CN109446689A - DC converter station electrical secondary system drawing recognition methods and system - Google Patents
DC converter station electrical secondary system drawing recognition methods and system Download PDFInfo
- Publication number
- CN109446689A CN109446689A CN201811318771.XA CN201811318771A CN109446689A CN 109446689 A CN109446689 A CN 109446689A CN 201811318771 A CN201811318771 A CN 201811318771A CN 109446689 A CN109446689 A CN 109446689A
- Authority
- CN
- China
- Prior art keywords
- model
- file
- connection relationship
- secondary system
- electrical secondary
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses DC converter station electrical secondary system drawing recognition methods, including following procedure: identifying each element for including in every page of drawing in the drawing file of single engineering project；For every page of drawing, according to it includes each element construct the corresponding component object model comprising component attributes, corresponding connection relationship model is constructed according to the connection relationship of each interelement, corresponding drawing model is constructed according to drawing type, includes each component object model and connection relationship model in drawing model；According to each element associated of drawing model analyzing of all drawings, the complete link circuit of electrical secondary system is established.The present invention establishes the complete component object model of electrical secondary system and connection relationship model according to the connection logic between different elements, pass through the connection relationship attribute between different elements, judge the incidence relation between each drawing, establish complete secondary circuit connection relationship, the great convenience debugging and fortune inspection work of converter station.
Description
Technical field
The invention belongs to technical field of direct current power transmission, and in particular to a kind of DC converter station electrical secondary system drawing recognition methods
And system.
Background technique
It is required to inquire electrical secondary system work repeatedly in installation, debugging, operation and the service work of UHVDC converter station
Journey drawing accurately describes in detail the functions such as the protection, control, measurement of electrical secondary system and the mode of connection in engineering drawing.By
In the complex process of UHVDC converter station, equipment is numerous, therefore the drawing huge number that entire engineering project is related to, manually
Access workload is very big, inefficiency, error rate are high.
Engineering drawing, which is primarily present form, to be had: paper drawing and electronic drawing, wherein electronic drawing can with DWG, DXF,
The forms such as PDF, picture exist, and such electronic drawing can only be stored with document form, manage figure by traditional information system
Paper file；All kinds of drawing files need to open using special-purpose software parsing, manually browse one by one, two can not be parsed between file
Subsystem completely connects and incidence relation, forms the principle and connection mode of entire electrical secondary system；For DXF formatted file,
The valid data that can be parsed are difficult to carry out data relation analysis mainly with the presence of point, line and textual form.
The problem of identification is primarily present is carried out to engineering drawing to be had:
(1) engineering drawing electronic document identifies problem.
At present electrical secondary system engineering drawing mainly by: in the form of paper document, CAD, DXF, PDF, picture etc. save, do not unite
One format specification, and be difficult to directly read its semanteme.
(2) engineering drawing classification problem.
Up to ten thousand of electrical secondary system drawing in one engineering project is divided into different types in the drawing of each project again and uses
To express different information, great difficulty is brought to the management, classification, retrieval of drawing.
(3) engineering drawing intelligent recognition problem.
The work of drawing content recognition includes the identification to text in the identification of element in figure and element, to information form
Content recognition and connection relationship between each element is identified.It, can between each different elements since component kind is many and diverse
It can there is only fine differences.Therefore common image recognition technology can generate the problems such as identification is not accurate, and time-consuming.
Summary of the invention
It is an object of the invention to overcome deficiency in the prior art, a kind of DC converter station electrical secondary system drawing is provided
Recognition methods and system, using various elements in neural network recognization electrical secondary system, according to the connection logic between different elements
Electrical secondary system is established completely to connect and incidence relation.
In order to solve the above technical problems, the present invention provides a kind of DC converter station electrical secondary system drawing recognition methods,
It is characterized in, including following procedure:
Identify each element for including in every page of drawing in the drawing file of engineering project；
For every page of drawing, according to it includes each element construct the corresponding component object model comprising component attributes,
Corresponding connection relationship model is constructed according to the connection relationship of each interelement, corresponding drawing model is constructed according to drawing type,
It include each component object model and connection relationship model in drawing model；
According to each element associated of drawing model analyzing of all drawings, the complete link circuit of electrical secondary system is established.
Further, the tool for each element for including in every page of drawing in the drawing file for identifying single engineering project
Body process are as follows:
The drawing file of single engineering project is converted into picture format, is obtained a pair of with single page drawing one in drawing file
The image answered；
Identify each element for including in each image.
Further, the drawing file by single engineering project is converted to the detailed process of picture format are as follows:
The drawing file of single engineering project is converted into PDF format file；
It is single page drawing file by each PDF format file division；
Each single page drawing file is converted into image.
Further, each element for including in each image is identified using convolutional neural networks.
Further, it according to each element associated of drawing model analyzing of all drawings, establishes electrical secondary system and completely connects back to
The detailed process on road are as follows:
It completes to analyze the element object that each drawing model includes after all drawing files identify and establish drawing model,
These element objects are extracted, component object model is established, analyzing each drawing model includes element connection relationship, is established
Connection relationship model establishes complete secondary circuit connection relationship finally according to component object model, connection relationship model.
Correspondingly, the present invention also provides a kind of DC converter station electrical secondary system drawing identifying systems, characterized in that including
Drawing identification module, drawing modeling module, drawing model identification module；
Drawing identification module, each element for including in every page of drawing in the drawing file of engineering project out for identification；
Drawing modeling module, for be directed to every page of drawing, according to it includes each element building it is corresponding include element category
Property component object model, corresponding connection relationship model is constructed according to the connection relationship of each interelement, according to drawing type structure
Corresponding drawing model is built, includes each component object model and connection relationship model in drawing model；
Drawing model identification module establishes secondary system for each element associated of drawing model analyzing according to all drawings
It unites complete link circuit.
Further, in drawing identification module, in the drawing file for identifying single engineering project in every page of drawing
The detailed process for each element for including are as follows:
The drawing file of single engineering project is converted into picture format, is obtained a pair of with single page drawing one in drawing file
The image answered；
Identify each element for including in each image.
Further, in drawing identification module, the drawing file by single engineering project is converted to picture format
Detailed process are as follows:
The drawing file of single engineering project is converted into PDF format file；
It is single page drawing file by each PDF format file division；
Each single page drawing file is converted into image.
Further, in drawing identification module, each element for including in each image is identified using convolutional neural networks.
Further, it is established in drawing model identification module according to each element associated of drawing model analyzing of all drawings
The detailed process of the complete link circuit of electrical secondary system are as follows:
It completes to analyze the element object that each drawing model includes after all drawing files identify and establish drawing model,
These element objects are extracted, component object model is established, analyzing each drawing model includes element connection relationship, is established
Connection relationship model establishes complete secondary circuit connection relationship finally according to component object model, connection relationship model.
Compared with prior art, the beneficial effects obtained by the present invention are as follows being:
The present invention identifies various elements in electrical secondary system, improves identification using neural network in depth learning technology
Accuracy establishes the complete component object model of electrical secondary system and connection relationship mould according to the connection logic between different elements
Type judges the incidence relation between each drawing by the connection relationship attribute between different elements, establishes complete secondary returning
Road connection relationship, the debugging and fortune inspection work of great convenience converter station, improves its working efficiency.
Detailed description of the invention
Fig. 1 is the training sample of tape label in embodiment；
Fig. 2 is the corresponding picture format of input and output drawing in embodiment；
Fig. 3 is the terminal component being partitioned into from Fig. 2 embodiment.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, a kind of DC converter station electrical secondary system drawing recognition methods of the invention, including following procedure:
The drawing file of single engineering project is converted to picture format by step S1, and acquisition respectively corresponds in drawing file
The multiple images of single page drawing.
Engineering drawing is designed as unit of shielding cabinet, usually there is multiple screen cabinets in an engineering, will be single
The drawing file of a engineering project carries out following treatment process by screen cabinet grouping, to the drawing file of each screen cabinet group:
1) it by the suffix of reading drawing file, determines file type, corresponding conversion method is transferred according to file type,
Drawing is uniformly converted to PDF format file；
2) each PDF drawing file is parsed, if in PDF drawing file including multipage drawing, by drawing file whole
It is divided into single page drawing；
It may include multipage drawing in one drawing file, how many drawing identified from drawing file first,
Then these drawings are converted into picture respectively.
3) RGB image is converted to after single page drawing being carried out noise reduction process, image and single page drawing correspond, and by figure
Screen cabinet grouping storage image belonging to paper.
Step S2 identifies all elements for including in each image.
In order to improve image recognition efficiency, first to image preprocessing, detailed process are as follows:
1) it is filtered: picture noise interference, and Protect edge information information is eliminated using median filtering technology.
2) using the parallel symmetrical thinning algorithm (BCTA) retained based on interior point and micronization processes: there is high processing rate
4 × 4 thinning algorithms (44TA) to image carry out micronization processes, keep image connectivity, retain image endpoint, holding figure
The symmetry of picture guarantees that refining result generates the skeleton for being located at former lines center simultaneously.
Each element in image is identified in the embodiment of the present invention using convolutional neural networks.
First choice segmentation tape label training data and training convolutional neural networks:
1) according to the drafting pattern of every kind of element in DC converter station electrical secondary system drawing, by the element in RGB image point
It is cut into tape label training data, its characteristic value is calculated HOG histograms of oriented gradients algorithm and is mentioned in the form of two-dimensional matrix
Supply neural network.Fig. 1 is the tape label training data an of terminal component.
2) training and verifying convolutional neural networks
It is modeled using the tape label training of segmentation with component data collection, training and verifying convolutional neural networks.
Then pretreated image is inputted into trained convolutional neural networks, the element in drawing is identified one by one.
Step S3 analyzes electrical secondary system element and drawing type, defines electrical secondary system component object model, connection relationship mould
Type and drawing model establish drawing model then according to each element identified in each image for each image.
Firstly, defining component object model, connection relationship model and drawing model in electrical secondary system, specifically describe are as follows:
1) element according to used in DC converter station electrical secondary system, for example, screen cabinet, cabinet, board, terminal block,
Terminal, light pre-define its model and its attribute for every kind of element every, interchanger etc..
Such as shielding cabinet object model includes title, number, property；Terminal object model includes title, number, reference
Name etc..The model that these elements are described using JSON format, the component information foundation for needing to extract when as drawing parsing.
2) according to the connection relationship of interelement each in DC converter station electrical secondary system, for example including screen cabinet connection relationship and end
Sub- connection relationship defines its model and its attribute.
Such as shielding cabinet connection relationship model includes that starting point screen cabinet and opposite side screen cabinet title, cabinet interface type and cabinet interface are retouched
It states；Terminal connection relationship model includes the reference name of starting point terminal and opposite side terminal, linkage function type and connection description etc..
The model that these connection relationships are described using JSON format, the link information foundation for needing to extract when as drawing parsing.
3) according to DC converter station electrical secondary system drawing type, generally include: screen cabinet figure, cabinet figure, terminal block figure, open into
Output the drawings types such as schematic diagram, catenation principle figure, bus connection figure, for information described by each type drawing difference and
Element-cont difference is wrapped, the model of each type drawing, the element pair comprising each element in figure in each drawing model are defined
As model and each interelement connection relationship model.
If the drawing model of terminal block includes screen cabinet, terminal block title, terminal block equipment reference name, terminal belonging to terminal block
Description, terminal number, terminal reference name, internal connection terminal reference name, the affiliated screen cabinet title of external institute's connection terminal, terminal
Reference name etc..These drawing models are described using JSON format.
Then according to the type of every drawing, according to the drawing model of definition, corresponding drawing mould is described into each drawing
Type is described using JSON format, obtains corresponding JSON formatted file.
Step S4 parses each element associated according to drawing model file, establishes the complete link circuit of electrical secondary system.
It completes to analyze the element pair that each drawing model file includes after all drawing files identify and establish drawing model
As these element objects are extracted, component object model is established, analyzing each drawing model file includes that element connection is closed
System, establish a connection model, finally according to component object model, connection relationship model, establishes complete secondary circuit connection
Relationship.
Specific method describes attribute, foundation screen for screen cabinet number, screen cabinet title and screen cabinet in analysing screen cabinet graph model first
Cabinet object model is analyzed and shields cabinet title, device name, equipment description, device type and equipment reference name category in cabinet graph model
Property, device object model is established, analyzes and shields cabinet title, device name, board title, slot name, terminal in board graph model
Title, terminal number and terminal reference name attribute, establish terminal object model, and so on, include by all in drawing model
Element object attribute extract, establish component object model；
Then starting point screen cabinet title described in analysis principle figure, opposite side connection screen cabinet title, connecting interface type and company
Connection interface describes attribute, establishes screen cabinet connection relationship model, analyzes screen cabinet, end belonging to terminal block described in terminal block graph model
Sub- ranking claims, terminal block equipment reference name, terminal describe, terminal number, terminal reference name, internal connection terminal reference name, outside
The attributes such as the affiliated screen cabinet title of institute, portion connection terminal, terminal reference name by terminal in terminal block and internal terminal connect, are held
Terminal and the terminal of external connection establish two terminal connection relationship models respectively in son row, analyze described in connected-graph model
Starting point screen cabinet title, starting point terminal reference name, opposite side screen cabinet title, opposite side terminal reference name, connection terminal function type and company
The attributes such as connecting terminal description, establish terminal connection relationship model, finally by the connection relationship attributes for including all in drawing model
Extraction establishes a connection model；
Finally by electrical secondary system drawing all in identification DC converter station, quoted by the terminal of terminal object model
Name attribute can completely construct the subordinate relation from screen cabinet, cabinet, board, slot element object to terminal object, lead to simultaneously
The terminal reference name attribute for crossing terminal object model can retrieve the reference of its opposite side connection terminal in terminal connection relationship model
Name continues to retrieve next stage opposite side terminal reference name by opposite side terminal reference name, until searching the reference of afterbody terminal
Name, constructs the complete electrical secondary system terminal link circuit of the terminal；DC converter station is established after finally having retrieved all terminals
The complete terminal subordinate of interior entire electrical secondary system and connection relationship.
Based on inventive concept same as the above method, the present invention also provides a kind of DC converter station electrical secondary system drawings
Identifying system, characterized in that including drawing identification module, drawing modeling module, drawing model identification module；
Drawing identification module, each element for including in every page of drawing in the drawing file of engineering project out for identification；
Drawing modeling module, for be directed to every page of drawing, according to it includes each element building it is corresponding include element category
Property component object model, corresponding connection relationship model is constructed according to the connection relationship of each interelement, according to drawing type structure
Corresponding drawing model is built, includes each component object model and connection relationship model in drawing model；
Drawing model identification module establishes secondary system for each element associated of drawing model analyzing according to all drawings
It unites complete link circuit.
Further, in drawing identification module, in the drawing file for identifying single engineering project in every page of drawing
The detailed process for each element for including are as follows:
The drawing file of single engineering project is converted into picture format, is obtained a pair of with single page drawing one in drawing file
The image answered；
Identify each element for including in each image.
Further, in drawing identification module, the drawing file by single engineering project is converted to picture format
Detailed process are as follows:
The drawing file of single engineering project is converted into PDF format file；
It is single page drawing file by each PDF format file division；
Each single page drawing file is converted into image.
Further, in drawing identification module, each element for including in each image is identified using convolutional neural networks.
Further, it is established in drawing model identification module according to each element associated of drawing model analyzing of all drawings
The detailed process of the complete link circuit of electrical secondary system are as follows:
It completes to analyze the element object that each drawing model includes after all drawing files identify and establish drawing model,
These element objects are extracted, component object model is established, analyzing each drawing model includes element connection relationship, is established
Connection relationship model establishes complete secondary circuit connection relationship finally according to component object model, connection relationship model.
Embodiment
Fig. 2 show an input and output schematic diagram after image is converted, and element is terminal in figure, establishes terminal member
Part object model and terminal connection relationship model.
For terminal component object model, defining its object model attributes includes title, description, number and terminal reference
Name is described using JSON format are as follows:
" port_ref " indicates that the terminal reference name attribute of terminal component object, "+.A:-D10:-X4:1 " indicate in attribute
Hold, wherein "+.A " indicates the affiliated cabinet title of terminal, "-D10 " indicates the affiliated board title of terminal, and "-X4 " is indicated belonging to terminal
Slot name, " 1 " indicate terminal names.
For terminal connection relationship model, define its model attributes include connection terminal description, connection terminal function type,
Starting point terminal reference name and opposite side terminal reference name are described using JSON format are as follows:
| Field name | Meaning |
| pc_desc | Connection terminal description |
| pc_type | Connection terminal function type |
| origin_port_ref | Starting point terminal reference name |
| dest_port_ref | Opposite side terminal reference name |
For input and output schematic diagram, defining its drawing model includes shielding cabinet title, connection terminal function class belonging to terminal
The attributes such as type, connection terminal description, starting point terminal reference name, opposite side screen cabinet title, opposite side terminal reference name, using JSON format
The model of description are as follows:
Fig. 3 show segmentation tape label training data, terminal component figure in input and output figure and instructs through convolutional neural networks
Each element for including can be automatically identified after white silk.
All terminal components in analysis chart 2, the format defined by input and output schematic model is by the category of terminal component
Property filling drawing model in, the model file format fragment of final output is as follows:
Complete all drawing file modelings.
The attribute in drawing model is extracted into according to the format of terminal object model and terminal connection relationship model later
Corresponding model the terminal object model of extraction four, is respectively as follows: totally for above-mentioned drawing model fragment
" port_ref " indicates the terminal reference name attribute of terminal component object, "=S2+CCP11A:+.A:-D10:-X4:
1 " indicates property content, wherein "=S2+CCP11A " indicates to shield cabinet title belonging to terminal, "+.A " indicates the affiliated cabinet name of terminal
Claim, "-D10 " indicates the affiliated board title of terminal, and "-X4 " indicates the affiliated slot name of terminal, and " 1 " indicates terminal names, and ": " is
Separator.
For above-mentioned drawing model fragment, totally two, the terminal connection relationship model of extraction is respectively as follows:
Finally after the completion of all drawings identify, it can be searched for according to the terminal reference name in terminal connection relationship model
Other terminal connection relationship models comprising starting point terminal reference name and opposite side terminal reference name are retrieved and corresponding are held next time
Sub- reference name constructs the complete electrical secondary system terminal link circuit of the terminal until searching afterbody terminal reference name.
The present invention identifies various elements in electrical secondary system, improves identification using neural network in depth learning technology
Accuracy establishes the complete component object model of electrical secondary system and connection relationship mould according to the connection logic between different elements
Type judges the incidence relation between each drawing by the connection relationship attribute between different elements, the great convenience change of current
The debugging and fortune inspection work stood, improve its working efficiency.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (10)
1. DC converter station electrical secondary system drawing recognition methods, characterized in that including following procedure:
Identify each element for including in every page of drawing in the drawing file of engineering project；
For every page of drawing, according to it includes each element construct the corresponding component object model comprising component attributes, according to
The connection relationship of each interelement constructs corresponding connection relationship model, constructs corresponding drawing model, drawing according to drawing type
It include each component object model and connection relationship model in model；
According to each element associated of drawing model analyzing of all drawings, the complete link circuit of electrical secondary system is established.
2. DC converter station electrical secondary system drawing recognition methods according to claim 1, characterized in that the identification is gone to work
The detailed process for each element for including in every page of drawing in journey item purpose drawing file are as follows:
The drawing file of single engineering project is converted into picture format, is obtained one-to-one with single page drawing in drawing file
Image；
Identify each element for including in each image.
3. the DC converter station electrical secondary system drawing recognition methods according to claim 2 based on deep learning, feature
It is that the drawing file by single engineering project is converted to the detailed process of picture format are as follows:
The drawing file of single engineering project is converted into PDF format file；
It is single page drawing file by each PDF format file division；
Each single page drawing file is converted into image.
4. DC converter station electrical secondary system drawing recognition methods according to claim 2, characterized in that use convolutional Neural
Network Recognition goes out each element for including in each image.
5. DC converter station electrical secondary system drawing recognition methods according to claim 1, characterized in that according to all drawings
Each element associated of drawing model analyzing, establish the detailed process of the complete link circuit of electrical secondary system are as follows:
It completes the element object that each drawing model includes to be analyzed, by this after all drawing files identify and establish drawing model
A little element objects extract, and establish component object model, and analyzing each drawing model includes element connection relationship, establish connection
Relational model establishes complete secondary circuit connection relationship finally according to component object model, connection relationship model.
6. DC converter station electrical secondary system drawing identifying system, characterized in that including drawing identification module, drawing modeling module,
Drawing model identification module；
Drawing identification module, each element for including in every page of drawing in the drawing file of engineering project out for identification；
Drawing modeling module, for being directed to every page of drawing, according to it includes each element construct it is corresponding comprising component attributes
Component object model constructs corresponding connection relationship model according to the connection relationship of each interelement, according to the building pair of drawing type
The drawing model answered includes each component object model and connection relationship model in drawing model；
It is complete to establish electrical secondary system for each element associated of drawing model analyzing according to all drawings for drawing model identification module
Whole link circuit.
7. DC converter station electrical secondary system drawing identifying system according to claim 6, characterized in that drawing identification module
In, the detailed process for each element for including in every page of drawing in the drawing file for identifying engineering project are as follows:
The drawing file of single engineering project is converted into picture format, is obtained one-to-one with single page drawing in drawing file
Image；
Identify each element for including in each image.
8. DC converter station electrical secondary system drawing identifying system according to claim 7, characterized in that drawing identification module
In, the drawing file by single engineering project is converted to the detailed process of picture format are as follows:
The drawing file of single engineering project is converted into PDF format file；
It is single page drawing file by each PDF format file division；
Each single page drawing file is converted into image.
9. DC converter station electrical secondary system drawing identifying system according to claim 7, characterized in that drawing identification module
In, each element for including in each image is identified using convolutional neural networks.
10. DC converter station electrical secondary system drawing identifying system according to claim 6, characterized in that drawing model is known
According to each element associated of drawing model analyzing of all drawings in other module, the specific mistake of the complete link circuit of electrical secondary system is established
Journey are as follows:
It completes the element object that each drawing model includes to be analyzed, by this after all drawing files identify and establish drawing model
A little element objects extract, and establish component object model, and analyzing each drawing model includes element connection relationship, establish connection
Relational model establishes complete secondary circuit connection relationship finally according to component object model, connection relationship model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811318771.XA CN109446689A (en) | 2018-11-07 | 2018-11-07 | DC converter station electrical secondary system drawing recognition methods and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811318771.XA CN109446689A (en) | 2018-11-07 | 2018-11-07 | DC converter station electrical secondary system drawing recognition methods and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109446689A true CN109446689A (en) | 2019-03-08 |
Family
ID=65550715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811318771.XA Pending CN109446689A (en) | 2018-11-07 | 2018-11-07 | DC converter station electrical secondary system drawing recognition methods and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446689A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070336A (en) * | 2019-04-16 | 2019-07-30 | 杭州坤天自动化系统有限公司 | Analog simulation method for automatic modeling and device based on artificial intelligence |
| CN110309807A (en) * | 2019-07-08 | 2019-10-08 | 西北工业大学 | CAD diagram paper intelligent identification Method |
| CN110795809A (en) * | 2019-11-07 | 2020-02-14 | 国网河北省电力有限公司电力科学研究院 | Method, system and medium for transformer substation electrical secondary circuit connection relation based on CAD graph automatic pickup |
| CN110909650A (en) * | 2019-11-15 | 2020-03-24 | 清华大学 | CAD drawing identification method and device based on domain knowledge and target detection |
| CN111079766A (en) * | 2019-12-19 | 2020-04-28 | 青岛科技大学 | Intelligent method for P & ID (peer-to-peer) graph |
| CN111898401A (en) * | 2020-05-26 | 2020-11-06 | 中建八局天津建设工程有限公司 | Intelligent identification method for construction engineering drawing |
| CN112541241A (en) * | 2020-12-10 | 2021-03-23 | 贵州电网有限责任公司 | Transformer substation secondary AC/DC flow graph paper digital model creation system and method |
| CN113255499A (en) * | 2021-05-18 | 2021-08-13 | 中国能源建设集团安徽省电力设计院有限公司 | Digital automatic modeling method for secondary circuit of transformer substation cable |
| CN115797291A (en) * | 2022-12-01 | 2023-03-14 | 中国南方电网有限责任公司超高压输电公司柳州局 | Circuit terminal identification method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484499A (en) * | 2014-11-18 | 2015-04-01 | 中国南方电网有限责任公司超高压输电公司南宁局 | Dynamic simulation image rapid generation method for substation secondary circuit |
| CN105718636A (en) * | 2016-01-14 | 2016-06-29 | 中国南方电网有限责任公司 | Automatic conversion method for station primary wiring diagram model |
| CN106446431A (en) * | 2016-09-30 | 2017-02-22 | 国网江苏省电力公司电力科学研究院 | Secondary visualization method based on extra-high voltage direct current transmission control protection device |
| CN108054719A (en) * | 2017-12-12 | 2018-05-18 | 南京国电南自电网自动化有限公司 | Intelligent substation networking secondary circuit modeling method and method for diagnosing faults |
-
2018
- 2018-11-07 CN CN201811318771.XA patent/CN109446689A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484499A (en) * | 2014-11-18 | 2015-04-01 | 中国南方电网有限责任公司超高压输电公司南宁局 | Dynamic simulation image rapid generation method for substation secondary circuit |
| CN105718636A (en) * | 2016-01-14 | 2016-06-29 | 中国南方电网有限责任公司 | Automatic conversion method for station primary wiring diagram model |
| CN106446431A (en) * | 2016-09-30 | 2017-02-22 | 国网江苏省电力公司电力科学研究院 | Secondary visualization method based on extra-high voltage direct current transmission control protection device |
| CN108054719A (en) * | 2017-12-12 | 2018-05-18 | 南京国电南自电网自动化有限公司 | Intelligent substation networking secondary circuit modeling method and method for diagnosing faults |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110070336A (en) * | 2019-04-16 | 2019-07-30 | 杭州坤天自动化系统有限公司 | Analog simulation method for automatic modeling and device based on artificial intelligence |
| CN110309807A (en) * | 2019-07-08 | 2019-10-08 | 西北工业大学 | CAD diagram paper intelligent identification Method |
| CN110795809A (en) * | 2019-11-07 | 2020-02-14 | 国网河北省电力有限公司电力科学研究院 | Method, system and medium for transformer substation electrical secondary circuit connection relation based on CAD graph automatic pickup |
| CN110795809B (en) * | 2019-11-07 | 2023-08-29 | 国网河北省电力有限公司电力科学研究院 | Method, system and medium for automatically picking up connection relation of electric secondary circuit of transformer substation based on CAD (computer aided design) drawing |
| CN110909650A (en) * | 2019-11-15 | 2020-03-24 | 清华大学 | CAD drawing identification method and device based on domain knowledge and target detection |
| CN111079766A (en) * | 2019-12-19 | 2020-04-28 | 青岛科技大学 | Intelligent method for P & ID (peer-to-peer) graph |
| CN111898401A (en) * | 2020-05-26 | 2020-11-06 | 中建八局天津建设工程有限公司 | Intelligent identification method for construction engineering drawing |
| CN112541241A (en) * | 2020-12-10 | 2021-03-23 | 贵州电网有限责任公司 | Transformer substation secondary AC/DC flow graph paper digital model creation system and method |
| CN113255499A (en) * | 2021-05-18 | 2021-08-13 | 中国能源建设集团安徽省电力设计院有限公司 | Digital automatic modeling method for secondary circuit of transformer substation cable |
| CN115797291A (en) * | 2022-12-01 | 2023-03-14 | 中国南方电网有限责任公司超高压输电公司柳州局 | Circuit terminal identification method and device, computer equipment and storage medium |
| CN115797291B (en) * | 2022-12-01 | 2024-07-23 | 中国南方电网有限责任公司超高压输电公司柳州局 | Loop terminal identification method, loop terminal identification device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446689A (en) | DC converter station electrical secondary system drawing recognition methods and system | |
| CN111563509B (en) | Tesseract-based substation terminal row identification method and system | |
| CN110765639B (en) | Electrical simulation modeling method and device and readable storage medium | |
| CN110795809B (en) | Method, system and medium for automatically picking up connection relation of electric secondary circuit of transformer substation based on CAD (computer aided design) drawing | |
| CN115329556A (en) | Transformer substation CAD drawing auditing method and device | |
| CN113485160A (en) | Simulation modeling method and device based on pattern matching recognition | |
| CN109840351A (en) | A kind of DC converter station electrical secondary system drawing modeling method, system and device | |
| CN105678344A (en) | Intelligent classification method for power instrument equipment | |
| CN109800156A (en) | A kind of subway signal system automation test method based on profile command | |
| CN109446345A (en) | Nuclear power file verification processing method and system | |
| CN111625964B (en) | Method, system and equipment for constructing transformer substation graph model based on logical relationship | |
| CN110019519A (en) | Data processing method, device, storage medium and electronic device | |
| CN104077727A (en) | Substation electric equipment machine account intelligent type-in method and system | |
| CN114547968B (en) | Physical loop modeling method of intelligent substation drawing | |
| CN111124892B (en) | Automatic testing method and system based on command line | |
| CN114494681A (en) | Intelligent comparison method and system for wiring terminal, computer equipment and storage medium | |
| CN113255499B (en) | Digital automatic modeling method for secondary loop of transformer substation cable | |
| CN116541912A (en) | Method and device for generating wiring diagram based on CAD image recognition | |
| CN115238428A (en) | Transformer substation secondary drawing visual editing digital configuration device, method and application | |
| CN115587190A (en) | Construction method and device of knowledge graph in power field and electronic equipment | |
| CN114154856A (en) | Power grid path planning node calculation method and system based on road network | |
| CN106557564A (en) | A kind of object data analysis method and device | |
| CN105279085A (en) | Rule self-defining based smart substation configuration file test system and method | |
| CN115437327B (en) | Intelligent nuclear security level DCS design and verification method, system and storage medium | |
| CN109472766A (en) | Bridge bolt area positioning method and terminal device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |