Secondary equipment state displacement detection method and system

Abstract

The invention discloses a secondary equipment state displacement detection method and system, and relates to the technical field of secondary equipment state detection, and the method comprises the steps: obtaining a reference equipment image and a to-be-checked equipment image of to-be-detected secondary equipment, and carrying out the working condition recognition of the reference equipment image and the to-be-checked equipment image according to the equipment type of the to-be-detected secondary equipment, and obtaining reference equipment state information and to-be-checked equipment state information, and determining a displacement detection result of the to-be-detected secondary equipment according to the reference equipment state information and the to-be-checked equipment state information. The technical problems that in the prior art, state displacement detection is mainly carried out on secondary equipment before and after work through inspection personnel according to a secondary measure list, however, during manual detection, due to visual fatigue, memory confusion and other reasons, the situation of missing detection of the secondary equipment is prone to occurring, and the reliability of power grid operation is reduced are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of secondary equipment state detection, and in particular to a secondary equipment state change detection method and system. Background Art

[0002] Secondary wiring is involved in the pre-test, regular inspection, maintenance, and troubleshooting of substations. Usually, after a power outage, the operation and maintenance personnel will execute according to the secondary measures list. However, in actual work, due to the excessive number of items in the secondary measures list, some disassembled terminals are not listed in the measures list, and the insufficient skills of the operation and maintenance personnel, it is easy to cause the secondary equipment to shift after work, resulting in the secondary equipment refusing to operate or malfunctioning, which has a great impact on the safe operation of the power grid. Therefore, it is very important to detect the state change of the secondary equipment.

[0003] At present, the existing technology mainly relies on inspection personnel to perform state change detection on secondary equipment before and after work based on secondary measure sheets. However, due to visual fatigue, memory confusion and other reasons, manual inspection is prone to missed inspection of secondary equipment, which reduces the reliability of power grid operation. Summary of the invention

[0004] The present invention provides a secondary equipment state change detection method and system, which solves the technical problem that the prior art mainly relies on inspection personnel to perform state change detection on secondary equipment before and after work based on secondary measure sheets, but due to visual fatigue, memory confusion and other reasons during manual detection, secondary equipment is easily missed, thereby reducing the reliability of power grid operation.

[0005] A first aspect of the present invention provides a method for detecting a state change of a secondary device, characterized by comprising:

[0006] Obtain the reference device image and the image of the device to be verified of the secondary device to be inspected;

[0007] According to the device type of the secondary device to be detected, the working condition of the reference device image and the device image to be checked are respectively identified to obtain the reference device status information and the device status information to be checked;

[0008] The displacement detection result of the secondary device to be detected is determined according to the reference device status information and the device status information to be checked.

[0009] Optionally, the step of performing working condition identification on the reference device image and the device image to be checked respectively according to the device type of the secondary device to be detected to obtain reference device status information and device status information to be checked includes:

[0010] When the device type of the secondary device to be detected is a terminal strip or a connecting piece, contour features are extracted from the reference device image and the image of the device to be checked respectively to obtain a plurality of target grid blocks, a reference edge image and an edge image to be checked;

[0011] Using target grid blocks associated with the reference edge image and the edge image to be checked respectively, the reference edge image and the edge image to be checked are subjected to gridding image processing to obtain a reference grid image and a grid image to be checked;

[0012] When the device type is a terminal wiring, the reference grid image and the grid image to be checked are respectively checked for wiring to obtain reference device status information and check device status information;

[0013] When the device type is a connection piece, connection channel detection is performed on the reference grid image and the grid image to be checked respectively to obtain reference device status information and check device status information.

[0014] Optionally, the step of respectively extracting contour features from the reference device image and the device image to be checked to obtain a plurality of target grid blocks, reference edge images and edge images to be checked comprises:

[0015] Using edge detection algorithms to perform edge detection on the reference device image and the device image to be checked, respectively, to obtain a reference edge image and a to-be-checked edge image;

[0016] Performing contour detection on the reference edge image and the edge image to be checked respectively to obtain reference size features and size features to be checked;

[0017] Respectively comparing the reference size feature and the size feature to be checked with each grid block in a preset grid block database one by one;

[0018] When the grid block matches the reference size feature or the to-be-checked size feature, the grid block is determined as a target grid block.

[0019] Optionally, the step of performing working condition identification on the reference device image and the device image to be checked respectively according to the device type of the secondary device to be detected to obtain reference device status information and device status information to be checked includes:

[0020] When the device type of the secondary device to be detected is a pressure plate, a circuit breaker or a handle, the reference device image and the image of the device to be checked are subjected to gridding image processing using a preset characteristic moment to obtain a reference grid image and a grid image to be checked;

[0021] When the device type is a pressure plate, the reference grid image and the to-be-checked grid image are respectively input into a pre-trained pressure plate recognition model to obtain reference device status information and to-be-checked device status information;

[0022] When the device type is open, a preset contour function is used to perform contour detection on the reference grid image and the grid image to be checked, respectively, to obtain a reference region of interest and a region of interest to be checked;

[0023] Performing status evaluation on the reference ROI and the pending ROI based on a preset color interval to obtain reference device status information and pending ROI status information;

[0024] When the device type is a handle, the reference grid image and the to-be-checked grid image are respectively input into a preset text recognition model to obtain reference device status information and to-be-checked device status information.

[0025] Optionally, the step of performing working condition identification on the reference device image and the device image to be checked respectively according to the device type of the secondary device to be detected to obtain reference device status information and device status information to be checked includes:

[0026] When the device type of the secondary device to be detected is an indicator light, the reference device image and the device image to be checked are respectively input into a preset text recognition model to obtain reference text coordinate information and text coordinate information to be checked;

[0027] Performing gridding image processing on the reference device image according to the reference text coordinate information to obtain a reference grid image;

[0028] Performing gridding image processing on the device image to be checked according to the coordinate information of the text to be checked, to obtain a grid image to be checked;

[0029] The reference grid image and the pending check grid image are respectively input into a pre-trained indicator light recognition model to obtain reference device status information and pending check device status information.

[0030] Optionally, the step of determining the displacement detection result of the secondary device to be detected according to the reference device status information and the device status information to be checked includes:

[0031] Determine whether the reference device status information is the same as the device status information to be verified;

[0032] If the reference equipment status information is the same as the equipment status information to be checked, the displacement detection result of the secondary equipment to be checked is determined as no displacement of the equipment;

[0033] If the reference equipment status information is different from the equipment status information to be checked, the displacement detection result of the secondary equipment to be checked is determined as equipment displacement.

[0034] Optionally, the pressure plate identification model includes a SVM model.

[0035] A second aspect of the present invention provides a secondary equipment state change detection system, comprising:

[0036] An acquisition module, used to obtain a reference device image and a device image to be verified of a secondary device to be inspected;

[0037] An identification module, used to identify the working conditions of the reference device image and the device image to be checked according to the device type of the secondary device to be checked, and obtain the reference device status information and the device status information to be checked;

[0038] The comparison module is used to determine the displacement detection result of the secondary device to be detected based on the reference device status information and the device status information to be checked.

[0039] A third aspect of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the secondary device state change detection method as described in any one of the above items.

[0040] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the secondary device state change detection method as described in any one of the above items.

[0041] It can be seen from the above technical solutions that the present invention has the following advantages:

[0042] The present invention performs working condition identification on the reference device image and the device image to be checked according to the device type of the secondary device to be detected, obtains the reference device status information and the device status information to be checked, and obtains the displacement detection result of the secondary device to be detected by comparing the reference device status information and the device status information to be checked. Thus, accurate identification of the displacement secondary device is achieved, and secondary missed detection caused by human factors is eliminated. The prior art overcomes the technical problem that the inspection personnel mainly perform state displacement detection on the secondary equipment before and after work according to the secondary measure sheet, but the secondary equipment is easily missed due to visual fatigue, memory confusion and other reasons during manual detection, which reduces the reliability of power grid operation. Compared with the traditional state displacement detection method, the present invention performs working condition identification on the reference device image and the device image to be checked based on the device type of the secondary device to be detected, obtains the reference device status information and the device status information to be checked, and realizes state displacement detection of multiple types of secondary equipment. And the efficiency of secondary equipment state displacement detection is improved, and the reliability of power grid operation is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0044] Figure 1 A flowchart of a method for detecting a state change of a secondary device provided in Embodiment 1 of the present invention;

[0045] Figure 2 A flowchart of a method for detecting a state change of a secondary device provided in Embodiment 2 of the present invention;

[0046] Figure 3 A structural diagram of a text recognition model provided in Embodiment 2 of the present invention;

[0047] Figure 4 A structural block diagram of a secondary equipment state change detection system provided in Embodiment 3 of the present invention;

[0048] Figure 5 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0049] The embodiments of the present invention provide a method and system for detecting state changes of secondary equipment, which are used to solve the technical problem that the prior art mainly relies on inspection personnel to perform state change detection on secondary equipment before and after work based on secondary measure sheets, but due to visual fatigue, memory confusion and other reasons during manual detection, secondary equipment is easily missed, thereby reducing the reliability of power grid operation.

[0050] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1 , Figure 1 This is a flowchart of a method for detecting a state change of a secondary device provided in Embodiment 1 of the present invention.

[0052] The present invention provides a method for detecting a state change of a secondary device, comprising:

[0053] Step 101, obtaining a reference device image and a device image to be verified of a secondary device to be detected;

[0054] The reference equipment image refers to the equipment image of the secondary equipment to be inspected before the measure order is implemented.

[0055] The equipment image to be reviewed refers to the equipment image of the secondary equipment to be inspected after the measure order is completed.

[0056] In the embodiment of the present invention, the device images of the secondary device to be inspected before and after the measure sheet is executed are obtained.

[0057] Step 102: According to the device type of the secondary device to be detected, the working condition of the reference device image and the image of the device to be checked are respectively identified to obtain the reference device status information and the device status information to be checked;

[0058] In the embodiment of the present invention, 1. When the device type of the secondary device to be detected is the first device type (the first device type includes terminal strips and connecting pieces), the edge detection algorithm is used to extract the contour features of the reference device image and the image of the device to be checked, respectively, to obtain the reference edge image, the edge image to be checked, and multiple target grid blocks. The reference edge image and the edge image to be checked are respectively processed by gridding using the target grid blocks associated with the reference edge image and the edge image to be checked, to obtain the reference grid image and the grid image to be checked. When the device type is the terminal strip, the wiring detection is performed on the reference grid image and the grid image to be checked, respectively, to obtain the reference device status information and the device status information to be checked. When the device type is the connecting piece, the connection channel detection is performed on the reference grid image and the grid image to be checked, respectively, to obtain the reference device status information and the device status information to be checked. 2. When the device type of the secondary device to be detected is the second device type (the second device type includes a pressure plate, an air switch, and a handle), the preset feature moment is used to perform gridding image processing on the reference device image and the image of the device to be checked, respectively, to obtain the reference grid image and the grid image to be checked. When the device type is a pressure plate, the reference grid image and the grid image to be checked are respectively input into the pre-trained pressure plate recognition model to obtain the reference device status information and the device status information to be checked. When the device type is an open circuit, the preset contour function is used to perform contour detection on the reference grid image and the grid image to be checked to obtain the reference region of interest and the region of interest to be checked. The status of the reference region of interest and the region of interest to be checked is evaluated based on the preset color range to obtain the reference device status information and the device status information to be checked. When the device type is a handle, the reference grid image and the grid image to be checked are respectively input into the preset text recognition model to obtain the reference device status information and the device status information to be checked. 3. When the device type of the secondary device to be detected is an indicator light, the reference device image and the device image to be checked are respectively input into the preset text recognition model to obtain multiple text coordinate information. The reference device image and the device image to be checked are respectively subjected to grid image processing according to the text coordinate information associated with the reference device image and the device image to be checked to obtain the reference grid image and the grid image to be checked.

[0059] Step 103: Determine the displacement detection result of the secondary equipment to be detected according to the reference equipment status information and the equipment status information to be checked.

[0060] In the embodiment of the present invention, it is determined whether the reference device status information is consistent with the device status information to be checked. If the reference device status information is consistent with the device status information to be checked, a displacement detection result of the secondary device without displacement is generated. If the reference device status information is inconsistent with the device status information to be checked, a displacement detection result of the secondary device is generated, and the secondary device with displacement is marked and sent to the background server.

[0061] In an embodiment of the present invention, the present invention performs working condition identification on the reference device image and the device image to be checked according to the device type of the secondary device to be checked, obtains the reference device status information and the device status information to be checked, and obtains the displacement detection result of the secondary device to be checked by comparing the reference device status information and the device status information to be checked. Thus, accurate identification of the displacement secondary device is achieved, and secondary missed detection caused by human factors is eliminated. The technical problem that the prior art mainly relies on the inspection personnel to perform state displacement detection on the secondary equipment before and after work based on the secondary measure sheet, but the secondary equipment is easily missed due to visual fatigue, memory confusion and other reasons during manual detection, which reduces the reliability of power grid operation is overcome. Compared with the traditional state displacement detection method, the present invention performs working condition identification on the reference device image and the device image to be checked based on the device type of the secondary device to be checked, obtains the reference device status information and the device status information to be checked, and realizes state displacement detection of multiple types of secondary equipment. And the efficiency of secondary equipment state displacement detection is improved, and the reliability of power grid operation is improved.

[0062] See also Figure 2 , Figure 2 This is a flow chart of the steps of a secondary device state change detection method provided in Embodiment 2 of the present invention.

[0063] The present invention provides a method for detecting a state change of a secondary device, comprising:

[0064] Step 201, obtaining a reference device image and a device image to be verified of a secondary device to be detected;

[0065] In the embodiment of the present invention, the device images of the secondary device to be inspected before and after the measure sheet is working are respectively obtained by using a photographing and collecting device.

[0066] Step 202: According to the device type of the secondary device to be detected, the working condition of the reference device image and the image of the device to be checked are respectively identified to obtain the reference device status information and the device status information to be checked;

[0067] Further, step 202 includes the following sub-steps:

[0068] S11, when the device type of the secondary device to be detected is a terminal strip or a connector, contour features are extracted from the reference device image and the image of the device to be checked, respectively, to obtain a plurality of target grid blocks, a reference edge image, and an edge image to be checked;

[0069] Furthermore, S11 includes the following sub-steps:

[0070] A1. Use edge detection algorithms to perform edge detection on the reference device image and the image of the device to be checked, respectively, to obtain a reference edge image and a to-be-checked edge image;

[0071] In the embodiment of the present invention, the Canny edge detection algorithm is used to perform edge detection on the reference device image and the device image to be checked, respectively, to obtain the reference edge image and the edge image to be checked.

[0072] It should be noted that Canny edge detection: , minThreshold,maxThreshold)], where ( ) is an image file, ( ) is the edge image.

[0073] A2. Perform contour detection on the reference edge image and the edge image to be checked respectively to obtain reference size features and size features to be checked;

[0074] In the embodiment of the present invention, the contours of the reference edge image and the edge image to be checked are respectively detected by using the contour feature extraction algorithm in the OpenCV library to obtain the reference size feature and the size feature to be checked.

[0075] It should be noted that the contour feature extraction algorithm is specifically: calculate the area (A) and perimeter of the contour

[0076] Identify the rectangle ratio: Get the bounding rectangle of the outline and calculate the aspect ratio: .

[0077] A3, respectively comparing the reference size feature and the size feature to be checked with each grid block in the preset grid block database;

[0078] A4. When the grid block matches the reference size feature or the size feature to be nucleated, the grid block is determined as the target grid block.

[0079] In the embodiment of the present invention, the reference size feature and the size feature to be checked are respectively input into a preset grid block database, and the target grid blocks corresponding to the reference size feature and the size feature to be checked are matched.

[0080] S12, respectively using the target grid blocks associated with the reference edge image and the edge image to be checked to perform gridding image processing on the reference edge image and the edge image to be checked, to obtain a reference grid image and a grid image to be checked;

[0081] In the embodiment of the present invention, the reference edge image and the to-be-correlated edge image are subjected to gridding image processing through target grid blocks associated with the reference edge image and the to-be-correlated edge image to obtain the reference grid image and the to-be-correlated grid image.

[0082] It should be noted that the process of performing grid image processing through target grid blocks is specifically as follows: grouping the target grid blocks according to a specified number (such as 10 or 20 blocks in a group) to form a grid, and calculating the perspective transformation matrix of the target grid block coordinates to the standardized coordinate system, and using the perspective transformation matrix to convert the target grid blocks in the grid to the standardized coordinate system to obtain the corresponding grid image.

[0083] S13, when the device type is a terminal wiring, wiring detection is performed on the reference grid image and the grid image to be checked respectively to obtain the reference device status information and the device status information to be checked;

[0084] In an embodiment of the present invention, when the device type is a terminal strip, the reference grid image and the grid image to be cored are respectively subjected to image conversion processing to obtain a reference conversion image and a conversion image to be cored. The HSV values ​​of each grid area of ​​the reference conversion image and the conversion image to be cored are respectively extracted, and it is determined whether each HSV value is in a preset color interval. If the HSV value is in the preset color interval, the grid interval associated with the HSV value is marked as connected. If the HSV value is not in the preset color interval, the grid interval associated with the HSV value is marked as not connected. The mark of each grid interval in the reference conversion image is determined as the reference device status information. The mark of each grid interval in the conversion image to be cored is determined as the device status information to be cored.

[0085] It should be noted that the specific process of the image conversion processing is: converting the reference grid image and the grid image to be core from the BGR (blue-green-red) format to the HSV (hue, saturation, value) format.

[0086] It should be noted that the color range values ​​are as follows: Red range (for example, refer to HSV parameters): [lower_red = np.array([0, 50, 50]), upper_red = np.array([10, 255, 255])]. Yellow range: [lower_yellow = np.array([20, 100, 100]), upper_yellow = np.array([30, 255,255])]. Blue range: [lower_blue = np.array([110, 50, 50]), upper_blue = np.array([130, 255, 255])].

[0087] S14. When the device type is a connection piece, connection channel detection is performed on the reference grid image and the grid image to be checked respectively to obtain reference device status information and check device status information.

[0088] In an embodiment of the present invention, when the device type is a connecting piece, a connection channel function (the connection channel function is the cv2.connectedComponentsWithStats function of OpenCV) is used to perform connected domain detection on the reference grid image and the grid image to be cored, respectively, to obtain the connected areas of each grid area in the reference grid image and the connected areas of each grid area in the grid image to be cored. The Euclidean distance of the connected areas in each grid area is calculated respectively, and it is determined whether each Euclidean distance is less than a preset distance threshold. If the Euclidean distance is less than the preset distance threshold, the grid area associated with the Euclidean distance is marked as connected. If the Euclidean distance is greater than or equal to the preset distance threshold, the grid area associated with the Euclidean distance is marked as disconnected. The mark of each grid interval in the reference conversion image is determined as the reference device status information. The mark of each grid interval in the conversion image to be cored is determined as the device status information to be cored.

[0089] It should be noted that the specific expression of Euclidean distance is:

[0090]

[0091] Where distance is the Euclidean distance, ((x1, y1)) and ((x2, y2)) are the centroid coordinates of the connected regions at both ends.

[0092] S15, when the device type of the secondary device to be detected is a pressure plate, a circuit breaker or a handle, a preset characteristic moment is used to perform grid image processing on the reference device image and the image of the device to be checked, to obtain a reference grid image and a grid image to be checked;

[0093] In an embodiment of the present invention, when the device type of the secondary device to be detected is a pressure plate, a circuit breaker or a handle, a preset characteristic moment (Hu moment or Zernike moment) is used to perform grid image processing on the reference device image and the image of the device to be checked to obtain a reference grid image and a grid image to be checked.

[0094] It should be noted that the Hu moment is an invariant feature based on image moments, which is invariant to translation, rotation and scale changes and is suitable for shape recognition. The Zernike moment is an orthogonal moment with rotation invariance, which can effectively describe the shape characteristics of the image.

[0095] S16, when the device type is a pressure plate, the reference grid image and the grid image to be verified are respectively input into a pre-trained pressure plate recognition model to obtain reference device status information and verification device status information;

[0096] In the embodiment of the present invention, when the device type is a pressure plate, the reference grid image and the grid image to be checked are respectively input into a pre-trained SVM model to obtain reference device state information and check device state information.

[0097] It should be noted that the pressure plate recognition model includes a SVM model.

[0098] It should be noted that support vector machine (SVM) is used for binary classification problems to classify the platen status into "in" or "out". SVM (Support Vector Machine), the core idea of ​​SVM is to separate data of different categories by mapping the training data into a high-dimensional space and finding an optimal hyperplane to achieve classification. SVM is divided into linear SVM and nonlinear SVM. Linear SVM: Linear SVM is an algorithm for finding the optimal hyperplane in the feature space. Its decision function can be expressed as:

[0099] f(x)=sign(w·x+b)

[0100] Among them, w is the weight vector, x is the input feature vector, b is the bias scalar, and sign is the sign function, which means that one side of the classification surface is the positive class (+1) and the other side is the negative class (-1). w·x represents the vector inner product, which can be regarded as the projection of the feature vector in the direction of the weight vector.

[0101] Nonlinear SVM: When the data is not linearly separable, the kernel technique can be used to map the data into a high-dimensional space, and then find the optimal hyperplane in the high-dimensional space. The decision function form of the nonlinear SVM is the same as that of the linear SVM, except that when calculating the vector inner product, the kernel function K(x1,x2) is used instead of x1·x2, that is:

[0102] f(x)=sign(Σ(αi*yi*K(xi,x)+b))

[0103] Among them, αi is the Lagrange multiplier, yi is the label of the training sample, xi is the feature vector of the training sample, b is the bias scalar, and K(x1,x2) is the kernel function, which can map the input feature vector to a high-dimensional space.

[0104] S17, when the device type is open, a preset contour function is used to perform contour detection on the reference grid image and the grid image to be checked, respectively, to obtain a reference region of interest and a region of interest to be checked;

[0105] In the embodiment of the present invention, when the device type is open, a preset contour function (findContours function in OpenCV) is used to perform contour detection on the reference grid image and the grid image to be checked, respectively, to obtain the reference region of interest and the region of interest to be checked.

[0106] S18, performing status evaluation on the reference ROI and the pending ROI based on a preset color range to obtain reference device status information and pending ROI status information;

[0107] In an embodiment of the present invention, the pixel average colors of the reference region of interest and the region of interest to be checked are calculated respectively to obtain the reference average color and the average color to be checked. It is determined whether the reference average color and the average color to be checked are in a preset color area. If the reference average color is in the preset color area, the reference device status information is determined to be connected. If the reference average color is not in the preset color area, the reference device status information is determined to be disconnected. If the average color to be checked is in the preset color area, the device status information to be checked is determined to be connected. If the average color to be checked is not in the preset color area, the device status information to be checked is determined to be disconnected.

[0108] It should be noted that before the status evaluation is performed on the reference ROI and the ROI to be verified, the shapes of the spaces in the regions are enhanced by performing erosion and dilation operations on the reference ROI and the ROI to be verified.

[0109] S19, when the device type is a handle, the reference grid image and the grid image to be checked are respectively input into a preset text recognition model to obtain reference device status information and device status information to be checked.

[0110] In the embodiment of the present invention, when the device type is a handle, the reference grid image and the to-be-checked grid image are respectively used as inputs of a preset text recognition model to obtain reference device state information and to-be-checked device state information.

[0111] It should be noted that, see Figure 3 As shown in the figure, the text recognition model includes a text detection network (DBNet is used for text information detection in the text detection network), a text direction correction network, and a text recognition network. The text detection network first detects the text line area of ​​the image, obtains the text line position information, and obtains the text line sub-image through image transformation. The text direction correction network determines the direction of the text header through the image classification network, and performs necessary image rotation to ensure that the text information is facing upward, obtains the corrected image, and inputs the corrected image into the text recognition network to obtain the corresponding reference device status information and the device status information to be verified.

[0112] S110, when the device type of the secondary device to be detected is an indicator light, the reference device image and the image of the device to be verified are respectively input into a preset text recognition model to obtain reference text coordinate information and text coordinate information to be verified;

[0113] In the embodiment of the present invention, when the device type of the secondary device to be detected is an indicator light, the reference grid image and the grid image to be verified are respectively used as inputs of a preset text recognition model to obtain reference text coordinate information and text coordinate information to be verified.

[0114] S111, performing gridding image processing on the reference device image according to the reference text coordinate information to obtain a reference grid image;

[0115] S112, performing gridding image processing on the image of the device to be checked according to the coordinate information of the text to be checked, to obtain a grid image to be checked;

[0116] In the embodiment of the present invention, the reference device image is subjected to gridding image processing based on the reference text coordinate information to obtain the reference grid image, and the device image to be checked is subjected to gridding image processing based on the to-be-checked text coordinate information to obtain the to-be-checked grid image.

[0117] S113, respectively inputting the reference grid image and the grid image to be checked into a pre-trained indicator light recognition model to obtain reference device status information and device status information to be checked.

[0118] In an embodiment of the present invention, the reference grid image and the to-be-checked grid image are respectively input into a pre-trained indicator light recognition model (the indicator light recognition model includes a CNN neural network and a YOLO neural network) to obtain reference device status information and to-be-checked device status information.

[0119] In another embodiment, the average brightness of each grid area in the reference grid image and each grid area in the to-be-core grid image are calculated respectively to obtain a plurality of reference average brightnesses and a plurality of to-be-core average brightnesses. It is determined whether each reference average brightness and each to-be-core average brightness are greater than a preset brightness threshold. When the reference average brightness is greater than the brightness threshold, the grid area associated with the reference average brightness is marked as lit. When the to-be-core average brightness is greater than the brightness threshold, the grid area associated with the to-be-core average brightness is marked as lit. The marking of each grid interval in the reference conversion image is determined as reference device status information. The marking of each grid interval in the to-be-core conversion image is determined as to-be-core device status information.

[0120] Step 203, determining whether the reference device status information is the same as the device status information to be verified;

[0121] In the embodiment of the present invention, it is determined whether the reference device status information is consistent with the device status information to be checked.

[0122] Step 204: If the reference equipment status information is the same as the equipment status information to be checked, the displacement detection result of the secondary equipment to be checked is determined as no displacement of the equipment;

[0123] In the embodiment of the present invention, if the reference device status information is consistent with the device status information to be checked, the displacement detection result of the secondary device to be checked is determined as no displacement of the device.

[0124] Step 205: If the reference equipment status information is different from the equipment status information to be checked, the displacement detection result of the secondary equipment to be checked is determined as equipment displacement.

[0125] In an embodiment of the present invention, if the reference device status information is inconsistent with the device status information to be checked, the displacement detection result of the secondary device to be checked is determined as a displacement of the device, and an alarm signal is generated and the information of the secondary device to be checked is sent to the background terminal for reminder.

[0126] In another embodiment, before executing the secondary measure list, the reference device images of multiple secondary devices to be detected in the power grid equipment are obtained, and the analysis is performed by the method of step 201-step 202 to obtain multiple reference device status information, and the reference database of the protection screen is constructed using all the reference device status information. After executing the secondary measure list, the reference device images to be checked of multiple secondary devices to be detected in the power grid equipment are obtained, and the analysis is performed by the method of step 201-step 202 to obtain multiple device status information to be checked. The reference device information corresponding to the device status information to be checked is selected from the reference database, and the analysis is performed by the method of step 203-step 205 to obtain multiple displacement detection results.

[0127] In an embodiment of the present invention, the present invention performs working condition identification on the reference device image and the device image to be checked according to the device type of the secondary device to be checked, obtains the reference device status information and the device status information to be checked, and obtains the displacement detection result of the secondary device to be checked by comparing the reference device status information and the device status information to be checked. Thus, accurate identification of the displacement secondary device is achieved, and secondary missed detection caused by human factors is eliminated. The technical problem that the prior art mainly relies on the inspection personnel to perform state displacement detection on the secondary equipment before and after work based on the secondary measure sheet, but the secondary equipment is easily missed due to visual fatigue, memory confusion and other reasons during manual detection, which reduces the reliability of power grid operation is overcome. Compared with the traditional state displacement detection method, the present invention performs working condition identification on the reference device image and the device image to be checked based on the device type of the secondary device to be checked, obtains the reference device status information and the device status information to be checked, and realizes state displacement detection of multiple types of secondary equipment. And the efficiency of secondary equipment state displacement detection is improved, and the reliability of power grid operation is improved.

[0128] See also Figure 4 , Figure 4 This is a structural block diagram of a secondary equipment state change detection system provided in Embodiment 3 of the present invention.

[0129] The present invention provides a secondary equipment state change detection system, comprising:

[0130] The acquisition module 301 is used to obtain the reference device image and the device image to be verified of the secondary device to be detected;

[0131] Identification module 302, used to identify the working conditions of the reference device image and the device image to be checked according to the device type of the secondary device to be checked, and obtain the reference device status information and the device status information to be checked;

[0132] The comparison module 303 is used to determine the displacement detection result of the secondary equipment to be detected according to the reference equipment status information and the equipment status information to be checked.

[0133] Furthermore, the identification module 302 includes:

[0134] The extraction submodule is used to extract contour features of the reference device image and the image of the device to be checked respectively when the device type of the secondary device to be checked is a terminal strip or a connector, so as to obtain multiple target grid blocks, reference edge images and edge images to be checked;

[0135] The first gridding submodule is used to perform gridding image processing on the reference edge image and the edge image to be checked by using target grid blocks associated with the reference edge image and the edge image to be checked, respectively, to obtain a reference grid image and a grid image to be checked;

[0136] The first detection submodule is used to perform wiring detection on the reference grid image and the grid image to be checked respectively when the device type is a terminal strip, so as to obtain the reference device status information and the device status information to be checked;

[0137] The second detection submodule is used to perform connection channel detection on the reference grid image and the grid image to be checked respectively when the device type is a connection piece, so as to obtain the reference device status information and the device status information to be checked.

[0138] Furthermore, the submodules are extracted, including:

[0139] An edge detection unit is used to perform edge detection on the reference device image and the device image to be checked by using an edge detection algorithm to obtain a reference edge image and a device image to be checked;

[0140] A contour detection unit is used to perform contour detection on the reference edge image and the edge image to be checked, respectively, to obtain a reference size feature and a size feature to be checked;

[0141] A matching unit, used for comparing the reference size feature and the size feature to be checked with each grid block in the preset grid block database one by one;

[0142] When the grid block matches the reference size feature or the to-be-core size feature, the grid block is determined as a target grid block.

[0143] Furthermore, the identification module 302 includes:

[0144] The second gridding submodule is used to perform gridding image processing on the reference device image and the device image to be checked by using a preset characteristic moment when the device type of the secondary device to be checked is a pressure plate, a circuit breaker or a handle, so as to obtain a reference grid image and a grid image to be checked;

[0145] The third detection submodule is used for inputting the reference grid image and the grid image to be checked into a pre-trained platen recognition model to obtain the reference device status information and the device status information to be checked when the device type is a platen;

[0146] The fourth detection submodule is used for, when the device type is open, using a preset contour function to perform contour detection on the reference grid image and the grid image to be checked, respectively, to obtain the reference region of interest and the region of interest to be checked;

[0147] Based on the preset color range, the status of the reference region of interest and the region of interest to be verified are evaluated to obtain the reference device status information and the device status information to be verified;

[0148] The fifth detection submodule is used to input the reference grid image and the grid image to be checked into a preset text recognition model respectively to obtain the reference device status information and the device status information to be checked when the device type is a handle.

[0149] Furthermore, the identification module 302 includes:

[0150] The third gridding submodule is used for inputting the reference device image and the image of the device to be checked into a preset text recognition model respectively to obtain the reference text coordinate information and the coordinate information of the text to be checked when the device type of the secondary device to be checked is an indicator light;

[0151] Performing gridding image processing on the reference device image according to the reference text coordinate information to obtain a reference grid image;

[0152] According to the coordinate information of the text to be checked, the image of the device to be checked is subjected to gridding image processing to obtain a grid image to be checked;

[0153] The sixth detection submodule is used to input the reference grid image and the pending check grid image into a pre-trained indicator light recognition model to obtain reference device status information and pending check device status information.

[0154] Furthermore, the comparison module 303 includes:

[0155] The first analysis submodule is used to determine whether the reference device status information is the same as the device status information to be verified;

[0156] The second analysis submodule is used to determine the displacement detection result of the secondary equipment to be detected as no displacement of the equipment if the reference equipment status information is the same as the equipment status information to be checked;

[0157] The third analysis submodule is used to determine the displacement detection result of the secondary device to be detected as the device being displaced if the reference device status information is different from the device status information to be checked.

[0158] Furthermore, the pressure plate recognition model includes a SVM model.

[0159] See also Figure 5 , Figure 5 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention.

[0160] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402, wherein the memory 402 stores a computer program; when the computer program is executed by the processor 402, the processor 402 executes a secondary device state change detection method according to any of the above embodiments.

[0161] The memory 401 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 401 has a storage space 403 for a program code 413 for executing any method step in the above method. For example, the storage space 403 for the program code may include individual program codes 413 for implementing the various steps in the above method, respectively. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a compact disk (CD), a memory card or a floppy disk. The program code may be compressed, for example, in an appropriate form. When these codes are run by a computing and processing device, the computing and processing device is caused to execute the various steps in the above-described method.

[0162] Embodiment 5 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the secondary device state change detection method as described in any of the above embodiments is implemented.

[0163] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0164] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0165] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0166] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0167] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0168] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting a state change of a secondary device, characterized in that: include: Obtain the reference device image and the image of the device to be verified of the secondary device to be inspected; According to the device type of the secondary device to be detected, the working condition of the reference device image and the device image to be checked are respectively identified to obtain the reference device status information and the device status information to be checked; The displacement detection result of the secondary device to be detected is determined according to the reference device status information and the device status information to be checked.

2. The secondary equipment state change detection method according to claim 1, characterized in that: The step of performing working condition identification on the reference device image and the device image to be checked according to the device type of the secondary device to be checked to obtain reference device status information and device status information to be checked comprises: When the device type of the secondary device to be detected is a terminal strip or a connecting piece, contour features are extracted from the reference device image and the image of the device to be checked respectively to obtain a plurality of target grid blocks, a reference edge image and an edge image to be checked; Using target grid blocks associated with the reference edge image and the edge image to be checked respectively, the reference edge image and the edge image to be checked are subjected to gridding image processing to obtain a reference grid image and a grid image to be checked; When the device type is a terminal wiring, the reference grid image and the grid image to be checked are respectively checked for wiring to obtain reference device status information and check device status information; When the device type is a connection piece, connection channel detection is performed on the reference grid image and the grid image to be checked respectively to obtain reference device status information and check device status information.

3. The secondary equipment state change detection method according to claim 2, characterized in that: The step of respectively extracting contour features from the reference device image and the device image to be checked to obtain a plurality of target grid blocks, a reference edge image and an edge image to be checked comprises: Using edge detection algorithms to perform edge detection on the reference device image and the device image to be checked, respectively, to obtain a reference edge image and a to-be-checked edge image; Performing contour detection on the reference edge image and the edge image to be checked respectively to obtain reference size features and size features to be checked; Respectively comparing the reference size feature and the size feature to be checked with each grid block in a preset grid block database one by one; When the grid block matches the reference size feature or the to-be-checked size feature, the grid block is determined as a target grid block.

4. The secondary equipment state change detection method according to claim 1, characterized in that: The step of performing working condition identification on the reference device image and the device image to be checked according to the device type of the secondary device to be checked to obtain reference device status information and device status information to be checked comprises: When the device type of the secondary device to be detected is a pressure plate, a circuit breaker or a handle, the reference device image and the image of the device to be checked are subjected to gridding image processing using a preset characteristic moment to obtain a reference grid image and a grid image to be checked; When the device type is a pressure plate, the reference grid image and the to-be-checked grid image are respectively input into a pre-trained pressure plate recognition model to obtain reference device status information and to-be-checked device status information; When the device type is open, a preset contour function is used to perform contour detection on the reference grid image and the grid image to be checked, respectively, to obtain a reference region of interest and a region of interest to be checked; Performing status evaluation on the reference ROI and the pending ROI based on a preset color interval to obtain reference device status information and pending ROI status information; When the device type is a handle, the reference grid image and the to-be-checked grid image are respectively input into a preset text recognition model to obtain reference device status information and to-be-checked device status information.

5. The secondary equipment state change detection method according to claim 1, characterized in that: The step of performing working condition identification on the reference device image and the device image to be checked according to the device type of the secondary device to be checked to obtain reference device status information and device status information to be checked comprises: When the device type of the secondary device to be detected is an indicator light, the reference device image and the device image to be checked are respectively input into a preset text recognition model to obtain reference text coordinate information and text coordinate information to be checked; Performing gridding image processing on the reference device image according to the reference text coordinate information to obtain a reference grid image; Performing gridding image processing on the device image to be checked according to the coordinate information of the text to be checked, to obtain a grid image to be checked; The reference grid image and the pending check grid image are respectively input into a pre-trained indicator light recognition model to obtain reference device status information and pending check device status information.

6. The secondary equipment state change detection method according to claim 1, characterized in that: The step of determining the displacement detection result of the secondary device to be detected according to the reference device status information and the device status information to be checked includes: Determine whether the reference device status information is the same as the device status information to be verified; If the reference equipment status information is the same as the equipment status information to be checked, the displacement detection result of the secondary equipment to be checked is determined as no displacement of the equipment; If the reference equipment status information is different from the equipment status information to be checked, the displacement detection result of the secondary equipment to be checked is determined as equipment displacement.

7. The secondary equipment state change detection method according to claim 4, characterized in that: The pressure plate identification model includes a SVM model.

8. A secondary equipment state change detection system, characterized in that: include: An acquisition module, used to obtain a reference device image and a device image to be verified of a secondary device to be inspected; An identification module, used to identify the working conditions of the reference device image and the device image to be checked according to the device type of the secondary device to be checked, and obtain the reference device status information and the device status information to be checked; The comparison module is used to determine the displacement detection result of the secondary device to be detected based on the reference device status information and the device status information to be checked.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the secondary device state change detection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the secondary device state change detection method as described in any one of claims 1 to 7 is implemented.

Images