Automatic extraction method and device for nuclear power plant electric instrument drawing data, medium and equipment

Abstract

The invention relates to a nuclear power plant electric instrument drawing data automatic extraction method and device, a medium and equipment. The method comprises the steps of obtaining a source drawing; identifying the drawing type of the source drawing; if the drawing type of the source drawing is a PDF drawing, extracting data of the PDF drawing according to a first data extraction method and storing the data as PDF structured data; if the drawing type of the source drawing is a VISIO drawing, extracting data of the VISIO drawing according to a second data extraction method, and storing the data as VISIO structured data; performing classified management on the PDF structured data and the VISIO structured data to form classified drawing data; and performing digital management on the classified drawing data to form digital drawing data. According to the method, automatic extraction of the electric instrument drawing data of the nuclear power plant can be realized, data unification is carried out, the data extraction efficiency is improved, meanwhile, the drawing data of each power plant achieves a universal effect, and the period of iCCM application practice is effectively prolonged.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of nuclear power paper processing, and more particularly to a nuclear power plant electrical instrument paper data automatic extraction method, device, medium and equipment. BACKGROUND

[0002] In the current application practice of the nuclear power key sensitive component informatization technology platform (iCCM), the full-link diagrams involved in the electrical instruments of each nuclear power plant are composed of scattered PDF diagrams, DBU and VSD files, and the PDF diagrams are respectively in different PDF pages for different electrical instrument components. At present, the data collection process can be completed through multiple operation modes such as data collection, cleaning, editing and checking by plant staff, IT project team and business users. This method has the problems of long implementation duration, high cost, uncontrollable data quality and the like, and is completely not up to standard for promoting iCCM application practice in group plants.

[0003] In addition, the data supported by the current diagram link diagram is derived from the diagram source, and the problems of the diagram source are various in format and type in each nuclear power plant, and the corresponding supply end manufacturers of the diagram sources of different nuclear power plants are different. In the process of collecting diagram source data manually, it is impossible to achieve universality, and the key parameter information of the components of the diagram sources of different nuclear power plants cannot be unified. The systems used by different nuclear power plants are different, and the data sorting and data arrangement processes are different. The component parameter information considered by each system of different nuclear power plants cannot be unified, and thus the universal effect cannot be achieved, which greatly reduces the cycle of iCCM application practice. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a nuclear power plant electrical instrument paper data automatic extraction method, device, medium and equipment in view of the problems in the prior art.

[0005] The technical solution adopted by the present application to solve the technical problem is that a nuclear power plant electrical instrument paper data automatic extraction method is constructed, comprising the following steps:

[0006] Obtaining source paper;

[0007] Identifying the paper type of the source paper;

[0008] If the paper type of the source paper is a PDF paper, the data of the PDF paper is extracted according to a first data extraction method and saved as PDF structured data;

[0009] If the paper type of the source paper is a VISIO paper, the data of the VISIO paper is extracted according to a second data extraction method and saved as VISIO structured data;

[0010] The PDF structured data and the VISIO structured data are classified and managed to form classified drawing data.

[0011] The classified drawing data is digitally managed to form digital drawing data.

[0012] In the nuclear power plant electrical instrument drawing data automatic extraction method, the data of the PDF drawing is extracted according to the first data extraction method and saved as PDF structured data, which includes:

[0013] The PDF drawing is recognized and data is extracted to obtain PDF drawing data;

[0014] An element symbol detection is performed using a target detection model to obtain PDF drawing element symbol data;

[0015] Lines and connection points are recognized, and a network is constructed based on the lines and connection points to obtain a link relationship network;

[0016] Text and elements are associated based on the PDF drawing data, the drawing element symbol data and the link relationship network to obtain associated data;

[0017] A target result is output based on the associated data and saved as the PDF structured data.

[0018] In the nuclear power plant electrical instrument drawing data automatic extraction method, the PDF drawing is recognized and data is extracted to obtain PDF drawing data, which includes:

[0019] PyMuPDF or pdfplumber is used to extract vector elements;

[0020] For a scanned copy or a bitmap, pdf2image is used to convert to obtain a high-resolution image;

[0021] Tesseract OCR is used to extract text and coordinates and save as structured data;

[0022] The vector elements, the high-resolution image and the structured data are arranged to obtain the PDF drawing data.

[0023] In the nuclear power plant electrical instrument drawing data automatic extraction method, the data of the VISIO drawing is extracted according to the second data extraction method and saved as VISIO structured data, which includes:

[0024] All shapes and layers of the VISIO drawing are obtained using ShapeSheet to obtain shape data and layer data;

[0025] Based on the shape data and the layer data, all node information and connection information are obtained through identification.

[0026] In the nuclear power plant electrical instrument drawing data automatic extraction method, the PDF structured data and the VISIO structured data are classified and managed to form classified drawing data.

[0027] The PDF structured data and the VISIO structured data are classified and managed according to systems, units, drawing types and drawing formats to form the classified drawing data.

[0028] In the nuclear power plant electrical instrument drawing data automatic extraction method, the classified drawing data are digitally managed to form digital drawing data.

[0029] The classified drawing data are associated according to corresponding units, systems and drawing types of each nuclear power plant to obtain the digital drawing data.

[0030] In the nuclear power plant electrical instrument drawing data automatic extraction method, the method further comprises:

[0031] The digital drawing data are subjected to permission management and identification.

[0032] The digital drawing data are subjected to integrated management.

[0033] The application further provides a nuclear power plant electrical instrument drawing data automatic extraction device, comprising:

[0034] A drawing digitization module is configured to perform the following steps:

[0035] Obtain source drawing data;

[0036] Identify the drawing type of the source drawing data;

[0037] If the drawing type of the source drawing data is a PDF drawing, the data of the PDF drawing is extracted according to a first data extraction method and saved as PDF structured data;

[0038] If the drawing type of the source drawing data is a VISIO drawing, the data of the VISIO drawing is extracted according to a second data extraction method and saved as VISIO structured data;

[0039] A drawing classification management module is configured to classify and manage the PDF structured data and the VISIO structured data to form classified drawing data.

[0040] A digital drawing management module is configured to digitally manage the classified drawing data to form digital drawing data.

[0041] The application further provides a storage medium storing a computer program, which is adapted to be loaded by a processor to execute the steps of the nuclear power plant electrical instrument drawing data automatic extraction method.

[0042] The application further provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the nuclear power plant electrical instrument drawing data automatic extraction method by calling the computer program stored in the memory.

[0043] The nuclear power plant electrical instrument drawing data automatic extraction method, device, medium and equipment provided by the application have the following beneficial effects: the method comprises the steps of obtaining a source drawing, identifying the drawing type of the source drawing, extracting data of a PDF drawing according to a first data extraction method and saving the data as PDF structured data if the drawing type of the source drawing is the PDF drawing, extracting data of a VISIO drawing according to a second data extraction method and saving the data as VISIO structured data if the drawing type of the source drawing is the VISIO drawing, classifying and managing the PDF structured data and the VISIO structured data to form classified drawing data, and digitally managing the classified drawing data to form digital drawing data. The application can realize automatic extraction of nuclear power plant electrical instrument drawing data, data unification, improvement of data extraction efficiency, generalization of drawing data of each power plant, and effective extension of the iCCM application practice cycle. BRIEF DESCRIPTION OF DRAWINGS

[0044] The application will be further described below with reference to the drawings and embodiments, wherein:

[0045] Figure 1 FIG. 1 is a flowchart of an embodiment of the nuclear power plant electrical instrument drawing data automatic extraction method provided by the application;

[0046] Figure 2 FIG. 3 is a schematic diagram of a VISIO drawing to be identified provided by the application;

[0047] Figure 3 FIG. 5 is a schematic diagram of a VISIO drawing identification effect provided by the application;

[0048] Figure 4 FIG. 7 is a logic block diagram of the nuclear power plant electrical instrument drawing data automatic extraction device provided by the application;

[0049] Figure 5 FIG. 9 is a business architecture diagram of the drawing intelligent extraction provided by the application;

[0050] Figure 6 is an application architecture diagram of intelligent extraction of drawing paper provided by the present application;

[0051] Figure 7 is a technical architecture diagram of intelligent extraction of drawing paper provided by the present application;

[0052] Figure 8 is an execution life cycle diagram of intelligent extraction of drawing paper provided by the present application. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0054] Reference Figure 1 In a preferred embodiment, the nuclear power plant electrical instrument drawing paper data automatic extraction method comprises the following steps:

[0055] Step S100: Obtain source drawing paper.

[0056] Optionally, in the embodiments of the present application, the source drawing paper can be obtained by using existing methods, which are not limited in the present application.

[0057] Step S200: Identify the drawing paper type of the source drawing paper.

[0058] In some embodiments, the source drawing paper can include, but is not limited to, PDF drawing paper (i.e., PDF format drawing paper), VISIO drawing paper (i.e., VISIO format drawing paper), DBU drawing paper (i.e.,.db format drawing paper), etc.

[0059] Step S300: If the drawing paper type of the source drawing paper is PDF drawing paper, then the data of the PDF drawing paper is extracted according to a first data extraction method and saved as PDF structured data.

[0060] In some embodiments, extracting the data of the PDF drawing paper according to the first data extraction method and saving it as PDF structured data comprises: identifying and extracting data from the PDF drawing paper to obtain PDF drawing paper data; using a target detection model to detect element symbols to obtain PDF drawing paper element symbol data; identifying lines and connection points and constructing a network based on the lines and connection points to obtain a link relationship network; associating text and elements based on the PDF drawing paper data, the drawing paper element symbol data and the link relationship network to obtain associated data; outputting a target result based on the associated data and saving it as PDF structured data.

[0061] The PDF drawing data is obtained by identifying and extracting data from the PDF drawing, including: extracting vector elements using PyMuPDF or pdfplumber; converting scanned copies or bitmaps into high-resolution images using pdf2image; extracting text and coordinates using Tesseract OCR and saving as structured data; and arranging vector elements, high-resolution images and structured data to obtain PDF drawing data. The vector elements include, but are not limited to, lines, text, paths, etc. Optionally, the PDF drawing includes a vector PDF drawing, a scanned PDF drawing or a bitmap PDF drawing. For a vector PDF drawing, lines, text, paths, etc. can be extracted using PyMuPDF or pdfplumber. For a scanned PDF drawing or a bitmap PDF drawing, pdf2image can be used to convert the PDF into a high-resolution image (such as PNG / JPEG). The resolution can be ≥ 300 dpi. After completing the extraction of vector elements of the PDF drawing or the conversion of the drawing, Tesseract OCR can be used to extract text and coordinates and save as structured data.

[0062] Further, after completing the extraction and preprocessing of the above-mentioned PDF drawing, a target detection model is used for detection to detect element symbols. The target detection model can be YOLOv8, pre-trained on a circuit symbol data set. Alternatively, custom training can be used, such as annotating element symbols (such as cabinets, terminal blocks, resistors, etc.), generating a format data set, and then training through the format data set. Then, line detection and connection point detection are performed. For vector drawings, straight lines and curves need to be detected. For connection point detection, the intersection of lines is detected, and the detected intersection of lines is taken as a connection point, and finally a link relationship network is constructed. Then, the text is associated with the element, and the associated data is output, and finally the PDF structured data is output according to the target result set. Optionally, in the embodiment of the present application, the PDF structured data can include, but is not limited to, related equipment, measurement points (such as pins, interfaces, line information, connection relationships, directions, attribute information, signal names, etc.) on the drawing.

[0063] Step S400: If the drawing type of the source drawing is a VISIO drawing, the data of the VISIO drawing is extracted according to the second data extraction method and saved as VISIO structured data.

[0064] In some embodiments, extracting the data of the VISIO drawing according to the second data extraction method and saving it as VISIO structured data includes: using ShapeSheet to obtain all shapes and layers of the VISIO drawing to obtain shape data and layer data; identifying based on the shape data and the layer data to obtain all node information and connection information. The VISIO drawing to be identified is, for example,Figure 2 For example, all shapes and layers of the VISIO drawing are obtained by using the ShapeSheet, shape data and layer data are obtained, and all node information and connection information are identified, and finally the structured data of the VISIO drawing is generated Figure 3 As shown in the identification effect, the structured data of the VISIO drawing is obtained.

[0065] It should be noted that in the embodiment of the present application, the DBU drawing can be identified and parsed according to its data format.

[0066] Step S500: The PDF structured data and the VISIO structured data are classified and managed to form classified drawing data.

[0067] In some embodiments, the classified management of the PDF structured data and the VISIO structured data to form the classified drawing data includes: archiving and classifying the PDF structured data and the VISIO structured data according to systems, units, drawing types and drawing formats to form the classified drawing data.

[0068] Specifically, after the data extraction of different types of drawings is completed, the classified drawing data can be archived and classified according to systems, units, drawing types and drawing formats, so as to realize the technical reuse of the same unit, the same system, the same drawing type and the same drawing format. Further, in the embodiment of the present application, the classified drawing data formed can be stored in the form of a folder, a new classified folder can be created, the file management can be classified according to business needs, and direct import of the folder is also supported. The system to which the drawing belongs includes but is not limited to: 704 cabinet and local wiring diagram, macs6 configuration diagram, macs6 cabinet wiring diagram, Mitsubishi meltac cabinet wiring diagram, Mitsubishi meltac configuration diagram, firmsys cabinet wiring diagram, firmsys configuration diagram, sh-n cabinet wiring diagram and sh-n configuration diagram. It should be noted that in the process of extracting the PDF drawing data, if the drawing extraction fails, the corresponding changes are made to the current drawing page. For the data extraction of the same type of PDF drawing, the same type of PDF drawing data can be directly obtained according to the corresponding JAVA code.

[0069] Step S600: The classified drawing data is digitally managed to form digital drawing data.

[0070] In some embodiments, the digital management of the classified drawing data to form the digital drawing data includes: corresponding association of the classified drawing data according to the units corresponding to each nuclear power plant, the systems to which the units belong and the corresponding drawing types, to obtain the digital drawing data.

[0071] Specifically, in the current management process of drawings of various nuclear power plants, the drawings import, drawing search, visual drawing browsing, drawing editing, viewing basic information of the drawing, viewing the original drawing file, link diagram management, version management, workflow management are managed according to the respective units, the corresponding system and the corresponding drawing type of each nuclear power plant. However, each nuclear power plant manages according to its own requirements, which lacks uniformity and universality. Based on this, the drawings import, drawing search, visual drawing browsing, drawing editing, viewing basic information of the drawing, viewing the original drawing file, link diagram management, version management, workflow management are correspondingly associated according to the corresponding unit and the corresponding system and the corresponding drawing type (704 cabinet and local wiring diagram, macs6 configuration diagram, macs6 cabinet wiring diagram, Mitsubishi meltac cabinet wiring diagram, Mitsubishi meltac configuration diagram, firmsys cabinet wiring diagram, firmsys configuration diagram, sh-n cabinet wiring diagram, sh-n configuration diagram) of each plant, so as to realize the corresponding management of the drawings import, drawing search, visual drawing browsing, drawing editing, viewing basic information of the drawing, viewing the original drawing file, link diagram management, version management, workflow management according to the corresponding unit, the corresponding system and the corresponding drawing type. The formed digital drawing data can be used for users to download various drawings. That is, the complete link can be downloaded. Specifically, the formed digital drawing data can directly display the link diagram on the interface by using the data node and data line, the file corresponding to the link diagram can be directly downloaded to the corresponding file page information, and the information corresponding to the current node and line can be directly queried through the link information of the page, such as device information, configuration information, spare part information and the like.

[0072] Further, in some embodiments, the nuclear power plant electrical instrument drawing data automatic extraction method further includes: performing permission management and identification on the digital drawing data; and performing integrated management on the digital drawing data.

[0073] Reference Figure 4 The application also provides a nuclear power plant electrical instrument drawing data automatic extraction device. Figure 4 As shown in the figure, the nuclear power plant electrical instrument drawing data automatic extraction device includes:

[0074] The drawing digitization module 401 is used to perform the following steps: acquiring a source drawing; identifying the drawing type of the source drawing; if the drawing type of the source drawing is a PDF drawing, extracting the data of the PDF drawing according to a first data extraction method and saving the data as PDF structured data; and if the drawing type of the source drawing is a VISIO drawing, extracting the data of the VISIO drawing according to a second data extraction method and saving the data as VISIO structured data.

[0075] The drawing classification management module 402 is used for classifying and managing the PDF structured data and the VISIO structured data to form classified drawing data.

[0076] The digital drawing management module 403 is used for digitally managing the classified drawing data to form digital drawing data.

[0077] Further, the nuclear power plant electrical instrument drawing data automatic extraction device further comprises a permission management module 404 and an integrated management module 405. The permission management module 404 is used for permission management and identification of the digital drawing data, and the integrated management module 405 is used for integrated management of the digital drawing data.

[0078] In some embodiments, Figure 5 The business architecture of the nuclear power plant electrical instrument drawing data automatic extraction device provided by the application is shown. As shown in Figure 5 The nuclear power plant electrical instrument drawing data automatic extraction device comprises a basic support layer, a data storage layer, a basic service layer and a functional application layer.

[0079] The basic support layer comprises distributed deployment, public cloud and private cloud. The distributed deployment is an architecture mode of dispersing application programs, services or data to run on multiple computing nodes. By using the distributed deployment, the high availability, scalability and data redundancy performance of the system can be enhanced, the risk of data loss can be reduced, and the overall performance of the system can be improved. The public cloud (Public Cloud) is a cloud computing service mode, which provides computing resources (such as servers, storage, databases, networks, software, etc.) to the public through the Internet. By using the public cloud, the initial investment cost can be reduced, and the user can dynamically adjust the use amount of resources according to the business demand. Moreover, the public cloud can provide high availability and redundancy mechanism to ensure the continuity of the service, and can create and deploy new resources within a few minutes without waiting for hardware procurement and installation, realizing rapid deployment. The private cloud (Private Cloud) is a cloud computing mode, which provides cloud computing resources and services for a single organization or enterprise, rather than being open to the public like the public cloud. By using the private cloud, the data security can be improved, the privacy requirements of data protection can be met, the customization ability is strong, the resource allocation can be flexibly adjusted to meet different application requirements, and the controllability is high, the allocation of resources, backup strategy, fault recovery, etc. can be decided autonomously, and the changes of business requirements can be better coped with.

[0080] The data storage layer can include an Oracle database, an MQL (MySQL) database, an ES database, a Redis database, etc. The Oracle database is a relational database that can support large-scale concurrent access, has strong transaction processing capability, is highly secure, has good scalability, and has rich functions, and can support complex SQL queries, stored procedures, triggers, and other advanced functions. The MySQL database is an open-source relational database that has high performance, ease of use, community support, good compatibility, and other advantages, and supports multiple programming languages such as PHP, Python, and Java. The Elasticsearch (ES) database is an open-source search engine based on Lucene. It supports complex full-text search functions, supports distributed deployment, can achieve real-time data (such as data can be queried immediately after being finalized, suitable for real-time data analysis), can support JSON format document storage, and can support multiple plugins. The Redis database is an open-source key-value storage that is commonly used as a database, cache, and message broker. It supports high-concurrency access, has extremely fast read and write speeds, stores data in memory, supports fast read and write operations, supports multiple persistence methods such as RDB (snapshot) and AOF (append file), and supports multiple data structures such as strings, hashes, lists, and sets. By adopting a mode of multiple databases coexisting, the overall data storage performance of the system can be significantly improved.

[0081] The basic service layer includes an AI service module, a graph element service module, a rendering service module, a data management service module, and an application development framework service module. By setting the AI service module, the system can have functions such as machine learning, deep learning, natural language processing, and computer vision, and can automatically process complex tasks, improve efficiency, and reduce manual intervention. Graph elements refer to the basic building blocks of graphics, such as points, lines, and surfaces. By setting the graph element service module, the underlying support for graphics-related applications can be provided, making it easy for developers to quickly build graphical interfaces or scenes. Rendering service refers to the process of converting graphic data into final images or videos. By setting the rendering service module, high-quality visual effects can be provided, supporting complex lighting, material, and animation effects. Application development framework service refers to a set of tools, libraries, and specifications provided for developing applications. It can help developers quickly build, deploy, and maintain applications. By setting the application development framework service module, development efficiency can be improved, repetitive code can be reduced, and standardized development patterns and best practices can be provided.

[0082] The functional application layer includes a drawing digitization module 401, a drawing classification management module 402, a digital drawing management module 403, a permission management module 404, and an integration management module 405.

[0083] The drawing digitization module 401 can realize intelligent identification, figure element management, figure element editing, and drawing drawing, etc. The drawing classification management module 402 can realize folder management, multi-level directory management, drawing list management, file export, state modification, and workflow management, etc. The digital drawing management module 403 can realize drawing browsing query, drawing editing, operation log, link diagram management, original drawing jump, drawing comparison, version change management, etc. The permission management module 404 can realize function management, data management, personnel management, role management, etc. The integrated management module 405 can realize document management system, configuration system, electrical and instrument application system, single sign-on, etc.

[0084] In some embodiments, Figure 6 The application architecture of the intelligent drawing extraction of the nuclear power plant electrical instrument drawing data automatic extraction device provided by the present application is shown. As Figure 6 shown, the nuclear power plant electrical instrument drawing data automatic extraction device can realize system association (such as data association between each system of the document management system, the configuration system, and the electrical and instrument application end system), can realize automatic import of design data (such as hardware drawing, group wiring diagram, data form, wiring diagram, etc.), can realize digital tool set (such as drawing digitization tool, drawing editing tool, configuration tool, etc.), and finally form electrical instrument drawing micro service (such as viewing original drawing (can browse drawing, view drawing attribute), searching and positioning (such as global search and positioning), viewing node attribute (such as drawing page, device description, etc.), viewing link diagram, drawing version management, etc.).

[0085] Figure 7 The technical architecture of the intelligent drawing extraction of the nuclear power plant electrical instrument drawing data automatic extraction device provided by the present application is shown. As Figure 7 shown, the nuclear power plant electrical instrument drawing data automatic extraction device includes four technical levels of platform layer, database layer, application layer, and portal layer.

[0086] The platform layer includes basic service platform, DevOps platform, data platform data interface, etc. The digital library layer includes historical drawing library, node connection model library, release version drawing library, figure element library, etc. The application layer includes business function unit and drawing management unit. The business function unit includes drawing browsing, version comparison, search positioning, rule prompt, association module, operation log, editing object, topology generation, comment module, link display, configuration object, data synchronization, etc. The drawing management unit includes my desktop, folder management, version management, my collection, directory management, workflow management, my comment, drawing state management, statistical report, my sharing, log management, import and export, rule management, permission management, and change record. The portal layer includes electrical drawing workstation.

[0087] Figure 8 The execution life cycle of the intelligent extraction of the drawing provided by the application is shown.

[0088] As shown in the figure, Figure 8 first, data collection is performed according to power plants, units, systems, drawing formats and drawing types; then, drawing data extraction requirements and data processing requirements are sorted according to power plants, units and systems; then, data extraction is performed according to power plants, units and systems according to extraction requirements; data processing is performed according to data processing requirements, such as first-round processing, second-round processing and third-round processing; the extracted data is cleaned, such as physical line data, virtual line data, virtual node data, device / component data associated with links, function position data related to links and related measurement point data; data initialization is performed according to function positions, devices, components, measurement points, PBS structures, physical lines, virtual lines and virtual nodes; finally, different environment link rendering verification is performed according to devices, virtual nodes, virtual lines, physical lines and associated files.

[0089] Specifically, the specific cooperation operation process between units in the nuclear power plant electrical instrument drawing data automatic extraction device can refer to the above-mentioned nuclear power plant electrical instrument drawing data automatic extraction method, which will not be described here.

[0090] The application can effectively shorten the implementation cycle of iCCM, reduce the implementation cost and improve the data quality, and can also realize the unification of key parameter information of the drawing source and the generality of the drawing source data. With the latest data mining, big data analysis and deep learning technologies, the application can extract unstructured data from the link diagrams of various power plant drawing systems, and can dynamically identify and apply the risk of unit shutdown and shutdown, and dynamically optimize the measures for preventing and predicting component faults.

[0091] In addition, the electronic device of the application includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to realize the nuclear power plant electrical instrument drawing data automatic extraction method of any one of the above. Specifically, according to the embodiments of the application, the process described above with reference to the flowchart can be realized as a computer software program. For example, the embodiments of the application include a computer program product including a computer program carried on a computer readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed by the electronic device and executed to perform the above-mentioned functions defined in the method of the embodiments of the application. The electronic device in the application can be a notebook, a desktop, a tablet computer, a smart phone or other terminal, and can also be a server.

[0092] In addition, the present application also provides a storage medium storing a computer program, which is executed by a processor to implement the nuclear power plant instrument drawing data automatic extraction method according to any one of the above. Specifically, it should be noted that the storage medium of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the above two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0093] The above computer readable medium can be contained in the above electronic device; or can exist separately and not be assembled into the electronic device.

[0094] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part.

[0095] Those skilled in the art will further realize that the mere conception of the examples described herein is not inducing the patentable subject matter recited in each claim. The combinations and / or sequences of various example elements, steps, operations, actions, and / or functions described in each example are not necessarily the only possible combinations and / or sequences for practicing the claimed subject matter. Those skilled in the art will further realize that the mechanisms of the various examples described herein are for implementing the several embodiments and are not meant to be limiting as to the scope of the claimed subject matter. That is, the protection afforded to the claimed subject matter is not limited to the mechanisms of practicing the described examples. Therefore, the claimed subject matter should be understood to encompass a variety of subject matter, and equally obvious to those in the art, including but not limited to the following:

[0096] The steps of a method or algorithm described in connection with the examples disclosed herein can be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module can reside in RAM, flash memory, ROM, electrically programmable ROM (EPROM or EEPROM), registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium can be integral to the processor. The processor and the storage medium can reside in an ASIC.

[0097] The examples described herein are only intended to illustrate the technical concepts and features of the present application, and the purpose is to enable those skilled in the art to understand the content of the present application and to implement it accordingly, and cannot limit the protection scope of the present application. Any equivalent changes and modifications made within the scope of the claims of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for automatic extraction of electrical instrument diagram data in a nuclear power plant, characterized by, The method comprises the following steps: obtaining a source drawing; identifying the drawing type of the source drawing; if the drawing type of the source drawing is a PDF drawing, extracting data of the PDF drawing according to a first data extraction method and saving the data as PDF structured data; if the drawing type of the source drawing is a VISIO drawing, extracting data of the VISIO drawing according to a second data extraction method and saving the data as VISIO structured data; classifying and managing the PDF structured data and the VISIO structured data to form classified drawing data; digitally managing the classified drawing data to form digital drawing data.

2. The method for automatically extracting data from nuclear power plant electrical diagrams according to claim 1, characterized in that, The method comprises the following steps: identifying and extracting data of the PDF drawing to obtain PDF drawing data; using a target detection model to detect element symbols to obtain PDF drawing element symbol data; identifying lines and connection points and constructing a network based on the lines and connection points to obtain a link relationship network; associating text and elements based on the PDF drawing data, the drawing element symbol data and the link relationship network to obtain associated data; outputting a target result based on the associated data and saving the result as the PDF structured data.

3. The method of claim 2, wherein the method further comprises: The method comprises the following steps: extracting vector elements using PyMuPDF or pdfplumber; converting a scanned copy or a bitmap using pdf2image to obtain a high-resolution image; extracting text and coordinates using Tesseract OCR and saving the text and coordinates as structured data; organizing the vector elements, the high-resolution image and the structured data to obtain the PDF drawing data.

4. The method for automatically extracting data from nuclear power plant electrical diagrams according to claim 1, wherein, The method comprises the following steps: using ShapeSheet to obtain all shapes and layers of the VISIO drawing to obtain shape data and layer data; identifying based on the shape data and the layer data to obtain all node information and connection information.

5. The method for automated extraction of nuclear power plant electrical instrumentation diagram data according to claim 1, wherein, The method comprises the following steps: classifying and managing the PDF structured data and the VISIO structured data according to systems, units, drawing types and drawing formats to form the classified drawing data.

6. The method for automatic extraction of nuclear power plant electrical instrumentation diagram data according to claim 5, wherein, The method comprises the following steps: correspondingly associating the classified drawing data according to units corresponding to each nuclear power plant, systems to which the units belong and corresponding drawing types to obtain the digital drawing data.

7. The method for automated extraction of nuclear power plant electrical instrumentation diagram data according to claim 1, wherein, The method further comprises: performing permission management and identification on the digital drawing data; performing integrated management on the digital drawing data.

8. A nuclear power plant electrical instrumentation diagram data automated extraction apparatus, characterized by, The method comprises the following steps: obtaining a source drawing; identifying the drawing type of the source drawing; ​ if the source drawing paper is a PDF drawing paper, extracting data of the PDF drawing paper according to a first data extraction method and saving the data as PDF structured data; if the source drawing paper is a VISIO drawing paper, extracting data of the VISIO drawing paper according to a second data extraction method and saving the data as VISIO structured data; a drawing paper classification management module, configured to classify and manage the PDF structured data and the VISIO structured data to form classified drawing paper data; a digital drawing paper management module, configured to digitally manage the classified drawing paper data to form digital drawing paper data.

9. A storage medium, characterized by The storage medium stores a computer program, and the computer program is adapted to be loaded by the processor to execute the steps of the nuclear power plant electrical instrument drawing paper data automatic extraction method according to any one of claims 1 to 7.

10. An electronic device, comprising: The device comprises a memory and a processor, and the memory stores a computer program. The processor executes the steps of the nuclear power plant electrical instrument drawing paper data automatic extraction method according to any one of claims 1 to 7 by calling the computer program stored in the memory.

Images