State evaluation method and device of high-voltage isolation switch, medium and equipment

Abstract

The invention discloses a state evaluation method and device of a high-voltage isolation switch, a medium and equipment. The method relates to the technical field of image processing, and comprises the following steps: detecting a to-be-evaluated image of a target area collected in real time by adopting a preset detection model to obtain a frame-selected image; performing image segmentation on the frame-selected image by adopting a preset instance segmentation model to obtain a current instance segmentation image corresponding to the frame-selected image; performing coordinate estimation by adopting a Kalman filtering estimation method on the basis of a historical instance segmentation image and a current instance segmentation image of the target area at the previous moment, so as to obtain a centroid coordinate of each segmentation area in the current instance segmentation image and a motion change state of each isolating switch; and evaluating the state of each isolating switch based on each centroid coordinate, the predetermined structure parameter of each isolating switch and the motion change state to obtain a state evaluation result. According to the invention, automatic identification of the on-off state is realized, and the safety and operation and maintenance efficiency of a power grid are improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, medium and equipment for evaluating the status of a high-voltage disconnector. Background Art

[0002] In the field of power grid, thanks to the rapid development and continuous progress of computer vision, intelligent monitoring and video analysis technology, intelligent inspection has been widely used in substation management. Computer vision technology and other intelligent analysis algorithms are used to process and analyze video images, and alarms are issued in time according to pre-set safety rules to handle and detect issues of concern to people. Through the video monitoring system, all-weather real-time image analysis and monitoring are realized, and image recognition algorithms are used to analyze and understand images, which completely changes the previous mode of completely relying on monitoring personnel for image analysis. This progress has enabled the power grid industry to make significant progress in improving safety and efficiency. In the field of ultra-high voltage power grid, the failure of high-voltage open-type disconnectors to open and close is one of the most common abnormal conditions. The occurrence of such abnormal conditions can easily lead to heating of switch contacts and arc discharge when operating adjacent disconnectors. Faults or accidents. Compared with GIS closed equipment, AIS open-type high-voltage disconnectors use control mechanical arms to perform opening and closing operations. Due to angle limitations, multiple angles are required to determine whether the dynamic contacts of opening and closing are in place. In addition, due to the existence of multiple mechanical interlocking loops and strong logical correlation, multiple standards are required to assist in determining whether there are defective characteristics. The status assessment of traditional disconnectors still relies on the experience of on-site personnel to make judgments, which is interfered by subjective factors. Summary of the invention

[0003] In view of this, the present invention provides a method, device, medium and equipment for evaluating the status of a high-voltage disconnector, the main purpose of which is to solve the problem that the current judgment of the status of the disconnector depends on manual work and the judgment is inaccurate.

[0004] To solve the above problems, the present application provides a method for evaluating the state of an isolating switch, comprising:

[0005] Using a preset detection model, the state assessment image of the target area collected in real time is detected to obtain a frame-selected image, wherein the target area is the area where the disconnector is located;

[0006] Using a preset instance segmentation model, perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image;

[0007] Based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image, a Kalman filter estimation method is used to perform coordinate estimation, and obtain the centroid coordinates of each segmentation area in the current instance segmentation image and the motion change state of each disconnector;

[0008] The state of each isolating switch is evaluated based on the coordinates of each centroid, the predetermined structural parameters of each isolating switch, and the motion change state of each isolating switch to obtain a state evaluation result.

[0009] Optionally, a preset detection model is used to detect the state evaluation image of the target area collected in real time to obtain a frame selection image, which specifically includes:

[0010] Based on the state recognition image, a first target backbone network of the preset detection model is used to perform feature extraction to obtain a first feature image;

[0011] Based on the first feature image, a first target classification network of the preset detection model is used to perform classification prediction to obtain a category prediction score of each disconnector in the first feature image, so as to obtain a current state category corresponding to each disconnector;

[0012] Based on the first feature image, the first target regression network of the preset detection model is used to perform boundary prediction to obtain the boundary boxes of each isolating switch in the first feature image, each of which carries a predicted coordinate value and a border mark to obtain the framed image.

[0013] Optionally, the adopting a preset instance segmentation model to perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image specifically includes:

[0014] Based on the framed image, a second target backbone network of the preset instance segmentation model is used to perform feature extraction to obtain a second feature image;

[0015] Based on the second feature image, a target feature pyramid network of the preset instance segmentation model is used to perform feature extraction to obtain a target feature image;

[0016] Based on the target feature map, a target region proposal network of the preset instance segmentation model is used to perform feature extraction to obtain a region feature image containing a plurality of candidate regions;

[0017] Based on the region feature image, a segmentation mask branch network of the preset instance segmentation model is used to perform mask prediction to obtain the current instance segmentation image including the segmentation masks of each candidate region.

[0018] Optionally, the coordinate estimation is performed based on the historical instance segmentation image at the previous moment of the target area and the current instance segmentation image using a Kalman filter estimation method to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector, specifically including:

[0019] Based on the historical instance segmentation image of the target area at the previous moment, coordinate calculation processing is performed on each segmented area to obtain the historical state corresponding to each segmented area, wherein the historical state includes the historical centroid coordinates and the historical centroid moving speed;

[0020] Performing state prediction based on the historical centroid coordinates to obtain an estimated state at a current moment and an estimated state covariance at a current moment, wherein the estimated state includes an estimated centroid coordinate and an estimated centroid moving speed;

[0021] Performing coordinate calculation processing based on each segmented area in the current instance segmented image to obtain current centroid coordinates and current centroid moving speed corresponding to each segmented area;

[0022] The current center of mass coordinates and the current center of mass moving speed are corrected based on the historical center of mass coordinates, the estimated center of mass coordinates, the historical center of mass moving speed, and the estimated center of mass moving speed to obtain the center of mass coordinates and the motion change state of each center of mass of each segmented area in the current instance segmented image.

[0023] Optionally, the evaluating the state of each isolating switch based on the coordinates of each centroid, the predetermined structural parameters of each isolating switch, and the motion change state of each isolating switch to obtain a state evaluation result specifically includes:

[0024] Performing inverse perspective transformation processing on the current instance segmented image based on a preset plane to obtain an inverse perspective image;

[0025] Based on the reverse perspective image, obtaining the moving contact center coordinates and the base center coordinates of each of the disconnectors in the reverse perspective image;

[0026] Calculation and processing are performed based on the center coordinates of the moving contact, the center coordinates of the base, and predetermined structural parameters corresponding to the same isolating switch to obtain the conductive arm angle corresponding to the same isolating switch;

[0027] The state of the same isolating switch is evaluated based on the conductive arm angle corresponding to the same isolating switch and the motion change state to obtain a state evaluation result.

[0028] Optionally, performing inverse perspective transformation processing on the current instance segmented image based on a preset plane to obtain an inverse perspective image specifically includes:

[0029] Construct the system of equations for plane projective transformation;

[0030] Determine a to-be-projected area based on the current instance segmented image and determine a mapping area based on the preset plane;

[0031] Solving the plane projection transformation equations based on the preset boundary coordinates of the area to be projected and the predetermined projection boundary coordinates of the mapping area to obtain a mapping matrix;

[0032] The inverse perspective image is obtained by mapping each pixel in the current instance segmented image using the mapping matrix.

[0033] Optionally, the calculating and processing based on the moving contact center coordinates, the base center coordinates, and predetermined structural parameters corresponding to the same isolating switch to obtain the conductive arm angle corresponding to the same isolating switch specifically includes:

[0034] Calculation is performed based on the center coordinates of the moving contact and the center coordinates of the base corresponding to the same isolating switch to obtain an image distance value from the center pixel point of the moving contact to the center pixel point of the base;

[0035] Based on the image distance value, a preset camera imaging method is used to perform calculation processing to obtain an actual distance value from the center of the moving contact to the center of the base;

[0036] The conductive arm angle corresponding to the same disconnector is obtained by performing calculation based on the actual distance value and the predetermined conductive arm length.

[0037] In order to solve the above problems, the present application provides a state assessment device for an isolating switch, comprising:

[0038] A detection module, used to detect the state assessment image of the target area collected in real time by using a preset detection model to obtain a frame-selected image, wherein the target area is the area where the disconnector is located;

[0039] An image segmentation module is used to perform image segmentation on the framed image using a preset instance segmentation model to obtain a current instance segmentation image corresponding to the framed image;

[0040] A coordinate estimation module, used to perform coordinate estimation based on the previous historical instance segmentation image of the target area and the current instance segmentation image using a Kalman filter estimation method to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector;

[0041] An evaluation module is used to evaluate the state of each isolating switch based on the coordinates of each centroid, the predetermined structural parameters of each isolating switch and the motion change state of each isolating switch to obtain a state evaluation result.

[0042] In order to solve the above problem, the present application provides a storage medium, characterized in that the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned state assessment method of the disconnector are implemented.

[0043] To solve the above problem, the present application provides an electronic device, characterized in that it includes at least a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program on the memory, the steps of the above-mentioned isolating switch status assessment method are implemented.

[0044] Beneficial effects of the present application: The present application detects the image to be evaluated through a preset detection model and performs image segmentation on the framed image output by the preset detection model based on the preset instance segmentation model, and obtains the current instance segmentation image to realize the automatic and intelligent recognition of the state of the disconnector, which does not rely on on-site personnel and improves the efficiency and accuracy of state evaluation; the Kalman filter estimation method is used to estimate the coordinates based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image, and the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector are obtained; the state of each disconnector is evaluated based on the centroid coordinates, the predetermined structural parameters of each disconnector, and the motion change state of each disconnector, and the state evaluation result is obtained. Not only the closing or opening state of the switch can be identified, but also the opening and closing operation angle of the current disconnector can be identified, which provides strong technical support for the operation and maintenance management of the power system and significantly improves the safety and operation efficiency of the power grid.

[0045] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0047] Figure 1A schematic diagram of a flow chart of a state assessment method for an isolating switch provided in an embodiment of the present application is shown;

[0048] Figure 2 A schematic diagram of a flow chart of a state assessment method for an isolating switch provided in an embodiment of the present application is shown;

[0049] FIG. 3( a ) and FIG. 3( b ) are schematic diagrams showing frame-selected images obtained after detection using a preset detection model in an embodiment of the present application;

[0050] FIG. 4( a ) and FIG. 4( b ) are schematic diagrams showing a current instance segmentation image obtained after segmentation using a preset instance segmentation model according to an embodiment of the present application;

[0051] FIG. 5( a ) and FIG. 5( b ) are schematic diagrams showing inverse perspective images of the isolating switch image after perspective transformation according to an embodiment of the present application;

[0052] Figure 6 A structural block diagram of a state evaluation device for an isolating switch provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0053] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0054] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of the embodiments. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0055] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0056] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0057] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.

[0058] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0059] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0060] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0061] The present application embodiment provides a method for evaluating the state of an isolating switch, such as Figure 1 As shown, including:

[0062] Step S101: using a preset detection model, detecting the state assessment image of the target area collected in real time to obtain a frame-selected image, wherein the target area is the area where the disconnector is located;

[0063] In the specific implementation process of this step, a preset detection model is used to detect the state assessment image of the target area to obtain a framed image, which carries the current state category and border mark of each disconnector in the target area, and the current state category includes the closed state and the open state; the framed image includes at least one disconnector in the target area. Specifically, based on the state recognition image, the first target backbone network of the preset detection model is used to extract features to obtain a first feature image; based on the first feature image, the first target classification network of the preset detection model is used to perform classification prediction to obtain the category prediction score of each disconnector in the first feature image to obtain the current state category corresponding to each disconnector; based on the first feature image, the first target regression network of the preset detection model is used to perform boundary prediction to obtain the boundary box of each disconnector in the first feature image, and each boundary box carries the predicted coordinate value and the border mark to obtain the framed image.

[0064] Step S102: using a preset instance segmentation model to perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image;

[0065] In the specific implementation process of this step, image segmentation processing is performed on the framed image based on a preset instance segmentation model to obtain a current instance segmentation image corresponding to the framed image; the current instance segmentation image is a part segmentation image of each isolating switch in the target area, and parts of multiple isolating switches are segmented, and each part of the isolating switch includes an insulator support part, a base part, a lower conductive tube part, a joint part, an upper conductive tube part, a moving contact part, a static contact part and other parts; the sub-instance segmentation images corresponding to each isolating switch in the current instance segmentation image carry a border mark.

[0066] Step S103: performing coordinate estimation using a Kalman filter estimation method based on the previous historical instance segmentation image of the target area and the current instance segmentation image, to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector;

[0067] In the specific implementation process of this step, coordinate calculation processing is performed on each segmented area in the historical instance segmentation image of the target area at the previous moment to obtain the historical state corresponding to each segmented area, and the historical state includes the historical center of mass coordinates and the historical center of mass moving speed; state prediction is performed based on the historical center of mass coordinates to obtain the estimated state at the current moment and the estimated state covariance at the current moment, and the estimated state includes the estimated center of mass coordinates and the estimated center of mass moving speed; coordinate calculation processing is performed on each segmented area in the current instance segmentation image to obtain the current center of mass coordinates and the current center of mass moving speed corresponding to each segmented area; the current center of mass coordinates and the current center of mass moving speed are corrected based on the historical center of mass coordinates, the estimated center of mass coordinates, the historical center of mass moving speed, and the estimated center of mass moving speed to obtain the center of mass coordinates of each segmented area in the current instance segmentation image and the motion change state of each isolating switch.

[0068] Step S104: evaluating the state of each isolating switch based on the coordinates of each centroid, the predetermined structural parameters of each isolating switch, and the motion change state of each isolating switch to obtain a state evaluation result.

[0069] In the specific implementation process of this step, the current instance segmented image is subjected to inverse perspective transformation processing based on a preset plane to obtain an inverse perspective image; based on the inverse perspective image, the moving contact center coordinates and the base center coordinates of each of the isolating switches in the inverse perspective image are obtained; based on the moving contact center coordinates, the base center coordinates, and predetermined structural parameters corresponding to the same isolating switch, calculation processing is performed to obtain the conductive arm angle corresponding to the same isolating switch; based on the conductive arm angle corresponding to the same isolating switch and the motion change state, the state of the same isolating switch is evaluated to obtain a state evaluation result.

[0070] This application detects the image to be evaluated through a preset detection model and performs image segmentation on the framed image output by the preset detection model based on the preset instance segmentation model, and obtains the current instance segmentation image to realize the automatic and intelligent recognition of the state of the disconnector, which does not rely on on-site personnel and improves the efficiency and accuracy of state evaluation; based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image, the Kalman filter estimation method is used to estimate the coordinates, and the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector are obtained; based on the centroid coordinates, the predetermined structural parameters of each disconnector, and the motion change state of each disconnector, the state of each disconnector is evaluated to obtain the state evaluation result. Not only can the closing or opening state of the switch be identified, but also the opening and closing operation angle of the current disconnector can be identified, which provides strong technical support for the operation and maintenance management of the power system and significantly improves the safety and operation efficiency of the power grid.

[0071] Another embodiment of the present application provides another method for evaluating the state of an isolating switch, such as Figure 2 As shown, including:

[0072] Step S201: constructing a preset detection model;

[0073] In the specific implementation process of this step, the pre-acquired image data is annotated to obtain each first label image, each of which includes a closed label image, an open label image and an isolating switch mark; based on each of the first label images as training samples, a preset convolutional neural network model is trained to generate the preset detection model; wherein the preset detection model includes a target backbone network and a target detection head network, and the target detection head network includes a target classification network and a target regression network. Specifically, each of the first label images is respectively input into the initial first backbone network of the preset convolutional neural network model for feature extraction to obtain the first label features corresponding to each of the first label images; based on each of the first label features, the initial first classification network of the preset convolutional neural network model is used for classification to obtain the category score corresponding to each of the first label images, and then the first predicted category corresponding to each of the first label images is determined; based on the first label category and the first predicted category corresponding to each of the first label images, the loss value is calculated to obtain the first loss value; based on the first loss value, the model parameters of the initial first classification network are updated by the gradient descent method to obtain the current first classification network; the model parameters of the current first classification network are updated cyclically and iteratively until the maximum number of iterations is reached or the first loss value is less than the preset threshold, to obtain the first target classification network. Based on each of the first label features, an initial regression network of the preset convolutional neural network model is used to perform boundary prediction, and a predicted boundary box and a predicted boundary mark corresponding to each isolating switch in each of the first label images are obtained. A loss value is calculated based on the predicted boundary box, the predicted boundary mark, the label boundary box and the label boundary mark to obtain a second loss value. Based on the second loss value, the model parameters of the initial regression network are updated using the gradient descent method to obtain a current regression network. The model parameters of the current regression network are updated in a cyclic iterative manner until the maximum number of iterations is reached or the second loss value is less than a preset threshold, and a target regression network is obtained to obtain the preset detection model.

[0074] Step S202: using a preset detection model to detect the state evaluation image of the target area collected in real time to obtain a frame selection image;

[0075] In the specific implementation process of this step, the preset detection model is used to detect the state assessment image of the target area to obtain a framed image, which carries the current state category and frame mark of each disconnector in the target area, and the current state category includes the closed state and the open state; specifically, based on the state recognition image, the first target backbone network of the preset detection model is used to extract features to obtain a first feature image; based on the first feature image, the first target classification network of the preset detection model is used to perform classification prediction to obtain the category prediction score of each disconnector in the first feature image, so as to obtain the current state category corresponding to each disconnector; specifically, the category corresponding to the larger prediction score is determined as the category of the first feature image. Based on the first feature image, the first target regression network of the preset detection model is used to perform boundary prediction to obtain the boundary box of each disconnector in the first feature image, and each boundary box carries the predicted coordinate value and the frame mark to obtain the framed image. As shown in Figure 3, it is a schematic diagram of the framed image obtained after detection using the preset detection model.

[0076] Step S203: constructing a preset instance segmentation model;

[0077] In the specific implementation process of this step, the pre-acquired image data is annotated again to obtain each second label image; each second label image carries a part label category, and the part label category includes part label categories such as insulator support part, insulator base part, lower conductive tube part, joint part, upper conductive tube part, moving contact part, and static contact part; based on each first label image as a training sample, a preset instance segmentation network is trained to obtain the preset instance segmentation model; the preset instance segmentation model includes: a second target backbone network, a target feature pyramid network, a target region proposal network, and a segmentation mask branch network; based on each second label image, the initial second backbone network of the preset instance segmentation model is used to extract features to obtain the components corresponding to each second label. The invention relates to a second label feature image corresponding to each image; based on each of the second label feature images, the initial feature pyramid network of the preset instance segmentation model is used to perform feature extraction to obtain each third label feature image; based on each of the third label features, the initial region proposal network of the preset instance segmentation model is used to perform feature extraction to obtain an initial region feature image containing several candidate regions; based on each of the initial region feature images, the initial segmentation mask branch network of the preset instance segmentation model is used to perform mask prediction to obtain the initial instance segmentation image containing the segmentation mask of each candidate region; based on each of the predicted initial instance segmentation images and each of the second label images, the model parameters of the preset instance segmentation network are adjusted using the back propagation algorithm until the model converges to obtain the preset instance segmentation model.

[0078] Step S204: using a preset instance segmentation model to perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image;

[0079] In the specific implementation process of this step, based on the framed image, the second target backbone network of the preset instance segmentation model is used to perform feature extraction to obtain a second feature image; based on the second feature image, the target feature pyramid network of the preset instance segmentation model is used to perform feature extraction to obtain a target feature image; based on the target feature map, the target region proposal network of the preset instance segmentation model is used to perform feature extraction to obtain a regional feature image containing several candidate regions; based on the regional feature image, the segmentation mask branch network of the preset instance segmentation model is used to perform mask prediction to obtain the current instance segmentation image containing the segmentation masks of each candidate region, as shown in Figure 4, which is a schematic diagram of the current instance segmentation image obtained after segmentation using the preset instance segmentation model.

[0080] Step S205: performing coordinate estimation using a Kalman filter estimation method based on the previous historical instance segmentation image of the target area and the current instance segmentation image, to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector;

[0081] In the specific implementation process of this step, coordinate calculation processing is performed on each segmented area in the segmented image based on the historical instance of the target area at the previous moment, and the historical state corresponding to each segmented area is obtained. The historical state includes the historical centroid coordinates and the historical centroid moving speed. The mathematical expression of the historical state can be expressed as the following formula (1):

[0082] x=[c x c y v x v y ] (1);

[0083] Among them, c x , c y v is the historical centroid coordinates of each segmented area of ​​the historical instance segmentation image in the previous moment in the x and y directions respectively; x , v y Indicates the speed at which the historical center of mass moves in the x and y directions respectively.

[0084] Based on the historical centroid coordinates, the state prediction is performed to obtain the estimated state at the current moment and the estimated state covariance at the current moment, wherein the estimated state includes the estimated centroid coordinates and the estimated centroid moving speed; the mathematical expression of the estimated state x′ is calculated and can be shown as the following formula (2):

[0085] x′=Fx (2);

[0086] Where x is the historical state of the disconnector at the previous time t-1, and F is the state transfer matrix. This formula predicts the estimated state at the current time t. The mathematical expression of the estimated state covariance P′ at the current time can be shown as follows:

[0087] P′=FPF T +Q (3);

[0088] Among them, P is the covariance of the disconnector at the previous moment and at time t-1, Q is the noise matrix of the system, which represents the reliability of the entire system and is generally initialized to a very small value. This formula predicts the estimated state covariance P′, F at time t T is the transposed matrix of the state transfer matrix.

[0089] Based on the estimated state of each segmented area in the current instance segmented image, coordinate calculation processing is performed to obtain an observed state; the mathematical expression of the observed state can be expressed as the following formula (4):

[0090] y=z-Hx′ (4);

[0091] Wherein, y is the observation state; z is the measurement matrix, H is the transfer matrix, and x′ is the estimated state; the observation state includes the current centroid coordinates and the current centroid moving speed corresponding to each segmented area;

[0092] Based on the historical centroid coordinates, the estimated centroid coordinates, the historical centroid moving speed, and the estimated centroid moving speed, the current centroid coordinates and the current centroid moving speed are corrected to obtain the centroid coordinates of each segmented area and the motion change state of each disconnector in the current instance segmented image. Specifically, based on the estimated state covariance P′, the transfer matrix H, and the transfer transposed matrix H corresponding to the transfer matrix H T The preset noise matrix R is used for calculation and processing to obtain the observation error covariance matrix S. The mathematical expression of the observation error covariance matrix S can be expressed as follows:

[0093] S=HP′H T +R (5);

[0094] Based on the observation error covariance matrix S, the estimated state covariance P′ and the transfer transposed matrix H T The Kalman gain K is obtained by performing calculation processing. The mathematical expression of the Kalman gain K can be expressed as follows:

[0095] K=P′H T S -1(6);

[0096] Among them, S -1 is the reversible matrix of the observation error covariance matrix S. Based on the estimated state x′, the observed state y and the Kalman gain K, the corrected target state x″ is obtained; the mathematical expression of the target state x″ can be expressed as the following formula (7):

[0097] x″=x′+Ky (7);

[0098] The target state includes the centroid coordinates of each segmented area in the current instance segmented image and the motion change state of each centroid. At the same time, based on the predetermined unit matrix, the Kalman gain K, the transfer matrix H and the estimated state covariance P′, a calculation process is performed to obtain the current correction state covariance P″; the mathematical expression of the current correction state covariance P″ can be shown as the following formula (8):

[0099] P″=(I-KH)P′ (8);

[0100] Among them, I is a predetermined unit matrix, which is an n×n square matrix with only diagonal elements being 1 and the rest being 0. This lays the foundation for the subsequent calculation of the Kalman gain at the next moment.

[0101] Step S206: performing inverse perspective transformation processing on the current instance segmented image based on a preset plane to obtain an inverse perspective image;

[0102] In the specific implementation process of this step, a plane projection transformation equation group is constructed; the mathematical expression of the plane projection transformation equation group can be expressed as the following formula (9):

[0103]

[0104] Among them, x1-x4 are the horizontal coordinate variables on the current instance segmentation image; y1-y4 are the vertical coordinate variables on the current instance segmentation image; x1′-x′2 are the horizontal coordinate variables on the preset plane; y1′-y4′ are the vertical coordinate variables on the preset plane; h 11 -h 33is a mapping relationship parameter variable. The area to be projected is determined based on the current instance segmentation image and the mapping area is determined based on the preset plane; the plane projection transformation equation group is solved based on the preset boundary coordinates of the area to be projected and the preset projection boundary coordinates of the mapping area to obtain a mapping matrix; specifically, the preset boundary coordinates of the area to be projected of the current instance segmentation image and the preset projection boundary coordinates of the mapping area of ​​the preset plane can be determined according to actual needs; then the preset boundary coordinates and the preset projection boundary coordinates are substituted into the plane projection transformation equation group for calculation to obtain a mapping matrix, that is, h is calculated. 11 -h 33 The parameter value corresponding to the mapping relationship parameter variable; based on each pixel point in the current instance segmentation image, the mapping matrix is ​​used to map to obtain the inverse perspective image. Based on each pixel point in the current instance segmentation image and the mapping matrix, calculation processing is performed to obtain the projection pixel point corresponding to the projection coordinate on the preset plane corresponding to each pixel point in the current instance segmentation image; based on each of the projection pixel points, a bilinear difference calculation method is used to expand each of the projection pixel points to obtain the inverse perspective image. As shown in Figure 5, it is a schematic diagram of the inverse perspective image after the isolation switch image is perspective transformed.

[0105] Step S207: based on the reverse perspective image, obtaining the moving contact center coordinates and the base center coordinates of each of the disconnectors in the reverse perspective image;

[0106] In the specific implementation process of this step, based on the reverse perspective image, the moving contact center coordinates (u1, v1) and the base center coordinates (u2, v2) of each of the disconnectors in the reverse perspective image are obtained.

[0107] Step S208: performing calculation processing based on the center coordinates of the moving contact, the center coordinates of the base, and predetermined structural parameters corresponding to the same isolating switch to obtain the conductive arm angle corresponding to the same isolating switch;

[0108] In the specific implementation process of this step, calculation and processing are performed based on the center coordinates of the moving contact and the center coordinates of the base corresponding to the same isolating switch to obtain the image distance value from the center pixel point of the moving contact to the center pixel point of the base; the mathematical expression of the image distance value d′ can be expressed as the following formula (10):

[0109]

[0110] Based on the image distance, a preset camera imaging method is used to perform calculation processing to obtain the actual distance value d from the center of the moving contact to the center of the base; the mathematical expression of the actual distance value d can be expressed as the following formula (11):

[0111]

[0112] Among them, s is the actual total length of the two guide arms in the real world, and s′ is the total image length of the two guide arms in the image space.

[0113] Based on the actual distance value and the predetermined conductive arm length, a calculation process is performed to obtain a conductive arm angle corresponding to the same disconnector. The calculation formula of the conductive arm angle can be expressed as the following formula (12):

[0114]

[0115] Where l is the actual length of a single conductive arm.

[0116] Step S209: evaluating the state of the same isolating switch based on the conductive arm angle and the motion change state corresponding to the same isolating switch to obtain a state evaluation result.

[0117] In the specific implementation process of this step, when the conductive arm angle is less than the preset threshold, the state of the disconnector is judged to be the closed state; the preset threshold can be set according to actual needs. When the conductive arm angle is less than the preset threshold and the actual distance value d is less than 2 times the actual length l of the conductive arm, that is, when the actual distance value d is less than or equal to 2l, the closing state is not in place; when the conductive arm angle is greater than the preset threshold, the state of the disconnector is judged to be the open state; thereby realizing the open and closed state recognition and angle estimation of the outdoor telescopic high-voltage disconnector, and outputting it to the console.

[0118] This application detects the image to be evaluated through a preset detection model and performs image segmentation on the framed image output by the preset detection model based on the preset instance segmentation model, and obtains the current instance segmentation image to realize the automatic and intelligent recognition of the state of the disconnector, which does not rely on on-site personnel and improves the efficiency and accuracy of state evaluation; based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image, the Kalman filter estimation method is used to estimate the coordinates, and the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector are obtained; based on the centroid coordinates, the predetermined structural parameters of each disconnector, and the motion change state of each disconnector, the state of each disconnector is evaluated to obtain the state evaluation result. Not only can the closing or opening state of the switch be identified, but also the opening and closing operation angle of the current disconnector can be identified, which provides strong technical support for the operation and maintenance management of the power system and significantly improves the safety and operation efficiency of the power grid.

[0119] Another embodiment of the present application provides a state assessment device for an isolating switch, such as Figure 6 As shown, including:

[0120] Detection module 1, used to detect the state assessment image of the target area collected in real time by using a preset detection model to obtain a frame-selected image, wherein the target area is the area where the disconnector is located;

[0121] An image segmentation module 2 is used to perform image segmentation on the framed image using a preset instance segmentation model to obtain a current instance segmentation image corresponding to the framed image;

[0122] A coordinate estimation module 3 is used to perform coordinate estimation based on the previous historical instance segmentation image of the target area and the current instance segmentation image using a Kalman filter estimation method to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector;

[0123] The evaluation module 4 is used to evaluate the state of each isolating switch based on the coordinates of each centroid, the predetermined structural parameters of each isolating switch and the movement change state of each isolating switch to obtain a state evaluation result.

[0124] In the specific implementation process, the detection module 1 is specifically used to: based on the state recognition image, use the first target backbone network of the preset detection model to perform feature extraction to obtain a first feature image; based on the first feature image, use the first target classification network of the preset detection model to perform classification prediction to obtain the category prediction score of each isolating switch in the first feature image, so as to obtain the current state category corresponding to each isolating switch; based on the first feature image, use the first target regression network of the preset detection model to perform boundary prediction to obtain the boundary box of each isolating switch in the first feature image, each of which carries a predicted coordinate value and a border mark to obtain the framed image.

[0125] In the specific implementation process, the image segmentation module 2 is specifically used to: based on the framed image, use the second target backbone network of the preset instance segmentation model to perform feature extraction to obtain a second feature image; based on the second feature image, use the target feature pyramid network of the preset instance segmentation model to perform feature extraction to obtain a target feature image; based on the target feature map, use the target region proposal network of the preset instance segmentation model to perform feature extraction to obtain a regional feature image containing several candidate regions; based on the regional feature image, use the segmentation mask branch network of the preset instance segmentation model to perform mask prediction to obtain the current instance segmentation image containing the segmentation masks of each candidate region.

[0126] In the specific implementation process, the coordinate estimation module 3 is specifically used for: performing coordinate calculation processing on each segmented area in the historical instance segmentation image of the target area at the previous moment to obtain the historical state corresponding to each segmented area, and the historical state includes the historical center of mass coordinates and the historical center of mass moving speed; performing state prediction based on the historical center of mass coordinates to obtain the estimated state at the current moment and the estimated state covariance at the current moment, and the estimated state includes the estimated center of mass coordinates and the estimated center of mass moving speed; performing coordinate calculation processing on each segmented area in the current instance segmentation image to obtain the current center of mass coordinates and the current center of mass moving speed corresponding to each segmented area; correcting the current center of mass coordinates and the current center of mass moving speed based on the historical center of mass coordinates, the estimated center of mass coordinates, the historical center of mass moving speed, and the estimated center of mass moving speed to obtain the center of mass coordinates and the motion change state of each center of mass of each segmented area in the current instance segmentation image.

[0127] In the specific implementation process, the evaluation module 4 is specifically used to: perform inverse perspective transformation processing on the current instance segmentation image based on a preset plane to obtain an inverse perspective image; based on the inverse perspective image, obtain the moving contact center coordinates and base center coordinates of each of the isolating switches in the inverse perspective image; perform calculation processing based on the moving contact center coordinates, the base center coordinates, and predetermined structural parameters corresponding to the same isolating switch to obtain the conductive arm angle corresponding to the same isolating switch; evaluate the state of the same isolating switch based on the conductive arm angle corresponding to the same isolating switch and the motion change state to obtain a state evaluation result.

[0128] In the specific implementation process, the evaluation module 4 is also used to: construct a group of plane projective transformation equations; determine the area to be projected based on the current instance segmentation image and determine the mapping area based on the preset plane; solve the group of plane projective transformation equations based on the preset boundary coordinates of the area to be projected and the preset projection boundary coordinates of the mapping area to obtain a mapping matrix; use the mapping matrix to map each pixel point in the current instance segmentation image to obtain the inverse perspective image.

[0129] In the specific implementation process, the evaluation module 4 is also used for: performing calculations based on the center coordinates of the moving contact and the center coordinates of the base corresponding to the same isolating switch to obtain the image distance value from the center pixel point of the moving contact to the center pixel point of the base; performing calculations based on the image distance using a preset camera imaging method to obtain the actual distance value from the center of the moving contact to the center of the base; performing calculations based on the actual distance value and a predetermined conductive arm length to obtain the conductive arm angle corresponding to the same isolating switch.

[0130] This application detects the image to be evaluated through a preset detection model and performs image segmentation on the framed image output by the preset detection model based on the preset instance segmentation model, and obtains the current instance segmentation image to realize the automatic and intelligent recognition of the state of the disconnector, which does not rely on on-site personnel and improves the efficiency and accuracy of state evaluation; based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image, the Kalman filter estimation method is used to estimate the coordinates, and the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector are obtained; based on the centroid coordinates, the predetermined structural parameters of each disconnector, and the motion change state of each disconnector, the state of each disconnector is evaluated to obtain the state evaluation result. Not only can the closing or opening state of the switch be identified, but also the opening and closing operation angle of the current disconnector can be identified, which provides strong technical support for the operation and maintenance management of the power system and significantly improves the safety and operation efficiency of the power grid.

[0131] Another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented:

[0132] Step 1: Use a preset detection model to detect the state assessment image of the target area collected in real time to obtain a frame-selected image, where the target area is the area where the disconnector is located;

[0133] Step 2: Using a preset instance segmentation model, perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image;

[0134] Step 3: Based on the previous historical instance segmentation image of the target area and the current instance segmentation image, a Kalman filter estimation method is used to perform coordinate estimation to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector;

[0135] Step 4: Evaluate the state of each isolating switch based on the center of mass coordinates, the predetermined structural parameters of each isolating switch, and the motion change state of each isolating switch to obtain a state evaluation result.

[0136] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0137] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0138] The specific implementation process of the above method steps can refer to the embodiments of the state assessment method of any disconnector mentioned above, and this embodiment will not be repeated here.

[0139] This application detects the image to be evaluated through a preset detection model and performs image segmentation on the framed image output by the preset detection model based on the preset instance segmentation model, and obtains the current instance segmentation image to realize the automatic and intelligent recognition of the state of the disconnector, which does not rely on on-site personnel and improves the efficiency and accuracy of state evaluation; based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image, the Kalman filter estimation method is used to estimate the coordinates, and the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector are obtained; based on the centroid coordinates, the predetermined structural parameters of each disconnector, and the motion change state of each disconnector, the state of each disconnector is evaluated to obtain the state evaluation result. Not only can the closing or opening state of the switch be identified, but also the opening and closing operation angle of the current disconnector can be identified, which provides strong technical support for the operation and maintenance management of the power system and significantly improves the safety and operation efficiency of the power grid.

[0140] Another embodiment of the present application provides an electronic device, which may be a server, and the electronic device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile and / or 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 network interface of the electronic device is used to communicate with an external client via a network connection. When the electronic device program is executed by the processor, the functions or steps on the server side of a method for evaluating the status of an isolating switch are implemented.

[0141] In one embodiment, an electronic device is provided, which may be a client. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external server via a network connection. When the electronic device program is executed by the processor, the functions or steps on the client side of a method for evaluating the state of an isolating switch are implemented.

[0142] Another embodiment of the present application provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the following method steps when executing the computer program in the memory:

[0143] Step 1: Use a preset detection model to detect the state assessment image of the target area collected in real time to obtain a frame-selected image, where the target area is the area where the disconnector is located;

[0144] Step 2: Using a preset instance segmentation model, perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image;

[0145] Step 3: Based on the previous historical instance segmentation image of the target area and the current instance segmentation image, a Kalman filter estimation method is used to perform coordinate estimation to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector;

[0146] Step 4: Evaluate the state of each isolating switch based on the center of mass coordinates, the predetermined structural parameters of each isolating switch, and the motion change state of each isolating switch to obtain a state evaluation result.

[0147] The specific implementation process of the above method steps can refer to the embodiments of the state assessment method of any disconnector mentioned above, and this embodiment will not be repeated here.

[0148] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A method for evaluating the state of an isolating switch, characterized in that: include: Using a preset detection model, the state assessment image of the target area collected in real time is detected to obtain a frame-selected image, wherein the target area is the area where the disconnector is located; Using a preset instance segmentation model, perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image; Based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image, a Kalman filter estimation method is used to perform coordinate estimation, and obtain the centroid coordinates of each segmentation area in the current instance segmentation image and the motion change state of each disconnector; The state of each isolating switch is evaluated based on the coordinates of each centroid, the predetermined structural parameters of each isolating switch, and the motion change state of each isolating switch to obtain a state evaluation result.

2. The method according to claim 1, characterized in that The method uses a preset detection model to detect the state evaluation image of the target area collected in real time to obtain a frame selection image, which specifically includes: Based on the state recognition image, a first target backbone network of the preset detection model is used to perform feature extraction to obtain a first feature image; Based on the first feature image, a first target classification network of the preset detection model is used to perform classification prediction to obtain a category prediction score of each disconnector in the first feature image, so as to obtain a current state category corresponding to each disconnector; Based on the first feature image, the first target regression network of the preset detection model is used to perform boundary prediction to obtain the boundary boxes of each isolating switch in the first feature image, each of which carries a predicted coordinate value and a border mark to obtain the framed image.

3. The method according to claim 1, characterized in that The adopting a preset instance segmentation model to perform image segmentation on the framed image to obtain a current instance segmentation image corresponding to the framed image specifically includes: Based on the framed image, a second target backbone network of the preset instance segmentation model is used to perform feature extraction to obtain a second feature image; Based on the second feature image, a target feature pyramid network of the preset instance segmentation model is used to perform feature extraction to obtain a target feature image; Based on the target feature map, a target region proposal network of the preset instance segmentation model is used to perform feature extraction to obtain a region feature image containing a plurality of candidate regions; Based on the region feature image, a segmentation mask branch network of the preset instance segmentation model is used to perform mask prediction to obtain the current instance segmentation image including the segmentation masks of each candidate region.

4. The method according to claim 1, characterized in that The coordinate estimation is performed based on the historical instance segmentation image of the target area at the previous moment and the current instance segmentation image using the Kalman filter estimation method to obtain the centroid coordinates of each segmentation area in the current instance segmentation image and the motion change state of each disconnector, specifically including: Based on the historical instance segmentation image of the target area at the previous moment, coordinate calculation processing is performed on each segmented area to obtain the historical state corresponding to each segmented area, wherein the historical state includes the historical centroid coordinates and the historical centroid moving speed; Performing state prediction based on the historical centroid coordinates to obtain an estimated state at a current moment and an estimated state covariance at a current moment, wherein the estimated state includes an estimated centroid coordinate and an estimated centroid moving speed; Performing coordinate calculation processing based on each segmented area in the current instance segmented image to obtain current centroid coordinates and current centroid moving speed corresponding to each segmented area; The current center of mass coordinates and the current center of mass moving speed are corrected based on the historical center of mass coordinates, the estimated center of mass coordinates, the historical center of mass moving speed, and the estimated center of mass moving speed to obtain the center of mass coordinates and the motion change state of each center of mass of each segmented area in the current instance segmented image.

5. The method according to claim 1, characterized in that The step of evaluating the state of each isolating switch based on the coordinates of the centroid, the predetermined structural parameters of each isolating switch and the motion change state of each isolating switch to obtain a state evaluation result specifically includes: Performing inverse perspective transformation processing on the current instance segmented image based on a preset plane to obtain an inverse perspective image; Based on the reverse perspective image, obtaining the moving contact center coordinates and the base center coordinates of each of the disconnectors in the reverse perspective image; Calculation and processing are performed based on the center coordinates of the moving contact, the center coordinates of the base, and predetermined structural parameters corresponding to the same isolating switch to obtain the conductive arm angle corresponding to the same isolating switch; The state of the same isolating switch is evaluated based on the conductive arm angle corresponding to the same isolating switch and the motion change state to obtain a state evaluation result.

6. The method according to claim 5, characterized in that The performing inverse perspective transformation processing on the current instance segmented image based on a preset plane to obtain an inverse perspective image specifically includes: Construct the system of equations for plane projective transformation; Determine a to-be-projected area based on the current instance segmented image and determine a mapping area based on the preset plane; Solving the plane projection transformation equations based on the preset boundary coordinates of the area to be projected and the predetermined projection boundary coordinates of the mapping area to obtain a mapping matrix; The inverse perspective image is obtained by mapping each pixel in the current instance segmented image using the mapping matrix.

7. The method according to claim 5, characterized in that The calculation and processing based on the moving contact center coordinates, the base center coordinates, and the predetermined structural parameters corresponding to the same isolating switch to obtain the conductive arm angle corresponding to the same isolating switch specifically includes: Calculation is performed based on the center coordinates of the moving contact and the center coordinates of the base corresponding to the same isolating switch to obtain an image distance value from the center pixel point of the moving contact to the center pixel point of the base; Based on the image distance value, a preset camera imaging method is used to perform calculation processing to obtain an actual distance value from the center of the moving contact to the center of the base; The conductive arm angle corresponding to the same disconnector is obtained by performing calculation based on the actual distance value and the predetermined conductive arm length.

8. A state assessment device for an isolating switch, characterized in that: include: A detection module, used to detect the state assessment image of the target area collected in real time by using a preset detection model to obtain a frame-selected image, wherein the target area is the area where the disconnector is located; An image segmentation module is used to perform image segmentation on the framed image using a preset instance segmentation model to obtain a current instance segmentation image corresponding to the framed image; A coordinate estimation module, used to perform coordinate estimation based on the previous historical instance segmentation image of the target area and the current instance segmentation image using a Kalman filter estimation method to obtain the centroid coordinates of each segmented area in the current instance segmentation image and the motion change state of each disconnector; An evaluation module is used to evaluate the state of each isolating switch based on the center of mass coordinates, the predetermined structural parameters of each isolating switch and the motion change state of each isolating switch to obtain a state evaluation result.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the disconnector status assessment method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The method comprises at least a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program in the memory, the method implements the steps of the disconnector status assessment method according to any one of claims 1 to 7.

Images