Intelligent identification method, device and equipment for wiring diagram of power grid plant station and storage medium

Abstract

The invention relates to the technical field of wiring diagram recognition, and discloses an intelligent recognition method, device and equipment for a power grid plant station wiring diagram and a storage medium, and the method comprises the steps: obtaining a to-be-recognized power grid plant station wiring diagram; performing image preprocessing on the power grid plant station wiring diagram; performing image recognition on the preprocessed power grid plant station wiring diagram by using an edge detection algorithm to obtain an equipment key part and a connecting line key part; comparing the key part of the equipment with a pre-stored standard equipment image, and matching a corresponding equipment label for the key part of the equipment; and according to the connection relationship between the equipment key part and the connection line key part, obtaining a connection result of each matched equipment label and other equipment labels through the connection line key part. The method can achieve the intelligent recognition of the wiring diagram of the power grid plant station, avoids the time-consuming and labor-consuming manual recognition, and is liable to cause errors or omission, and improves the recognition precision and efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of wiring diagram recognition, and particularly to an intelligent recognition method, device, equipment and storage medium for the wiring diagram of a power grid substation. Background Art

[0002] With the rapid development of smart grid technology, the equipment layout and line connections in power grid substations are becoming increasingly complex. The traditional manual method of drawing and checking wiring diagrams can no longer meet the requirements of high efficiency and accuracy. The wiring diagram of a power grid substation is an important basic data for the design and maintenance of the power system, accurately recording various equipment and their connection relationships in the power grid. It includes the layout of main equipment such as transformers, circuit breakers, switches, and busbars to ensure the safe and stable operation of the power system.

[0003] In practical applications, the accuracy of the wiring diagram of a power grid substation is directly related to the normal operation of the power grid and the convenience of subsequent maintenance. Traditional wiring diagrams are mostly stored in paper form or saved as electronic drawings. Manually identifying these complex drawings, especially when dealing with a large number of equipment and complex connection relationships, is not only time-consuming and laborious but also prone to errors or omissions. Summary of the Invention

[0004] In view of this, the present invention provides an intelligent recognition method, device, equipment and storage medium for the wiring diagram of a power grid substation to solve the technical problem that the existing wiring diagram of a power grid substation needs to be manually recognized, which is not only time-consuming and laborious but also prone to errors or omissions.

[0005] In a first aspect, the present invention provides an intelligent recognition method for the wiring diagram of a power grid substation, including: obtaining the wiring diagram of the power grid substation to be recognized; performing image preprocessing on the wiring diagram of the power grid substation; using an edge detection algorithm to perform image recognition on the preprocessed wiring diagram of the power grid substation to obtain the key parts of the equipment and the key parts of the connection lines; comparing the key parts of the equipment with the pre-stored standard equipment images to match the corresponding equipment labels for the key parts of the equipment; and obtaining the connection results of each matched equipment label with other equipment labels through the key parts of the connection lines according to the connection relationship between the key parts of the equipment and the key parts of the connection lines.

[0006] An intelligent recognition method for the wiring diagram of a power grid substation in the present invention. By obtaining the wiring diagram of the power grid substation to be recognized, performing image preprocessing on the wiring diagram of the power grid substation, using an edge detection algorithm to perform image recognition on the preprocessed wiring diagram of the power grid substation, obtaining the key parts of the equipment and the key parts of the connection lines, comparing the key parts of the equipment with the pre-stored standard equipment images, matching the corresponding equipment labels for the key parts of the equipment, and according to the connection relationship between the key parts of the equipment and the key parts of the connection lines, obtaining the connection results of each matched equipment label through the key parts of the connection lines and other equipment labels, it is possible to realize the intelligent recognition of the wiring diagram of the power grid substation, avoiding the situation that manual recognition is not only time-consuming and laborious, but also prone to errors or omissions.

[0007] At the same time, through image preprocessing and edge detection algorithms, the key parts of the equipment and the key parts of the connection lines can be recognized more accurately. By comparing and matching the key parts of the equipment with the standard equipment images, it can be ensured that each equipment is correctly recognized and marked, thereby improving the overall recognition accuracy.

[0008] Furthermore, using an edge detection algorithm to perform image recognition on the preprocessed wiring diagram of the power grid substation to obtain the key parts of the equipment and the key parts of the connection lines includes: detecting the preprocessed wiring diagram of the power grid substation through the edge detection algorithm to generate a binary wiring edge diagram of the power grid substation; using a contour detection algorithm to detect the closed figures with closed edges in the wiring edge diagram of the power grid substation, and screening out the closed figures with an area larger than the minimum threshold in the closed figures. If the closed figures with an area larger than the minimum threshold do not contain other closed figures with an area larger than the minimum threshold, then the closed figures with an area larger than the minimum threshold are the key parts of the equipment; using a contour detection algorithm to detect the non-closed edges or straight-line figures in the wiring edge diagram of the power grid substation, and the non-closed edges or straight-line figures are the key parts of the connection lines.

[0009] In this method, by generating a binary wiring edge diagram of the power grid substation, the image information can be simplified, facilitating subsequent contour detection. By screening out the closed figures with an area larger than the minimum threshold, irrelevant noise and smaller figures can be excluded, improving the recognition accuracy.

[0010] Furthermore, according to the connection relationship between the key parts of the equipment and the key parts of the connection lines, obtaining the connection results of each matched equipment label through the key parts of the connection lines and other equipment labels includes: identifying whether the key parts of the connection lines on each key part of the equipment in the wiring edge diagram of the power grid substation are connected to other key parts of the equipment; if the key parts of the connection lines are not connected to other key parts of the equipment, then record the key parts of the connection lines as the parts to be excluded; if the key parts of the connection lines are connected to other key parts of the equipment, then record the connection results of the equipment labels corresponding to the key parts of the equipment through the key parts of the connection lines and other equipment labels.

[0011] In this method, by identifying whether the key part of the connection line on the key part of the device is connected to the key part of other devices, the key part of the connection line that is not connected to the key part of other devices is taken as the part to be removed, which can reduce the influence of incorrect connections on the recognition result.

[0012] Further, after obtaining the connection results between the key part of the connection line and other device tags for each matched device tag, it includes: analyzing in the connection results whether the two device tags connected at both ends of the current key part of the connection line are mutually in each other's connection device set, where each device tag is preset with a corresponding connection device set, and the connection device set includes several device tags that the current device tag is allowed to connect to; if the two device tags are not mutually in each other's connection device set, then mark the current key part of the connection line as the part to be removed, and delete or retain the part to be removed based on the user input instruction.

[0013] In this method, by analyzing whether the device tags at both ends of the key part of the connection line are mutually in each other's connection device set, the incorrect connection relationship can be further verified and corrected, and the user is allowed to perform operations of deleting or retaining the part to be removed based on the analysis result, increasing the flexibility and adaptability of the method.

[0014] Further, perform image preprocessing on the wiring diagram of the power grid substation, including: converting the wiring diagram of the power grid substation from the spatial domain to the frequency domain through Fourier transform to obtain the representation of the wiring diagram of the power grid substation in the frequency domain, and the conversion formula is:

[0015]

[0016] where F(u, v) is the representation of the wiring diagram of the power grid substation in the frequency domain after Fourier transform; M and N are respectively the width and height of the wiring diagram of the power grid substation; I(x, y) is the pixel value of the original image of the wiring diagram of the power grid substation in the spatial domain; x and y are the pixel coordinates in the time domain; u and v are the coordinates in the frequency domain; i is the imaginary unit;

[0017] Calculate the main direction angle through the representation of the wiring diagram of the power grid substation in the frequency domain after Fourier transform, and the calculation formula is:

[0018]

[0019] where θ is the main direction angle; |F(u, v)| is the amplitude of the Fourier transform result; tan -1 represents the arctangent function;

[0020] According to the main direction angle, use the rotation matrix to perform coordinate rotation correction on the pixel coordinates of the wiring diagram of the power grid substation to obtain the wiring diagram of the power grid substation after rotation correction, and the coordinate rotation correction formula is:

[0021]

[0022] Among them, x ′ and y ′ are the pixel coordinates after rotation correction; R(θ) is the rotation matrix.

[0023] In this method, by calculating the main direction angle and performing coordinate rotation correction, the image can be aligned, and the recognition error caused by the shooting angle can be reduced.

[0024] Furthermore, after performing coordinate rotation correction on the pixel coordinates of the grid substation wiring diagram using the rotation matrix according to the main direction angle to obtain the rotated and corrected grid substation wiring diagram, it includes: calculating the gradient of the rotated and corrected grid substation wiring diagram, and the gradient calculation formula is:

[0025]

[0026] Among them, I ′ (x ′ , y ′ ) is the image pixel value of the rotated and corrected grid substation wiring diagram; is the gradient of the corrected grid substation wiring diagram; and are the partial derivatives of the image in the x ′ and y ′ directions respectively;

[0027] According to the gradient of the rotated and corrected grid substation wiring diagram, perform smoothing correction on the rotated and corrected grid substation wiring diagram through the interpolation formula, and the smoothing correction formula is:

[0028]

[0029] Among them, I smooth (x ′ , y ′ ) is the image pixel value after smoothing correction; I′(↓y′) is the image pixel value before smoothing correction; dn is the small increment along the gradient direction for integral smoothing.

[0030] In this method, by calculating the image gradient and performing smoothing correction based on the image gradient, the pixel values after rotation can be further optimized, and the pixel distortion generated during the rotation process can be eliminated.

[0031] Further, after performing smoothing correction on the rotation-corrected wiring diagram of the power grid substation according to the gradient of the rotation-corrected wiring diagram of the power grid substation through an interpolation formula, it includes: performing bilateral filtering to maintain the edge features of the rotation-corrected wiring diagram of the power grid substation and removing the noise and redundant pixel point information of the rotation-corrected wiring diagram of the power grid substation; performing adaptive histogram equalization on the wiring diagram of the power grid substation.

[0032] In this method, bilateral filtering can remove image noise and redundant pixel point information, and at the same time, adaptive histogram equalization can enhance the contrast of edges in the image, thereby improving the recognition accuracy of subsequent recognition steps.

[0033] In a second aspect, the present invention provides an intelligent recognition device for a wiring diagram of a power grid substation, including: a wiring diagram acquisition module for acquiring the wiring diagram of the power grid substation to be recognized; an image preprocessing module for performing image preprocessing on the wiring diagram of the power grid substation; a key part recognition module for performing image recognition on the preprocessed wiring diagram of the power grid substation using an edge detection algorithm to obtain the key parts of the equipment and the key parts of the connection lines; an equipment label matching module for comparing the key parts of the equipment with the pre-stored standard equipment images to match the corresponding equipment labels for the key parts of the equipment; a connection result acquisition module for obtaining the connection results of each matched equipment label through the key parts of the connection lines and other equipment labels according to the connection relationship between the key parts of the equipment and the key parts of the connection lines.

[0034] In a third aspect, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the intelligent recognition method for the wiring diagram of the power grid substation in the first aspect or any corresponding embodiment thereof.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute the intelligent recognition method for the wiring diagram of the power grid substation in the first aspect or any corresponding embodiment thereof. Description of the Drawings

[0036] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1It is a schematic flowchart of the intelligent recognition method for the wiring diagram of the power grid substation in the embodiment of the present invention;

[0038] Figure 2 It is a structural block diagram of the intelligent recognition device for the wiring diagram of the power grid substation in the embodiment of the present invention;

[0039] Figure 3 It is a schematic diagram of the hardware structure of the computer device in the embodiment of the present invention. Detailed implementation manners

[0040] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0041] Currently, the wiring diagrams of power grid substations are mostly stored in paper form or saved in the form of electronic drawings. Manually identifying these complex drawings is not only time-consuming and laborious but also prone to errors or omissions, especially when dealing with a large number of devices and complex connection relationships. This method requires a high level of professional quality from power design engineers and is likely to lead to an increase in labor costs and a decrease in work efficiency.

[0042] In view of this, the embodiments of the present invention propose an intelligent recognition method for the wiring diagram of a power grid substation. By introducing image correction, edge detection, contour recognition, and connection relationship rationality verification technologies, it can efficiently and accurately identify the devices and connection lines in the wiring diagram of the power grid substation and automatically generate connection relationships. This method effectively solves the problems of imperfect image distortion processing, difficulty in distinguishing devices and connection lines, and insufficient connection relationship verification in the prior art. Through intelligent recognition and an interactive interface, the present invention not only improves the recognition accuracy and efficiency but also allows users to manually adjust the recognition results to ensure that the generated wiring diagram complies with the design specifications of the power system.

[0043] According to the embodiments of the present invention, an embodiment of an intelligent recognition method for the wiring diagram of a power grid substation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0044] The intelligent recognition method for the wiring diagram of a power grid substation provided in this embodiment can be used in intelligent mobile devices or servers, etc. As Figure 1 shown, the intelligent recognition method for the wiring diagram of the power grid substation in the embodiment of the present invention includes the following steps:

[0045] Step S101: Obtain the wiring diagram of the power grid substation to be recognized.

[0046] Specifically, the wiring diagram of the power grid substation includes a wiring diagram obtained by scanning a drawing or an electronic document, which can completely describe the layout and connection relationship of electrical equipment in the power grid substation.

[0047] For traditional paper wiring diagrams of power grid substations, a scanning device can be used to convert the drawing into a digital image (such as PDF, JPEG, PNG format). Through high-resolution scanning, ensure that the image clarity is high enough for subsequent image processing and recognition.

[0048] If the wiring diagram of the power grid substation already exists in a digital engineering design software (such as AutoCAD, Visio, etc.), then the electronic document input (such as PDF, DXF, DWG, etc.) can be directly used. These formats save the complete graphic structure information and can be directly processed and parsed.

[0049] Step S102: Perform image preprocessing on the wiring diagram of the power grid substation.

[0050] Specifically, after collecting and obtaining the wiring diagram of the power grid substation, it is necessary to perform image correction, filtering, image enhancement, etc. to improve the accuracy of subsequent detection and recognition.

[0051] Step S103: Use an edge detection algorithm to perform image recognition on the preprocessed wiring diagram of the power grid substation to obtain the key parts of the equipment and the key parts of the connection lines.

[0052] The key parts of the equipment include various equipment graphics in the power grid substation. Based on the Canny edge detection algorithm, each equipment graphic is extracted from the wiring diagram of the power grid substation to obtain the key parts of the equipment.

[0053] The key parts of the connection lines include various types of lines, such as straight lines, broken lines, and curves, etc. These lines are connected to equipment graphics at both ends. By recognizing specific lines, the key parts of the connection lines can be obtained.

[0054] Step S104: Compare the key parts of the equipment with the pre-stored standard equipment images and match the corresponding equipment labels for the key parts of the equipment.

[0055] Specifically, the standard equipment image is a binary edge map of the equipment. The standard equipment images are pre-stored in the database, and a equipment label is associated with the standard equipment images.

[0056] Perform corresponding binarization processing on the key parts of the device, then compare the key parts of the device with the standard device images to obtain the similarity degree. Take the standard device image with the highest similarity degree as the matched standard device image, and take the device label associated with the standard device image as the matched device label.

[0057] In one example, by scaling the key parts of the device and the standard device images to the same size, and then comparing the differences in pixel points to obtain the similarity degree. Among them, the more identical pixel points, the higher the similarity degree.

[0058] Step S105, according to the connection relationship between the key parts of the device and the key parts of the connection line, obtain the connection result of each matched device label through the key parts of the connection line and other device labels.

[0059] Specifically, one device label corresponds to one device.

[0060] Each key part of the device matches a corresponding device label. According to the connection relationship between the key parts of the device and the key parts of the connection line, record the connection relationship between the corresponding device label and other device labels, and then obtain the connection result.

[0061] The connection result includes the connection relationship between the device labels corresponding to each key part of the device identified from the wiring diagram of the power grid substation.

[0062] An intelligent recognition method for the wiring diagram of a power grid substation according to an embodiment of the present invention, by obtaining the wiring diagram of the power grid substation to be recognized, performing image preprocessing on the wiring diagram of the power grid substation, using an edge detection algorithm to perform image recognition on the preprocessed wiring diagram of the power grid substation, obtaining the key parts of the device and the key parts of the connection line, comparing the key parts of the device with the pre-stored standard device images, matching the corresponding device labels for the key parts of the device, and according to the connection relationship between the key parts of the device and the key parts of the connection line, obtaining the connection result of each matched device label through the key parts of the connection line and other device labels, can realize the intelligent recognition of the wiring diagram of the power grid substation, avoiding the situation that manual recognition is not only time-consuming and laborious, but also prone to errors or omissions.

[0063] At the same time, through image preprocessing and edge detection algorithm, the key parts of the device and the key parts of the connection line can be recognized more accurately. Comparing and matching the key parts of the device with the standard device images can ensure that each device is correctly recognized and marked, thereby improving the overall recognition accuracy.

[0064] In some embodiments, step S102, performing image preprocessing on the wiring diagram of the power grid substation includes:

[0065] Step S1021: Transform the wiring diagram of the power grid substation from the spatial domain to the frequency domain through Fourier transform to obtain the representation of the wiring diagram of the power grid substation in the frequency domain. The transformation formula is as follows:

[0066]

[0067] where F(u, v) is the representation of the wiring diagram of the power grid substation in the frequency domain after Fourier transform; M and N are the width and height of the wiring diagram of the power grid substation respectively; I(x, y) is the pixel value of the original image of the wiring diagram of the power grid substation in the spatial domain; x and y are the pixel coordinates in the time domain; u and v are the coordinates in the frequency domain; i is the imaginary unit;

[0068] Step S1022: Calculate the main direction angle through the representation of the wiring diagram of the power grid substation in the frequency domain after Fourier transform. The calculation formula is as follows:

[0069]

[0070] where θ is the main direction angle; |F(u, v)| is the amplitude of the Fourier transform result; tan -1 represents the arctangent function;

[0071] Step S1023: According to the main direction angle, use the rotation matrix to perform coordinate rotation correction on the pixel coordinates of the wiring diagram of the power grid substation to obtain the wiring diagram of the power grid substation after rotation correction. The coordinate rotation correction formula is as follows:

[0072]

[0073] where x ′ and y ′ are the pixel coordinates after rotation correction; R(θ) is the rotation matrix.

[0074] Specifically, according to the identified main direction angle θ, use the rotation matrix to adjust the pixel coordinates of the image according to the rotation angle, and perform rotation correction on the image to make the image present a front view.

[0075] In this method, by calculating the main direction angle and performing coordinate rotation correction, the image can be aligned, and the recognition error caused by the shooting angle can be reduced.

[0076] Furthermore, in step S1023, after using the rotation matrix to perform coordinate rotation correction on the pixel coordinates of the wiring diagram of the power grid substation according to the main direction angle to obtain the wiring diagram of the power grid substation after rotation correction, it includes:

[0077] Step S1024: Calculate the gradient of the wiring diagram of the power grid substation after rotation correction. The gradient calculation formula is as follows:

[0078]

[0079] Among them, I ′ (x ′ , y ′ ) is the image pixel value of the grid substation wiring diagram after rotation correction; is the gradient of the corrected grid substation wiring diagram; and are the partial derivatives of the image in the x ′ and y ′ directions respectively;

[0080] Step S1025, according to the gradient of the rotated and corrected grid substation wiring diagram, perform smoothing correction on the rotated and corrected grid substation wiring diagram through the interpolation formula. The smoothing correction formula is:

[0081]

[0082] Among them, I smooth (x ′ , y ′ ) is the image pixel value after smoothing correction; I′(↓y′) is the image pixel value before smoothing correction; dn is the small increment along the gradient direction for integral smoothing.

[0083] Through smoothing correction, the output image pixel value I smooth (x ′ , y ′ ) should be in the same range as the original grid substation wiring diagram image. Usually, in the case of a grayscale image, the range of pixel values is [0, 255]. After smoothing correction, the highlight areas (with larger value ranges) and dark areas (with smaller value ranges) of the image will show a more natural transition.

[0084] If the input image is a black-and-white image, then the value range of I smooth (x ′ , y ′ ) is within the range of [0, 255]. If the input image is a color image, then the R, G, and B components of each pixel are respectively within the range of [0, 255].

[0085] By calculating the image gradient and performing smoothing correction based on the image gradient, the rotated pixel values can be further optimized, and the pixel distortion generated during the rotation process can be eliminated.

[0086] Furthermore, in step S1025, after performing smoothing correction on the rotated and corrected grid substation wiring diagram through the interpolation formula according to the gradient of the rotated and corrected grid substation wiring diagram, it includes:

[0087] Step S1026, perform bilateral filtering to preserve the edge features of the rotated and corrected wiring diagram of the power grid substation and remove the noise and redundant pixel information in the rotated and corrected wiring diagram of the power grid substation;

[0088] Step S1027, perform adaptive histogram equalization on the wiring diagram of the power grid substation.

[0089] Specifically, after completing image smoothing and correction, bilateral filtering is used to remove noise and redundant pixel information while preserving the edge features of the image, and adaptive histogram equalization is used to enhance the contrast of the edges in the image, thereby improving the recognition accuracy of subsequent recognition steps.

[0090] Furthermore, in step S103, an edge detection algorithm is used to perform image recognition on the preprocessed wiring diagram of the power grid substation to obtain the key parts of the equipment and the key parts of the connection lines, including:

[0091] Step S1031, detect the preprocessed wiring diagram of the power grid substation through an edge detection algorithm to generate a binary wiring edge diagram of the power grid substation;

[0092] Step S1032, use a contour detection algorithm to detect the closed figures with closed edges in the wiring edge diagram of the power grid substation, and filter out the closed figures with an area greater than the minimum threshold in the closed figures. If the closed figures with an area greater than the minimum threshold do not contain other closed figures with an area greater than the minimum threshold, the closed figures with an area greater than the minimum threshold are the key parts of the equipment;

[0093] Step S1033, use a contour detection algorithm to detect the non-closed edges or straight-line figures in the wiring edge diagram of the power grid substation. The non-closed edges or straight-line figures are the key parts of the connection lines.

[0094] Specifically, the Canny edge detection algorithm is used as the edge detection algorithm.

[0095] Use the Canny edge detection algorithm to detect the preprocessed wiring diagram of the power grid substation to generate a binary wiring edge diagram of the power grid substation.

[0096] In the wiring edge diagram of the power grid substation, all the edges in the image will be extracted and presented in the form of black and white contrast. The edge pixels are displayed as white, and the background pixels are displayed as black.

[0097] Use the contour detection algorithm to further detect the key parts of the equipment and the key parts of the connection lines.

[0098] By generating a binary wiring edge diagram of the power grid substation, the image information can be simplified, facilitating subsequent contour detection. By filtering out the closed figures with an area greater than the minimum threshold, irrelevant noise and smaller figures can be excluded, improving the recognition accuracy.

[0099] Further, in step S105, according to the connection relationship between the key parts of the device and the key parts of the connection line, obtain the connection result of each matching device label through the key parts of the connection line and other device labels, including:

[0100] Step S1051, identify whether the key parts of the connection line on each key part of the device in the wiring edge diagram of the power grid substation are connected to other key parts of the device;

[0101] Step S1052, if the key part of the connection line is not connected to other key parts of the device, record the key part of the connection line as the part to be excluded;

[0102] Step S1053, if the key part of the connection line is connected to other key parts of the device, record the connection result of the device label corresponding to the key part of the device through the key part of the connection line and other device labels.

[0103] Specifically, according to the binary wiring edge diagram of the power grid substation, identify whether the key parts of the connection line on each key part of the device are connected to other key parts of the device. If there is no connection, record the key part of the connection line as the part to be excluded. If there is a connection, record the connection result of each device label through the key part of the connection line and other device labels.

[0104] It should be noted that by analyzing the binary wiring edge diagram of the power grid substation, it is possible to automatically identify whether there is a key part of the connection line connected to each key part of the device. The design purpose of this step is to reduce manual intervention and realize the automatic identification of the connection relationship between devices and lines in the wiring of the power grid substation.

[0105] In this method, by identifying whether the key parts of the connection line on the key part of the device are connected to other key parts of the device, and taking the key parts of the connection line not connected to other key parts of the device as the parts to be excluded, the influence of incorrect connections on the identification result can be reduced.

[0106] Further, after obtaining the connection result of each matching device label through the key parts of the connection line and other device labels in step S105, including:

[0107] Step S106, analyze whether the two device labels connected at both ends of the current key part of the connection line are located in each other's connection device sets in the connection result, where each device label is pre-set with a corresponding connection device set, and the connection device set includes several device labels allowed to be connected by the current device label;

[0108] Step S107: If the two device tags are not in each other's connection device sets, mark the key part of the current connection line as the part to be removed, and delete or retain the removed part based on the user input instruction.

[0109] Specifically, set the connectable limit conditions in advance in each device tag through the connection device set, and analyze whether the two devices connected at both ends of each key part of the connection line in the connection result are connectable; if they are not connectable, extract the key part of the connection line as the part to be removed; if they are connectable, retain it.

[0110] When it is determined whether the two device tags connected at both ends of the key part of the current connection line are in each other's connection device sets, it is considered that the connectable limit conditions are met.

[0111] The connection device set includes several device tags that the current device tag is allowed to connect to. When other devices connected to device A are in the connection device set B, it is considered connectable; otherwise, it is considered non-connectable.

[0112] Use the preprocessed image as the wiring diagram of the power grid substation recognized by intelligence. At the same time, dye all the key parts of the non-connectable connection lines and mark them as the parts to be removed. The user can select the dyed removed parts to be retained through the front-end operation interface and clear the un-retained removed parts.

[0113] It should be understood that each device in the power grid substation has its specific connection rules. For example, some devices can only be connected to specific types of devices and cannot be randomly connected to other devices. The design of this step ensures that the generated wiring diagram conforms to the design specifications of the actual power system through the connectable limit conditions of the devices. The connection device set B in each device tag predefines which devices the device can be connected to. Through this limit condition, it can be automatically determined whether the connection between two devices conforms to the specifications and avoid the occurrence of unreasonable connections. If the connection between two devices does not meet the preset connectable conditions, the system will automatically mark this connection line as the "part to be removed", ensuring that only the connection relationships that conform to the power grid safety specifications are retained in the finally generated wiring diagram.

[0114] Through this automated connection verification mechanism, potential problems caused by unreasonable connections between devices can be avoided, ensuring the accuracy of the device connection relationships.

[0115] Meanwhile, users can review and retain the removed connection parts through the front-end interface, further enhancing the flexibility and customization of the recognition results. In some special power grid designs, there may be complex connection relationships that are difficult for the system to judge. Through this user interaction design, users can make adjustments according to the actual situation to ensure that the wiring diagram meets the actual requirements. Through automated connection rationality verification and user adjustment, an intelligent wiring diagram that meets the requirements of power system design can be finally generated.

[0116] To verify the beneficial effects of the embodiments of the present invention, scientific demonstrations are carried out through economic benefit calculations and simulation experiments.

[0117] The simulation experiment uses an actual power grid wiring diagram, which contains several devices (such as transformers, circuit breakers, buses, etc.) and their connecting lines. The test contents include image preprocessing, recognition and matching of key parts, and rationality verification of connection relationships, etc.

[0118] Test preparation:

[0119] The wiring diagram is scanned from a paper form into a high-resolution electronic image with a size of 2000x1500 pixels. The image contains 8 devices and 10 connecting lines, forming a typical layout of a power grid substation wiring diagram. The scanned image is saved in PNG format.

[0120] The system first performs a Fourier transform on the input wiring diagram to identify the main direction of the image and perform rotation correction to ensure that all devices are in a front view. The corrected image is processed by bilateral filtering to remove the noise in the image while retaining the edge information of the devices and connecting lines.

[0121] Test process:

[0122] After the power grid substation wiring diagram to be recognized is preprocessed, the Canny edge detection algorithm is used to generate a binary edge map of the power grid substation wiring. The binary edge map of the power grid substation wiring clearly shows the outlines of the devices and the boundaries of the connecting lines. White pixels represent the edges of the devices and connecting lines, and black pixels represent the background. Then, the contour detection algorithm is used to identify the closed device graphics and non-closed connecting line graphics to obtain the key parts of the devices and the key parts of the connecting lines. For each closed device contour, the graphics with an area larger than the set threshold are screened to ensure that these devices are independent device symbols.

[0123] After the key parts of each device are recognized by contour, they are scaled and rotationally matched with the standard device images of the devices in the database in binary form. According to the matching results, the recognized devices are inserted into the corresponding device labels, generating a preliminary connection relationship between the device labels and the key parts of the devices. After the matching is completed, the connection status of each device label is automatically recorded according to the connection situation of the connecting lines.

[0124] After generating the preliminary connection relationship, it is verified whether the devices at both ends of the key parts of each connection line can be reasonably connected. The set of connected devices included in each device label is used to compare the rationality of the connection result. If the devices at both ends of a certain connection line are not in the set of connected devices, the key part of this connection line is marked as the "part to be removed". After the marking is completed, all the removed parts are displayed by coloring, and the user can choose to retain or finally remove these removed parts on the interface.

[0125] Test object:

[0126] To prove the innovation and advantages of the intelligent recognition method for the power grid substation wiring diagram of the present invention, the embodiments of the present invention also compare the automatic recognition methods for power grid wiring diagrams in the prior art through experiments. The prior art includes the traditional Canny edge detection plus template matching method, and the method of using Convolutional Neural Networks (CNN) for recognition. The experiments tested the accuracy of each method in recognizing devices and connection lines, the effect of judging the rationality of connection relationships, and the recognition efficiency. The experimental data is shown in Table 1.

[0127] Table 1 Data Record Table

[0128]

[0129] It can be seen from the tabular data that the method of the present invention is significantly superior to the traditional Canny algorithm and CNN recognition algorithm in multiple key indicators, reflecting the innovation and advantages of the present invention.

[0130] Device recognition accuracy: The accuracy of the present invention in device recognition reaches 98.7%, which is much higher than 85.3% of the traditional Canny algorithm and 92.5% of the CNN algorithm. This shows that through bilateral filtering preprocessing, contour detection, and feature matching technology for the key parts of devices, the present invention can more accurately recognize the devices in the wiring diagram, avoiding the recognition deviation caused by noise interference and incomplete edges in the Canny algorithm, and also avoiding the inaccurate recognition problem caused by over-reliance on training data in the CNN algorithm.

[0131] Connection line recognition accuracy: The connection line recognition accuracy of the present invention is 96.2%, which is also superior to the traditional method. The connection line recognition rate of the traditional Canny algorithm is only 80.1%. This disadvantage is mainly due to its improper handling of complex connection lines, resulting in ineffective recognition of some connection line parts. By effectively distinguishing between closed and non-closed shapes, the present invention can accurately recognize the relationship between devices and connection lines, especially the non-closed line parts are processed more accurately.

[0132] Judgment of connection rationality: In terms of judging connection rationality, the present invention sets connection limit conditions through the set of connected devices in the device tags, achieving an accuracy rate of 97.8%, significantly better than 70.4% of the traditional solution B and 90.6% of the CNN recognition solution. This indicates that the present invention can not only identify devices and connection lines, but also automatically eliminate unreasonable connection lines through the connection limit conditions, thus ensuring that the generated wiring diagram conforms to the actual power grid design specifications. However, due to the lack of verification of connection rationality, the traditional Canny algorithm often has unreasonable connections between devices.

[0133] Number of invalid connection lines eliminated: Solution A eliminated 8 invalid connection lines. In contrast, Solution B eliminated 12, and Solution C eliminated 10. This shows that the present invention has higher accuracy in identifying connection lines and can eliminate unreasonable connection lines on the premise of reducing misjudgment.

[0134] Processing time: The processing time of the present invention is 2.1 seconds, much faster than 3.5 seconds of the traditional Canny algorithm and 4.2 seconds of CNN recognition. This shows that the present invention has significant advantages in computing efficiency, can quickly process complex wiring diagrams, and provide instant feedback to users.

[0135] Frequency of user intervention: The frequency of user intervention of the present invention is only 2 times, much lower than 8 times of the traditional solution and 5 times of the CNN algorithm. The reduction in the number of user interventions means that the present invention has a higher level of automation, can independently complete most of the recognition and connection judgment tasks, reduce the need for manual adjustment by users, and improve the overall efficiency.

[0136] In summary, through the above data analysis, it can be concluded that the present invention is superior to the prior art in terms of the accuracy of device and connection line recognition, verification of connection relationship rationality, processing speed, and user-friendliness, demonstrating strong innovation and practicality. These results not only prove the superiority of the present invention in automatically processing wiring diagrams, but also indicate its potential application value in power grid design and maintenance.

[0137] The embodiment of the present invention also provides an intelligent recognition device for the wiring diagram of a power grid substation, as Figure 2 shown, including:

[0138] A wiring diagram acquisition module 201 for acquiring the wiring diagram of the power grid substation to be recognized;

[0139] An image preprocessing module 202 for preprocessing the wiring diagram of the power grid substation;

[0140] A key part recognition module 203 for performing image recognition on the preprocessed wiring diagram of the power grid substation using an edge detection algorithm to obtain the key parts of the devices and the key parts of the connection lines;

[0141] The device label matching module 204 is used to compare the key parts of the device with the pre-stored standard device images, and match the corresponding device labels for the key parts of the device;

[0142] The connection result obtaining module 205 is used to obtain the connection results of each matched device label with other device labels through the key parts of the connection lines according to the connection relationship between the key parts of the device and the key parts of the connection lines.

[0143] The intelligent recognition device for the wiring diagram of the power grid substation in the embodiment of the present invention can realize the intelligent recognition of the wiring diagram of the power grid substation by obtaining the wiring diagram of the power grid substation to be recognized, performing image preprocessing on the wiring diagram of the power grid substation, using the edge detection algorithm to perform image recognition on the preprocessed wiring diagram of the power grid substation to obtain the key parts of the device and the key parts of the connection lines, comparing the key parts of the device with the pre-stored standard device images, matching the corresponding device labels for the key parts of the device, and obtaining the connection results of each matched device label with other device labels through the key parts of the connection lines according to the connection relationship between the key parts of the device and the key parts of the connection lines, avoiding the situation that manual recognition is not only time-consuming and laborious, but also prone to errors or omissions.

[0144] Further, the key part recognition module 203 includes:

[0145] The image binarization module is used to detect the preprocessed wiring diagram of the power grid substation through the edge detection algorithm to generate a binary wiring edge diagram of the power grid substation;

[0146] The device recognition module is used to detect the closed figures with closed edges in the wiring edge diagram of the power grid substation by using the contour detection algorithm, and screen out the closed figures with an area larger than the minimum threshold. If the closed figures with an area larger than the minimum threshold do not contain other closed figures with an area larger than the minimum threshold, the closed figures with an area larger than the minimum threshold are the key parts of the device;

[0147] The connection line recognition module is used to detect the non-closed edges or straight line figures in the wiring edge diagram of the power grid substation by using the contour detection algorithm, and the non-closed edges or straight line figures are the key parts of the connection lines.

[0148] Further, the connection result obtaining module 205 includes:

[0149] The connection judgment module is used to identify whether the key parts of the connection lines on each key part of the device in the wiring edge diagram of the power grid substation are connected to other key parts of the device;

[0150] The partial record elimination module is used to record the key parts of the connection lines as the eliminated parts if the key parts of the connection lines are not connected to other key parts of the device;

[0151] A connection result recording module, which is configured to record the connection result of the device label corresponding to the key part of the device and other device labels through the key part of the connection line if the key part of the connection line is connected to the key part of other devices.

[0152] Furthermore, the intelligent recognition device for the wiring diagram of the power grid substation further includes:

[0153] A connection result verification module, which is configured to analyze whether the two device labels connected at both ends of the current key part of the connection line are located in each other's connection device sets respectively. Each device label is pre-set with a corresponding connection device set, and the connection device set includes several device labels allowed to be connected by the current device label.

[0154] An elimination part marking module, which is configured to mark the current key part of the connection line as an elimination part if the two device labels are not located in each other's connection device sets respectively, and delete or retain the elimination part based on the user input instruction.

[0155] Furthermore, the image preprocessing module includes:

[0156] A Fourier transform module, which is configured to transform the wiring diagram of the power grid substation from the spatial domain to the frequency domain through Fourier transform to obtain the representation of the wiring diagram of the power grid substation in the frequency domain. The transformation formula is:

[0157]

[0158] where F(u, v) is the representation of the wiring diagram of the power grid substation in the frequency domain after Fourier transform; M and N are the width and height of the wiring diagram of the power grid substation respectively; I(x, y) is the pixel value of the original image of the wiring diagram of the power grid substation in the spatial domain; x and y are the pixel coordinates in the time domain; u and v are the coordinates in the frequency domain; i is the imaginary unit.

[0159] A main direction angle calculation module, which is configured to calculate the main direction angle through the representation of the wiring diagram of the power grid substation in the frequency domain after Fourier transform. The calculation formula is:

[0160]

[0161] where θ is the main direction angle; |F(u, v)| is the amplitude of the Fourier transform result; tan -1 represents the arctangent function;

[0162] A rotation correction module, which is configured to perform coordinate rotation correction on the pixel coordinates of the wiring diagram of the power grid substation according to the main direction angle by using a rotation matrix to obtain the rotated and corrected wiring diagram of the power grid substation. The coordinate rotation correction formula is:

[0163]

[0164] Among them, x ′ and y ′ are the pixel coordinates after rotation correction; R(θ) is the rotation matrix.

[0165] Furthermore, the image preprocessing module 202 further includes:

[0166] A gradient calculation module, which is used to calculate the gradient of the power grid substation wiring diagram after rotation correction. The gradient calculation formula is:

[0167]

[0168] Among them, I ′ (x ′ , y ' ) is the image pixel value of the power grid substation wiring diagram after rotation correction; is the gradient of the power grid substation wiring diagram after correction; and are the partial derivatives of the image in the x ' and y ′ directions respectively;

[0169] A smoothing correction module, which is used to perform smoothing correction on the power grid substation wiring diagram after rotation correction according to the gradient of the power grid substation wiring diagram after rotation correction through an interpolation formula. The smoothing correction formula is:

[0170]

[0171] Among them, I smooth (x ′ , y ′ ) is the image pixel value after smoothing correction; I′(↓y′) is the image pixel value before smoothing correction; dn is a small increment along the gradient direction for integral smoothing.

[0172] Furthermore, the image preprocessing module 202 further includes:

[0173] A filtering module, which is used to maintain the edge features of the power grid substation wiring diagram after rotation correction through bilateral filtering, and remove the noise and redundant pixel point information of the power grid substation wiring diagram after rotation correction;

[0174] A histogram equalization module, which is used to perform adaptive histogram equalization on the power grid substation wiring diagram.

[0175] The embodiment of the present invention also provides a structural schematic diagram of a computer device, as shown in Figure 3As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if needed, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as an array of servers, a set of blade servers, or a multi-processor system). Figure 3 In the figure, a processor 10 is taken as an example.

[0176] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above programmable logic device can be a complex programmable logic device, a field programmable gate array, a generic array logic, or any combination thereof.

[0177] Among them, the memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiments.

[0178] The memory 20 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 can include high-speed random access memory and can also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 can optionally include a memory remotely set relative to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0179] The memory 20 can include volatile memory, such as random access memory; the memory can also include non-volatile memory, such as flash memory, a hard disk, or a solid-state drive; the memory 20 can also include a combination of the above types of memory.

[0180] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30, and the output device 40 can be connected through a bus or other means.Figure 3 Take the bus connection as an example.

[0181] The input device 30 can receive input digital or character information, and generate key signal inputs related to the user settings and function controls of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED), and a haptic feedback device (e.g., a vibration motor), etc. The above display device includes, but is not limited to, a liquid crystal display, a light emitting diode, a display, and a plasma display. In some alternative embodiments, the display device may be a touch screen.

[0182] The embodiments of the present invention also provide a computer-readable storage medium. The methods according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the methods described herein can be stored as such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0183] A part of the present invention can be applied as a computer program product, such as computer program instructions. When executed by a computer, through the operation of the computer, the methods and / or technical solutions according to the present invention can be called or provided. Those skilled in the art should be able to understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible by the computer.

[0184] Although embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations fall within the scope of protection.

Claims

1. An intelligent identification method for a power grid plant wiring diagram, characterized in that: include: Obtain the wiring diagram of the power grid plant to be identified; Perform image preprocessing on power grid plant wiring diagrams; The edge detection algorithm is used to perform image recognition on the pre-processed power grid plant wiring diagram to obtain the key parts of the equipment and the key parts of the connecting lines; Comparing the key part of the device with a pre-stored standard device image, and matching a corresponding device tag for the key part of the device; According to the connection relationship between the device key part and the connection line key part, the connection result of each matched device tag through the connection line key part and other device tags is obtained.

2. The intelligent identification method of the power grid plant wiring diagram according to claim 1 is characterized in that: The edge detection algorithm is used to perform image recognition on the pre-processed power grid plant wiring diagram to obtain the key parts of the equipment and the key parts of the connecting lines, including: The pre-processed power grid plant wiring diagram is detected by edge detection algorithm to generate a binary power grid plant wiring edge diagram; Detect closed figures with closed edges in the power grid plant connection edge map using a contour detection algorithm, and screen the closed figures whose areas are greater than a minimum threshold among the closed figures; if the closed figures whose areas are greater than the minimum threshold do not contain other closed figures whose areas are greater than the minimum threshold, then the closed figures whose areas are greater than the minimum threshold are the key parts of the equipment; A contour detection algorithm is used to detect non-closed edges or straight line graphics in the power grid plant connection edge diagram, and the non-closed edges or the straight line graphics are key parts of the connecting line.

3. The intelligent identification method of the power grid plant wiring diagram according to claim 2 is characterized in that: The step of obtaining the connection result between each matched device tag and other device tags through the key part of the connection line according to the connection relationship between the key part of the device and the key part of the connection line includes: Identify whether the key part of the connection line on each key part of the equipment in the power grid plant connection edge diagram is connected to other key parts of the equipment; If the key part of the connecting line is not connected to the key part of other equipment, the key part of the connecting line is recorded as a discarded part; If the key part of the connection line is connected to the key part of other equipment, the connection result between the equipment tag corresponding to the key part of the equipment and the other equipment tags through the key part of the connection line is recorded.

4. The intelligent identification method of power grid plant wiring diagram according to claim 1 is characterized in that: After obtaining the connection results of each matching device tag through the connection line key part and other device tags, including: Analyze the connection result to determine whether two device tags connected at both ends of the key portion of the current connection line are located in each other's connection device set, wherein each device tag is pre-set with a corresponding connection device set, and the connection device set includes a number of device tags that the current device tag allows to connect; If the two device tags are not located in each other's connected device set, the key part of the current connection line is marked as a discarded part, and the discarded part is deleted or retained based on the user input instruction.

5. The intelligent identification method of power grid plant wiring diagram according to claim 1 is characterized in that: The image preprocessing of the power grid plant wiring diagram includes: The power grid plant wiring diagram is converted from the spatial domain to the frequency domain through Fourier transform, and the representation of the power grid plant wiring diagram in the frequency domain is obtained. The conversion formula is: Among them, F(u,v) is the representation of the power grid plant wiring diagram in the frequency domain after Fourier transformation; M and N are the width and height of the power grid plant wiring diagram respectively; I(x,y) is the pixel value of the original image of the power grid plant wiring diagram in the spatial domain; x and y are the pixel coordinates in the time domain; u and v are the coordinates in the frequency domain; i is the imaginary unit; The main direction angle is calculated by Fourier transforming the power grid plant wiring diagram in the frequency domain. The calculation formula is: Among them, θ is the main direction angle; |F(u,v)| is the amplitude of the Fourier transform result; tan -1 represents the inverse tangent function; According to the main direction angle, the pixel coordinates of the power grid plant wiring diagram are corrected by using the rotation matrix to obtain the power grid plant wiring diagram after rotation correction. The coordinate rotation correction formula is: Among them, x ′ and ′ is the pixel coordinate after rotation correction; R(θ) is the rotation matrix.

6. The intelligent identification method of the power grid plant wiring diagram according to claim 5 is characterized in that: After the pixel coordinates of the power grid plant wiring diagram are rotated and corrected using a rotation matrix according to the main direction angle to obtain the power grid plant wiring diagram after rotation correction, the method includes: Calculate the gradient of the power plant wiring diagram after rotation correction. The gradient calculation formula is: Among them, I ′ (x ′ ,y ′ ) is the image pixel value of the power grid plant wiring diagram after rotation correction; is the gradient of the corrected power grid plant wiring diagram; and The images are ′ and ′ Partial derivatives in direction; According to the gradient of the power grid plant wiring diagram after rotation correction, the power grid plant wiring diagram after rotation correction is smoothed by the interpolation formula. The smoothing correction formula is: Among them, I smooth (x ′ ,y ′ ) is the image pixel value after smoothing correction; I′(↓y′) is the image pixel value before smoothing correction; dn is a small increment along the gradient direction, which is used for integral smoothing.

7. The intelligent identification method of power grid plant wiring diagram according to claim 6 is characterized in that: After smoothing the rotation-corrected power grid plant wiring diagram through an interpolation formula according to the gradient of the rotation-corrected power grid plant wiring diagram, the method includes: By using bilateral filtering, the edge features of the power grid plant wiring diagram after rotation correction are maintained, and the noise and redundant pixel information of the power grid plant wiring diagram after rotation correction are removed; Adaptive histogram equalization is performed on the power grid plant wiring diagram.

8. An intelligent recognition device for power grid plant wiring diagram, characterized in that: include: A wiring diagram acquisition module, used to acquire the wiring diagram of the power grid plant to be identified; An image preprocessing module is used to perform image preprocessing on the power grid plant wiring diagram; The key part identification module is used to perform image recognition on the pre-processed power grid plant wiring diagram using an edge detection algorithm to obtain the key parts of the equipment and the key parts of the connecting lines; A device label matching module, used for comparing the key part of the device with a pre-stored standard device image, and matching the corresponding device label for the key part of the device; The connection result acquisition module is used to acquire the connection result of each matched device tag through the key part of the connection line and other device tags according to the connection relationship between the key part of the device and the key part of the connection line.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the intelligent identification method for the power grid plant wiring diagram according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the intelligent identification method for a power grid plant wiring diagram according to any one of claims 1 to 7.

Images