Terminal wiring checking method and device of transformer substation, electronic equipment and program product

Abstract

The invention belongs to the technical field of transformer substations, and provides a terminal wiring checking method and device for a transformer substation, electronic equipment and a program product, and the terminal wiring checking method for the transformer substation comprises the steps: obtaining scanning images of a plurality of terminals of the transformer substation; preprocessing the scanned image to obtain a processed image, the preprocessing being used for enhancing actual wiring data related to the plurality of terminals in the scanned image; the processed images are recognized, actual wiring data of the multiple terminals are obtained, and the actual wiring data at least comprise terminal labels, terminal marking numbers, number pipeline numbers and wiring relations; and checking the actual wiring data based on the standard wiring data to obtain a checking result, the standard wiring data being wiring data correspondingly set in advance according to a design drawing of the plurality of terminals, and the checking result being used for indicating whether the plurality of terminals are wrongly wired or missed to be wired and indicating the terminal mark number corresponding to the wrong wiring or the missed wiring.

Description

Technical Field

[0001] The present application belongs to the technical field of substations, and more specifically, to a terminal wiring verification method, device, electronic equipment and program product for a substation. Background Art

[0002] With the continuous expansion of the scale of power systems and the improvement of their intelligence level, substations, as key nodes for power transmission and distribution, are particularly important for the stable and reliable operation of their internal secondary equipment. Terminal blocks, as insulating structural components that carry multiple or grouped terminal components that maintain electrical insulation from each other, have the ability to fix wiring cables, thereby firmly connecting the wiring of the devices inside the panel and external devices, and play a key role in signal (current and voltage) transmission.

[0003] Since wiring work is highly dependent on the experience of skilled workers, terminal block verification is an important part of the inspection work, an important link to ensure the safe and reliable operation of the electrical system, and a key measure to improve maintenance efficiency and extend the service life of equipment. However, in the current terminal block wiring verification process, due to the lack of intelligent troubleshooting methods, there are still problems such as low verification efficiency and high maintenance costs. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a terminal wiring verification method, device, electronic equipment and program product for a substation, aiming to solve the problem that the existing terminal block wiring verification is not intelligent enough and has low verification efficiency.

[0005] To achieve the above object, according to a first aspect of the present application, a method for verifying terminal connection of a substation is provided, the method comprising:

[0006] Acquire scanned images of multiple terminals of a substation;

[0007] Preprocessing the scanned image to obtain a processed image, wherein the preprocessing is used to enhance actual wiring data related to the plurality of terminals in the scanned image;

[0008] Recognize the processed image to obtain actual wiring data of the plurality of terminals, wherein the actual wiring data at least includes: terminal labels, terminal marking numbers, number pipeline numbers, and wiring relationships;

[0009] The actual wiring data is checked based on standard wiring data to obtain a check result, wherein the standard wiring data is wiring data pre-set according to design drawings of multiple terminals, and the check result is used to indicate whether the multiple terminals are miswired or missing, and the terminal marking number corresponding to the miswired or missing connection.

[0010] Optionally, in a possible implementation manner of the first aspect, preprocessing the scanned image to obtain a processed image includes:

[0011] Using a filtering algorithm to filter out irregularly distributed and / or irregularly sized noise points in the scanned image while retaining edge detail features of the text in the scanned image, thereby obtaining a denoised image;

[0012] Using a histogram equalization algorithm to perform contrast enhancement on the denoised image to obtain an enhanced image;

[0013] An adaptive threshold algorithm is used to perform grayscale processing on the enhanced image to obtain the processed image.

[0014] Optionally, in a possible implementation manner of the first aspect, recognizing the processed image to obtain actual wiring data of the plurality of terminals includes:

[0015] By adding target box angle information to the prediction head of the target detection network and adding rotation angle loss to the loss function of the target detection network, a rotation target detection network based on the target detection network is constructed;

[0016] Using the rotation target detection network to detect the rotated text area in the processed image, and obtaining the text frame in the processed image;

[0017] Based on a convolutional neural network sequence data recognition algorithm, optical character recognition processing is performed on the text frame to obtain a plurality of initial characters;

[0018] Correcting incorrectly recognized characters among the plurality of initial characters according to prior information to obtain a plurality of valid characters;

[0019] By analyzing the row and column distribution positions and the spatial relationship between the multiple valid characters, the actual wiring data of the multiple terminals are determined.

[0020] Optionally, in a possible implementation manner of the first aspect, determining actual wiring data of the plurality of terminals by analyzing row and column distribution positions and spatial relationships between the plurality of valid characters includes:

[0021] By analyzing the row and column distribution positions and spatial relationships between the plurality of valid characters, a corresponding association relationship between the plurality of terminals is established, wherein the association relationship at least includes: a combination relationship between the terminal label and the terminal label number, and a connection relationship between the terminal marking number and the number pipeline number;

[0022] Based on the predetermined typesetting structure of the plurality of characters, typesetting processing is performed on the associated relationship to obtain actual wiring data of the plurality of terminals.

[0023] Optionally, in a possible implementation manner of the first aspect, verifying the actual wiring data based on the standard wiring data to obtain a verification result includes:

[0024] Based on the terminal marking numbers of the plurality of terminals, acquiring the latest version of the standard wiring data from a first database table of a database, wherein the actual wiring data is stored in a second database table of the database based on the terminal marking numbers;

[0025] An intelligent verification algorithm is used to compare the standard wiring data with the actual wiring data to determine whether the plurality of terminals are miswired or missing, and the terminal marking numbers corresponding to the miswires or missing connections, to obtain the verification result.

[0026] Optionally, in a possible implementation manner of the first aspect, in the process of verifying the actual wiring data based on the standard wiring data to obtain the verification result, the method further includes:

[0027] If the terminal marking number of at least one terminal in the current row is not in the same position in the first data table and the second data table, the terminal marking numbers and verification results of the adjacent rows of the current row in the first data table and the second data table are analyzed, wherein the terminal marking numbers of the plurality of terminals are incremented in sequence;

[0028] If in the first data table and the second data table, the terminal marking numbers of the adjacent rows of the current row correspond and the verification results are correct, the terminal marking numbers of the current row are corrected according to the terminal marking numbers of the adjacent rows.

[0029] Optionally, in a possible implementation manner of the first aspect, the method further includes:

[0030] In the graphical display interface, terminals with misconnections or missing connections and terminal marking numbers corresponding to the misconnections or missing connections are displayed in a visual element highlighting manner.

[0031] According to a second aspect of the present application, a terminal connection verification device for a substation is provided, the device comprising:

[0032] An acquisition unit, used for acquiring scanned images of a plurality of terminals of the substation;

[0033] A preprocessing unit, used for preprocessing the scanned image to obtain a processed image, wherein the preprocessing is used for enhancing actual wiring data related to the plurality of terminals in the scanned image;

[0034] An identification unit, used for identifying the processed image, and obtaining actual wiring data of the plurality of terminals, wherein the actual wiring data at least includes: terminal labels, terminal marking numbers, number pipeline numbers, and wiring relationships;

[0035] A verification unit is used to verify the actual wiring data based on standard wiring data to obtain a verification result, wherein the standard wiring data is wiring data pre-set according to the design drawings of multiple terminals, and the verification result is used to indicate whether the multiple terminals are miswired or missing, and the terminal marking number corresponding to the miswired or missing connection.

[0036] The second aspect and any implementation of the second aspect correspond to the first aspect and any implementation of the first aspect, respectively. The technical effects corresponding to the second aspect and any implementation of the second aspect can refer to the technical effects corresponding to the first aspect and any implementation of the first aspect, which will not be repeated here.

[0037] According to a third aspect of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements any of the methods described in one embodiment.

[0038] According to a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above is implemented.

[0039] According to a fifth aspect of the present application, a computer program product is provided. When the computer program product is run on an electronic device, the electronic device executes any one of the methods described in the first aspect.

[0040] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0041] In the embodiment of the present application, the terminal wiring verification method of the substation obtains the scanned images of multiple terminals of the substation; pre-processes the scanned images to obtain the processed images, and the pre-processing is used to enhance the actual wiring data related to the multiple terminals in the scanned images; identifies the processed images to obtain the actual wiring data of the multiple terminals, and the actual wiring data at least includes: terminal labels, terminal marking numbers, number pipeline numbers, and wiring relationships; verifies the actual wiring data based on standard wiring data to obtain verification results, and the standard wiring data is the wiring data set in advance according to the design drawings of the multiple terminals. The verification results are used to indicate whether the multiple terminals are miswired or missing, and the terminal marking numbers corresponding to the miswires or missing wiring. It can effectively and accurately verify the terminal wiring conditions, improve the intelligent level and verification efficiency of the terminal row wiring verification, avoid problems such as short circuits and open circuits caused by improper wiring, and thus ensure the safe and stable operation of the electrical system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 It is a flow chart of a terminal wiring verification method of a substation provided by an embodiment of the present application;

[0044] Figure 2 It is a schematic diagram of an optional terminal connection of a substation provided in an embodiment of the present application;

[0045] Figure 3a is a schematic diagram of a scanned image before an optional preprocessing provided in an embodiment of the present application;

[0046] Figure 3b is a schematic diagram of an optional pre-processed image provided in an embodiment of the present application;

[0047] Figure 4 is a schematic diagram of an optional text box in a processed image provided in an embodiment of the present application;

[0048] Figure 5 is a schematic diagram of actual wiring data after optional typesetting provided by another embodiment of the present application;

[0049] Figure 6 It is a structural schematic diagram of a terminal connection verification device for a substation provided in an embodiment of the present application;

[0050] Figure 7It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0052] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0053] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0054] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0055] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0056] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0057] With the continuous expansion of the scale of power systems and the improvement of their intelligence level, substations, as key nodes for power transmission and distribution, are particularly important for the stable and reliable operation of their internal secondary equipment. Terminal blocks, as insulating structural components that carry multiple or grouped terminal components that maintain electrical insulation from each other, have the ability to fix wiring cables, thereby firmly connecting the wiring of the devices inside the panel and external devices, and play a key role in signal (current and voltage) transmission.

[0058] Since wiring work is highly dependent on the experience of skilled workers, human errors such as confusion between terminal markings and wire numbers, wrong connections, and missed connections are unavoidable during long-term, high-intensity work. Due to the lack of an effective error troubleshooting mechanism, it is difficult to fully and accurately locate the error points.

[0059] Therefore, terminal block verification is an important part of the inspection work, an important link to ensure the safe and reliable operation of the electrical system, and a key measure to improve maintenance efficiency and extend the service life of equipment. However, in the process of terminal block wiring verification, there are still problems such as low verification efficiency, high maintenance cost, and lack of intelligent troubleshooting methods:

[0060] Low verification efficiency: Traditional verification methods rely on manual point-by-point inspection, which is time-consuming and labor-intensive, and is prone to omissions due to visual fatigue or negligence, making it difficult to ensure the comprehensiveness and accuracy of the inspection work in a short period of time. Moreover, in a complex wiring environment, manual verification is more difficult and less efficient.

[0061] Lack of intelligent troubleshooting methods: With the rapid development of intelligent technology, the operation and maintenance management of substations is also moving towards intelligence. However, in the key link of panel cabinet terminal block wiring troubleshooting, there is still a lack of effective intelligent means to support it. This makes it impossible for wiring and verification work to fully utilize the advantages of modern information technology, thus limiting the improvement of work efficiency and accuracy.

[0062] High maintenance cost: If wiring errors cannot be discovered in the early stage of troubleshooting, they are often discovered only during subsequent debugging, trial operation, or even operation. As a result, troubleshooting and repair require a lot of manpower and material resources, increasing operation and maintenance costs. If not corrected in time, it may also cause short circuits, open circuits, and other faults, causing equipment damage or even system paralysis, further increasing the cost of repairing and replacing equipment.

[0063] In response to the problems existing in the above-mentioned background technology, the present invention proposes an intelligent verification method for substation cabinet terminal wiring based on image recognition technology, aiming to improve the accuracy and efficiency of wiring verification through intelligent means, reduce the human error rate, reduce operation and maintenance costs, and ensure the safe and stable operation of the electrical system.

[0064] This application example provides an example of a terminal wiring verification method for a substation. Please refer to Figure 1 As shown, Figure 1 The present application shows a schematic flow chart of a terminal wiring verification method for a substation. As an example but not a limitation, the method can be applied to the verification scenario of the terminal wiring of the substation, and can be specifically applied to the correctness verification of the terminal block wiring of the secondary electrical equipment such as protection, measurement and control in the substation, aiming to avoid problems such as short circuits and open circuits caused by improper wiring, thereby ensuring the safe and stable operation of the electrical system. The method includes:

[0065] S101, acquiring scanned images of multiple terminals of a substation;

[0066] S102, preprocessing the scanned image to obtain a processed image, wherein the preprocessing is used to enhance actual wiring data related to multiple terminals in the scanned image;

[0067] S103, identifying the processed image to obtain actual wiring data of multiple terminals, the actual wiring data at least including: terminal labels, terminal marking numbers, number pipeline numbers, and wiring relationships;

[0068] S104, verifying the actual wiring data based on the standard wiring data to obtain verification results, wherein the standard wiring data is the wiring data pre-set according to the design drawings of the multiple terminals, and the verification results are used to indicate whether the multiple terminals are miswired or missing, and the terminal marking numbers corresponding to the miswires or missing connections.

[0069] Optionally, in the example of this application, a high-definition image acquisition device, such as a high-resolution industrial camera, can be used, but is not limited to, to scan and photograph multiple terminals (i.e., terminal blocks) on the substation cabinet to obtain the scanned image. It should be understood that in a specific application scenario, the high-definition image acquisition device must have sufficient pixels and clarity to ensure that a scanned image containing clear and detailed information of the terminals can be obtained.

[0070] For example, during the shooting process, ensure that the shooting angle is appropriate and the light is even, and avoid factors such as poor shooting angle (such as excessive tilt angle causing deformation of the terminal shape) or too dark or too bright light (causing overexposure or heavy shadows in some areas of the terminal, affecting detail recognition) that affect the image quality. For another example, the camera can be fixed on a specific bracket and the angle can be adjusted so that it faces the terminal row, and auxiliary lighting equipment can be used to ensure that the light is sufficient and evenly distributed on the surface of the terminal row.

[0071] After acquiring scanned images of multiple terminals of the substation, the scanned images are pre-processed by one or more of a variety of processing methods such as denoising, contrast enhancement, visual enhancement, grayscale processing, etc. to obtain processed images.

[0072] Specifically, since there are often high-frequency components, i.e., noise points, in the scanned image, which interfere with the subsequent accurate recognition of terminal-related information, a filtering algorithm can be used to remove the noise points, such as Gaussian filtering, bilateral filtering, etc. By comparing the original scanned image before denoising and the image after denoising, it can be intuitively determined that the noise points are significantly reduced and the image becomes clearer and smoother.

[0073] In addition, the histogram equalization method can also be used to enhance the contrast of the image. This method improves the uneven grayscale distribution in the image by redistributing the grayscale of the image, making the difference between different grayscale levels more obvious. From a visual point of view, the clarity and recognition of the terminals and related text information in the image after contrast enhancement are greatly improved. Furthermore, the example of this application can also use an adaptive threshold method to grayscale the entire scanned image, for example, to reduce the complexity of the image, so that the effective text area will be highlighted, which is more conducive to focusing on key information such as terminal-related text.

[0074] In this application example, the detection network and character recognition algorithm based on the target detection network (Yolov8 detection network) can be used to identify the processed image and obtain the actual wiring data of multiple terminals, as an example but not a limitation. Figure 2 As shown, the actual wiring data at least includes: terminal labels, terminal marking numbers, number pipeline numbers, and may also include data such as wiring relationships. Afterwards, standard wiring data that is pre-set according to the design drawings of multiple terminals is obtained, and then the actual wiring data is checked based on the standard wiring data to obtain a check result, that is, whether multiple terminals are miswired or missing, and the terminal marking numbers corresponding to the miswires or missing.

[0075] Through the above implementation, the terminal wiring verification method of the substation can effectively and accurately verify the terminal wiring conditions, improve the intelligence level and verification efficiency of terminal block wiring verification, and reduce electrical accidents caused by wiring errors.

[0076] In a possible implementation, the scanned image (such as Figure 3a As shown) is preprocessed to obtain the processed image (as shown Figure 3b shown), including:

[0077] A filtering algorithm is used to filter out irregularly distributed and / or irregularly sized noise points in the scanned image while retaining the edge detail features of the text in the scanned image, thereby obtaining a denoised image.

[0078] The histogram equalization algorithm is used to enhance the contrast of the denoised image to obtain an enhanced image.

[0079] Adaptive threshold algorithm is used to process the grayscale of the enhanced image to obtain the processed image.

[0080] Optionally, in the example of the present application, a filtering algorithm is used to perform specific mathematical operations on the pixels in the scanned image to change the pixel values, thereby achieving the effect of removing noise and retaining useful information.

[0081] Optionally, there are multiple filtering algorithms, such as Gaussian filtering, bilateral filtering, etc., which can meet the requirements of filtering out noise points and retaining text edge detail features to a certain extent.

[0082] Taking the Gaussian filter algorithm as an example, the Gaussian filter algorithm determines the weight of the neighboring pixels around each pixel based on the Gaussian function, and then updates the value of the pixel by weighted averaging. For noise points in the scanned image, since the noise points are usually randomly distributed and have large differences from the surrounding pixel values, after the weighted averaging operation of the Gaussian filter algorithm, the influence of the noise points will be weakened and thus filtered out. For details such as text edges, since the changes in pixel values ​​are regular, they can be relatively well preserved in the weighted averaging process.

[0083] It should be understood that the bilateral filtering algorithm is more sophisticated, not only focusing on the spatial distance between pixels (similar to Gaussian filtering), but also focusing on the difference between pixel values. In this way, when processing images, noise points with large pixel values ​​different from the edge details of text can be filtered out more accurately, while further ensuring the clarity of the text edge.

[0084] After being processed by the filtering algorithm, visually, the irregularly distributed (such as randomly scattered throughout the image) and irregularly sized (some noise points may be very small, some may be large) noise points in the scanned image will be significantly reduced. For example, there were some snowflake-like noise interferences in the original scanned image, but after processing, these noise points basically disappeared. At the same time, the edge details of the terminal-related text in the scanned image, such as the stroke edges of the text and the outline of the label, can still be clearly discerned.

[0085] It should be noted that histogram equalization is a method to enhance the image contrast by adjusting the grayscale distribution of the image. The grayscale of an image can be understood as the different brightness levels in the image, usually represented by a value from 0 to 255 (for 8-bit grayscale images). In the original scanned image, there may be an uneven distribution of grayscale levels, resulting in an unclear contrast between the text or terminals and the background in some areas, which is not conducive to subsequent recognition.

[0086] Based on the histogram equalization algorithm, the frequency of each gray level in the image can be recalculated, and then the gray levels can be redistributed according to the new frequency distribution, so that the gray levels of the image are more evenly distributed in the entire value range. In addition, the difference between gray levels in areas with low contrast will be amplified, thereby enhancing the contrast of the image.

[0087] For the denoised image, after being processed by the histogram equalization algorithm, visually, the contrast between the text, terminals and other objects in the image and the background is significantly improved. For example, the text on the terminal label may be a little blurry and not very distinguishable from the background. After contrast enhancement, the text becomes clearer, the color depth contrast is more obvious, and it is easier to stand out from the background. The contrast enhancement helps to more accurately locate and identify key information such as text and terminals in the image during image recognition, and improve the accuracy and efficiency of recognition.

[0088] Furthermore, in the example of the present application, an adaptive threshold algorithm can be used to convert the color enhanced image into a grayscale image. In a color image, each pixel has values ​​for three color channels: red (R), green (G), and blue (B), while a grayscale image uses a single value to represent the brightness of each pixel. The adaptive threshold algorithm automatically determines a threshold based on the pixel features of different areas in the enhanced image, and then compares the RGB value of each pixel with the threshold.

[0089] If the RGB value of a pixel is greater than a threshold, the pixel is set to white (usually represented by a higher grayscale value, such as 255); if the RGB value of a pixel is less than the threshold, the pixel is set to black (usually represented by a lower grayscale value, such as 0), thereby realizing the process of converting a color image into a grayscale image.

[0090] It should be understood that, unlike the fixed threshold algorithm, the adaptive threshold algorithm does not use a fixed threshold to process the entire image, but automatically determines the appropriate threshold based on the actual conditions of different areas of the image. This is because in the scanned image, different areas may have different brightness, contrast, etc. The use of an adaptive threshold can more accurately convert the image into a grayscale image and better highlight the effective text area. After being processed by the adaptive threshold algorithm, the original color enhanced image becomes a single-channel grayscale image. Visually, the color information of the image is removed, leaving only black and white, and the complexity of the image is greatly reduced.

[0091] More importantly, in this process, the effective text area will be better highlighted: because the difference in grayscale value between the text part and the background will be more obvious, for example, the text is usually black and the background is white, so in subsequent text recognition and other operations, it is easier to focus on the text area, thereby improving the accuracy and efficiency of recognition.

[0092] Through the preprocessing operations of the above three steps, the scanned image is subjected to denoising, contrast enhancement and grayscale processing. The processed image obtained not only removes interference information, but also highlights key text and other information, making it easier to accurately identify terminal wiring related information.

[0093] In a possible implementation, recognizing the processed image to obtain actual wiring data of multiple terminals includes:

[0094] By adding the target box angle information to the prediction head of the target detection network and adding the rotation angle loss to the loss function of the target detection network, a rotation target detection network based on the target detection network is constructed;

[0095] A rotation object detection network is used to detect the rotated text area in the processed image to obtain the text frame in the processed image;

[0096] Based on the convolutional neural network sequence data recognition algorithm, optical character recognition processing is performed on the text frame to obtain multiple initial characters;

[0097] Correcting incorrectly recognized characters among the multiple initial characters according to prior information to obtain multiple valid characters;

[0098] By analyzing the row and column distribution positions and spatial relationships between multiple valid characters, actual wiring data of multiple terminals are determined.

[0099] It should be noted that the target detection network is a deep learning architecture used to locate and identify different targets in images. For example, target detection algorithms such as Yolov8 (You Only Look Once version 8) detection network and Faster RCNN (Region-based Convolutional Neural Network) can output information such as the location (such as through bounding box coordinates) and category of the target.

[0100] First, in the example of this application, the original target detection network is improved and expanded by adding target box angle information to the prediction head of the conventional target detection network and adding rotation angle loss to the loss function of the target detection network, and a rotating target detection network based on the target detection network is constructed. The rotating target detection network has a stronger ability to detect rotated text areas, and can accurately detect rotated text areas in the processed image.

[0101] The prediction head is the part of the target detection network that is responsible for the final output of the prediction results. Adding the target frame angle information means that while predicting the target position, the angle information of the target (mainly the text area here, because the text in the processed image will be detected later) relative to the image coordinate system can also be obtained. For example, for tilted or rotated text areas that may exist in the processed image, by adding this angle information, the network can more accurately locate the text areas in these rotated states, rather than just the conventional horizontal or vertical positioning.

[0102] The loss function is an indicator used to measure the difference between the network prediction result and the true label. The goal of the detection network training is to minimize the value of this loss function. After adding the rotation angle loss, the detection network pays more attention to the accurate prediction of the rotation angle of the target (text area) during the training process. When the rotation angle predicted by the detection network deviates greatly from the actual rotation angle, the value of the loss function will increase, prompting the network to continuously adjust parameters during the training process to more accurately predict the rotation angle of the text area, thereby improving the detection ability of the rotated text area.

[0103] Furthermore, in the example of this application, a rotating target detection network is used to detect the text area that is rotated in the processed image, and a text frame (such as Figure 4 shown).

[0104] Specifically, due to factors such as the shooting angle and the installation angle of the terminal itself in the images related to the substation terminals, the text area in the image is rotated to a certain extent. Therefore, in the example of this application, the processed image is detected using a constructed rotating target detection network. The rotating target detection network can accurately detect the rotated text area based on the added target box angle information and the training mechanism of the rotation angle loss. For example, for the text on a slightly tilted terminal label, the rotating target detection network can identify the rotation state and determine the specific position range of the text in the image. This position range is defined by the text box.

[0105] After detection by the rotation target detection network, a corresponding text box will be obtained for each detected rotated text area. The text box defines the specific position of the text area in the image in the form of coordinates (such as the coordinates of the upper left corner and the lower right corner), providing a clear target area for subsequent optical character recognition processing of the text area, ensuring that subsequent recognition operations can be accurately performed on these text areas without being interfered by other irrelevant areas in the image.

[0106] Secondly, in the example of the present application, the text box can also be subjected to optical character recognition processing based on the sequence data recognition algorithm of the convolutional neural network to obtain multiple initial characters. Optionally, the sequence data recognition algorithm based on the convolutional neural network (CNN) can be an algorithm such as CRNN (Convolutional Recurrent Neural Network). The sequence data recognition algorithm based on the convolutional neural network combines the feature extraction capability of CNN and the sequence processing capability of the recurrent neural network (RNN), and can effectively process image data with sequence features, such as the text data in the text box here.

[0107] Optical character recognition processing: Perform optical character recognition processing on the text in the text box detected by the rotating target detection network. Specifically, the text image data in the text box can be input into a sequence data recognition algorithm based on a convolutional neural network. The algorithm first extracts various features of the text, such as stroke features, structural features, etc., through the CNN part, and then processes these features according to the writing order of the text (from left to right and from top to bottom for most texts) through the RNN part, thereby converting the text image in the text box into a computer-recognizable character form to obtain multiple initial characters. For example, for a text box containing terminal label text, after recognition processing, an initial character sequence such as "ABC123" is obtained.

[0108] Furthermore, the incorrectly recognized characters in the multiple initial characters are corrected based on the prior information to obtain multiple valid characters. It should be understood that the prior information refers to some information about possible errors in the characters and the correct correction methods that are known before character recognition. In the text related to the substation terminals, there may be some specific characters that are easy to confuse, such as the separator " / " and "1" in the middle of the text, which are easy to confuse. According to the prior information, when there are characters that may be confused in the multiple initial characters obtained by recognition, targeted corrections can be made.

[0109] For example, the character correction operation refers to checking multiple initial characters one by one. When it is found that a certain initial character matches the easily confused situation mentioned in the prior information, it is corrected according to the correction method provided by the prior information. For example, if there is a "1" in the recognized initial character, and it is known according to the prior information that " / " should be in this position, then "1" is corrected to " / ". Through the above correction operation, the incorrectly recognized characters are corrected to correct characters, thereby obtaining multiple valid characters, which more accurately reflect the true content of the text in the image.

[0110] Finally, by analyzing the row and column distribution positions and spatial relationships between multiple valid characters, the actual wiring data of multiple terminals is determined. Among them, analyzing the character relationship is to analyze the multiple valid characters obtained, mainly focusing on the row and column distribution positions and spatial relationships between multiple valid characters. In the images related to substation terminals, different character combinations may represent different meanings, for example, the relationship between the terminal label and the terminal label number corresponding to the terminal number, the relationship between the terminal number and the number pipeline number (external wiring), etc. By carefully analyzing the row and column distribution positions and spatial relationships between valid characters, these different relationships can be sorted out.

[0111] According to the analysis results of the row and column distribution positions and spatial relationships between multiple valid characters, the actual wiring data of multiple terminals are determined, and the actual wiring data includes information such as terminal labels, terminal marking numbers, number tube line numbers, wiring relationships, etc. For example, through analysis, it is found that the label of a certain terminal is "ABC", the marking number is "123", and the wiring relationship with the number tube "XYZ" is "connected", thereby completely determining the actual wiring data of the terminal.

[0112] Through the above specific implementation, the actual wiring data of multiple terminals can be accurately identified from the processed image, so as to realize the verification of the terminal wiring of the substation.

[0113] In a possible implementation, actual wiring data of multiple terminals is determined by analyzing row and column distribution positions and spatial relationships between multiple valid characters, including:

[0114] By analyzing the row and column distribution positions and spatial relationships between multiple valid characters, corresponding association relationships between multiple terminals are established, and the association relationships at least include: a combination relationship between terminal labels and terminal label numbers, and a connection relationship between terminal marking numbers and number pipeline numbers;

[0115] Based on the predetermined typesetting structure of the multiple characters, typesetting processing is performed on the associated relationship to obtain actual wiring data of the multiple terminals.

[0116] First, we need to determine the row and column distribution of multiple valid characters in the image. For example, some characters may be closely arranged in the same row, while others are distributed in different rows. At the same time, we also need to pay attention to the spatial relationship between them, such as the spacing between characters, relative orientation, etc.

[0117] For example, the terminal labels and terminal marking numbers are usually adjacent in space and arranged in a certain pattern. Figure 5 As shown, the terminal label (serial number 1, 2) is in front, followed by the terminal marking number (1D2-6, 1D2-7), and their positional relationship in the same row or the upper and lower rows is relatively fixed. The corresponding relationship between the terminal marking number (1D2-6, 1D2-7) and the number pipeline number (1D1-45 / 1 P15-4, 1D2-7 / 1 P7-10) is reflected through the specific position and spatial layout of the characters in the image.

[0118] Based on the observed character positions and spatial relationships, when certain characters meet the characteristics of terminal labels (such as having a specific format, representing a specific terminal function, etc.) and are followed by characters that meet the characteristics of terminal marking numbers, the combination relationship between them can be determined. For example, if the "ABC" character group is judged to be a terminal label, and the subsequent "123" character group is identified as a terminal marking number, then the combination relationship of "ABC" and "123" can be established, and this combination relationship constitutes a complete terminal number (such as "ABC123").

[0119] Similarly, by analyzing the spatial layout between characters, when there is a specific positional association between a terminal marking character group and a number pipeline character group (such as being in the same area, connected by a certain line or mark, etc.), the connection relationship between them can be determined. For example, the terminal marking number "123" and the number pipeline number "XYZ" are determined to have a "connected" connection relationship through a certain line in the image or their relative positions in a specific area.

[0120] Furthermore, since different character information in the images related to the substation terminals usually has a predetermined typesetting structure, the associated relationship can be typeset based on the predetermined typesetting structure of multiple characters to obtain actual wiring data of multiple terminals.

[0121] It should be understood that the typesetting structure refers to the arrangement of characters according to certain rules and orders to accurately convey various information of the terminal. For example, the terminal label appears first, followed by the terminal marking number, followed by the number pipeline number and other information related to the terminal, and they have a specific distribution pattern in rows and columns. In addition, the predetermined typesetting structure can also be determined based on industry standards, design specifications or equipment manufacturer's requirements, which helps to maintain consistency and accuracy when reading and understanding terminal information.

[0122] Based on the established association relationships (such as the combination relationship between the terminal label and the terminal marking number, the wiring relationship between the terminal marking number and the number pipeline number, etc.), these relationships are sorted and typeset according to the predetermined typesetting structure of multiple characters. For example, according to the predetermined typesetting structure, the terminal label and the terminal marking number are first combined into a complete terminal number, and then the terminal number and the corresponding number pipeline number and their wiring relationship are arranged in sequence. Assuming that the terminal label "ABC", the terminal marking number "123" and the wiring relationship with the number pipeline number "XYZ" have been determined to be "connected", then after typesetting according to the predetermined typesetting structure, the actual wiring data obtained may be presented in the form of "terminal number: ABC123, number pipeline number: XYZ, wiring relationship: connected" and the like.

[0123] Through the above-mentioned typesetting processing, the originally scattered actual wiring data of multiple terminals, which are in line with industry standards and easy to understand, can be organized into various association relationships established by analyzing character relationships, providing clear and accurate information basis for subsequent verification, maintenance and other work.

[0124] In a possible implementation, the actual wiring data is verified based on the standard wiring data to obtain a verification result, including:

[0125] Based on the terminal marking numbers of the plurality of terminals, obtaining the latest version of standard wiring data from a first database table of the database, wherein the actual wiring data is stored in a second database table of the database based on the terminal marking numbers;

[0126] An intelligent verification algorithm is used to compare standard wiring data with actual wiring data to determine whether multiple terminals are miswired or missing, and the terminal marking numbers corresponding to the miswires or missing connections to obtain verification results.

[0127] In the example of this application, two important database tables are set in the entire verification system, namely the first database table and the second database table. The first database table is mainly used to store standard wiring data. It should be understood that these standard wiring data are wiring data set in advance according to the design drawings of multiple terminals, and will be updated to the latest version in time with the equipment modification, upgrade or change to ensure accuracy and timeliness. The second database table is used to store actual wiring data. These actual wiring data are information about the actual wiring conditions of multiple terminals obtained through a series of previous image acquisition, preprocessing, recognition and other operations, and are stored based on terminal marking numbers. That is, the actual wiring data of each terminal can be indexed and searched by the terminal marking number in the second database table.

[0128] When the verification operation is to be performed, the latest version of the standard wiring data is first obtained from the first database table based on the terminal marking numbers of multiple terminals. This is because the terminal marking number is a key identifier in the entire wiring data system, which can uniquely correspond to a specific terminal and its related wiring information. For example, if the wiring of a certain group of specific terminals is to be verified, the corresponding standard wiring data can be accurately found in the first database table based on the terminal marking number of each terminal in the group of terminals. These data include information such as standard terminal labels, number pipeline numbers, wiring relationships, etc.

[0129] In the present application example, the intelligent verification algorithm is an algorithm specially designed for comparing and analyzing standard wiring data and actual wiring data. It can efficiently and accurately process the differences between the two sets of data, thereby determining whether there are wrong wiring or missing wiring, and further determining the terminal marking numbers corresponding to these abnormal wiring conditions.

[0130] Furthermore, an intelligent verification algorithm can be used to compare the standard wiring data with the actual wiring data to determine whether multiple terminals are miswired or missing, and the terminal marking numbers corresponding to the miswires or missing connections, to obtain verification results. Specifically, during the comparison process, key information in the standard wiring data and the actual wiring data can be checked point by point, including terminal marking numbers, number pipeline numbers, wiring relationships, etc. For example, the terminal marking numbers in the standard wiring data are compared with the terminal marking numbers in the actual wiring data to see if they are consistent, and at the same time, the corresponding number pipeline numbers are checked to see if they match and whether the wiring relationships are consistent.

[0131] In an optional comparison and analysis process, first, an intelligent verification algorithm can be used to compare the terminal marking numbers in the standard wiring data and the actual wiring data. If the two are inconsistent, it indicates that there is a wiring error or the data acquisition is incorrect. However, it should be noted that there may be some minor deviations in the actual wiring (such as cable bending, slight misalignment) that lead to partial character recognition errors in the terminal number. Therefore, this inconsistency cannot be simply judged as wrong wiring, and further analysis is required in combination with other factors, such as the subsequent combination of the terminal numbers and verification results in the upper and lower rows for comprehensive judgment.

[0132] In addition to comparing the terminal marking numbers, an intelligent verification algorithm can also be used to compare the number pipeline numbers and wiring relationships in the standard wiring data and the actual wiring data. If a terminal and a number pipeline number are in a "connected" relationship in the standard wiring data, but the relationship between the terminal and the number pipeline number is not a "connected" relationship in the actual wiring data, or the corresponding number pipeline number itself does not match, it can be determined that there is a wiring error, and it can be determined that there is a problem with the wiring involved in the corresponding terminal marking number.

[0133] Through the above comprehensive comparison and analysis process, based on the intelligent verification algorithm, it is possible to determine whether multiple terminals are miswired or missing, and accurately find the terminal marking numbers corresponding to the miswires or missing connections. The final verification results can clearly indicate which terminals have wiring errors (miswiring), which terminals have missing connections (missing connections), and which specific terminal marking numbers are involved in these abnormal wiring situations. For example, the verification results may show "the terminal with terminal marking number 123 has a miswiring situation, and the actual wiring relationship does not match the standard wiring relationship" or "the terminal with terminal marking number 456 has a missing connection situation, and the number pipeline number connection relationship corresponding to the standard wiring is not found in the actual wiring data" and other information.

[0134] Through the above optional implementation methods, the actual wiring data can be effectively checked based on the standard wiring data, and the verification results can be accurately obtained, thereby providing strong support for ensuring the correctness and stability of the substation terminal wiring.

[0135] In a possible implementation, in the process of verifying the actual wiring data based on the standard wiring data to obtain the verification result, the method further includes:

[0136] If the terminal marking number of at least one terminal in the current row is not in the same position in the first data table and the second data table, the terminal marking numbers and verification results of the adjacent rows of the current row in the first data table and the second data table are analyzed, wherein the terminal marking numbers of the plurality of terminals are incremented in sequence;

[0137] If in the first data table and the second data table, the terminal marking numbers of the adjacent rows of the current row correspond and the verification results are correct, the terminal marking numbers of the current row are corrected according to the terminal marking numbers of the adjacent rows.

[0138] In the process of checking the standard wiring data (stored in the first data table) and the actual wiring data (stored in the second data table), the terminal marking number is used as the key identifier to compare the wiring information. Under normal circumstances, the terminal marking numbers of the same group of related terminals should correspond in the two data tables, so that it can be accurately judged whether the wiring is correct.

[0139] However, due to some factors that may exist in actual wiring, such as cable bending, slight misalignment, etc., when image recognition is used to obtain actual wiring data, the terminal marking number of at least one terminal in the current row may be inconsistent in position in the first data table and the second data table. Further analysis is needed to determine whether this inconsistency really represents a wiring error or is an acceptable deviation caused by the above-mentioned interference factors.

[0140] In normal wiring layout, the terminal marking numbers are usually arranged in a certain order, such as starting from 1, followed by 2, 3, 4, etc. Based on the characteristics of the terminal marking numbers of multiple terminals increasing in sequence, when it is found that the terminal marking numbers of the current row are inconsistent in the two data tables, it is necessary to check the terminal marking numbers of the adjacent rows (i.e. the previous row and the next row of the current row) in the two data tables and the corresponding verification results. If the terminal marking numbers of the adjacent rows are normally corresponding, the current row is further inferred, and the inconsistency of the current row is considered acceptable.

[0141] In the first data table and the second data table, the terminal marking numbers of the adjacent rows of the current row are indeed corresponding, that is, the terminal marking numbers of the previous row are the same in the two data tables, and the terminal marking numbers of the next row are also the same in the two data tables. In addition, after verifying the various wiring information (including terminal marking numbers, number pipeline numbers, wiring relationships, etc.) of these adjacent rows, the verification results obtained are all correct, so it can be determined that within the range of adjacent rows, the wiring conditions meet the standards and the data correspond.

[0142] When the above conditions are met, the terminal marking number of the current row can be corrected according to the terminal marking number of the adjacent row. For example, if the terminal marking number of the previous row is 5 in both data tables, and the terminal marking number of the next row is 7 in both data tables, and the terminal marking number of the current row in the second data table (actual wiring data) is 6, and the terminal marking number in the first data table (standard wiring data) is 8, since the adjacent rows correspond and the verification results are correct, then it can be considered that this difference in the current row is acceptable, and reasonable corrections can be made with reference to the terminal marking numbers of the adjacent rows. For example, according to the rule of increasing terminal marking numbers of adjacent rows, the terminal marking number of the current row in the second data table can be corrected to a value closer to the value in the standard wiring data, and corrected to 7 (assuming that it is based on a reasonable method such as simple averaging or interpolation), which to a certain extent better meets the consistency requirements of the actual wiring situation and the standard wiring situation, thereby more accurately completing data comparison and wiring situation combing and detection.

[0143] Through this processing method, when faced with inconsistent terminal markings due to some interference factors in the actual wiring, reasonable corrections and accurate judgments can be made to a certain extent, thereby improving the accuracy and reliability of the verification results, thereby better ensuring the correctness and stability of the substation terminal wiring.

[0144] In a possible implementation, the method further includes:

[0145] In the graphical display interface, terminals with miswires or missing connections and terminal marking numbers corresponding to the miswires or missing connections are displayed in a highlighted visual element manner.

[0146] As an example and not limitation, after completing the verification of the substation terminal wiring and obtaining verification results such as which terminals have miswiring or missing wiring and the corresponding terminal marking numbers, these key information can also be intuitively presented to operation and maintenance personnel and other relevant users so that the operation and maintenance personnel can quickly and clearly understand the wiring situation and accurately locate the problem.

[0147] Optionally, in the example of this application, the visual elements may include various forms, such as color, shape, flashing effect, etc. For example, you may choose to highlight terminals with miswired connections in red, and terminals with missed connections in yellow. For terminal marking numbers, you may highlight them in bold font, larger font size, or different colors (such as the same color as the corresponding terminal but more eye-catching), so that they are more conspicuous on the interface and easier to be noticed by operation and maintenance personnel.

[0148] On the graphical display interface, terminals that have been checked and determined to have miswired or missed wiring can be accurately highlighted with selected visual elements. For example, if a terminal has an incorrect wiring relationship (miswired) compared to the standard wiring in actual wiring, this terminal will be presented in a corresponding highlighted manner (such as red, etc.) on the interface, allowing users to intuitively see which specific terminal has a wiring error. At the same time, the terminal marking numbers corresponding to these terminals with miswired or missed wiring will also be displayed on the interface in the same intuitive manner (such as bold, color change, etc.). In this way, users can not only know which terminal has a problem, but also clearly understand the specific marking number of the terminal, which is convenient for accurately locating and handling the wiring problem of the terminal in actual operation (such as finding the specific terminal location, checking related wiring records, etc.).

[0149] By highlighting terminals with miswired or missing connections and the corresponding terminal marking numbers with visual elements in the graphical display interface, operation and maintenance personnel and other users can focus on the terminals with wiring problems and their corresponding marking numbers at a glance when browsing the graphical display interface, greatly improving the efficiency and intuitiveness of information transmission, helping operation and maintenance personnel to carry out subsequent maintenance and rectification work more efficiently, and ensuring the correctness and stability of substation terminal wiring.

[0150] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0151] Corresponding to the terminal connection verification method of the substation in the above embodiment, Figure 6is a schematic diagram of the structure of a terminal connection verification device for a substation provided in an embodiment of the present application. The device can be implemented as part or all of a computer device by software, hardware, or a combination of both. The computer device can be Figure 7 Electronic equipment shown.

[0152] Reference Figure 6 The terminal connection verification device of the substation includes:

[0153] An acquisition unit 601 is used to acquire scanned images of multiple terminals of a substation;

[0154] A preprocessing unit 602 is used to preprocess the scanned image to obtain a processed image, wherein the preprocessing is used to enhance actual wiring data related to multiple terminals in the scanned image;

[0155] The recognition unit 603 is used to recognize the processed image and obtain the actual wiring data of multiple terminals, the actual wiring data at least including: terminal label, terminal mark number, number pipeline number, and wiring relationship;

[0156] The verification unit 604 is used to verify the actual wiring data based on the standard wiring data to obtain a verification result. The standard wiring data is the wiring data set in advance according to the design drawings of multiple terminals. The verification result is used to indicate whether the multiple terminals are miswired or missing, and the terminal marking number corresponding to the miswired or missing wiring.

[0157] It should be noted that the terminal wiring verification device for the substation provided in the above embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0158] The functional units and modules in the above embodiments 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, and the above integrated units may be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present application.

[0159] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0160] An embodiment of the present application further provides an electronic device, the electronic device comprising one or more processors and a memory;

[0161] The memory is coupled to one or more processors, and the memory is used to store computer program codes, the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the terminal connection verification method of the substation shown above.

[0162] Figure 7 The schematic diagram of the structure of an electronic device provided in the embodiment of the present application is that the electronic device 700 can be a mobile phone, a smart screen, a tablet computer, a wearable electronic device, an in-vehicle electronic device, an augmented reality (AR) device, a virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a projector, or a communication device such as a server, a storage device, a base station, or a smart car, etc. The embodiment of the present application does not impose any restrictions on the specific type of the electronic device.

[0163] The memory 701 can be used to store computer software programs 702 and modules, and the processor 703 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 701. The memory 701 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device (such as audio data, a phone book, etc.), etc. In addition, the memory 701 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0164] Among them, the processor 703 may include one or more processors such as a central processing unit, an application processor (AP), a baseband processor, etc. The processor may be the nerve center and command center of the wireless router. The processor 703 may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching and executing instructions. The memory 701 may be used to store computer executable program codes, and the executable program codes include instructions. The processor 703 executes various functional applications and data processing of the network device by running the instructions stored in the memory. The memory 701 may include a program storage area and a data storage area, such as storing data of a sound signal to be played. For example, the memory may be a double rate synchronous dynamic random access memory DDR or a flash memory Flash.

[0165] An embodiment of the present application also provides a computer-readable storage medium, in which computer instructions are stored; when the computer-readable storage medium is run on an electronic device, the electronic device executes the terminal wiring verification method for the substation shown above.

[0166] The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium, or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0167] The embodiment of the present application also provides a computer program product including computer instructions. When the computer program product is run on an electronic device, the electronic device can execute the terminal wiring verification method for the substation shown above.

[0168] The computer storage medium and computer program product provided in the above-mentioned embodiments of the present application are used to execute the method provided above. Therefore, the beneficial effects that can be achieved can refer to the corresponding beneficial effects of the method provided above, and will not be repeated here.

[0169] In the above embodiments, it can also be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (such as: coaxial cable, optical fiber, data subscriber line (Digital Subscriber Line, DSL)) or wireless (such as: infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a digital versatile disc (DVD)), or a semiconductor medium (such as a solid state disk (SSD)).

[0170] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0171] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments applied for herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0172] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0173] 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.

[0174] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person 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. Such 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 application, and should all be included in the protection scope of the present application.

Claims

1. A terminal connection verification method for a substation, characterized in that: include: Acquire scanned images of multiple terminals of a substation; Preprocessing the scanned image to obtain a processed image, wherein the preprocessing is used to enhance actual wiring data related to the plurality of terminals in the scanned image; Recognize the processed image to obtain actual wiring data of the plurality of terminals, wherein the actual wiring data at least includes: terminal labels, terminal marking numbers, number pipeline numbers, and wiring relationships; The actual wiring data is checked based on standard wiring data to obtain a check result, wherein the standard wiring data is wiring data pre-set according to design drawings of multiple terminals, and the check result is used to indicate whether the multiple terminals are miswired or missing, and the terminal marking number corresponding to the miswired or missing connection.

2. The method according to claim 1, characterized in that: Preprocessing the scanned image to obtain a processed image includes: Using a filtering algorithm to filter out irregularly distributed and / or irregularly sized noise points in the scanned image while retaining edge detail features of the text in the scanned image, thereby obtaining a denoised image; Using a histogram equalization algorithm to perform contrast enhancement on the denoised image to obtain an enhanced image; An adaptive threshold algorithm is used to perform grayscale processing on the enhanced image to obtain the processed image.

3. The method according to claim 1, characterized in that Recognizing the processed image to obtain actual wiring data of the plurality of terminals includes: By adding target box angle information to the prediction head of the target detection network and adding rotation angle loss to the loss function of the target detection network, a rotation target detection network based on the target detection network is constructed; Using the rotation target detection network to detect the rotated text area in the processed image, and obtaining the text frame in the processed image; Based on a convolutional neural network sequence data recognition algorithm, optical character recognition processing is performed on the text frame to obtain a plurality of initial characters; Correcting incorrectly recognized characters among the plurality of initial characters according to prior information to obtain a plurality of valid characters; By analyzing the row and column distribution positions and the spatial relationship between the multiple valid characters, the actual wiring data of the multiple terminals are determined.

4. The method according to claim 3, characterized in that The step of determining actual wiring data of the plurality of terminals by analyzing the row and column distribution positions and spatial relationships between the plurality of valid characters comprises: By analyzing the row and column distribution positions and spatial relationships between the plurality of valid characters, a corresponding association relationship between the plurality of terminals is established, wherein the association relationship at least includes: a combination relationship between the terminal label and the terminal label number, and a connection relationship between the terminal marking number and the number pipeline number; Based on the predetermined typesetting structure of the plurality of characters, typesetting processing is performed on the associated relationship to obtain actual wiring data of the plurality of terminals.

5. The method according to claim 1, characterized in that The actual wiring data is verified based on the standard wiring data to obtain a verification result, including: Based on the terminal marking numbers of the plurality of terminals, acquiring the latest version of the standard wiring data from a first database table of a database, wherein the actual wiring data is stored in a second database table of the database based on the terminal marking numbers; An intelligent verification algorithm is used to compare the standard wiring data with the actual wiring data to determine whether the plurality of terminals are miswired or missing, and the terminal marking numbers corresponding to the miswires or missing connections, to obtain the verification result.

6. The method according to claim 5, characterized in that In the process of verifying the actual wiring data based on the standard wiring data to obtain the verification result, the method further includes: If the terminal marking number of at least one terminal in the current row is not in the same position in the first data table and the second data table, the terminal marking numbers and verification results of the adjacent rows of the current row in the first data table and the second data table are analyzed, wherein the terminal marking numbers of the plurality of terminals are incremented in sequence; If in the first data table and the second data table, the terminal marking numbers of the adjacent rows of the current row correspond and the verification results are correct, the terminal marking numbers of the current row are corrected according to the terminal marking numbers of the adjacent rows.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: In the graphical display interface, terminals with misconnections or missing connections and terminal marking numbers corresponding to the misconnections or missing connections are displayed in a visual element highlighting manner.

8. A terminal connection verification device for a substation, characterized in that: include: An acquisition unit, used for acquiring scanned images of a plurality of terminals of the substation; A preprocessing unit, used for preprocessing the scanned image to obtain a processed image, wherein the preprocessing is used for enhancing actual wiring data related to the plurality of terminals in the scanned image; An identification unit, used for identifying the processed image, and obtaining actual wiring data of the plurality of terminals, wherein the actual wiring data at least includes: terminal labels, terminal marking numbers, number pipeline numbers, and wiring relationships; A verification unit is used to verify the actual wiring data based on standard wiring data to obtain a verification result, wherein the standard wiring data is wiring data pre-set according to the design drawings of multiple terminals, and the verification result is used to indicate whether the multiple terminals are miswired or missing, and the terminal marking number corresponding to the miswired or missing connection.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed, causes the method according to any one of claims 1 to 7 to be performed.

Images