Method and device for determining discharge intensity of insulator, computer equipment, readable storage medium and program product

Abstract

The invention relates to the technical field of insulator discharge intensity monitoring, and provides an insulator discharge intensity determination method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: carrying out feature extraction on a partial discharge ultraviolet image of an insulator to obtain image features; according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and a pulse current peak value prediction model, obtaining a pulse current prediction peak value corresponding to the partial discharge ultraviolet image; and obtaining the discharge intensity of the insulator according to the relationship between the pulse current prediction peak value and the discharge intensity grade. By adopting the method, the prediction error of the discharge intensity of the insulator can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of insulator discharge intensity monitoring, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for determining insulator discharge intensity. Background Art

[0002] Insulator discharge usually manifests as partial discharge or flashover, which may lead to insulator aging, breakdown and failure of power facilities, and then cause power outages or safety accidents. In order to ensure the stability and safety of the power system, it is necessary to monitor the discharge intensity of insulators.

[0003] At present, ultraviolet images of insulators can be obtained through ultraviolet detectors, and regression models can be established based on least squares regression support vector machines. The ultraviolet images are processed and analyzed to obtain the discharge conditions of the insulators to determine the discharge intensity of the insulators. However, the existing methods for determining the discharge intensity of insulators do not consider the influence of temperature and humidity environments. In practical applications, the regression model has poor adaptability and robustness, and the prediction error of the insulator discharge intensity is large. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining the discharge strength of an insulator in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for determining the discharge strength of an insulator, comprising:

[0006] Extract features from the partial discharge ultraviolet image of the insulator to obtain image features;

[0007] Obtaining a pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak prediction model;

[0008] The discharge intensity of the insulator is obtained according to the relationship between the predicted peak value of the pulse current and the discharge intensity level.

[0009] In one embodiment, extracting features from the partial discharge ultraviolet image of the insulator to obtain image features includes:

[0010] Obtaining a light spot image according to the partial discharge ultraviolet image;

[0011] Obtaining a spot pixel area of ​​the spot image according to a contour point pixel value in the spot image;

[0012] Performing graphic fitting on the light spot image to determine the light spot geometric shape of the light spot image;

[0013] According to the light spot geometry, a light spot size parameter is obtained;

[0014] Image features are obtained according to the light spot pixel area and the light spot size parameter.

[0015] In one embodiment, obtaining a spot image according to the partial discharge ultraviolet image includes:

[0016] Performing grayscale processing and filtering noise reduction processing on the partial discharge ultraviolet image to obtain a noise-reduced grayscale image;

[0017] Binarizing the denoised grayscale image to obtain a binary image;

[0018] The binary image is traversed according to an edge detection algorithm to obtain the light spot image.

[0019] In one embodiment, performing graphic fitting on the light spot image to determine the light spot geometry of the light spot image includes:

[0020] According to the pixel coordinates of the contour points of the light spot image, an ellipse fitting is performed on the light spot contour in the light spot image to obtain an ellipse light spot contour;

[0021] Obtaining the eccentricity of the light spot according to the major axis and the minor axis of the elliptical light spot profile;

[0022] When the light spot eccentricity is greater than a threshold, determining the light spot geometric shape of the light spot image as an ellipse;

[0023] When the spot eccentricity is less than a threshold value, the spot in the spot image is fitted with a maximum inscribed circle to obtain the maximum inscribed circle of the spot of the spot image; the circularity of the spot of the spot image is obtained according to the maximum inscribed circle of the spot of the spot image; when the spot eccentricity is less than a threshold value and the circularity of the spot is greater than a threshold value, the geometric shape of the spot of the spot image is determined to be a circle.

[0024] In one of the embodiments, before obtaining the pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak prediction model, the method further includes:

[0025] Obtaining the distance from the optical system of the detector to the sensor; the detector is used to obtain visible light of the insulator; the optical system and the sensor are components of the detector;

[0026] Obtaining a proportionality coefficient according to the pixel height occupied by the insulator in the visible light image and the actual height of the insulator;

[0027] According to the distance and the proportionality coefficient, the detection distance corresponding to the partial discharge ultraviolet image is obtained.

[0028] In one of the embodiments, before obtaining the pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak prediction model, the method further includes:

[0029] Obtain image feature samples, detection distance samples, detection gain samples, temperature environment parameter samples and humidity environment parameter samples corresponding to the partial discharge ultraviolet image samples to form an initial training set;

[0030] According to the initial training set, a plurality of sub-training sets are obtained;

[0031] For any sub-training set, a first decision tree is constructed and a splitting process is performed at least once; wherein, each time a split occurs, a feature subset is randomly selected at each node of the first decision tree, and the optimal feature is selected for splitting according to a set evaluation criterion to obtain each newly formed child node; the splitting process is repeated for each newly formed child node until a stop condition is met, thereby obtaining a second decision tree; and the step of constructing the second decision tree is repeated until a predetermined number of second decision trees is reached;

[0032] A pulse current peak prediction model is obtained according to the second decision trees corresponding to the multiple sub-training sets.

[0033] In a second aspect, the present application also provides a device for determining the discharge strength of an insulator, comprising:

[0034] An image feature acquisition module is used to extract features from the partial discharge ultraviolet image of the insulator to obtain image features;

[0035] A predicted peak value acquisition module, used to obtain the predicted peak value of the pulse current corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak value prediction model;

[0036] The discharge intensity acquisition module is used to obtain the discharge intensity of the insulator according to the relationship between the pulse current prediction peak value and the discharge intensity level.

[0037] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the above method.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to execute the above method.

[0039] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and the computer program is executed by a processor to execute the above method.

[0040] The above-mentioned determination method, device, computer equipment, computer-readable storage medium and computer program product for the discharge intensity of the insulator perform feature extraction on the partial discharge ultraviolet image of the insulator to obtain image features; obtain the pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance, detection gain, temperature environmental parameters, humidity environmental parameters and pulse current peak prediction model corresponding to the partial discharge ultraviolet image; obtain the discharge intensity of the insulator according to the relationship between the pulse current prediction peak value and the discharge intensity level. The present application comprehensively considers multiple factors of insulator discharge, including the image features, detection distance, detection gain, temperature environmental parameters and humidity environmental parameters of the partial discharge ultraviolet image, performs feature mapping on the multi-dimensional factors, and combines the use of the pulse current peak prediction model to comprehensively reflect the discharge situation of the insulator, reduce the error caused by a single discharge factor, and reduce the prediction error of the insulator discharge intensity. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 is an application environment diagram of a method for determining discharge strength of an insulator in one embodiment;

[0043] Figure 2 is a flow chart of a method for determining the discharge strength of an insulator in one embodiment;

[0044] Figure 3 A schematic diagram of a process for obtaining image features in one embodiment;

[0045] Figure 4 is a structural block diagram of a device for determining discharge intensity of an insulator in one embodiment;

[0046] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] The present application embodiment provides a method for determining the discharge strength of an insulator. The present embodiment can be executed by a computer device, such as Figure 1 As shown, the computer device can obtain the partial discharge ultraviolet image of the insulator, as well as the detection distance, detection gain, temperature environment parameters, and humidity environment parameters corresponding to the partial discharge ultraviolet image, and then obtain the discharge intensity of the insulator. It is understandable that the computer device can be implemented through a server, a terminal, or an interactive system between a terminal and a server. In this embodiment, the method includes Figure 2 The steps shown are:

[0049] Step S201 , extracting features from the partial discharge ultraviolet image of the insulator to obtain image features.

[0050] Insulators generate ultraviolet (UV) radiation during the discharge process, especially during arc and partial discharge. The UV signal is obvious and strong. Based on the UV / visible dual-channel detector, the visible light image of the insulator and the UV image of the partial discharge can be collected. The detection distance can be estimated based on the collected visible light image through image processing and visual geometry principles; the feature extraction of the UV image of the partial discharge of the insulator can be performed, and the spot of the discharge area can be segmented to obtain the image features. The detection gain of the detector, as well as the temperature and humidity environmental parameters can be obtained synchronously.

[0051] Step S202, obtaining the pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak prediction model.

[0052] The detection distance is the distance between the target insulator and the detector (monocular ranging method), which can be represented by the parameter d. The detection gain is the detection gain of the ultraviolet detector (imager), which can be represented by the parameter g. The pulse current peak is the pulse current peak generated by the local discharge (corona discharge, spark or arc) of the insulator. The pulse signal in the corona discharge stage appears as a narrow pulse, and the pulse signal in the arc discharge stage appears as a wide pulse. With the increase of discharge time and discharge intensity (discharge amount), the peak value of the pulse signal changes in a positive correlation, which characterizes the discharge intensity. The temperature environmental parameters and humidity environmental parameters represent the ambient temperature and humidity in a specific time period, which can be represented by time (T, H), where T represents temperature and H represents humidity.

[0053] The pulse current peak prediction model can comprehensively analyze the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environmental parameters and the humidity environmental parameters, and predict the pulse current peak corresponding to the partial discharge ultraviolet image.

[0054] The spot pixel area S, the detection distance d corresponding to the partial discharge ultraviolet image, the detection gain g, the temperature environment parameter and the humidity environment parameter time (T, H) in the image features can be input into the pulse current peak prediction model f, that is, y=f(d, g, S, time (T, H)), to obtain the pulse current prediction peak y corresponding to the partial discharge ultraviolet image.

[0055] Step S203, obtaining the discharge intensity of the insulator according to the relationship between the pulse current prediction peak value and the discharge intensity level.

[0056] According to the arc and danger degree generated by the partial discharge of the insulator, the corresponding relationship between the pulse current peak value and the discharge intensity level can be established. That is, according to the safety impact of the corona and arc generated by the insulator discharge on the insulator electrical equipment, the pulse current peak value in the corresponding stage can be divided into different discharge intensity levels (danger levels).

[0057] For example, when the pulse current peak value is within the first setting range [Int1~Int2), it indicates that corona discharge begins to occur, corresponding to the danger level 1, and the insulator ultraviolet discharge intensity level output is level 1; when the pulse current peak value is within the second setting range [Int2~Int3), the discharge current peak value further increases, indicating that an arc begins to occur, posing a danger to the safety of the insulator equipment, corresponding to the danger level 2, and the insulator ultraviolet discharge intensity level output is level 2; and when the pulse current peak value exceeds Int3, it indicates that the current insulator discharge intensity is too high, causing serious safety hazards, and intervention and processing are required as soon as possible, corresponding to the danger level 3, and the insulator ultraviolet discharge intensity level output is level 3.

[0058] In the case of insulator discharge, as the pulse current continues to increase and the peak value increases, the discharge intensity level and the danger level also increase accordingly. Especially when the insulator is in a high discharge intensity, there is a nonlinear relationship between the pulse current peak value and the discharge intensity level. For example, the discharge intensity level will increase exponentially with the increase of the pulse current peak value.

[0059] According to the pulse current predicted peak value and the relationship between the pulse current peak value and the discharge intensity level, the discharge intensity level corresponding to the pulse current predicted peak value can be obtained, thereby determining the discharge intensity of the insulator.

[0060] In the above-mentioned method for determining the insulator discharge intensity, multiple factors of insulator discharge are comprehensively considered, including the image characteristics of the local discharge ultraviolet image, the detection distance, the detection gain, the temperature environment parameters and the humidity environment parameters, and the multi-dimensional factors are feature mapped. Combined with the use of the pulse current peak prediction model, the discharge of the insulator is fully reflected, the error caused by a single discharge factor is reduced, and the prediction error of the insulator discharge intensity is reduced. It provides strong support for the early warning of power system faults, helps to timely discover insulator discharge fault problems, prevent the occurrence of power safety accidents, ensure the stability and reliable operation of the power grid, and provide important technical means for the health management and fault prevention of power equipment. In addition, the method for determining the insulator discharge intensity of the present application is a non-contact insulator discharge intensity detection method, which does not require direct contact with the power equipment, ensures the safety of operation, is particularly suitable for the monitoring of high-voltage equipment, and supports the realization of real-time online monitoring, real-time acquisition of equipment operation status, timely discovery and positioning of insulator discharge faults and early warning, and improves the safety and reliability of equipment operation.

[0061] In one embodiment, feature extraction is performed on the partial discharge ultraviolet image of the insulator to obtain image features. The specific steps are as follows: Figure 3 As shown: Step S301, obtaining a spot image according to a partial discharge ultraviolet image; Step S302, obtaining a spot pixel area of ​​the spot image according to the pixel value of the contour point in the spot image; Step S303, performing graphic fitting on the spot image to determine the spot geometry of the spot image; Step S304, obtaining a spot size parameter according to the spot geometry; Step S305, obtaining image features according to the spot pixel area and the spot size parameter.

[0062] The local discharge ultraviolet image can be processed to obtain a spot image of the discharge area.

[0063] The spot area in the spot image is white, and the pixel value of the white area is set to 1. The other areas outside the white area are black, and the pixel value of the black area is set to 0. The number of pixels with a pixel value of 1 in the spot image is counted as the spot pixel area of ​​the spot image.

[0064] Based on the statistics of the shape of the spot in the partial discharge ultraviolet image in actual situations, it can be known that the shape of the spot in the partial discharge ultraviolet image is generally circular or elliptical. Therefore, the spot image can be fitted with an ellipse or a circle, and the spot geometric shape of the spot image can be judged whether it is close to a circle or an ellipse according to the spot eccentricity (eccentricity) and the spot circularity.

[0065] When the spot geometry is an ellipse, the major axis and minor axis of the ellipse are used as the spot size parameters Mx and My (XY dimension parameters); when the spot geometry is a circle, the diameter of the circle is used as the spot size parameters Mx and My.

[0066] The spot pixel area and spot size parameters are used as image features.

[0067] In this embodiment, a spot image is obtained based on the partial discharge ultraviolet image; and the spot pixel area and spot size parameters are obtained based on the spot image, thereby obtaining relatively accurate image features.

[0068] In one of the embodiments, a spot image is obtained based on a partial discharge ultraviolet image, and the specific steps are as follows: grayscale processing and filtering noise reduction processing are performed on the partial discharge ultraviolet image to obtain a noise-reduced grayscale image; binarization processing is performed on the noise-reduced grayscale image to obtain a binary image; and the binary image is traversed according to an edge detection algorithm to obtain a spot image.

[0069] The partial discharge ultraviolet image can be gray-scale processed and filtered for noise reduction to obtain a noise-reduced gray-scale image; the filtering and noise reduction can be performed using median filtering, mean filtering or dynamic threshold filtering (adaptive filtering). Taking median filtering as an example, median filtering is performed on the noise points and scattered points randomly distributed at the edge of the light spot in the partial discharge ultraviolet image to eliminate noise. The filter template size can be set, generally 3*3 or 5*5, and median filtering is performed on each pixel of the partial discharge ultraviolet image according to the filter template. The neighborhood of the pixel corresponds to multiple pixels (the 3*3 template corresponds to 8 pixels), eliminating salt and pepper noise points (impulse noise points) and protecting the contour edge information of the light spot.

[0070] The denoised grayscale image is binarized to obtain a binarized image; the binarized image is traversed according to an edge detection algorithm such as a Canny detection algorithm to extract the light spot in the discharge area to obtain a light spot image.

[0071] In this embodiment, the partial discharge ultraviolet image is processed to obtain a light spot image with higher precision.

[0072] In one of the embodiments, a spot image is graphically fitted to determine a spot geometry of the spot image, and the specific steps are as follows: according to the pixel coordinates of the contour points of the spot image, an ellipse is fitted to the spot contour in the spot image to obtain an elliptical spot contour; according to the major axis and the minor axis of the elliptical spot contour, the spot eccentricity is obtained; when the spot eccentricity is greater than a threshold value, the spot geometry of the spot image is determined to be an ellipse; when the spot eccentricity is less than the threshold value, a maximum inscribed circle is fitted to the spot in the spot image to obtain a maximum inscribed circle of the spot of the spot image; according to the maximum inscribed circle of the spot of the spot image, the spot circularity of the spot image is obtained; when the spot eccentricity is less than the threshold value and the spot circularity is greater than the threshold value, the spot geometry of the spot image is determined to be a circle.

[0073] According to the pixel coordinates of the contour points of the spot image, the principal component analysis (PCA) or ellipse fitting algorithm can be used to fit the spot contour in the spot image to an ellipse. For example, based on the least squares method, the parameters of the ellipse are determined by minimizing the sum of the squares of the distances from the contour points to the fitting ellipse to obtain an elliptical spot contour. In addition, the ellipse fitting can be performed according to the Hough transformation method or using the Open Source Computer Vision Library (OpenCV) to obtain an elliptical spot contour.

[0074] According to the major axis a and minor axis b of the elliptical spot profile, the spot eccentricity E is obtained, as shown in formula (1).

[0075] E=sqrt(1-(b² / a²)) (1)

[0076] The closer the spot eccentricity E is to 0, the closer the spot geometry of the spot image is to a circle; the closer the spot eccentricity E is to 1, the closer the spot geometry of the spot image is to an ellipse.

[0077] The threshold value Ev may be preset according to actual conditions. When the light spot eccentricity E is greater than the threshold value Ev, the light spot geometric shape of the light spot image is determined to be an ellipse.

[0078] When the spot eccentricity E is less than the threshold Ev, the maximum inscribed circle fitting is performed on the spot in the spot image. By traversing all the pixels in the spot image (considering each pixel as a candidate point for the center of the circle), a pixel is found that minimizes the sum of the distances from the pixel to all contour points. The pixel is taken as the center of the circle, and the maximum inscribed circle of the spot in the spot image is obtained by calculating the maximum inscribed circle of the triangle.

[0079] The spot circularity C of the spot image can be obtained according to the area F of the largest inscribed circle of the spot and the maximum distance lmax from the center point of the spot image to the contour point, as shown in formula (2).

[0080] C=F / (π*lmax 2 ) (2)

[0081] The closer the spot circularity C is to 1, the closer the spot geometry of the spot image is to a circle.

[0082] When the spot eccentricity E is less than the threshold value Ev and the spot circularity C is greater than the threshold value Ev, the spot geometric shape of the spot image is determined to be a circle.

[0083] In this embodiment, the spot geometric shape of the spot image is determined to be circular or elliptical according to the spot eccentricity and the spot circularity, so that the spot geometric shape of the spot image can be determined more accurately.

[0084] In one of the embodiments, before obtaining the predicted peak value of the pulse current corresponding to the local discharge ultraviolet image based on the image features, the detection distance corresponding to the local discharge ultraviolet image, the detection gain, the temperature environmental parameters, the humidity environmental parameters and the pulse current peak prediction model, the method provided by the present application also includes: obtaining the distance from the optical system of the detector to the sensor; the detector is used to obtain the visible light image of the insulator; the optical system and the sensor are components of the detector; obtaining the proportionality coefficient based on the pixel height occupied by the insulator in the visible light image and the actual height of the insulator; and obtaining the detection distance corresponding to the local discharge ultraviolet image based on the distance and the proportionality coefficient.

[0085] Based on the UV / visible light dual-channel detector, the visible light image and the partial discharge UV image of the insulator can be collected; the actual size of the detection object, i.e., the insulator, can be used to calculate the detection distance by calculating the size of the insulator in the visible light image. For example, when the detector camera photographs the insulator, there is a similar relationship between the actual height H of the insulator and the pixel height h of the insulator in the visible light image, wherein the height of the insulator in the visible light image can be determined and the pixel value of the height can be obtained through the open computer vision library, and the pixel value is used as the pixel height h of the insulator in the visible light image.

[0086] The detector can be regarded as a projection device, and the actual height of the insulator is proportional to the height of the insulator projection in the image. Using a virtual triangle as an equivalent, the base of the triangle is the distance D from the detector to the insulator, and the height of the triangle is the actual height H of the insulator; the optical system in the detector projects the triangle onto the image sensor in the detector, forming a new triangle, the base of which is the distance from the optical system to the sensor (regarded as the focal length f, known), and the height of the new triangle is the pixel height h occupied by the insulator in the visible light image. The perspective principle can be used to obtain the distance D from the detector to the insulator based on the proportional relationship when the angle between the detector and the insulator is known.

[0087] Specifically, the distance f from the optical system of the detector to the sensor can be obtained; the proportionality coefficient h / H is obtained according to the pixel height h occupied by the insulator in the visible light image and the actual height H of the insulator; according to the distance f and the proportionality coefficient, the detection distance corresponding to the partial discharge ultraviolet image is obtained as D=fH / h.

[0088] In this embodiment, the proportionality coefficient can be obtained according to the pixel height occupied by the insulator in the visible light image and the actual height of the insulator; the detection distance corresponding to the partial discharge ultraviolet image can be quickly and accurately obtained according to the distance from the optical system of the detector to the sensor and the proportionality coefficient.

[0089] In one of the embodiments, before obtaining the predicted peak value of the pulse current corresponding to the local discharge ultraviolet image based on image features, the detection distance corresponding to the local discharge ultraviolet image, the detection gain, temperature environmental parameters, humidity environmental parameters and the pulse current peak prediction model, the method provided in the present application also includes: acquiring a visible light image; obtaining a depth map corresponding to the visible light image based on the visible light image and the deep learning model; and obtaining the detection distance corresponding to the local discharge ultraviolet image based on the pixel values ​​of the depth map.

[0090] Based on the UV / visible light dual-channel detector, visible light images of insulators and UV images of partial discharges can be collected.

[0091] Visible light images can be input into a deep learning model to obtain a depth map corresponding to the visible light image. The deep learning model can be a convolutional neural network model, a monocular depth estimation model (Monocular Depth Estimation) and a depth image inference model (DPT). The deep learning model can be pre-trained using a labeled visible light image dataset.

[0092] The total pixel value of the depth map can be obtained according to the pixel value of the depth map.

[0093] The pixel value in the depth map usually represents the distance from the camera to each pixel in the scene, so the total pixel value of the depth map can be used as the detection distance corresponding to the partial discharge ultraviolet image.

[0094] In this embodiment, a depth map is obtained based on the visible light image and the deep learning model; and the detection distance corresponding to the partial discharge ultraviolet image is quickly and accurately obtained based on the pixel values ​​of the depth map.

[0095] In one of the embodiments, before obtaining the pulse current prediction peak value corresponding to the local discharge ultraviolet image according to the image features, the detection distance, detection gain, temperature environment parameters, humidity environment parameters and pulse current peak prediction model corresponding to the local discharge ultraviolet image, the method provided by the present application also includes: obtaining image feature samples, detection distance samples, detection gain samples, temperature environment parameter samples and humidity environment parameter samples corresponding to the local discharge ultraviolet image samples to form an initial training set; according to the initial training set, obtaining multiple sub-training sets; for any sub-training set, constructing a first decision tree and performing at least one splitting process; wherein, each time the splitting occurs, a feature subset is randomly selected at each node of the first decision tree, and the optimal feature is selected for splitting according to the set evaluation criteria to obtain each newly formed child node; the splitting process is repeated for each newly formed child node until the stopping condition is met to obtain a second decision tree; the step of constructing the second decision tree is repeated until a predetermined number of second decision trees is reached; and a pulse current peak prediction model is obtained according to the second decision trees corresponding to the multiple sub-training sets.

[0096] Image feature samples, detection distance samples, detection gain samples, temperature environment parameter samples and humidity environment parameter samples corresponding to the partial discharge ultraviolet image samples can be obtained to form an initial training set. The initial training set contains N samples, each of which includes an image feature sample, a detection distance sample, a detection gain sample, a temperature environment parameter sample and a humidity environment parameter sample corresponding to a partial discharge ultraviolet image sample.

[0097] Bootstrap Sampling can be used to randomly select a sample from the initial training set and put it into the sub-training set; sampling with replacement can be repeated to form a sub-training set containing N samples. This repeated sampling process with replacement will be repeated many times (for example, 100 times), each time generating a different sub-training set, thereby obtaining multiple sub-training sets. Due to the sampling with replacement, some samples may be selected multiple times, and some samples may not be selected at all.

[0098] For multiple sub-training sets, a random forest regression model can be used for training. By constructing multiple decision trees (regression trees) and integrating the prediction results of multiple decision trees for regression tasks, a pulse current peak prediction model is obtained.

[0099] You can use the RandomForestRegressor class in the Scientific Computing Toolkit (Scikit-learn library) to build a random forest regression model and set the parameters of the random forest regression model, including the number of decision trees, the maximum depth of the decision tree, the minimum number of samples for node splitting, the minimum number of samples for leaf nodes, and the number of node splitting features. The number of decision trees refers to the different branch trees established. The maximum depth of the decision tree is used to control the depth of decision tree generation. The minimum number of samples for node splitting is used to control node splitting. If the number of samples of a node is less than this value, the node will no longer be split.

[0100] For any subset of training sets, an empty first decision tree is initialized, and the first decision tree is split at least once; wherein, each time a split occurs, a feature subset is randomly selected at each node of the first decision tree, for example, if the total number of feature subsets is 8, 3-4 feature subsets are randomly selected, and according to a set evaluation criterion such as minimizing the mean square error, the optimal feature is selected for splitting to obtain each newly formed child node, for example, the feature subset corresponding to the optimal feature is divided into two feature subsets, and the two feature subsets form a new child node; the splitting process is repeated for each newly formed child node until a stopping condition is met to obtain a second decision tree, wherein the stopping condition may be that the number of samples in the node is less than a set minimum number of samples, the node reaches a preset maximum tree depth, or the impurity of the node drops to a set purity threshold; the step of constructing the second decision tree is repeated until a predetermined number of second decision trees is reached.

[0101] According to the second decision trees corresponding to the multiple sub-training sets, a pulse current peak prediction model is obtained. Each second decision tree will give a predicted value for the target variable of the observed sample, and the prediction result of the pulse current peak prediction model is the aggregation of the prediction results of all second decision trees for each sample, including the average or weighted average. After obtaining the pulse current peak prediction model, the validation set divided from the initial training set can be used to optimize and improve the pulse current peak prediction model, and further optimize the parameters of the pulse current peak prediction model.

[0102] In this embodiment, samples are randomly selected with replacement from the initial training set to construct a sub-training set for each decision tree, so that the samples are random and allow a certain amount of repetition, thereby ensuring the diversity of the sub-training sets, and thus significantly improving the resolution of the feature space, forming a more accurate and smooth decision boundary, and increasing the differences between different second decision trees.

[0103] For any sub-training set, a predetermined number of second decision trees are constructed; based on the second decision trees corresponding to multiple sub-training sets, a pulse current peak prediction model with better performance is obtained. Each second decision tree is independent and trained on randomly selected sub-samples, with diverse sample types and high tolerance to noise, which reduces the risk of overfitting and improves the robustness and accuracy of the pulse current peak prediction model.

[0104] In addition, this embodiment does not need to adopt a supervision mechanism when processing large-scale initial training sets, especially for data with nonlinear relationships, such as the image feature samples, detection distance samples, detection gain samples, temperature environment parameter samples and humidity environment parameter samples in this embodiment. When deciding to divide features, a small number of randomly selected features are considered, and the best division features are selected recursively to reduce redundancy between features, further increase the differences between the second decision trees, and improve the generalization ability, prediction ability and performance of the pulse current peak prediction model.

[0105] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0106] Based on the same inventive concept, the embodiment of the present application also provides a device for determining the discharge strength of an insulator for implementing the above-mentioned method for determining the discharge strength of an insulator. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more devices for determining the discharge strength of an insulator provided below can refer to the limitations of the method for determining the discharge strength of an insulator in the above text, and will not be repeated here.

[0107] In an exemplary embodiment, Figure 4 As shown, a device for determining the discharge intensity of an insulator is provided, wherein:

[0108] An image feature acquisition module 401 is used to extract features from the partial discharge ultraviolet image of the insulator to obtain image features;

[0109] A predicted peak value acquisition module 402 is used to obtain a pulse current predicted peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak value prediction model;

[0110] The discharge intensity acquisition module 403 is used to obtain the discharge intensity of the insulator according to the relationship between the pulse current prediction peak value and the discharge intensity level.

[0111] In one of the embodiments, the image feature acquisition module 401 is also used to: obtain a spot image based on the local discharge ultraviolet image; obtain a spot pixel area of ​​the spot image based on the contour point pixel value in the spot image; perform graphic fitting on the spot image to determine the spot geometry of the spot image; obtain a spot size parameter based on the spot geometry; and obtain image features based on the spot pixel area and the spot size parameter.

[0112] In one of the embodiments, the image feature acquisition module 401 is further used to: perform grayscale processing and filtering noise reduction processing on the local discharge ultraviolet image to obtain a noise-reduced grayscale image; perform binarization processing on the noise-reduced grayscale image to obtain a binary image; and traverse the binary image according to an edge detection algorithm to obtain the spot image.

[0113] In one of the embodiments, the image feature acquisition module 401 is also used to: perform ellipse fitting on the spot contour in the spot image according to the pixel coordinates of the contour points of the spot image to obtain an elliptical spot contour; obtain the spot eccentricity according to the major axis and the minor axis of the elliptical spot contour; when the spot eccentricity is greater than a threshold, determine the spot geometry of the spot image as an ellipse; when the spot eccentricity is less than a threshold, perform maximum inscribed circle fitting on the spot in the spot image to obtain the maximum inscribed circle of the spot of the spot image; obtain the spot circularity of the spot image according to the maximum inscribed circle of the spot of the spot image; when the spot eccentricity is less than a threshold and the spot circularity is greater than a threshold, determine the spot geometry of the spot image as a circle.

[0114] In one embodiment, the device also includes a detection distance acquisition module, which is used to: obtain the distance from the optical system of the detector to the sensor; the detector is used to obtain a visible light image of the insulator; the optical system and the sensor are components of the detector; a proportionality coefficient is obtained based on the pixel height occupied by the insulator in the visible light image and the actual height of the insulator; and the detection distance corresponding to the partial discharge ultraviolet image is obtained based on the distance and the proportionality coefficient.

[0115] In one embodiment, the device also includes a detection distance acquisition module, which is used to: obtain image feature samples, detection distance samples, detection gain samples, temperature environment parameter samples and humidity environment parameter samples corresponding to local discharge ultraviolet image samples to form an initial training set; based on the initial training set, multiple sub-training sets are obtained; for any sub-training set, a first decision tree is constructed and a splitting process is performed at least once; wherein, each time a split occurs, a feature subset is randomly selected at each node of the first decision tree, and the optimal feature is selected for splitting according to a set evaluation criterion to obtain each newly formed child node; the splitting process is repeated for each newly formed child node until a stop condition is met to obtain a second decision tree; the step of constructing the second decision tree is repeated until a predetermined number of second decision trees is reached; and a pulse current peak prediction model is obtained based on the second decision trees corresponding to multiple sub-training sets.

[0116] Each module in the above-mentioned device for determining the discharge intensity of an insulator can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0117] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as 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. The processor of the computer device is used 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data of an embodiment of a method for determining the discharge intensity of an insulator. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining the discharge intensity of an insulator is implemented.

[0118] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0120] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0121] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0122] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0123] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0124] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0125] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining the discharge strength of an insulator, characterized in that: The method comprises: Extract features from the partial discharge ultraviolet image of the insulator to obtain image features; Obtaining a pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak prediction model; The discharge intensity of the insulator is obtained according to the relationship between the predicted peak value of the pulse current and the discharge intensity level.

2. The method according to claim 1, characterized in that The feature extraction of the partial discharge ultraviolet image of the insulator to obtain the image features includes: Obtaining a light spot image according to the partial discharge ultraviolet image; Obtaining a spot pixel area of ​​the spot image according to a contour point pixel value in the spot image; Performing graphic fitting on the light spot image to determine the light spot geometric shape of the light spot image; According to the light spot geometry, a light spot size parameter is obtained; Image features are obtained according to the light spot pixel area and the light spot size parameter.

3. The method according to claim 2, characterized in that The step of obtaining a spot image according to the partial discharge ultraviolet image comprises: Performing grayscale processing and filtering noise reduction processing on the partial discharge ultraviolet image to obtain a noise-reduced grayscale image; Binarizing the denoised grayscale image to obtain a binary image; The binary image is traversed according to an edge detection algorithm to obtain the light spot image.

4. The method according to claim 2, characterized in that: The performing graphic fitting on the light spot image to determine the light spot geometric shape of the light spot image includes: According to the pixel coordinates of the contour points of the light spot image, an ellipse fitting is performed on the light spot contour in the light spot image to obtain an ellipse light spot contour; Obtaining the eccentricity of the light spot according to the major axis and the minor axis of the elliptical light spot profile; When the light spot eccentricity is greater than a threshold, determining the light spot geometric shape of the light spot image as an ellipse; When the spot eccentricity is less than a threshold value, the spot in the spot image is fitted with a maximum inscribed circle to obtain the maximum inscribed circle of the spot of the spot image; the circularity of the spot of the spot image is obtained according to the maximum inscribed circle of the spot of the spot image; when the spot eccentricity is less than a threshold value and the circularity of the spot is greater than a threshold value, the geometric shape of the spot of the spot image is determined to be a circle.

5. The method according to claim 1, characterized in that: Before obtaining the pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak prediction model, the method further includes: Acquire the distance from the optical system of the detector to the sensor; the detector is used to acquire the visible light image of the insulator; the optical system and the sensor are components of the detector; Obtaining a proportionality coefficient according to the pixel height occupied by the insulator in the visible light image and the actual height of the insulator; According to the distance and the proportionality coefficient, the detection distance corresponding to the partial discharge ultraviolet image is obtained.

6. The method according to claim 1, characterized in that Before obtaining the pulse current prediction peak value corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak prediction model, the method further includes: Obtain image feature samples, detection distance samples, detection gain samples, temperature environment parameter samples and humidity environment parameter samples corresponding to the partial discharge ultraviolet image samples to form an initial training set; According to the initial training set, a plurality of sub-training sets are obtained; For any sub-training set, a first decision tree is constructed and a splitting process is performed at least once; wherein, each time a split occurs, a feature subset is randomly selected at each node of the first decision tree, and the optimal feature is selected for splitting according to a set evaluation criterion to obtain each newly formed child node; the splitting process is repeated for each newly formed child node until a stop condition is met, thereby obtaining a second decision tree; and the step of constructing the second decision tree is repeated until a predetermined number of second decision trees is reached; A pulse current peak prediction model is obtained according to the second decision trees corresponding to the multiple sub-training sets.

7. A device for determining the discharge strength of an insulator, characterized in that: The device comprises: An image feature acquisition module is used to extract features from the partial discharge ultraviolet image of the insulator to obtain image features; A predicted peak value acquisition module, used to obtain the predicted peak value of the pulse current corresponding to the partial discharge ultraviolet image according to the image features, the detection distance corresponding to the partial discharge ultraviolet image, the detection gain, the temperature environment parameter, the humidity environment parameter and the pulse current peak value prediction model; The discharge intensity acquisition module is used to obtain the discharge intensity of the insulator according to the relationship between the pulse current prediction peak value and the discharge intensity level.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images