Substation wiring diagram paper processing method and device, computer equipment and program product

Abstract

This application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing wiring diagrams of substations. The method includes: acquiring an image of a substation wiring diagram and performing quality enhancement processing on the image to obtain a processed image; performing optical character recognition (OCR) to obtain a title recognition result and determine the diagram type; based on the diagram type, performing region segmentation on the processed image to identify and locate the wiring diagram area, text area, and table area; parsing to obtain the structural data of each device in the wiring diagram; converting the data into standardized data for the power industry; and, provided the standardized data passes rule review, performing similarity matching between the standardized data and reference standardized data to obtain a matching result; and based on the matching result, outputting the quality review result of the wiring diagram. This method can improve the accuracy of wiring diagram review.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing wiring diagrams of substations. Background Technology

[0002] Electrical wiring diagrams are an important part of electrical engineering drawings. The design and description of the power system of the substation affect the safe and stable operation of the substation after its installation.

[0003] In related technologies, the review of wiring diagrams for power engineering currently relies mainly on manual methods, with computer-aided design software used for review. This method is inefficient, prone to errors and omissions, and requires high human and time costs, thus having obvious limitations. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing substation wiring diagrams that can improve the accuracy of wiring diagram review, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for processing wiring diagrams for substations, including:

[0006] Obtain an image of the substation wiring diagram and perform quality enhancement processing on the image to obtain a processed image;

[0007] Optical character recognition is performed on the title area of ​​the processed image to obtain the title recognition result, and the drawing type of the wiring diagram is determined based on the title recognition result;

[0008] Based on the drawing type, the processed image is segmented to identify and locate the wiring diagram area, text area, and table area of ​​the processed image;

[0009] The wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram.

[0010] The structural data is converted into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0011] Based on the matching results, the quality audit results of the wiring diagram are output.

[0012] In one embodiment, the step of performing quality enhancement processing on the image to obtain a processed image includes:

[0013] Identify the outer border of the largest rectangle in the image, and calculate the rotation angle of the outer border relative to a preset plane;

[0014] The image is straightened based on the rotation angle to obtain the straightened image;

[0015] The image after alignment is denoised to obtain the processed image.

[0016] In one embodiment, performing optical character recognition on the title area of ​​the processed image to obtain a title recognition result, and determining the drawing type of the wiring diagram based on the title recognition result, includes:

[0017] Based on a preset fixed position, locate the title area of ​​the processed image;

[0018] Optical character recognition is performed on the title area to obtain the title recognition result;

[0019] The title recognition result is semantically analyzed to extract key feature words. The key feature words are then matched with a preset drawing type keyword library. Based on the matching result, the drawing type of the wiring drawing is determined.

[0020] In one embodiment, the drawing types include main wiring diagrams, system wiring diagrams, and transformer substation configuration wiring diagrams.

[0021] In one embodiment, parsing the wiring diagram area, text area, and table area to obtain the structural data of each device in the wiring diagram includes:

[0022] Based on the table line features in the wiring diagram area, the wiring diagram area is divided into units based on electrical cabinets, and the image sub-region corresponding to each electrical cabinet unit is determined.

[0023] For each image sub-region, identify the electrical components inside the cabinet and output the coordinates and type of the electrical components;

[0024] Identify cells in the table area, perform text recognition on the image area in each cell, and output the text content corresponding to the cell;

[0025] The coordinate positions of the electrical components, the component types, the text areas, and the text content are integrated to obtain the structural data of each device in the wiring diagram; the text areas include descriptive text of the electrical components.

[0026] In one embodiment, the rule review process for the standardized data includes:

[0027] The standardized data is matched one by one with the preset review rules. If the processed parsing results meet all the pre-review review rules, the standardized data passes the rule review.

[0028] Secondly, this application also provides a substation wiring diagram processing device, comprising:

[0029] The acquisition module is used to acquire images of the wiring diagrams of the substation and perform quality improvement processing on the images to obtain processed images;

[0030] The recognition module is used to perform optical character recognition on the title area of ​​the processed image, obtain the title recognition result, and determine the drawing type of the wiring diagram based on the title recognition result;

[0031] The recognition module is also used to perform region segmentation on the processed image based on the drawing type, and to identify and locate the wiring diagram area, text area and table area of ​​the processed image;

[0032] The parsing module is used to parse the wiring diagram area, text area, and table area to obtain the structural data of each device in the wiring diagram;

[0033] The matching module is used to convert the structural data into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0034] The output module is used to output the quality review result of the wiring diagram based on the matching result.

[0035] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0036] Obtain an image of the substation wiring diagram and perform quality enhancement processing on the image to obtain a processed image;

[0037] Optical character recognition is performed on the title area of ​​the processed image to obtain the title recognition result, and the drawing type of the wiring diagram is determined based on the title recognition result;

[0038] Based on the drawing type, the processed image is segmented to identify and locate the wiring diagram area, text area, and table area of ​​the processed image;

[0039] The wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram.

[0040] The structural data is converted into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0041] Based on the matching results, the quality audit results of the wiring diagram are output.

[0042] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0043] Obtain an image of the substation wiring diagram and perform quality enhancement processing on the image to obtain a processed image;

[0044] Optical character recognition is performed on the title area of ​​the processed image to obtain the title recognition result, and the drawing type of the wiring diagram is determined based on the title recognition result;

[0045] Based on the drawing type, the processed image is segmented to identify and locate the wiring diagram area, text area, and table area of ​​the processed image;

[0046] The wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram.

[0047] The structural data is converted into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0048] Based on the matching results, the quality audit results of the wiring diagram are output.

[0049] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0050] Obtain an image of the substation wiring diagram and perform quality enhancement processing on the image to obtain a processed image;

[0051] Optical character recognition is performed on the title area of ​​the processed image to obtain the title recognition result, and the drawing type of the wiring diagram is determined based on the title recognition result;

[0052] Based on the drawing type, the processed image is segmented to identify and locate the wiring diagram area, text area, and table area of ​​the processed image;

[0053] The wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram.

[0054] The structural data is converted into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0055] Based on the matching results, the quality audit results of the wiring diagram are output.

[0056] The aforementioned substation wiring diagram processing method, device, computer equipment, computer-readable storage medium, and computer program product acquire images of substation wiring diagrams and perform quality enhancement processing to obtain processed images. Optical character recognition (OCR) is performed on the title area of ​​the processed image to obtain title recognition results, and the diagram type is determined based on these results. Based on the diagram type, the processed image is segmented to identify and locate the wiring diagram area, text area, and table area. The wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram. This structural data is converted into standardized data for the power industry. If the standardized data passes the wiring diagram rule review, it is matched with the reference standardized data of the corresponding reference wiring diagram to obtain a matching result. Based on the matching result, the quality review result of the wiring diagram is output. In this way, various information in the wiring diagram is converted into a related, multi-layered, nested array format conforming to tabular logic, and the review checklist content is converted into multiple interrelated judgment mechanisms for information review, simulating the review work of a drafting engineer in a real-world scenario, resulting in a more accurate final review result. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is an application environment diagram of a substation wiring diagram processing method in one embodiment;

[0059] Figure 2 This is a flowchart illustrating a method for processing wiring diagrams in a substation, as shown in one embodiment.

[0060] Figure 3 This is a structural block diagram of a substation wiring diagram processing device in one embodiment;

[0061] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0064] Current technologies lack the ability to "semantically understand" and "analyze logical connections" in drawings. Existing basic software cannot effectively and accurately parse the electrical functions and control logic between devices represented by the graphic symbols in the drawings, requiring engineers' professional knowledge. However, faced with a large number of drawing review tasks, engineers also find it difficult to establish complete and correct logical connections between all relevant components (relays, fuses, transformers, etc.) in a short period of time. When wiring diagrams do not conform to the wiring circuit principle, or do not comply with safety specifications, or lack redundant safety measures, oversights may go undetected.

[0065] The substation wiring diagram processing method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located on the cloud or other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be projection devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0066] In one exemplary embodiment, such as Figure 2 As shown, a method for processing wiring diagrams of substations is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 212. Wherein:

[0067] Step 202: Obtain an image of the substation wiring diagram and perform quality improvement processing on the image to obtain the processed image.

[0068] In some embodiments, a digital image is obtained by scanning a paper wiring diagram with a scanner or by photographing the wiring diagram with a digital camera or smartphone.

[0069] In some embodiments, the acquired wiring diagram image may have problems such as skewness and noise, and preprocessing is required to reduce the image quality degradation caused by scanning.

[0070] For example, an image of a substation wiring diagram is acquired, and the image is processed in different ways depending on the acquisition method to improve the image quality and obtain a processed image.

[0071] The image data format can be PNG, JPG, or other data formats, and can be set according to the actual situation. This application embodiment does not limit this.

[0072] In some embodiments, for image noise problems, an adaptive filtering algorithm is used for image regions with different noise levels. The filtering intensity is adjusted according to the noise variance of the local region, strengthening noise removal in flat areas and weakening noise removal in edge areas to avoid excessive smoothing that leads to loss of details.

[0073] In some embodiments, the processed image can be enhanced by histogram equalization or sharpening.

[0074] Step 204: Perform optical character recognition on the title area of ​​the processed image to obtain the title recognition result, and determine the drawing type of the wiring diagram based on the title recognition result.

[0075] Optionally, OCR (Optical Character Recognition) is performed on the title of the drawing at a fixed location. By semantically parsing the title, the type of the drawing can be determined, such as a primary wiring diagram, a system wiring diagram, or a transformer substation configuration wiring diagram.

[0076] In some embodiments, according to the standardized drafting specifications for substation wiring diagrams, the title block is typically located in a fixed position at the lower right corner or directly below the drawing. Based on the dimensions of the processed image, this fixed area is calculated and cropped out as the title area image.

[0077] In some embodiments, a trained layout analysis model is used to perform region detection on the entire drawing. The model outputs the bounding box coordinates and region type labels for each region. When the model identifies a region with title features within the "title region" or "text region," the bounding box coordinates of that region are used as the title region.

[0078] Step 206: Based on the drawing type, perform region segmentation on the processed image, and identify and locate the wiring diagram area, text area, and table area of ​​the processed image.

[0079] The wiring diagram area includes key graphic information such as electrical symbols, connecting lines, and key components; the text area includes equipment codes, models, and descriptive text; and the table area includes detailed information on the wiring equipment, such as switchgear models, dimensions, high-voltage equipment names, specifications, and cable models.

[0080] For example, based on the drawing type of the wiring diagram, layout analysis is performed, and the boundary frame coordinates and corresponding area type labels of the wiring diagram area, text area, and table area are determined through layout analysis to identify the model.

[0081] In some embodiments, based on preset division rules, the electrical cabinets are divided into units. The table information of the electrical cabinet is shown below the same part of the drawing. Adjacent electrical cabinets are divided by table lines. Therefore, the intelligent analysis of the wiring diagram can also follow this drawing rule. First, the electrical cabinets are divided into blocks, and then the information of each electrical cabinet in the wiring diagram is analyzed.

[0082] In some embodiments, for each electrical cabinet device, the manually labeled content in the component symbols of the wiring diagram includes various symbols appearing in the tabular labeling information. The identification of key component symbols inside the equipment is achieved using template matching and key feature extraction methods. First, a standard symbol template library is established, containing graphic templates for each component symbol. When identifying component symbols within the graphic device area, feature-based matching algorithms (such as SIFT and ORB algorithms) are used to search for similar feature structures within the device area that match those in the symbol template library. The search results, including the coordinates of the found symbols and the component symbol type, are returned, thus completing the identification.

[0083] In some embodiments, the equipment may be a high-voltage switchgear, a low-voltage switchgear, an incoming line cabinet, an outgoing line cabinet, a metering cabinet, a capacitor cabinet, etc.

[0084] Step 208: Analyze the wiring diagram area, text area, and table area to obtain the structural data of each device in the wiring diagram.

[0085] Optionally, the wiring diagram area, text area, and table area can be parsed separately, and the parsing results of each area can be integrated to determine the structural data of each device in the wiring diagram.

[0086] Step 210: Convert the structural data into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, perform similarity matching between the standardized data and the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0087] For example, the structured data is processed into standardized data for the power industry. The standardized data is then subject to rule review. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0088] In some embodiments, a multi-layered nested array is constructed based on the wiring diagrams and table area structure data of each electrical cabinet device for subsequent rule review. The structure data includes the identification type of the component symbol and the coordinates of the component identification.

[0089] For example, the structural data for the wiring diagram section is shown below:

[0090] [{"transcription": "high-voltage surge arrester", "points": [[82, 571], [128, 571],[128, 641], [82, 641]], "difficult": false},

[0091] {"transcription": "High-voltage load switch", "points": [[544, 136], [661, 136],[661, 216], [544, 216]], "difficult": false},

[0092] {"transcription": "grounding switch", "points": [[619, 371], [721, 371],[721, 445], [619, 445]], "difficult": false},

[0093] {"transcription": "current transformer", "points": [[1589, 247], [1772, 247],[1772, 326], [1589, 326]], "difficult": false},

[0094] In some embodiments, the structure data of the table area nests the contents of each row and column of the table in a data format and outputs them, as shown in the following format:

[0095] [[{'Switch cabinet number':'G01','Switch cabinet model':'XGN15-12(+B+)','Switch cabinet dimensions (W×D×H) (mm)':'500×750×1900',

[0096] 'Switch cabinet name': 'Incoming line cabinet'

[0097] 'Main equipment in the high-voltage section':

[0098] {'Equipment Name':{'High Voltage Switch':{'Code':'601','Specification':'630A / 20KA (Circuit Breaker)','Quantity':'1'},

[0099] 'High-voltage fuse':{'Code':'FU11','Specification':'10kV / 1A','Quantity':'3'},

[0100] 'Grounding switch':{},

[0101] 'High-voltage current transformer': {'Code':'TA12','Specification':'100 / 5 0.2S class','Quantity':'2'},

[0102] 'Voltage Transformer':{'Code':'TV11','Specifications':'10 / 0.1kV 0.5 class','Quantity':'2'},

[0103] 'Zero-sequence current transformer':{'Specifications':'150 / 5 5P 10-class 5VA','Quantity':'2'},

[0104] 'Live indicator':{'Quantity':'2'},

[0105] 'Fault Indicator':{},

[0106] 'High-voltage surge arrester':{'Specifications':'17KV / 50KV','Quantity':'3'},

[0107] 'Cable connector (mm2)':{'Specifications':'30*7','Quantity':'3'},

[0108] 'Knife (Fuse) Switch':{'Specifications':'630A / 20kA','Quantity':'2'},

[0109] 'Voltmeter':{'Specifications':'0~12kV','Quantity':'1'},

[0110] 'Ammeter':{'Specifications':'0~100A','Quantity':'3'}}}

[0111] 'Equipment Capacity / Calculated Current': '800kVA / 46.2A'

[0112] Cable type and specifications: FYZRYJV22-8.7 / 15kV-3x70

[0113] Protection methods: Instantaneous interruption, overcurrent protection, zero-sequence protection, and undervoltage protection.

[0114] 'Remark':''}]]

[0115] In some embodiments, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the drawing type to obtain the matching result.

[0116] Step 212: Based on the matching results, output the quality audit results of the wiring diagram.

[0117] In practice, the quality audit results of the wiring diagrams are determined by combining the rule review results and matching results.

[0118] In some embodiments, a corresponding reference wiring diagram is retrieved from a preset drawing set database. The database stores image files and structured data models of various wiring diagrams. Search criteria can be drawing set name and drawing number, employing a fuzzy matching strategy, supporting synonym matching and partial matching.

[0119] In some embodiments, similarity matching can be performed by calculating the structural similarity index of two images to evaluate the similarity of the images in terms of brightness, contrast and structure, with a value ranging from 0 to 1, where the closer to 1, the more similar the images are; and by calculating the perceptual hash value of the two images and evaluating the similarity using Hamming distance, where the smaller the distance, the more similar the images are.

[0120] In some embodiments, the drawing similarity matching result is used as a reference indicator. When the similarity is lower than the preset value, it is indicated that the wiring drawing may differ significantly from the standard design, and it is recommended to conduct a thorough review.

[0121] In some embodiments, the quality audit results include the audit results of each preset audit rule, including rule description, audit status, violation details, rectification suggestions, etc.; similarity matching result reference atlas information, similarity score, matching conclusion, etc.; and areas in the wiring diagram that may have problems.

[0122] The above-mentioned substation wiring diagram processing method involves acquiring an image of the substation wiring diagram and performing quality enhancement processing to obtain a processed image. Optical character recognition (OCR) is then performed on the title area of ​​the processed image to obtain the title recognition result, and the diagram type is determined based on this result. Based on the diagram type, the processed image is segmented to identify and locate the wiring diagram area, text area, and table area. The wiring diagram area, text area, and table area are then parsed to obtain the structural data of each device in the wiring diagram. This structural data is converted into standardized data for the power industry. If the standardized data passes the wiring diagram rule review, it is matched with the reference standardized data of the corresponding reference wiring diagram to obtain a matching result. Based on the matching result, the quality review result of the wiring diagram is output. In this way, various information in the wiring diagram is converted into a related, multi-layered, nested array format conforming to table logic, and the review checklist content is converted into multiple interrelated judgment mechanisms for information review. This simulates the review work of a drafting engineer in a real-world scenario, making the final review result more accurate.

[0123] In one exemplary embodiment, the image is enhanced to obtain a processed image, including: identifying the outer border of the largest rectangle in the image and calculating the rotation angle of the outer border relative to a preset plane; straightening the image based on the rotation angle to obtain a straightened image; and denoising the straightened image to obtain a processed image.

[0124] In practice, to address the skewness of the drawing, the largest rectangular outer border of the drawing is identified using OpenCV. After determining the position of the outer border, its rotation angle is calculated to straighten the image. Once the drawing is straightened, Gaussian filtering and median filtering are used to reduce image noise and improve image clarity, completing the image preprocessing and yielding the processed image.

[0125] In the above embodiments, the combined application of tilt correction and noise reduction improves image quality, significantly enhancing image clarity and usability, and providing high-quality input data for subsequent automated processing.

[0126] In an exemplary embodiment, optical character recognition is performed on the title area of ​​the processed image to obtain a title recognition result, and the drawing type of the wiring diagram is determined based on the title recognition result. This includes: locating the title area of ​​the processed image based on a preset fixed position; performing optical character recognition on the title area to obtain a title recognition result; performing semantic parsing on the title recognition result to extract key feature words; matching the key feature words with a preset drawing type keyword library; and determining the drawing type of the wiring diagram based on the matching result.

[0127] In practice, the title area of ​​the processed image is located based on a preset fixed position; optical character recognition is performed on the title area to obtain the title recognition result; semantic analysis is performed on the title recognition result to extract key feature words, and the key feature words are matched with a preset drawing type keyword library to determine the drawing type of the wiring diagram based on the matching result.

[0128] In the above embodiments, by quickly locating the title area based on a fixed position and combining OCR recognition and semantic parsing technology, type information can be automatically and accurately extracted from the drawing, avoiding the tedious process of manual review and judgment; by matching the recognition results with a preset keyword library, ambiguity caused by differences in the drawing title expression (such as abbreviations and synonyms) can be eliminated, ensuring the standardization and consistency of drawing type determination.

[0129] In one exemplary embodiment, the drawing types include main wiring diagrams, system wiring diagrams, and transformer substation configuration wiring diagrams.

[0130] The main wiring diagram primarily displays the main electrical equipment (such as transformers, circuit breakers, disconnectors, busbars, etc.) and their connection relationships in the substation or distribution station, reflecting the transmission and distribution path of electrical energy. The system wiring diagram displays the wiring relationships of a specific system (such as protection system, control system, measurement system, etc.), usually including detailed connections of multiple subsystems or equipment. The prefabricated substation configuration wiring diagram displays the configuration and wiring relationships of the equipment inside the prefabricated substation (prefabricated substation), usually divided by electrical cabinet, with each electrical cabinet corresponding to a table displaying equipment parameters.

[0131] In practice, the types of drawings include system wiring diagrams, main wiring diagrams, system wiring diagrams, transformer substation configuration wiring diagrams, and low-voltage meter wiring diagrams.

[0132] In the above embodiments, by accurately identifying the drawing type and adopting a targeted parsing strategy, it is possible to adapt to the structural characteristics and review focus of different types of drawings, avoid misidentification and omission caused by general methods, and significantly improve the accuracy of symbol recognition, topology analysis and table parsing.

[0133] In an exemplary embodiment, the wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram. This includes: dividing the wiring diagram area into units based on the table line features, and determining the image sub-area corresponding to each electrical cabinet unit; for each image sub-area, identifying the electrical components within the cabinet and outputting the coordinate position and component type of the electrical components; identifying the cells in the table area and performing text recognition on the image area in each cell, outputting the text content corresponding to the cell; and integrating the coordinate position, component type, text area, and text content of the electrical components to obtain the structural data of each device in the wiring diagram. The text area includes descriptive text of the electrical components.

[0134] In practical implementation, based on the table line features in the wiring diagram area, the wiring diagram area is divided into units based on electrical cabinets, and the image sub-region corresponding to each electrical cabinet unit is determined. For each image sub-region, the electrical components inside the electrical cabinet are identified, and the coordinate position and component type of the electrical components are output. The cells in the table area are identified, and text recognition is performed on the image area in each cell, and the text content corresponding to the cell is output. The coordinate position, component type, text area, and text content of the electrical components are integrated to obtain the structural data of each device in the wiring diagram. The text area includes descriptive text of the electrical components.

[0135] In some embodiments, the table structure is identified, including merged areas and the number of rows and columns, and OCR recognition is performed on the table content to identify text and symbols in the table.

[0136] In one embodiment, after determining the table structure, the graphic area of ​​each cell in the table is cropped out based on the obtained precise cell coordinates. The cropped individual cells are then used to recognize the text within the cells using paddleOCR. Finally, the recognized OCR content is matched one-to-one with the cells to complete the recognition of the entire table content.

[0137] The table recognition algorithm uses a deep learning table structure recognition model based on PaddlePaddle. The algorithm can handle cells that span rows and columns, restore the logical structure of the table, and finally output a network structure composed of cells.

[0138] In the above embodiments, by dividing the wiring diagram area into electrical cabinet units based on the table line features, modular processing of complex drawings is achieved, enabling precise binding of electrical component identification with the corresponding electrical cabinet and avoiding confusion across electrical cabinets; by identifying the coordinate position and type of electrical components in the electrical cabinet and combining it with text recognition of table cells, graphic information and table parameters are associated and integrated to form multi-dimensional structured data containing component type, position coordinates and descriptive text.

[0139] In an exemplary embodiment, the rule review process for standardized data includes: matching the standardized data with preset review rules one by one; and if the processed parsing result satisfies all the pre-reviewed review rules, the standardized data passes the rule review.

[0140] In practice, a relevant knowledge graph is established based on the preset review rules.

[0141] For example, the preset review rules are described as follows:

[0142] If the area is identified as a high-voltage switchgear zone, and a circuit breaker exists in the high-voltage switchgear zone, satisfying both of the above conditions, then determine whether the high-voltage switchgear uses an 80*10 copper plate. If there is no circuit breaker in the high-voltage switchgear zone, then the circuit breaker uses a 60*6 copper plate.

[0143] If a high-voltage switchgear is detected in the drawings, and a circuit breaker is present in the area of ​​that high-voltage switchgear, it is necessary to check whether a matching DC power supply is present in the drawings, and the DC power supply for each high-voltage switchgear should be no less than 4AH.

[0144] In some embodiments, the above-mentioned preset review rules can be transformed into the following form:

[0145] Preset review rules: ① {High-voltage switchgear: True, Circuit breaker: True, 80*10 bronze plate: True} or {High-voltage switchgear: True, Circuit breaker: null, 60*6 bronze plate: True}

[0146] ② {High-voltage switchgear: True, Circuit breaker: True, DC power supply: True, 4AH: True}

[0147] The pre-approval rules are converted into computer-executable language rules. The results of the processed parsing are then checked to see if they meet the requirements. If the processed parsing results meet all the pre-approval rules, the standardized data passes the rule review.

[0148] For example, the preset audit rules are as follows: determine whether the high-voltage switchgear uses copper plate specifications in compliance with the following rules: {High-voltage switchgear: True, Circuit breaker: True, 80*10 copper plate: True}.

[0149] In some embodiments, the image and table data extracted from the switchgear number G01 are evaluated. Based on the structured table information, G01 contains major high-voltage equipment and is identified as a high-voltage switchgear. A search for the major high-voltage equipment reveals the presence of a circuit breaker. The image information extracted from G01 indicates that the bronze plate of G01 is TMY 80*10, and the overall result conforms to the preset review rules.

[0150] In the above embodiments, by converting unstructured drawing information into quantifiable and comparable structured data and automatically matching it with preset standard rules, the standardization of review criteria and the objectification of the review process are achieved, avoiding omissions and errors in manual review due to differences in experience or subjective judgment. The one-to-one matching of each rule ensures the comprehensiveness and rigor of the review, and can systematically identify problems such as configuration errors, parameter discrepancies and violations of safety specifications in the drawings.

[0151] To illustrate the substation wiring diagram processing method in this application in detail, an embodiment is provided below. For example, this application describes a substation wiring diagram processing method in a specific scenario.

[0152] First, images of the substation wiring diagrams are acquired. Depending on the acquisition method, different image processing techniques are applied to improve image quality, resulting in processed images. OCR (Optical Character Recognition) is used to recognize the title of the diagram at a fixed location. Semantic parsing of the title determines the diagram type, such as a primary wiring diagram, system wiring diagram, or prefabricated substation configuration wiring diagram.

[0153] Based on the drawing type of the wiring diagram, layout analysis is performed. The model is identified through layout analysis to determine the bounding box coordinates and corresponding area type labels for the wiring diagram area, text area, and table area. The wiring diagram area, text area, and table area are analyzed separately, and the analysis results are integrated to determine the structural data of each device in the wiring diagram.

[0154] The structural data is processed into standardized data for the power industry. This standardized data undergoes rule-based review. Once the standardized data passes the rule review for the wiring diagram, it is matched with the reference standardized data of the corresponding reference wiring diagram to obtain the matching result. The quality review result of the wiring diagram is determined by combining the rule review result and the matching result.

[0155] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0156] Based on the same inventive concept, this application also provides a substation wiring diagram processing device for implementing the above-described substation wiring diagram processing method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more substation wiring diagram processing device embodiments provided below can be found in the limitations of the substation wiring diagram processing method described above, and will not be repeated here.

[0157] In one exemplary embodiment, such as Figure 3 As shown, a substation wiring diagram processing device is provided, including: an acquisition module 301, an identification module 302, a parsing module 303, a matching module 304, and an output module 305, wherein:

[0158] The acquisition module is used to acquire images of the wiring diagrams of the substation and perform quality improvement processing on the images to obtain processed images;

[0159] The recognition module is used to perform optical character recognition on the title area of ​​the processed image, obtain the title recognition result, and determine the drawing type of the wiring diagram based on the title recognition result;

[0160] The recognition module is also used to perform region segmentation on the processed image based on the drawing type, and to identify and locate the wiring diagram area, text area and table area of ​​the processed image;

[0161] The parsing module is used to parse the wiring diagram area, text area, and table area to obtain the structural data of each device in the wiring diagram;

[0162] The matching module is used to convert the structural data into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result.

[0163] The output module is used to output the quality review result of the wiring diagram based on the matching result.

[0164] In one exemplary embodiment, the above-described apparatus further includes a processing module for:

[0165] Identify the outer border of the largest rectangle in the image and calculate the rotation angle of the outer border relative to a preset plane;

[0166] The image is straightened based on the rotation angle to obtain the straightened image;

[0167] The image after alignment is denoised to obtain the processed image.

[0168] In one exemplary embodiment, the identification module is further configured to:

[0169] Based on a preset fixed position, locate the title area of ​​the processed image;

[0170] Optical character recognition is performed on the title area to obtain the title recognition result;

[0171] Semantic analysis is performed on the title recognition results to extract key feature words. These key feature words are then matched with a pre-set drawing type keyword library. Based on the matching results, the drawing type of the wiring diagram is determined.

[0172] In one exemplary embodiment, the above-described parsing module is further configured to:

[0173] Based on the table line features in the wiring diagram area, the wiring diagram area is divided into units based on electrical cabinets, and the image sub-region corresponding to each electrical cabinet unit is determined.

[0174] For each image sub-region, identify the electrical components inside the cabinet and output the coordinates and type of the electrical components;

[0175] Identify cells in a table area, perform text recognition on the image area in each cell, and output the text content corresponding to the cell.

[0176] The coordinates, types, text areas, and text content of electrical components are integrated to obtain the structural data of each device in the wiring diagram; the text area includes descriptive text of the electrical components.

[0177] In one exemplary embodiment, the above-described apparatus further includes an auditing module for:

[0178] The standardized data is matched one by one with the preset review rules. If the processed parsing results meet all the pre-review review rules, the standardized data passes the rule review.

[0179] Each module in the aforementioned substation wiring diagram processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0180] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for processing wiring diagrams in a substation.

[0181] The display unit of this computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of this computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad set on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0182] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0183] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0184] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0185] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0186] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0187] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0188] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0189] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for processing wiring diagrams of a substation, characterized in that, The method includes: Obtain an image of the substation wiring diagram and perform quality enhancement processing on the image to obtain a processed image; Optical character recognition is performed on the title area of ​​the processed image to obtain the title recognition result, and the drawing type of the wiring diagram is determined based on the title recognition result; Based on the drawing type, the processed image is segmented to identify and locate the wiring diagram area, text area, and table area of ​​the processed image; The wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram. The structural data is converted into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result. Based on the matching results, the quality audit results of the wiring diagram are output.

2. The method according to claim 1, characterized in that, The process of improving the quality of the image to obtain the processed image includes: Identify the outer border of the largest rectangle in the image, and calculate the rotation angle of the outer border relative to a preset plane; The image is straightened based on the rotation angle to obtain the straightened image; The image after alignment is denoised to obtain the processed image.

3. The method according to claim 1, characterized in that, The step of performing optical character recognition on the title area of ​​the processed image to obtain a title recognition result, and determining the drawing type of the wiring diagram based on the title recognition result, includes: Based on a preset fixed position, locate the title area of ​​the processed image; Optical character recognition is performed on the title area to obtain the title recognition result; The title recognition result is semantically analyzed to extract key feature words. The key feature words are then matched with a preset drawing type keyword library. Based on the matching result, the drawing type of the wiring drawing is determined.

4. The method according to claim 3, characterized in that, The drawing types include main wiring diagrams, system wiring diagrams, and transformer substation configuration wiring diagrams.

5. The method according to claim 1, characterized in that, The wiring diagram area, text area, and table area are parsed to obtain the structural data of each device in the wiring diagram, including: Based on the table line features in the wiring diagram area, the wiring diagram area is divided into units based on electrical cabinets, and the image sub-region corresponding to each electrical cabinet unit is determined. For each image sub-region, identify the electrical components inside the cabinet and output the coordinates and type of the electrical components; Identify cells in the table area, perform text recognition on the image area in each cell, and output the text content corresponding to the cell; The coordinate positions of the electrical components, the component types, the text areas, and the text content are integrated to obtain the structural data of each device in the wiring diagram; the text areas include descriptive text of the electrical components.

6. The method according to claim 1, characterized in that, The rule review process for the standardized data includes: The standardized data is matched one by one with the preset review rules. If the processed parsing results meet all the pre-review review rules, the standardized data passes the rule review.

7. A substation wiring diagram processing device, characterized in that, The device includes: The acquisition module is used to acquire images of the wiring diagrams of the substation and perform quality improvement processing on the images to obtain processed images; The recognition module is used to perform optical character recognition on the title area of ​​the processed image, obtain the title recognition result, and determine the drawing type of the wiring diagram based on the title recognition result; The recognition module is also used to perform region segmentation on the processed image based on the drawing type, and to identify and locate the wiring diagram area, text area and table area of ​​the processed image; The parsing module is used to parse the wiring diagram area, text area, and table area to obtain the structural data of each device in the wiring diagram; The matching module is used to convert the structural data into standardized data for the power industry. If the standardized data passes the rule review of the wiring diagram, the standardized data is matched with the reference standardized data of the reference wiring diagram corresponding to the diagram type to obtain the matching result. The output module is used to output the quality review result of the wiring diagram based on the matching result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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

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

Images