Insulator leakage current detection method and device based on video monitoring

Abstract

The invention discloses an insulator leakage current detection method based on video monitoring, and the method comprises the following steps: carrying out the visible light video detection of a to-be-detected insulator, obtaining a first monitoring video, carrying out the thermal imaging video detection of the insulator, and obtaining a second monitoring video; carrying out discharge trace size identification on the first monitoring video to obtain a discharge trace area, and carrying out classification to obtain first leakage current information; identifying the second monitoring video to obtain second leakage current information; according to the first leakage current information and the second leakage current information, leakage current information is obtained through calculation and serves as a leakage current detection result of the insulator. The invention further discloses a corresponding method. According to the invention, the detection precision of the leakage current of the insulator can be improved, and the detection effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and device for detecting insulator leakage current based on video monitoring. Background Art

[0002] Insulators are an indispensable key component in power systems. Their main function is to isolate conductors from the ground or other conductive structures to prevent power leakage or short circuits. However, insulators are easily affected by environmental factors during long-term outdoor use, such as the deposition of pollutants such as rain, fog, dust, and salt. These pollutants form conductive channels on the surface of the insulators, resulting in leakage current. If the leakage current is too large, it will cause the breakdown or flashover of the insulator, seriously affecting the safety and stability of the power system.

[0003] At present, the insulator leakage current detection is generally tested by using sensors, which has low accuracy and has technical problems such as low insulator leakage current detection accuracy and poor detection effect. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and device for detecting insulator leakage current based on video monitoring, which can improve the accuracy of insulator leakage current detection and improve the detection effect.

[0005] In order to solve the above technical problems, as a first aspect of the present invention, a method for detecting insulator leakage current based on video monitoring is provided, the method comprising:

[0006] Step S1, performing visible light video detection on the insulator to be detected to obtain a first monitoring video, and performing thermal imaging video detection on the insulator to obtain a second monitoring video;

[0007] Step S2, identifying the size of the discharge trace on the first monitoring video, obtaining the discharge trace area, and classifying to obtain first leakage current information;

[0008] Step S3, identifying the second monitoring video to obtain second leakage current information;

[0009] Step S4: Calculate leakage current information according to the first leakage current information and the second leakage current information as a leakage current detection result of the insulator.

[0010] Preferably, the step S1 further comprises:

[0011] Under visible light, collect video of the insulator to be detected to obtain a first monitoring video;

[0012] Thermal imaging video is collected on the insulator to obtain a second monitoring video.

[0013] Preferably, the step S2 further comprises:

[0014] Construct a discharge trace identifier;

[0015] The first monitoring video is input into the discharge trace identifier, and the discharge trace area is obtained by identifying the output.

[0016] Preferably, in step S2, constructing a discharge trace identifier includes:

[0017] Collecting a sample first monitoring video set of the insulator, and marking the discharge trace area in the sample first monitoring video to obtain a sample discharge trace area set;

[0018] A convolutional neural network is used to train a discharge trace identifier using the sample first monitoring video set and the sample discharge trace area set, wherein the discharge trace identifier is trained using gradient descent during training, and the training rule is:

[0019]

[0020] Among them, θ t is the model parameter at the tth iteration, η is the step size, is the gradient.

[0021] Preferably, in step S2, obtaining the first leakage current information by classification includes:

[0022] According to the historical leakage current detection data of the insulator, a sample discharge trace area set and a sample first leakage current information set are collected;

[0023] Constructing a mapping relationship between the sample discharge trace area set and the sample first leakage current information set to obtain a first leakage current classifier;

[0024] The discharge trace area is input into the first leakage current classifier, and first leakage current information is obtained through classification.

[0025] Preferably, the step S3 further comprises:

[0026] Collecting a sample second monitoring video set of the insulator and collecting a sample second leakage current information set;

[0027] Using a convolutional neural network, the sample second monitoring video set and the sample second leakage current information set are used to train a second leakage current identifier;

[0028] The second monitoring video is input into the second leakage current identifier to identify and obtain second leakage current information.

[0029] Preferably, the step S4 further comprises:

[0030] The first leakage current information and the second leakage current information are weightedly calculated to obtain leakage current information as a leakage current detection result of the insulator.

[0031] As another aspect of the present invention, an insulator leakage current detection device based on video monitoring is also provided, including a processor and a memory, wherein the memory stores a computer program executable by a processor; when the processor executes the computer program, the insulator leakage current detection method based on video monitoring as described in the present invention is executed.

[0032] The implementation of the embodiments of the present invention has the following beneficial effects:

[0033] The present invention provides an insulator leakage current detection method based on video monitoring. Through the dual monitoring means of visible light video and thermal imaging video, the discharge traces and temperature anomaly information on the surface of the insulator are fully obtained, which significantly improves the detection accuracy and avoids the error of a single monitoring method. In addition, thermal imaging and visible light detection still maintain good stability in complex environments, enhancing the environmental adaptability of the detection.

[0034] At the same time, based on the video monitoring method, the detection can be carried out continuously and in real time, so that when the leakage current increases sharply, it can be identified and warned in time, thus improving the safety of the system.

[0035] In addition, the flexible deployment of video surveillance expands the monitoring coverage, enabling it to cover remote or difficult-to-maintain areas and reducing detection blind spots.

[0036] In summary, the solution of the present invention realizes the automatic classification and calculation of leakage current information, and can realize more efficient and accurate leakage current monitoring. It meets the intelligent requirements of the power system and can provide comprehensive and reliable technical guarantees for the efficient operation and maintenance of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0038] Figure 1 It is a main process diagram of an insulator leakage current detection method based on video monitoring provided by the present invention. DETAILED DESCRIPTION

[0039] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings.

[0040] like Figure 1 FIG. 1 is a schematic diagram showing the main process of an embodiment of a method for detecting insulator leakage current based on video monitoring provided by the present invention. In this embodiment, the method at least includes the following steps:

[0041] Step S1: Perform visible light video detection on the insulator to be detected to obtain a first monitoring video, and perform thermal imaging video detection on the insulator to obtain a second monitoring video;

[0042] Step 1 in the method provided in the embodiment of the present invention includes:

[0043] Under visible light, collect video of the insulator to be detected to obtain a first monitoring video;

[0044] Thermal imaging video is collected on the insulator to obtain a second monitoring video.

[0045] In the embodiment of the present invention, firstly, a visible light video inspection is performed on the insulator to be inspected, that is, a visible light camera is used to obtain an appearance image of the insulator to generate a clear first monitoring video. Visible light video inspection can record the external features of the insulator, such as the visible range and shape changes of the discharge traces. The discharge traces refer to the traces left by the corona discharge phenomenon generated on the surface of the insulator. These traces are usually contamination or tiny cracks on the surface of the insulator.

[0046] In the embodiment of the present invention, a thermal imaging video is performed on the insulator to obtain a second monitoring video. The thermal imaging video is a visual image generated by capturing the temperature distribution on the surface and surroundings of the insulator through a thermal imaging camera. Thermal imaging technology can detect abnormal temperature areas, especially local overheating or abnormal temperature distribution. The temperature abnormality is usually caused by the generation of leakage current.

[0047] Thermal imaging cameras can sense infrared radiation emitted by objects and convert it into a visible temperature image, or “heat map”. This heat map can reveal possible temperature anomalies on the insulator and identify the leakage current that causes the temperature anomaly.

[0048] Leakage current may cause local temperature rise. By monitoring the temperature change of the insulator through the second monitoring video, these abnormal areas with temperature rise can be effectively captured, improving the accuracy of leakage current detection.

[0049] Step S2: identifying the size of the discharge trace on the first monitoring video, obtaining the discharge trace area, and classifying to obtain first leakage current information;

[0050] In the embodiment of the present invention, firstly, a detailed image analysis is performed on the first monitoring video to identify the size of the discharge trace that may exist on the surface of the insulator, that is, the area of ​​the discharge trace.

[0051] After the area of ​​the discharge trace is identified, it is classified by a preset classification algorithm to obtain preliminary leakage current information, that is, first leakage current information. The larger the area of ​​the discharge trace, the larger the first leakage current information.

[0052] Step S2 in the method provided in the embodiment of the present invention includes:

[0053] In an embodiment of the present invention, a discharge trace identifier is constructed to specifically identify discharge traces on the surface of an insulator. The identifier is based on advanced image processing algorithms and deep learning technology, and can accurately extract the features of discharge traces from video images. The discharge trace identifier is trained on a large number of labeled insulator discharge samples, so that it can identify the features of various discharge traces, such as the area of ​​the discharge trace.

[0054] Among them, constructing a discharge trace identifier includes:

[0055] Collecting a sample first monitoring video set of the insulator, and marking the discharge trace area in the sample first monitoring video to obtain a sample discharge trace area set;

[0056] A convolutional neural network is adopted to train a discharge trace identifier using the sample first monitoring video set and the sample discharge trace area set.

[0057] In the embodiment of the present invention, it is first necessary to collect a large number of sample first monitoring video sets of insulators, that is, insulator video samples shot under different conditions, to record possible discharge marks on their surfaces. In order to facilitate the training of subsequent models, in these sample videos, the visible discharge mark area in each frame is manually or semi-automatically marked. The marking of the discharge mark area includes outlining the discharge mark and calculating the area, generating a sample discharge mark area set as real reference data to be used for training.

[0058] Exemplarily, a convolutional neural network (CNN) is used to train the discharge trace identifier. Convolutional neural network is a deep learning model widely used in image recognition. It extracts and recognizes local features in images through multiple convolutional layers and pooling layers, and is particularly suitable for processing complex graphics and shapes in images. The collected sample first monitoring video set and the sample discharge trace area set are input into the convolutional neural network. Through repeated iterations of a large number of training samples, the recognition accuracy of the identifier is gradually optimized, so that it can automatically detect discharge traces of different forms in the video.

[0059] The convolution layer in the discharge trace identifier performs the convolution feature extraction operation on the insulator image in the first monitoring video as follows:

[0060] S(i,j)=(I*K)(i,j)=∑ m ∑ n I(i+m,j+n)·K(m,n);

[0061] Among them, S(i,j) is the output after convolution, I(i,j) is the pixel value of the insulator image, K(m,n) is the weight of the convolution kernel, and (i,j) is the coordinate of the pixel position in the insulator image.

[0062] The discharge trace identifier is trained using gradient descent, and the training rules are:

[0063]

[0064] Among them, θ t is the model parameter at the tth iteration, η is the step size, is the gradient.

[0065] During the training process, the convolutional neural network adjusts its internal parameters by comparing the difference between the recognition results and the identification data, and gradually enhances the recognition accuracy of the discharge trace area through gradient descent training. Finally, the trained discharge trace identifier can accurately identify the area information of the discharge trace from the actual video, providing real-time and reliable input data for the leakage current detection of the insulator. Through this training process based on the convolutional neural network, the discharge trace identifier not only has the ability to efficiently process large amounts of video data, but also has strong generalization ability, and can maintain high recognition accuracy in different environments.

[0066] The first monitoring video of the insulator currently collected is input into the trained discharge trace identifier, and the discharge trace area is obtained by identification output.

[0067] The establishment of the discharge trace identifier makes it possible to automatically and accurately identify the trace area caused by current leakage on the insulator surface through video detection. Through an efficient and accurate image processing process, the area information of the discharge trace can be obtained in real time, providing important basic data for further analysis and monitoring of leakage current.

[0068] In the embodiment of the present invention, obtaining the first leakage current information by classification includes:

[0069] According to the historical leakage current detection data of the insulator, a sample discharge trace area set and a sample first leakage current information set are collected;

[0070] Constructing a mapping relationship between the sample discharge trace area set and the sample first leakage current information set to obtain a first leakage current classifier;

[0071] The discharge trace area is input into the first leakage current classifier, and first leakage current information is obtained through classification.

[0072] In the embodiment of the present invention, based on the historical leakage current detection data of the insulator, a large number of insulator samples with discharge marks are collected, the discharge mark area set of each sample and its corresponding leakage current data are obtained, and the sample first leakage current information set is generated. The sample discharge mark area set includes the size of each sample discharge mark, and the sample first leakage current information set includes the corresponding leakage current value, such as 10mA. The collection of these data lays a data foundation for establishing a relationship model between discharge marks and leakage currents.

[0073] Construct a mapping relationship between the sample discharge trace area set and the sample first leakage current information set to generate a first leakage current classifier. The mapping relationship is to find the corresponding relationship between the discharge trace area and the leakage current in the data, that is, the size of the discharge trace area corresponds to different leakage current levels in different ranges. The first leakage current classifier is a mapping table between the sample discharge trace area set and the sample first leakage current information set.

[0074] The currently identified discharge trace area is input into the first leakage current classifier, and the classifier maps and classifies the area according to the pre-established mapping relationship, and outputs the corresponding first leakage current information. For example, the sample first leakage current information corresponding to the sample discharge trace area that is closest to the current discharge trace area (the difference between the two is the smallest) is output as the first leakage current information.

[0075] The first leakage current information is the leakage current level determined by the discharge trace area, which provides a reference for further insulator health assessment. This classification model based on historical data makes leakage current detection more efficient and accurate, and can dynamically evaluate the status of insulators, improving the accuracy and practicality of detection.

[0076] Step S3: Identify the second monitoring video to obtain second leakage current information;

[0077] In the embodiment of the present invention, the second monitoring video is identified and analyzed to identify the leakage current according to the temperature anomaly of the insulator in the thermal imaging video, so as to obtain the second leakage current information.

[0078] Step 3 in the method provided in the embodiment of the present invention includes:

[0079] Collecting a sample second monitoring video set of the insulator and collecting a sample second leakage current information set;

[0080] Using a convolutional neural network, the sample second monitoring video set and the sample second leakage current information set are used to train a second leakage current identifier;

[0081] The second monitoring video is input into the second leakage current identifier to identify and obtain second leakage current information.

[0082] In an embodiment of the present invention, a sample second monitoring video set of an insulator is collected. The sample second monitoring video set is a collection of insulator heat map videos taken by a thermal imaging camera, which records the temperature distribution of the insulator surface under different environmental conditions and pollution states. Correspondingly, the actual leakage current data of each video is collected to form a sample second leakage current information set. The sample second leakage current information set records the leakage current level of the insulator under different temperature states, providing accurate reference data for the model.

[0083] Furthermore, the second leakage current identifier is trained using a convolutional neural network (CNN). A convolutional neural network is a deep learning model that is highly suitable for image processing. Through multi-layer convolution and pooling operations on the image, it can extract features in the temperature image, such as the size, position, and shape of the temperature abnormality area. These features are related to the leakage current information. The sample second monitoring video set and the sample second leakage current information set are input into the convolutional neural network for training. Through repeated iterations and error correction, the network gradually learns the relationship between different temperature image features and leakage current levels.

[0084] After the training is completed, the second monitoring video currently being actually detected is input into the second leakage current identifier. Based on its understanding of the temperature image features, the identifier analyzes the temperature distribution in the video, especially the size of the overheated area and the temperature change pattern, and outputs the second leakage current information. The second leakage current information is the leakage current judgment result obtained after the thermal imaging video analysis, which can reflect the correlation between the real-time temperature state of the insulator and the current leakage level.

[0085] The second leakage current identifier can efficiently and accurately map the temperature features in the video image to the leakage current level, realize the intelligent correlation analysis between temperature anomalies and leakage current, and provide more comprehensive technical support for insulator status monitoring.

[0086] Step S4: Calculate and obtain leakage current information according to the first leakage current information and the second leakage current information as a leakage current detection result of the insulator.

[0087] In an embodiment of the present invention, the first leakage current information and the second leakage current information are combined to obtain the final leakage current information through calculation as the leakage current detection result of the insulator. The first leakage current information is the leakage current level inferred based on the size and distribution of the discharge traces in the visible light video, reflecting the visible discharge situation on the surface of the insulator. The second leakage current information comes from the abnormal temperature detected in the thermal imaging video. The leakage current that causes the temperature change is obtained by analyzing the thermal map of the insulator surface. These two sources of information reveal the state of the insulator leakage current from different angles, complement each other, and help to form a more complete judgment.

[0088] Step S4 in the method provided in the embodiment of the present invention includes:

[0089] The first leakage current information and the second leakage current information are weightedly calculated to obtain leakage current information as a leakage current detection result of the insulator.

[0090] In the embodiment of the present invention, weighted calculation is performed on the first leakage current information and the second leakage current information to generate final leakage current information as the leakage current detection result of the insulator.

[0091] The formula for weighted calculation of the first leakage current information and the second leakage current information is as follows:

[0092] C final =w1·C1+w2·C2;

[0093] Among them, C final is leakage current information, w1 and w2 are weights, the sum of w1 and w2 is 1, C1 and C2 are first leakage current information and second leakage current information.

[0094] During the weighted calculation process, appropriate weights w1 and w2 are assigned to the first leakage current information and the second leakage current information. The weight assignment is dynamically adjusted based on environmental conditions, historical detection data, and reliability analysis. For example, when the lighting conditions are good during the day, the discharge trace characteristics in the visible light video are more obvious, and a higher weight is given to the first leakage current information, for example, w1 and w2 are 0.6 and 0.4 respectively. In low light or bad weather conditions, thermal imaging detection is more reliable, and the weight of the second leakage current information tends to be increased, for example, w1 and w2 are 0.4 and 0.6 respectively. This weighted calculation method ensures that under a variety of working conditions, the final leakage current information can accurately reflect the actual state of the insulator.

[0095] The calculated output leakage current information is the insulator leakage current detection result that combines visible light and thermal imaging data. This result reflects the leakage current more comprehensively, helps to improve the accuracy and real-time performance of the detection, and provides a reliable basis for the operation and maintenance personnel to judge the health status of the insulator. Through this weighted calculation method, the detection system can quickly adapt to environmental changes and realize accurate monitoring and early warning of leakage current, providing important guarantees for the safe operation of the power system.

[0096] The embodiment of the present invention further provides an insulator leakage current detection device based on video monitoring, comprising a processor and a memory, wherein the memory stores a computer program executable by the processor; when the processor executes the computer program, the insulator leakage current detection method based on video monitoring as described in the present invention is executed. For more details, please refer to and combine with the aforementioned Figure 1 The description is not repeated here.

[0097] The implementation of the embodiments of the present invention has the following beneficial effects:

[0098] The present invention provides an insulator leakage current detection method based on video monitoring. Through the dual monitoring means of visible light video and thermal imaging video, the discharge traces and temperature anomaly information on the surface of the insulator are fully obtained, which significantly improves the detection accuracy and avoids the error of a single monitoring method. In addition, thermal imaging and visible light detection still maintain good stability in complex environments, enhancing the environmental adaptability of the detection.

[0099] At the same time, based on the video monitoring method, the detection can be carried out continuously and in real time, so that when the leakage current increases sharply, it can be identified and warned in time, thus improving the safety of the system.

[0100] In addition, the flexible deployment of video surveillance expands the monitoring coverage, enabling it to cover remote or difficult-to-maintain areas and reducing detection blind spots.

[0101] In summary, the solution of the present invention realizes the automatic classification and calculation of leakage current information, and can realize more efficient and accurate leakage current monitoring. It meets the intelligent requirements of the power system and can provide comprehensive and reliable technical guarantees for the efficient operation and maintenance of the power system.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0103] Obviously, the embodiments described above are only some embodiments of the present invention, rather than all embodiments. The preferred embodiments of the present invention are given in the accompanying drawings, but they do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific embodiments, or to perform equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of the present invention, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present invention.

Claims

1. A method for detecting insulator leakage current based on video monitoring, characterized in that: The method comprises: Step S1, performing visible light video detection on the insulator to be detected to obtain a first monitoring video, and performing thermal imaging video detection on the insulator to obtain a second monitoring video; Step S2, identifying the size of the discharge trace on the first monitoring video, obtaining the discharge trace area, and classifying to obtain first leakage current information; Step S3, identifying the second monitoring video to obtain second leakage current information; Step S4: Calculate leakage current information according to the first leakage current information and the second leakage current information as a leakage current detection result of the insulator.

2. The method according to claim 1, characterized in that The step S1 further comprises: Under visible light, collect video of the insulator to be detected to obtain a first monitoring video; Thermal imaging video is collected on the insulator to obtain a second monitoring video.

3. The method according to claim 2, characterized in that The step S2 further comprises: Construct a discharge trace identifier; The first monitoring video is input into the discharge trace identifier, and the discharge trace area is obtained by identifying the output.

4. The method according to claim 3, characterized in that: In the step S2, a discharge trace identifier is constructed, including: Collecting a sample first monitoring video set of the insulator, and marking the discharge trace area in the sample first monitoring video to obtain a sample discharge trace area set; A convolutional neural network is used to train a discharge trace identifier using the sample first monitoring video set and the sample discharge trace area set, wherein the discharge trace identifier is trained using gradient descent during training, and the training rule is: Among them, θ t is the model parameter at the tth iteration, η is the step size, is the gradient.

5. The method according to claim 4, characterized in that In the step S2, obtaining first leakage current information by classification includes: According to the historical leakage current detection data of the insulator, a sample discharge trace area set and a sample first leakage current information set are collected; Constructing a mapping relationship between the sample discharge trace area set and the sample first leakage current information set to obtain a first leakage current classifier; The discharge trace area is input into the first leakage current classifier, and first leakage current information is obtained through classification.

6. The method according to claim 5, characterized in that The step S3 further comprises: Collecting a sample second monitoring video set of the insulator and collecting a sample second leakage current information set; Using a convolutional neural network, the sample second monitoring video set and the sample second leakage current information set are used to train a second leakage current identifier; The second monitoring video is input into the second leakage current identifier to identify and obtain second leakage current information.

7. The method according to claim 6, characterized in that The step S4 further comprises: The first leakage current information and the second leakage current information are weightedly calculated to obtain leakage current information as a leakage current detection result of the insulator.

8. An insulator leakage current detection device based on video monitoring, characterized in that: It includes a processor and a memory, wherein the memory stores a computer program executable by the processor; when the processor executes the computer program, it executes the insulator leakage current detection method based on video monitoring as described in any one of claims 1 to 7.

Images