CN115294595A - Intelligent analysis method for primary wiring diagram of transformer substation - Google Patents
Intelligent analysis method for primary wiring diagram of transformer substation Download PDFInfo
- Publication number
- CN115294595A CN115294595A CN202210727367.8A CN202210727367A CN115294595A CN 115294595 A CN115294595 A CN 115294595A CN 202210727367 A CN202210727367 A CN 202210727367A CN 115294595 A CN115294595 A CN 115294595A
- Authority
- CN
- China
- Prior art keywords
- primitive
- wiring diagram
- primary wiring
- primitives
- transformer substation
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/42—Document-oriented image-based pattern recognition based on the type of document
- G06V30/422—Technical drawings; Geographical maps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent analysis method for a primary wiring diagram of a transformer substation, which comprises the following steps: 1) The position detection and the rotation angle identification of the primitive of the primary wiring diagram are realized based on a target detection algorithm and a template matching method; 2) Identifying main connecting lines in the wiring diagram by utilizing Hough line detection, and detecting the end points of the graphic elements according to the positions of the graphic elements; 3) Filling a pixel area where the primitive is located with background color to obtain a primary wiring diagram only containing the connecting lines, and extracting the connecting line pixels by adopting threshold segmentation; 4) Selecting an end point of any one primitive as an initial growth point, acquiring a communication area with the initial growth point, and detecting and fitting the communication area by adopting or copying; the invention has the advantages that: the method can intelligently extract structural information such as elements, topological relations, keywords and the like from the unstructured primary wiring diagram, automatically generate a wiring table, can effectively carry out digital management on the existing primary wiring diagram, and greatly improves the working efficiency of operation and maintenance managers of the transformer substation.
Description
Technical Field
The invention relates to the technical field of digital image recognition, in particular to an intelligent analysis method for a primary wiring diagram of a transformer substation.
Background
The transformer substation primary wiring diagram is the core basis of the dispatching work of the power system, and the digital management of the transformer substation primary wiring diagram is greatly convenient for the dispatching work of the power. At present, a transformer substation primary wiring diagram is mainly read and input in a manual mode, and along with the rapid construction of a power grid, the workload of manually inputting the wiring diagram is huge, so that the requirement of actual operation and maintenance work is difficult to meet.
Disclosure of Invention
The invention aims to provide an intelligent analysis method for a primary wiring diagram of a transformer substation, which can intelligently identify the topological structure of the primary wiring diagram of the transformer substation through picture data and form computer-understandable structured data, thereby realizing intelligent identification and automatic input of the primary wiring diagram of the transformer substation.
In order to achieve the purpose, the invention adopts the technical scheme that:
a transformer substation primary wiring diagram intelligent analysis method comprises the following steps:
step 1, realizing primary wiring diagram primitive position detection and rotation angle identification based on a target detection algorithm and a template matching method;
step 2, identifying main connecting lines in the wiring diagram by utilizing Hough line detection, and detecting a primitive endpoint according to a primitive position;
step 3, filling a pixel area where the primitive is located with background color to obtain a primary wiring diagram only containing the connecting lines, and extracting the connecting line pixels by adopting threshold segmentation;
step 4, selecting an endpoint of any primitive as an initial growth point, acquiring a communication area with the initial growth point, detecting and fitting the communication area by adopting or copying, acquiring a linear connecting line, the endpoint and equipment connected with the endpoint in the area, and adding the equipment in the communication area into a connected equipment set;
step 5, sequentially selecting the end points which are not detected by the connected equipment and repeating the step 4 to expand the connected domain until all the end points are connected;
step 6, repeating the step 4 and the step 5 for the equipment which is not added with the connected domain to form a new connected domain until all the equipment on the wiring diagram is connected;
step 7, adopting optical character recognition to detect character identification in the primary wiring diagram, and matching characters with the primitives according to the nearest matching relationship;
and 8, storing the recognition result in a classification mode according to the graphic elements, the characters and the connecting lines, wherein the characters need to be associated with corresponding elements, and the connecting lines need to be associated with corresponding elements and ports.
In the above method for intelligently analyzing the primary wiring diagram of the transformer substation, the step 1 can be specifically realized by the following steps:
step 1.1, marking all primitives in a primary wiring diagram of a transformer substation, cutting the wiring diagram into a plurality of picture blocks for model training and target detection testing, mapping the positions of the primitives to an original wiring diagram after the testing is finished, and obtaining the types and the positions of the primitives according to the target detection result; the graphic elements comprise 11 categories of a circuit breaker, an isolation disconnecting link, a grounding disconnecting link, two-winding transformers, three-winding transformers, a capacitor, a reactor, a bus, a circuit, a reactive power compensation device and a generator;
step 1.2, making a standard primitive template library, which mainly comprises templates of various primitives with different rotation angles, wherein, for example, a single symmetry axis primitive needs to comprise four templates of 0 degree, 90 degrees, 180 degrees and 270 degrees, and a double symmetry axis primitive needs to comprise two templates of 0 degree and 180 degrees;
and step 1.3, carrying out template matching on the primitive obtained by target detection and a standard primitive template library, obtaining the rotation angle of the primitive, and obtaining the terminal distribution sequence of the primitive according to electrical professional knowledge.
In the above method for intelligently analyzing the primary wiring diagram of the transformer substation, the step 2 may be specifically implemented as the following steps:
step 2.1, preprocessing an original wiring diagram by adopting Gaussian filtering and threshold segmentation to reduce the interference of irrelevant pixels;
step 2.2, fitting and combining straight lines in the wiring diagram by adopting Hough straight line detection to obtain connecting lines among the pixels;
and 2.3, performing AND operation on the rectangular frame containing the primitives and the connecting lines, wherein the intersection points of the rectangles and the connecting lines can be used as the terminal positions of the corresponding primitives, and meanwhile, numbering the primitive terminals according to the terminal distribution sequence in the step 1.3.
In the above method for intelligently analyzing the primary wiring diagram of the transformer substation, the step 3 can be specifically realized by the following steps:
step 3.1, in order to effectively extract the specific position of the connecting line, filling the pixel corresponding to the primitive in the picture by adopting a background color, wherein the top left vertex of the primitive rectangle is (x) min ,y min ) And the coordinate of the lower right vertex is (x) max ,y max ) Let P stand in i,j {i∈(x min ,x max ),j∈(y min ,y max ) =255, eliminating the influence of primitive pixels on the connection line extraction;
and 3.2, performing Gaussian smoothing and threshold segmentation on the wiring diagram with the primitive removed, and extracting pixels of the connecting lines.
In the above method for intelligently analyzing the primary wiring diagram of the transformer substation, the step 4 can be specifically realized by the following steps:
step 4.1, randomly selecting a primitive, taking one terminal on the primitive as an initial growth point, expanding the initial point by adopting an expansion algorithm, and solving a connected domain of the initial point according to an 8-connected domain rule, wherein the connected domain is a connecting line which can pass through the initial point;
step 4.2, carrying out Hough line detection on the connected domain to obtain line segments corresponding to the connecting lines;
4.3, calculating the intersection point between every two line segments of the detected line segments, and dividing the intersection point into an L-shaped intersection point, a T-shaped intersection point and a ten-shaped intersection point, wherein for the ten-shaped intersection point, the two line segments are respectively cut into two sections at the intersection point to obtain a new connecting line;
step 4.4, dividing the end points of all the line sections into connecting line end points and element end points, wherein the connecting line end points are obtained in the step 4.3, the element end points can be obtained according to the positions of the primitive terminals in the step 2.3, and meanwhile, primitives connected with the element end points are obtained to form a topological relation between the connecting lines and the primitives; if two end points of a section of connecting line are not the connecting line end points or the element end points, the connecting line is considered as a bus;
and 4.5, adding the graphic primitives connected with the element end points into the existing connected domain, taking the new connected domain as the identified area, and taking all the graphic primitive end points which are not connected with the element or the connecting line in the connected domain as alternative initial growing points.
In the above method for intelligently analyzing the primary wiring diagram of the transformer substation, the step 5 can be specifically realized by the following steps:
and 5.1, randomly selecting one point from the alternative initial growing points, and calculating a new connected domain from the point until all element end points in the connected domain are connected with the connecting line or the primitive end point.
In the above method for intelligently analyzing the primary wiring diagram of the transformer substation, the step 6 can be specifically realized by the following steps:
and 6.1, after the step 5 is executed, if the graphic elements are not contained in the connected domain, continuously selecting the graphic elements from the graphic elements, and executing the step 4 and the step 5.
In the above method for intelligently analyzing the primary wiring diagram of the transformer substation, the step 7 can be specifically realized by the following steps:
7.1, extracting character strings and positions thereof in the wiring diagram by adopting an optical character recognition technology;
and 7.2, calculating a graphic element closest to each character string, wherein the distance between the outer boundary of the graphic element and the outer boundary of the character string does not exceed a certain threshold value, using the character string as a keyword of the graphic element, and otherwise, discarding the character string.
Compared with the prior art, the intelligent analysis method for the primary wiring diagram of the transformer substation can intelligently extract structural information such as elements, topological relations, keywords and the like from the unstructured primary wiring diagram, automatically generate the wiring table, effectively carry out digital management on the existing primary wiring diagram, and greatly improve the working efficiency of operation and maintenance managers of the transformer substation.
Drawings
FIG. 1 is a general flow chart of a method for intelligent identification of a primary wiring diagram in accordance with an embodiment of the present invention;
FIG. 2 is a diagram of primitive erasure effects in accordance with one embodiment of the present invention;
FIG. 3 is a diagram illustrating the effect of connecting line extraction according to an embodiment of the present invention;
FIG. 4 is a visualization of recognition results in one embodiment of the invention;
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The embodiment combines the existing image processing, target detection and optical character recognition algorithms to intelligently recognize the primary wiring diagram of the transformer substation in the power system, so that the intelligent analysis of the primary wiring diagram from the image to the structured data is realized, and the method has very important significance for improving the intelligent operation and maintenance level of the transformer substation.
The embodiment is realized by the following technical scheme, and the intelligent analysis method for the primary wiring diagram of the transformer substation comprises the following steps:
s1: and realizing primary wiring diagram primitive position detection and rotation angle identification based on a target detection algorithm and a template matching method.
S2: identifying main connecting lines in the wiring diagram by utilizing Hough line detection, and detecting the end points of the graphic elements according to the positions of the graphic elements;
s3: filling a pixel area where the primitive is located with background color to obtain a primary wiring diagram only containing the connecting lines, and extracting the connecting line pixels by adopting threshold segmentation;
s4: selecting an end point of any one primitive as an initial growth point, acquiring a connected region with the initial growth point, fitting the connected region by adopting Hough line detection to obtain a line connecting line, the end point and equipment connected with the end point in the region, and adding the equipment in the connected region into a connected equipment set;
s5: sequentially selecting the end points which are not detected by the connected equipment and repeating the step 4 to expand the connected domain until all the end points are connected;
s6: and (5) repeating the steps 4 and 5 for the devices which are not added with the connected domain to form a new connected domain until all the devices on the wiring diagram are connected.
S7: and detecting character identification in the primary wiring diagram by adopting optical character recognition, and matching characters with the primitives according to the nearest matching relation.
S8: and storing the recognition result in a classification mode according to the graphic elements, the characters and the connecting lines, wherein the characters need to be associated with the corresponding elements, and the connecting lines need to be associated with the corresponding elements and ports.
In specific implementation, the intelligent analysis method for the primary wiring diagram of the transformer substation provided by the invention can be realized through the following steps:
1. the position detection and the rotation angle identification of the primitive of the primary wiring diagram are realized based on a target detection algorithm and a template matching method;
1) In this embodiment, a primary wiring diagram primitive identification algorithm is developed based on a YOLO v4 model, and the primary wiring diagram primitives are divided into 11 categories, specifically including a circuit breaker, an isolation disconnecting link, a grounding disconnecting link, two-volume transformation, three-volume transformation, a capacitor, a reactor, a bus, a line, a reactive power compensation device and a generator; the embodiment marks the primitive types according to the VOC standard, and trains on the marked data set to obtain a primitive recognition model;
2) Since YOLO v4 needs to resample the input picture to 608 × 608 before primitive recognition, and the actual primary wiring diagram is much larger than the size, if the primary wiring diagram is directly scaled, the primitive recognition is difficult, the embodiment proposes a wiring diagram clipping strategy, specifically: cutting the original picture of the primary wiring diagram into a plurality of pictures with the size of 608 × 608, marking the first picture at the upper left corner as the (1,1) cut picture, and then the pixel range of the (m, n) picture is [ m × 550;
3) On the basis of the primitive identification result, the port of each primitive needs to be further confirmed, so the embodiment adopts a template matching method to detect the rotation angle and the port of the primitive; the method specifically comprises the following steps: for each type of primitive, primitive templates with different shapes and different rotation angles (for example, a single-symmetry-axis primitive needs to include four types of 0 degrees, 90 degrees, 180 degrees and 270 degrees, and a double-symmetry-axis primitive needs to include two types of 0 degrees and 180 degrees) need to be prepared, and two attributes of the rotation angle and a connection port need to be manually set for each template; matching the recognition result obtained by the primitive recognition algorithm with a pre-manufactured template set by adopting a template matching method, finding a template with the highest matching pair with the recognition result, and transmitting the attribute of the template to the recognition result to obtain the rotation angle and the connection port number of the recognized primitive;
2. identifying main connecting lines in the wiring diagram by utilizing Hough line detection, and detecting the end points of the pixels according to the positions of the pixels;
1) In the embodiment, firstly, a Gaussian filter and threshold segmentation algorithm is adopted to carry out image preprocessing on a primary wiring diagram, so that the interference of noise on subsequent identification is reduced, and specifically, in the implementation process, a Gaussian filter function and a threshold segmentation function in an OpenCV algorithm library are adopted to carry out processing;
2) Fitting the connecting lines in the image by using a Hough straight line fitting algorithm in an OpenCV algorithm library based on the image obtained in the step, and dividing the straight lines obtained by fitting into horizontal connecting lines and vertical connecting lines;
3) And (4) respectively calculating straight lines intersected with the pixel blocks of the pixels detected in the step one, and taking the intersection points of the straight lines and the boundaries of the pixels as connection points of the pixels. In particular, assume that the position of the current primitive can be represented as (x) 1 ,y 1 ,x 2 ,y 2 ) For each straight line obtained by fitting in the previous step, respectively calculating the intersection point of the straight line and the pixel area of the primitive detected in the first step, and taking the intersection point as the connection endpoint of the corresponding primitive; specifically, if the intersection point of the horizontal line and the primitive is calculated, it is assumed that two end points of the line are respectively a (x) A ,y A ) And B (x) B ,y B ) In which y is known A ＝y B For the straight line endpoint a, it can be considered to be connected to the primitive if the following conditions are satisfied, and the endpoint a is taken as a connection point:
where T is a discontinuity threshold, T =5 in this embodiment, and the unit is a pixel. Endpoint B is calculated in the same manner as above.
If the intersection point of the vertical line and the primitive is calculated, assume that the two endpoints of the line are A (x) respectively A ,y A ) And B (x) B ,y B ) In which x is known A ＝x B The judgment basis of the connection of the end point and the primitive is as follows:
for each primitive, all connection endpoint information is recorded.
3. Filling a pixel area where the graphic primitive is located with background color to obtain a primary wiring diagram only containing the connecting lines, and extracting the connecting lines by adopting threshold segmentation;
1) In the first step, the graphic elements in the wiring diagram are identified, and a plurality of graphic elements have structures similar to the connecting lines, so that the graphic elements are firstly coated and covered by using a background, specificallyIn other words, assume that the upper left vertex of the primitive rectangle is (x) min ,y min ) And the coordinate of the lower right vertex is (x) max ,y max ) Let P stand i,j {i∈(x min ,x max ),j∈(y min ,y max ) =255, eliminating the effect of primitive pixels on the connection line extraction; the effect graph after the primitive erasure is shown in fig. 2;
2) The wiring diagram after the primitive removal mainly comprises connecting lines and a text part, and the embodiment further utilizes OpenCV to perform Gaussian smoothing processing and threshold segmentation, so that the interference of stray points and noise is reduced; the effect graph after the connecting line extraction is shown in fig. 3;
4. selecting an end point of any one primitive as an initial growth point, acquiring a connected region with the initial growth point, fitting the connected region by adopting Hough line detection to obtain a line connecting line, the end point and equipment connected with the end point in the region, and adding the equipment in the connected region into a connected equipment set;
1) Randomly selecting a primitive, taking one terminal on the primitive as an initial growth point, expanding the initial point by adopting an expansion algorithm, and solving a connected domain of the initial point according to an 8-connected domain rule, wherein the connected domain is a connecting line which can pass through the initial point;
2) Carrying out Hough line detection on the connected domain to obtain line segments corresponding to the connecting lines;
3) Calculating the intersection point between every two line segments of the detected line segments, and dividing the intersection point into an L-shaped intersection point, a T-shaped intersection point and a ten-shaped intersection point, wherein for the ten-shaped intersection point, the two line segments are respectively cut into two sections at the intersection point to obtain a new connecting line;
4) Dividing the end points of all the line sections into connecting line end points and element end points, wherein the connecting line end points are obtained by 3), the element end points can be obtained according to the positions of the primitive terminals in the step two, and meanwhile, the primitives connected with the element end points are obtained to form the topological relation between the connecting lines and the primitives; if two end points of a section of connecting line are not the connecting line end points or the element end points, the connecting line is considered as a bus;
5) Adding the graphic primitives connected with the element end points into the existing connected domain, taking the new connected domain as an identified area, and taking all graphic primitive end points which are not connected with the element or the connecting line in the connected domain as alternative initial growing points;
5. randomly selecting one point from the alternative initial growing points, and calculating a new connected domain from the point until all element end points in the connected domain are connected with the connecting line or the primitive end point;
6. for the equipment which is not added with the connected domain, repeating the fourth step and the fifth step to form a new connected domain until all the equipment on the wiring diagram is connected;
7. detecting character identification in the primary wiring diagram by adopting optical character recognition, and matching characters with the primitives according to the nearest matching relation;
1) The optical character recognition detection in the embodiment is realized based on PaddlePaddle OCR, and the content and the position of each character block in the wiring diagram can be recognized through the module;
2) Considering that the characters in the wiring diagram may have multiple lines of representations or vertically arranged characters, and paddlepaddleocr can only detect a single line of characters, the embodiment merges multiple lines of characters, and specifically, if the distance between two character blocks in the vertical direction does not exceed the average height of the two character blocks, it is considered that the two character blocks can be merged into the same character, the character contents are spliced in the order from top to bottom, and the text position is the smallest rectangular frame containing the two character blocks;
3) For each character string, calculating a primitive closest to the character string, wherein the distance between the outer boundary of the primitive and the outer boundary of the character string does not exceed a certain threshold value, the character string is used as a keyword of the primitive, and otherwise, the character string is discarded; in the embodiment, the distance threshold is set according to the size of the primitive, and the average value of the long edges of all circuit breaker primitives is taken as the distance judgment threshold;
8. classifying and storing the recognition result according to the graphic elements, the characters and the connecting lines, wherein the characters need to be associated with corresponding elements, and the connecting lines need to be associated with corresponding elements and ports;
the recognition result visualization of this embodiment is shown in fig. 4.
It should be understood that parts of the specification not set forth in detail are well within the prior art.
Although specific embodiments of the present invention have been described above with reference to the accompanying drawings, it will be appreciated by those skilled in the art that these are merely illustrative and that various changes or modifications may be made to these embodiments without departing from the principles and spirit of the invention. The scope of the invention is only limited by the appended claims.
Claims (8)
1. A transformer substation primary wiring diagram intelligent analysis method is characterized by comprising the following steps:
step 1, realizing primary wiring diagram primitive position detection and rotation angle identification based on a target detection algorithm and a template matching method;
step 2, identifying main connecting lines in the wiring diagram by utilizing Hough line detection, and detecting a primitive endpoint according to a primitive position;
step 3, filling a pixel area where the primitive is located with background color to obtain a primary wiring diagram only containing the connecting lines, and extracting the connecting line pixels by adopting threshold segmentation;
step 4, selecting an endpoint of any primitive as an initial growth point, acquiring a communication area with the initial growth point, detecting and fitting the communication area by adopting or copying, acquiring a linear connecting line, the endpoint and equipment connected with the endpoint in the area, and adding the equipment in the communication area into a connected equipment set;
step 5, sequentially selecting the end points which are not detected by the connected equipment and repeating the step 4 to expand the connected domain until all the end points are connected;
step 6, repeating the step 4 and the step 5 for the equipment which is not added with the connected domain to form a new connected domain until all the equipment on the wiring diagram is connected;
step 7, detecting character marks in the primary wiring diagram by adopting optical character recognition, and matching characters with the primitives according to the nearest matching relation;
and 8, storing the recognition result in a classification mode according to the graphic elements, the characters and the connecting lines, wherein the characters need to be associated with corresponding elements, and the connecting lines need to be associated with corresponding elements and ports.
2. The intelligent analysis method for the primary wiring diagram of the transformer substation as claimed in claim 1, wherein the implementation of the step 1 comprises the following steps:
step 1.1, marking all primitives in a primary wiring diagram of a transformer substation, cutting the wiring diagram into a plurality of picture blocks for model training and target detection testing, mapping the positions of the primitives to an original wiring diagram after the testing is finished, and obtaining the types and the positions of the primitives according to the target detection result; the graphic elements comprise 11 categories of a circuit breaker, an isolation disconnecting link, a grounding disconnecting link, two-winding transformers, three-winding transformers, a capacitor, a reactor, a bus, a circuit, a reactive power compensation device and a generator;
step 1.2, making a standard primitive template library, which mainly comprises templates of various primitives with different rotation angles, wherein, for example, a single symmetry axis primitive needs to comprise four templates of 0 degree, 90 degrees, 180 degrees and 270 degrees, and a double symmetry axis primitive needs to comprise two templates of 0 degree and 180 degrees;
and step 1.3, carrying out template matching on the primitive obtained by target detection and a standard primitive template library, obtaining the rotation angle of the primitive, and obtaining the terminal distribution sequence of the primitive according to electrical professional knowledge.
3. The intelligent analysis method for the primary wiring diagram of the transformer substation as claimed in claim 2, wherein the implementation of the step 2 comprises the following steps:
step 2.1, preprocessing an original wiring diagram by adopting Gaussian filtering and threshold segmentation to reduce the interference of irrelevant pixels;
step 2.2, fitting and combining straight lines in the wiring diagram by adopting Hough straight line detection to obtain connecting lines among the pixels;
and 2.3, performing AND operation on the rectangular frame containing the primitives and the connecting lines, wherein the intersection points of the rectangles and the connecting lines can be used as the terminal positions of the corresponding primitives, and meanwhile, numbering the primitive terminals according to the terminal distribution sequence in the step 1.3.
4. The intelligent analysis method for the primary wiring diagram of the transformer substation as claimed in claim 1, wherein the implementation of the step 3 comprises the following steps:
step 3.1, in order to effectively extract the specific position of the connecting line, filling the pixel corresponding to the primitive in the picture by adopting a background color, wherein the top left vertex of the primitive rectangle is (x) min ,y min ) And the coordinate of the lower right vertex is (x) max ,y max ) Let P stand i,j {i∈(x min ,x max ),j∈(y min ,y max ) =255, eliminating the influence of primitive pixels on the connection line extraction;
and 3.2, performing Gaussian smoothing and threshold segmentation on the wiring diagram with the primitive removed, and extracting pixels of the connecting lines.
5. The intelligent analysis method for the primary wiring diagram of the transformer substation as claimed in claim 1, 2 or 3, wherein the implementation of the step 4 comprises the following steps:
step 4.1, randomly selecting a primitive, taking one terminal on the primitive as an initial growth point, expanding the initial point by adopting an expansion algorithm, and solving a connected domain of the initial point according to an 8-connected domain rule, wherein the connected domain is a connecting line which can pass through the initial point;
step 4.2, carrying out Hough line detection on the connected domain to obtain line segments corresponding to the connecting lines;
4.3, calculating the intersection point between every two line segments of the detected line segments, and dividing the intersection point into an L-shaped intersection point, a T-shaped intersection point and a ten-shaped intersection point, wherein for the ten-shaped intersection point, the two line segments are respectively cut into two sections at the intersection point to obtain a new connecting line;
step 4.4, dividing the end points of all the line sections into connecting line end points and element end points, wherein the connecting line end points are obtained in the step 4.3, the element end points can be obtained according to the positions of the primitive terminals in the step 2.3, and meanwhile, primitives connected with the element end points are obtained to form a topological relation between the connecting lines and the primitives; if two endpoints of a section of connecting line are not the connecting line endpoint or the element endpoint, the connecting line is considered as a bus;
and 4.5, adding the graphic primitives connected with the element end points into the existing connected domain, taking the new connected domain as the identified area, and taking all the graphic primitive end points which are not connected with the element or the connecting line in the connected domain as alternative initial growing points.
6. The intelligent analysis method for the primary wiring diagram of the transformer substation as claimed in claim 5, wherein the implementation of the step 5 comprises the following steps:
and 5.1, randomly selecting one point from the alternative initial growing points, and calculating a new connected domain from the point until all element end points in the connected domain are connected with the connecting line or the primitive end point.
7. The intelligent analysis method for the primary wiring diagram of the transformer substation as claimed in claim 6, wherein the implementation of the step 6 comprises the following steps:
and 6.1, after the step 5 is executed, if the primitives are not contained in the connected domain, continuously selecting the primitives from the primitives, and executing the step 4 and the step 5.
8. The intelligent analysis method for the primary wiring diagram of the transformer substation as claimed in claim 7, wherein the implementation of step 7 comprises the following steps:
7.1, extracting character strings and positions thereof in the wiring diagram by adopting an optical character recognition technology;
and 7.2, calculating a graphic element closest to each character string, wherein the distance between the outer boundary of the graphic element and the outer boundary of the character string does not exceed a certain threshold value, using the character string as a keyword of the graphic element, and otherwise, discarding the character string.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727367.8A CN115294595A (en) | 2022-06-24 | 2022-06-24 | Intelligent analysis method for primary wiring diagram of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210727367.8A CN115294595A (en) | 2022-06-24 | 2022-06-24 | Intelligent analysis method for primary wiring diagram of transformer substation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115294595A true CN115294595A (en) | 2022-11-04 |
Family
ID=83819877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210727367.8A Pending CN115294595A (en) | 2022-06-24 | 2022-06-24 | Intelligent analysis method for primary wiring diagram of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115294595A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116310765A (en) * | 2023-05-23 | 2023-06-23 | 华雁智能科技(集团)股份有限公司 | Electrical wiring graphic primitive identification method |
-
2022
- 2022-06-24 CN CN202210727367.8A patent/CN115294595A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116310765A (en) * | 2023-05-23 | 2023-06-23 | 华雁智能科技(集团)股份有限公司 | Electrical wiring graphic primitive identification method |
| CN116310765B (en) * | 2023-05-23 | 2023-09-01 | 华雁智能科技(集团)股份有限公司 | Electrical wiring graphic primitive identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104751142B (en) | A kind of natural scene Method for text detection based on stroke feature | |
| CN110008809A (en) | Acquisition methods, device and the server of list data | |
| CN105205488B (en) | Word area detection method based on Harris angle points and stroke width | |
| CN108648169A (en) | The method and device of high voltage power transmission tower defects of insulator automatic identification | |
| CN103295009B (en) | Based on the license plate character recognition method of Stroke decomposition | |
| CN112149548B (en) | CAD drawing intelligent input and identification method and device suitable for terminal row | |
| CN111859805B (en) | Method for detecting topological relation of electric power drawing based on artificial intelligence | |
| CN112613339A (en) | Automatic identification and examination method and device for electrical drawings | |
| CN115661848A (en) | Form extraction and identification method and system based on deep learning | |
| CN114565930A (en) | Electrical plant station wiring drawing bus identification method based on morphological processing | |
| CN110598698A (en) | Natural scene text detection method and system based on adaptive regional suggestion network | |
| CN115294595A (en) | Intelligent analysis method for primary wiring diagram of transformer substation | |
| CN115457591A (en) | Identification method for topological relation of main wiring diagram of power grid station | |
| CN111368695A (en) | Table structure extraction method | |
| CN115376155A (en) | Station wiring diagram detection method based on YOLOv6 and traditional image processing technology | |
| CN115690012A (en) | Detection method for wrong connection line of electric energy meter | |
| CN114547968A (en) | Physical loop modeling method of intelligent substation drawing | |
| CN109271882B (en) | Method for extracting color-distinguished handwritten Chinese characters | |
| CN114842494A (en) | Method for automatically identifying connection relation of station wiring diagrams of power system | |
| CN115100657A (en) | Line recognition method for characters and strip widths of electrical CAD drawing scanned graph | |
| CN111444903B (en) | Method, device and equipment for positioning characters in cartoon bubbles and readable storage medium | |
| CN116541912A (en) | Method and device for generating wiring diagram based on CAD image recognition | |
| CN115995086A (en) | Identification method, equipment and storage medium for terminal strip drawing short-link primitive | |
| CN114627463A (en) | Non-contact power distribution data identification method based on machine identification | |
| CN112907734B (en) | TEDS fault detection method based on virtual CRH380A model and deep learning |
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 |