embodiment, as shown in fig. 3, the method further comprises:
step 202, loading a line image material set, wherein the line image material set comprises a plurality of fault line images marked with fault positions and fault types and normal line images;
The loading of the line image material sets refers to loading the line image material sets prepared in advance into the system so that the system can use the images for model training and learning. The line image material set containing fault line images marked with fault positions and fault types means that line images marked with actual fault positions and fault types information are contained in the material set, and the images are used for training models to identify faults. The normal line image refers to a line image in a loaded line image material set, and also comprises a line image in a normal running state, which is used for model training to identify a normal condition.
In practice, a material set containing various line images is loaded into a system's storage or memory 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 noted by professionals, providing supervised training data for the model. Besides fault images, the material set also comprises line images without faults, so that the model can be ensured to distinguish normal conditions from abnormal conditions, and the generalization capability of the model is improved.
In this step, the system provides training data for subsequent machine learning models by loading a set of line image material containing rich information. The material set contains fault line images marked with actual fault information and normal line images, so that the training model can accurately identify fault conditions in the power system.
Step 204, dividing the line image material set into line image material subsets corresponding to a plurality of categories according to the line erection environment and/or shooting weather conditions;
the line image material set refers to a set containing line images for training and learning, wherein the line image material set comprises marked fault line images and normal line images. By line set-up environment and/or photographed weather conditions is meant that the images are classified or grouped based on the photographed environment and weather conditions of the line images for more targeted model training. The line image material subsets corresponding to the multiple categories refer to dividing the image into multiple subsets according to different environments and weather conditions on the basis of the whole line image material set, and each subset corresponds to a specific condition of one category.
In practice, a dataset composed of multiple line images is used to provide the machine learning model with the diversified data needed for training. The images in the material set are classified according to the specific environmental conditions and shooting weather conditions of the line images so as to provide finer training data. The line image material set is subdivided into a plurality of small sets, each set representing a particular line set-up environment and/or class of images taken under weather conditions, in order to train the model more specifically.
In this step, the system divides the entire line image material set into a plurality of subsets according to the set-up environment of the line image and the photographed weather conditions. The classification is helpful for the model to better understand the line images under different conditions, and improves the adaptability of the model to diversified environments.
And 206, training an initial image recognition model by utilizing line image material subsets corresponding to different categories, and generating line fault detection models corresponding to different categories.
The line image material subsets corresponding to different categories refer to the subsets obtained by dividing in step 204, and each subset represents an image category under a specific line setting environment and/or shooting weather condition. Training the initial image recognition model refers to using machine learning techniques to build an initial image recognition model by training the line image for recognition of key features and patterns in the image. Generating line fault detection models corresponding to different categories refers to generating line fault detection models applicable to different categories of conditions through further training and adjustment on the basis of an initial image recognition model.
In practice, small sets are formed according to different environmental and weather conditions, and each small set contains line images corresponding to specific conditions. And (3) establishing an initial image recognition model by utilizing line image material subsets corresponding to different categories and optimizing training algorithm and model parameters, so that the line image recognition model can understand line images under different environments and weather conditions. And (3) performing further model training and optimization on the line image material subsets corresponding to each category by using the initial image recognition model, and generating a line fault detection model for specific environments and weather conditions.
In the step, the system establishes an initial image recognition model through a training process of machine learning by utilizing line image material subsets corresponding to different types obtained through division. Then, by further training and adjusting the initial model, a line fault detection model applicable to different conditions is generated, so that the sensitivity and accuracy of the model to diversified conditions are improved.
In one embodiment, as shown in fig. 4, after reporting the line detection result to the maintenance center corresponding to the fault location and the fault type, the method further includes:
step 302, receiving a real fault position and a real fault type fed back by a maintenance center, and marking a line monitoring image;
the step of receiving feedback of the maintenance center refers to obtaining actual information about line faults from the maintenance center, wherein the actual information comprises actual fault positions and actual fault types. The true fault location and the true fault type refer to accurate information about line faults provided by a maintenance center, wherein the true fault location represents the exact location of the fault occurrence, and the true fault type represents the specific fault type occurring. Marking the line monitoring image refers to marking the corresponding line monitoring image according to the real fault position and the real fault type fed back by the maintenance center so as to display the position and the type of the actual fault.
In practice, the system obtains actual fault information through a communication channel with the maintenance center, and the information is confirmed and calibrated by professionals. The maintenance center provides feedback about the exact location and specific type of line fault that is derived from in-field inspection and analysis. The actual fault information obtained from the dimension checking center is associated with the corresponding line monitoring image, and the position and type of the actual fault are marked, annotated or otherwise indicated on the image.
In this step, the system receives the actual fault information from the maintenance center and then correlates this information with the corresponding line monitoring image to mark the actual fault location and fault type on the image. The method is beneficial to subsequent model evaluation and improvement of the system, and the accuracy of the model on the real fault condition is improved.
And step 304, training a line fault detection model corresponding to the target class based on the marked line monitoring image.
The marked line monitoring image refers to marking the line monitoring image according to the real fault position and the real fault type fed back by the maintenance center in step 302, so as to display the position and the type of the actual fault. The line fault detection model corresponding to the target class refers to the line fault detection model corresponding to the different class generated in step 206, and is used for identifying line faults under specific environments and weather conditions. Training the model means that the marked line monitoring image is utilized, and the line fault detection model corresponding to the target class is further trained through a training algorithm and optimization of model parameters.
In practice, the system has built a series of specialized line fault detection models for different classes of environmental and weather conditions, each model being used to handle fault detection under specific conditions. And carrying out iterative training on the corresponding line fault detection model by using a line monitoring image with real fault information so as to improve the fault identification accuracy of the model in a real environment. The marked line monitoring image is an image with real fault information, which is marked manually or automatically, and can be used for model training.
In this step, the system uses the marked line monitoring image to further train the line fault detection model under specific environmental and weather conditions through a training algorithm and adjustment of model parameters. This helps to better adapt the model to the diversity in the real environment and improves the reliability of fault detection.
In one embodiment, as shown in fig. 5, after determining the fault location and the fault type according to the line detection result, the method further includes:
step 402, acquiring historical line monitoring images including fault positions, which are close to shooting time;
wherein, acquiring the close of the shooting time refers to acquiring the related information or data in a time period close to or adjacent to the current shooting time. A historical line monitoring image containing a fault location refers to a historical line monitoring image having a previous fault location for analyzing and researching the context and trend of the fault occurrence.
In practice, other relevant information is acquired about the time of the current line monitoring image, so as to compare and analyze. Line monitoring images including previous fault locations, which can be used to learn the historical context and changes of the fault occurrence, are captured during a historical time period that is similar to the current photographing time.
In this step, the system acquires historical line monitoring images, which are close to the current shooting time, and contain information of the position where the fault occurs previously. This helps the system analyze the historical evolution and trends of the fault, providing more comprehensive information to support fault detection and maintenance decisions.
Step 404, determining a line change time according to the historical line monitoring image;
the historical line monitoring image is an image with the past time point line state and is used for knowing the change condition of the line at different times. Determining the line change time refers to determining the time point when the line state is substantially changed or failed by analyzing the historical line monitoring image.
In practice, images containing prior time point line state information can be used to analyze trends and characteristics of the line over time. Using image processing and analysis techniques, the system can identify when the line state changes in the historical line monitoring images to locate when problems may occur.
In this step, the system uses the historical line monitoring image to determine the point in time when the line state has substantially changed, i.e., the line change time, by analyzing the image content. This helps understand the evolution trend of the line and provides more context information for fault diagnosis.
Step 406, sending the historical line monitoring image corresponding to each line change time to the maintenance center.
The historical line monitoring image corresponding to the line change time refers to the historical line monitoring image corresponding to the specific time when the line is changed, which is determined in step 404. The step of sending to the maintenance center is to send the historical line monitoring image corresponding to the line change moment to the maintenance center through a communication channel so as to facilitate the professional to further check and analyze.
In practice, for each determined line change time, the system prepares and extracts a corresponding historical line monitoring image for subsequent analysis and processing. By means of communication protocol or network connection, the system transmits historical line monitoring images of each line change moment to the maintenance center so as to assist maintenance personnel to more comprehensively know the evolution of the line state.
In this step, the system transmits the historical line monitoring image corresponding to each determined line change time to the maintenance center so that the professional can perform detailed inspection and analysis in terms of fault diagnosis and maintenance. This helps provide more comprehensive information, supporting decisions and operations for the wizard center.
In one embodiment, as shown in fig. 6, the method further comprises:
step 502, summarizing line detection results, and counting fault positions and fault types;
the summary line detection results refer to collecting and integrating line detection results obtained from different line monitoring images to form comprehensive fault information. The step of counting the fault positions and fault types is to analyze the summarized line detection results, calculate and summarize the positions of faults and the fault types to form a statistical report.
In practice, the detection results from the line monitoring images at various time points and under different conditions are collectively summarized so as to provide comprehensive knowledge of the fault condition of the entire line system. Based on the detection result of the line monitoring image, the system performs statistics and calculation on the position where the fault occurs and the specific type of the fault, and provides detailed fault information for maintenance personnel.
In this step, the system integrates and aggregates the detection results from the line monitoring images at different times and conditions, and then counts the fault location and fault type. This helps generate a comprehensive fault statistics report providing a clear overview of the fault for maintenance personnel to take corresponding maintenance and repair actions.
And step 504, generating a reference scheme of line material selection and line erection planning according to the state parameters of the line corresponding to the fault position and the fault type.
The line state parameters corresponding to the fault positions and the fault types are obtained by the pointers for each fault position and each fault type, and the line state parameters related to each fault position and each fault type are obtained, wherein the line state parameters comprise current, voltage, temperature and the like. The reference scheme is generated by utilizing line state parameters corresponding to the fault position and the fault type to formulate a proposal scheme of material selection and line erection planning for maintenance and repair work.
In practice, for each fault event, the system collects and analyzes various status parameters of the line corresponding to the fault location and fault type to comprehensively understand the working condition of the line. Based on the analysis of the line status parameters, the system generates a reference plan for each fault location and fault type, including material selection and setup planning, to guide subsequent maintenance and repair operations.
In this step, the system provides detailed information about the working condition of the line according to the line status parameters corresponding to the fault location and the fault type, and generates a corresponding reference scheme to support maintenance personnel to perform line material selection and erection planning. This helps to improve the accuracy and efficiency of maintenance decisions.
The following are examples of the wiring material selection and wiring setup plan in this step, respectively:
it is assumed that the fault occurs at a cable junction of an electric power transmission tower and that the fault type is cable insulation damage. The system obtains the following line state parameters according to the fault position and the fault type: the cable temperature rises and the current fluctuation is larger. The reference scheme provided for the situation mainly focuses on the material selection aspect, for example, copper wires with better conductivity and stability are selected to meet the current transmission requirement in view of larger current fluctuation. Or the insulation material with high temperature electric breakdown resistance is selected to adapt to the condition of the temperature rise of the cable.
It is assumed that the line connects urban and suburban areas and that there are multiple points of failure. By analyzing the line state parameters corresponding to the fault location and type, the system knows that the current demand in the urban area is high, and the suburban area is possibly affected by different weather conditions. The reference scheme provided for this situation is mainly focused on the planning of line erection, for example, in the urban part, a higher capacity transmission line is adopted to meet the current demand, and an insulating material with pollution resistance and weather resistance is selected to reduce the influence of weather conditions on the line. In suburban areas, more stable transmission lines are considered to be used, and insulating materials suitable for different weather conditions are selected to improve the reliability of the lines.
These two examples illustrate the process of line material selection and line set-up planning based on line state parameters corresponding to fault location and type. The specific scheme will vary according to the fault condition and the actual requirements, and this comprehensive consideration method helps to improve the maintainability and stability of the line.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the present application also provides a line image processing apparatus for implementing the above-mentioned line image processing method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the line image processing device or devices provided below may refer to the limitation of the line image processing method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 7, there is provided a line image processing apparatus including: an image processing module 602, an image analysis module 604, and a communication module 606, wherein:
the image processing module 602 is configured to acquire line monitoring image data and process the acquired image data.
The image analysis module 604 is configured to select and run a line detection model, analyze the input line monitoring image data, and output a line detection result.
And the communication module 606 is configured to report the line detection result to a maintenance center corresponding to the fault location and the fault type.
In one embodiment, the image analysis module 604 is further configured to identify image content of the line inspection image, determine a line set up environment and/or capture weather conditions;
And determining the segmentation mode and rule of the line monitoring image according to the line setting environment and/or the photographed weather condition.
In one embodiment, the image analysis module 604 is further configured to load a line image material set, the line image material set containing a plurality of faulty line images marked with fault locations and fault types, and normal line images;
in one embodiment, the image processing module 602 is further configured to divide the line image material set into line image material subsets corresponding to a plurality of categories according to a line setup environment and/or shooting weather conditions;
in one embodiment, the image analysis module 604 is further configured to train the initial image recognition model using the line image material subsets corresponding to different categories, and generate line fault detection models corresponding to the different categories.
In one embodiment, the communication module 606 is further configured 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 configured to tag the line monitoring image, and train the line fault detection model corresponding to the target class based on the tagged line monitoring image.
In one embodiment, the image processing module 602 is further configured to obtain a historical line monitoring image including a fault location near the shooting time;
In one embodiment, the image analysis module 604 is further configured to determine a line change time from the historical line monitoring image;
in one embodiment, the communication module 606 is further configured to send a historical line monitoring image corresponding to each line change time to the maintenance center.
In one embodiment, the image analysis module 604 is further configured to aggregate line detection results, and count fault locations and fault types; and generating a reference scheme of material selection for the line and line erection planning according to the state parameters of the line corresponding to the fault position and the fault type.
The respective modules in the above-described line image processing apparatus may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a 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 configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the 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 the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a line image processing method.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A line image processing method, the method comprising:
acquiring a line monitoring image, and determining a target category to which the line monitoring image belongs according to image content;
inputting the line monitoring image into a preset line fault detection model corresponding to the 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.
2. The line image processing method according to claim 1, wherein the determining, from image content, a target category to which the line monitoring image belongs includes:
identifying the image content of the line detection image, and determining a line setting environment and/or shooting weather conditions;
and determining the segmentation mode and rule of the line monitoring image according to the line setting environment and/or the shooting weather condition.
3. The line image processing method according to claim 2, characterized in that the method further comprises:
loading a line image material set, wherein the line image material set comprises a large number of fault line images marked with fault positions and fault types and normal line images;
dividing the line image material set into line image material subsets corresponding to a plurality of categories according to line setting environments and/or shooting weather conditions;
and training an initial image recognition model by utilizing the line image material subsets corresponding to different categories, and generating line fault detection models corresponding to different categories.
4. The line image processing method according to claim 1, wherein after the line detection result is reported to the maintenance center corresponding to the fault location and the fault type, the method further comprises:
Receiving the real fault position and the real fault type fed back by the maintenance center, and marking the line monitoring image;
and training a line fault detection model corresponding to the target class based on the marked line monitoring image.
5. The line image processing method according to claim 4, further comprising, after determining a fault location and a fault type from the line detection result:
acquiring historical line monitoring images including the fault positions, which are close to the shooting time;
determining a line change moment according to the historical line monitoring image;
and sending a historical line monitoring image corresponding to each line change moment to the maintenance center.
6. The line image processing method according to claim 1, characterized in that the method further comprises:
summarizing line detection results, and counting fault positions and fault types;
and generating a reference scheme for line material selection and line erection planning according to the state parameters of the line corresponding to the fault position and the fault type.
7. A line image processing apparatus, characterized in that the apparatus comprises:
the image processing module is used for acquiring line monitoring image data and processing the acquired image data;
The image analysis module is used for selecting and operating a line detection model, analyzing the input line monitoring image data and outputting a line detection result;
and the communication module is used for reporting the line detection result to the maintenance center corresponding to the fault position and the fault type.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311719732.1A CN117765311A (en) | 2023-12-14 | 2023-12-14 | Circuit image processing method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311719732.1A CN117765311A (en) | 2023-12-14 | 2023-12-14 | Circuit image processing method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117765311A true CN117765311A (en) | 2024-03-26 |
Family
ID=90315471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311719732.1A Pending CN117765311A (en) | 2023-12-14 | 2023-12-14 | Circuit image processing method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117765311A (en) |
-
2023
- 2023-12-14 CN CN202311719732.1A patent/CN117765311A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111401418A (en) | Employee dressing specification detection method based on improved Faster r-cnn | |
| CN117214617B (en) | Smart power grid fault real-time monitoring and positioning system and method | |
| CN115395646B (en) | Intelligent operation and maintenance system of digital twin traction substation | |
| CN111044149A (en) | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium | |
| CN110910360A (en) | Power grid image positioning method and image positioning model training method | |
| CN114550073A (en) | Monitoring system of new energy automobile charging pile | |
| CN109389322A (en) | The disconnected broken lot recognition methods of grounded-line based on target detection and long memory models in short-term | |
| CN111401437A (en) | Deep learning-based power transmission channel hidden danger early warning grade analysis method | |
| CN115060312A (en) | Building material safety monitoring system based on artificial intelligence | |
| CN111306051B (en) | Probe type state monitoring and early warning method, device and system for oil transfer pump unit | |
| CN117114420A (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN117765311A (en) | Circuit image processing method and device and computer equipment | |
| CN116381419A (en) | Transmission line fault processing method, device, computer equipment and storage medium | |
| CN116723157A (en) | Terminal behavior detection model construction method, device, equipment and storage medium | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN114463683A (en) | Transformer equipment intelligent monitoring system and method based on artificial intelligence and big data | |
| CN112529881A (en) | Method and device for identifying cable abnormity of electric control cabinet | |
| CN116310760B (en) | Intelligent water conservancy monitoring system based on machine vision | |
| CN118430216B (en) | A multiple communication protocol smog early warning system for filling electric pile | |
| CN115373329B (en) | Unmanned system of railway distribution substation | |
| KR20240021334A (en) | Diagnosis apparatus for underground power transmission facility and method thereof | |
| CN113435579A (en) | Intelligent power equipment identification method based on deep neural network | |
| CN118713591A (en) | Abnormality detection method and apparatus, storage medium, electronic apparatus, and computer program product | |
| CN117853774A (en) | Energy storage system abnormality identification method and system | |
| Guo et al. | Deep neural network-based video air cloud detection algorithm implementation research |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |