CN115797960A - Analysis system and method based on engineering drawing - Google Patents
Analysis system and method based on engineering drawing Download PDFInfo
- Publication number
- CN115797960A CN115797960A CN202211441088.1A CN202211441088A CN115797960A CN 115797960 A CN115797960 A CN 115797960A CN 202211441088 A CN202211441088 A CN 202211441088A CN 115797960 A CN115797960 A CN 115797960A
- Authority
- CN
- China
- Prior art keywords
- engineering drawing
- area data
- engineering
- analyzer
- based analysis
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an analysis system and a method based on engineering drawings, wherein the system comprises the following steps: the character analyzer is used for identifying and reading the length and the width of the engineering drawing, and calculating the real size represented by each pixel according to the number of the pixels; the space analyzer is used for dividing the engineering drawing into a plurality of subspaces, and summarizing the subspace after calculation to obtain first area data; the element recognizer is used for recognizing components with various different characteristics in the engineering drawing; the boundary analyzer is used for automatically identifying the boundary of the engineering drawing and calculating based on the identified assembly and the input height data to obtain second area data; the processor is used for processing the obtained first area data and the second area data by combining a preset budget file to obtain corresponding cost information; the beneficial effects are as follows: the engineering drawing is used as input, and then various components on the drawing are automatically identified, and the relevance between the components is automatically identified, so that the cost and profit are quickly estimated.
Description
Technical Field
The invention relates to the technical field of engineering projects, in particular to an analysis system and method based on engineering drawings.
Background
At present, in an engineering project, a designer is generally required to draw an engineering drawing by using engineering software, and relevant elements, corresponding information such as size, quantity and position and the like are represented on the drawing. Meanwhile, cost valuation personnel calculate the manufacturing cost and the profit according to the designed drawing, and because information required by calculation is derived from the design drawing, related personnel only calculate the engineering quantity and the cost manually according to the design drawing, the whole calculation process is high in complexity, large in workload and prone to errors.
Disclosure of Invention
Aiming at the technical defects in the prior art, the embodiment of the invention aims to provide an analysis system and method based on engineering drawings, so as to overcome the defects of high complexity, large workload and high error probability in the prior art.
In order to achieve the above object, in a first aspect, an embodiment of the present invention provides an analysis system based on engineering drawings, where the system includes:
the character analyzer is used for identifying and reading the length and the width of the engineering drawing, and calculating the real size represented by each pixel according to the number of the pixels;
the space analyzer is used for dividing the engineering drawing into a plurality of subspaces, wherein each subspace is associated with a corresponding pixel number; calculating and summarizing each subspace respectively to obtain first area data;
the element identifier is used for identifying components with various different characteristics in the engineering drawing;
the boundary analyzer is used for automatically identifying the boundary of the engineering drawing and calculating based on the identified assembly and the input height data to obtain second area data;
and the processor is used for processing the obtained first area data and the second area data by combining with a preset budget file to obtain corresponding cost information.
Preferably, the number of the pixels is obtained by reading the engineering drawing by using an OpenCV technique to obtain an M × N × C matrix, where M and N represent the number of pixels in the horizontal direction and the vertical direction of the engineering drawing, and C represents the number of channels of the color of the engineering drawing.
Preferably, the space analyzer divides the engineering drawing into a plurality of subspaces, specifically:
and adopting a watershed algorithm technology, taking the result of the boundary analyzer as the outline of the building, and judging other pixel points on the image by the algorithm according to the outline to realize the partition of the area of each pixel point.
Preferably, the element recognizer recognizes components with various characteristics in the engineering drawing through a trained deep learning model, and reflects the relevance of each component.
Preferably, the assembly comprises a cross-section sign, a staircase, a window, a door and a wash basin.
In a second aspect, an embodiment of the present invention further provides an engineering drawing-based analysis method, which is applied to the engineering drawing-based analysis system in the first aspect, and the method includes:
identifying and reading the length and the width of the engineering drawing, and calculating the real size represented by each pixel according to the number of the pixels;
dividing the engineering drawing into a plurality of subspaces, wherein each subspace is associated with a corresponding pixel number; calculating and summarizing each subspace respectively to obtain first area data;
identifying components of various different characteristics in the engineering drawing;
automatically identifying boundaries of the engineering drawing and calculating based on the identified assembly and the input height data to obtain second area data;
and combining the obtained first area data and the second area data with a preset budget file for processing to obtain corresponding cost information.
Preferably, the number of the pixels is obtained by reading the engineering drawing by using an OpenCV technique to obtain a matrix of M × N × C, where M and N represent the number of pixels in the horizontal direction and the vertical direction of the engineering drawing, and C represents the number of channels of the color of the engineering drawing.
Preferably, the engineering drawing is divided into a plurality of subspaces, specifically:
and adopting a watershed algorithm technology, taking the result of the boundary analyzer as the outline of the building, and judging other pixel points on the image by the algorithm according to the outline to realize the partition and the demarcation of the area of each pixel point.
Preferably, through the trained deep learning model, the components with various characteristics in the engineering drawing are identified, and the relevance of each component is embodied.
The analysis system and method based on the engineering drawing provided by the embodiment of the invention take the engineering drawing of a building as input, automatically identify various components on the drawing by applying the identifier and each analyzer, and analyze the relationship of each subspace and the association among the components by combining the identified boundary and the number of pixels, thereby quickly estimating the manufacturing cost and the profit, and further overcoming the defects of high complexity, large workload and easy error in the prior art.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings used in the detailed description or the prior art description will be briefly described below.
FIG. 1 is a schematic block diagram of an analysis system based on engineering drawings according to an embodiment of the present invention;
fig. 2 is a flowchart of an analysis method based on engineering drawings according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Referring to fig. 1, an analysis system based on engineering drawings according to an embodiment of the present invention includes:
and the character analyzer is used for identifying and reading the length and the width of the engineering drawing, and calculating the real size represented by each pixel according to the number of the pixels.
Specifically, the engineering drawing can be guided into the text analyzer;
the number of the pixels is obtained by reading the engineering drawing by adopting an OpenCV technology to obtain a matrix of M N C, wherein M and N represent the number of pixels of the engineering drawing in the horizontal direction and the vertical direction, and C represents the number of channels of the color of the engineering drawing; in this embodiment, the engineering drawing is described by taking a building construction drawing as an example, and the type of file is stored and information is transmitted in a PDF file or picture format.
The space analyzer is used for dividing the engineering drawing into a plurality of subspaces, wherein each subspace is associated with a corresponding pixel number; and calculating and summarizing each subspace to obtain first area data.
Specifically, the area of each subspace is the sum of the areas of all pixels within that space. For example, in calculating the floor area, the floor area of the construction drawing is the sum of the areas of all the subspaces where the floor is installed, according to the floor requirements of different customers for different subspaces.
Further, the text analyzer may also identify categories of different subspaces, such as bedrooms, kitchens, etc., when applied.
And the element identifier is used for identifying components with various different characteristics in the engineering drawing.
In particular, the assembly comprises section symbols, stairs, windows, doors and wash basins; the element recognizer is used for recognizing various components with different characteristics in the engineering drawing through a trained deep learning model and reflecting the relevance of each component;
that is, the symbol recognizer, which is developed based on deep learning, is obvious in characteristics because the categories of various components in the construction drawing are limited; the deep learning model is obtained through training and learning of at least 1000 construction drawings, so that the element recognizer has the capability of automatically recognizing and analyzing each component in the construction drawings; in addition, the various components in the construction drawings are strongly related, such as windows are usually embedded in walls, toilets usually contain wash basins and toilets; therefore, in the training and learning process, the symbol recognizer has the capability of analyzing the relevance of each component; the relevance of each component is beneficial to improving the accuracy of deep learning and avoiding the omission of identification.
The boundary analyzer is used for automatically identifying the boundary of the engineering drawing and calculating based on the identified assembly and the input height data to obtain second area data;
specifically, the boundary of the construction plan can be automatically identified, including the wall and the windows embedded in the wall, so that the length of the wall, the number of the windows and the length of the windows can be obtained. The area of the wall is obtained by subtracting the total area of the window from the total area of the inner side of the house (the total length of the boundary x the height of the house) based on the height of the house and the height of the window input by the user.
Further, in order to realize the processing of complex conditions and solve different requirements of customers, the space analyzer adopts a watershed algorithm technology, the result of the boundary analyzer is used as the outline of the building, and the algorithm judges other pixel points on the image according to the outline, so that the region of each pixel point is divided into regions to obtain corresponding space categories; the space categories comprise living rooms, kitchens, toilets, child rooms and the like;
wherein the categories of the different spaces are determined according to the results of the space analyzer; for example, when a customer needs to paint different spaces in different space categories, the cost estimate for the paint is the sum of the estimates for each different space, rather than the total area of the paint multiplied by the unit price of the paint, because the different paint prices are different, such as a child bedroom and a living room on each side of a wall, then the paint areas for different subspaces need to work in conjunction with a space analyzer to calculate the boundary lengths of the different subspaces and the number and length of windows, respectively, in the cost estimate.
And the processor is used for processing the obtained first area data and the second area data by combining with a preset budget file to obtain corresponding cost information.
Specifically, the budget document is a national standard of related project budget, and comprises budget price compilation of manpower, materials, machinery, equipment and the like and a determined technical and economic document of construction cost of the building installation project, and further the cost information required by a customer is quickly obtained by combining the obtained area data; items such as floors, painted surfaces, walls, etc. can be derived or combined so that a builder can quickly make cost and profit estimates.
According to the scheme, the construction drawing is used as input, various assemblies on the drawing are automatically identified through the application of the identifier and the analyzers, and the relationships and the associations among the spaces are analyzed by combining the identified boundaries and the number of pixels, so that the cost and the profit are quickly estimated, and the defects of high complexity, large workload and high error probability in the prior art are overcome.
Based on the same inventive concept, an embodiment of the present invention further provides an engineering drawing-based analysis method, which is applied to the engineering drawing-based analysis system described above, and as shown in fig. 2, the method includes:
s101, identifying and reading the length and the width of the engineering drawing, and calculating the real size represented by each pixel according to the number of the pixels;
s102, dividing the engineering drawing into a plurality of subspaces, wherein each subspace is associated with a corresponding pixel number; calculating and summarizing each subspace respectively to obtain first area data;
s103, identifying components with various different characteristics in the engineering drawing; identifying various components with different characteristics in the engineering drawing through the trained deep learning model, and reflecting the relevance of each component;
s104, automatically identifying the boundary of the engineering drawing, and calculating based on the identified assembly and the input height data to obtain second area data;
and S105, combining the obtained first area data and the second area data with a preset budget file for processing to obtain corresponding cost information.
Further, in implementation, the number of the pixels is obtained by reading the engineering drawing by using an OpenCV technique to obtain a matrix of M × N × C, where M and N represent the number of pixels in the horizontal direction and the vertical direction of the engineering drawing, and C represents the number of channels of the color of the engineering drawing.
Meanwhile, the engineering drawing is divided into a plurality of subspaces, specifically:
and adopting a watershed algorithm technology, taking the result of the boundary analyzer as the outline of the building, and judging other pixel points on the image by the algorithm according to the outline to realize the partition and the demarcation of the area of each pixel point.
It should be noted that, for a more specific workflow of the method embodiment, please refer to the system embodiment part, which is not described herein again.
By the method, the construction drawings of buildings are taken as input, various assemblies on the drawings are automatically identified, the relation of each space and the relevance between the spaces are analyzed, the existing working mode of the drawing analysis in the building industry is improved, the manufacturing cost and the profit are rapidly estimated, and the defects of high complexity, large workload and high possibility of errors in the prior art are overcome.
Those of ordinary skill in the art will appreciate that the elements and steps of the various examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed method and system may be implemented in other ways. For example, the system embodiments described above are merely illustrative, and for example, the analyzer may be divided into only one logical functional division, and may be implemented in other ways, for example, multiple analyzers or components may be combined or integrated into another system, or some features may be omitted, or not implemented.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention.
Claims (9)
1. An engineering drawing-based analysis system, the system comprising:
the character analyzer is used for identifying and reading the length and the width of the engineering drawing, and calculating the real size represented by each pixel according to the number of the pixels;
the space analyzer is used for dividing the engineering drawing into a plurality of subspaces, wherein each subspace is associated with a corresponding pixel number; calculating and summarizing each subspace respectively to obtain first area data;
the element identifier is used for identifying components with various different characteristics in the engineering drawing;
the boundary analyzer is used for automatically identifying the boundary of the engineering drawing and calculating based on the identified assembly and the input height data to obtain second area data;
and the processor is used for processing the obtained first area data and the second area data by combining with a preset budget file to obtain corresponding cost information.
2. The engineering drawing-based analysis system according to claim 1, wherein the number of pixels is obtained by reading the engineering drawing by using an OpenCV technique to obtain a matrix of M × N × C, where M and N represent the number of pixels in the horizontal direction and the vertical direction of the engineering drawing, and C represents the number of channels of the color of the engineering drawing.
3. The engineering drawing-based analysis system according to claim 2, wherein the space analyzer divides the engineering drawing into a plurality of subspaces, specifically:
and adopting a watershed algorithm technology, taking the result of the boundary analyzer as the outline of the building, and judging other pixel points on the image by the algorithm according to the outline to realize the partition of the area of each pixel point.
4. The engineering drawing-based analysis system of claim 1, wherein the element recognizer is a deep learning model completed through training, recognizes components with various characteristics in the engineering drawing, and reflects the relevance of the components.
5. The engineering drawing-based analysis system of claim 1, wherein the components include section signs, stairs, windows, doors, and wash basins.
6. An engineering drawing-based analysis method applied to the engineering drawing-based analysis system of claim 1, the method comprising:
identifying and reading the length and the width of the engineering drawing, and calculating the real size represented by each pixel according to the number of the pixels;
dividing the engineering drawing into a plurality of subspaces, wherein each subspace is associated with a corresponding pixel number; calculating and summarizing each subspace to obtain first area data;
identifying components of various features in the engineering drawing;
automatically identifying boundaries of the engineering drawing and calculating based on the identified assembly and the input height data to obtain second area data;
and combining the obtained first area data and the second area data with a preset budget file for processing to obtain corresponding cost information.
7. The engineering drawing-based analysis method according to claim 6, wherein the number of pixels is obtained by reading the engineering drawing by using an OpenCV technique to obtain a matrix of M × N × C, where M and N represent the number of pixels in the horizontal direction and the vertical direction of the engineering drawing, and C represents the number of channels of the color of the engineering drawing.
8. The engineering drawing-based analysis method according to claim 7, wherein the engineering drawing is divided into a plurality of subspaces, specifically:
and adopting a watershed algorithm technology, taking the result of the boundary analyzer as the outline of the building, and judging other pixel points on the image by the algorithm according to the outline to realize the partition and the demarcation of the area of each pixel point.
9. The engineering drawing-based analysis method according to claim 8, wherein the trained deep learning model is used for identifying various components with different characteristics in the engineering drawing and reflecting the relevance of each component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211441088.1A CN115797960A (en) | 2022-11-17 | 2022-11-17 | Analysis system and method based on engineering drawing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211441088.1A CN115797960A (en) | 2022-11-17 | 2022-11-17 | Analysis system and method based on engineering drawing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115797960A true CN115797960A (en) | 2023-03-14 |
Family
ID=85438518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211441088.1A Pending CN115797960A (en) | 2022-11-17 | 2022-11-17 | Analysis system and method based on engineering drawing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115797960A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117711010A (en) * | 2024-01-09 | 2024-03-15 | 北京理正软件股份有限公司 | Automatic recognition method and recognition system for engineering drawing tab |
-
2022
- 2022-11-17 CN CN202211441088.1A patent/CN115797960A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117711010A (en) * | 2024-01-09 | 2024-03-15 | 北京理正软件股份有限公司 | Automatic recognition method and recognition system for engineering drawing tab |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112883798B (en) | Method for identifying components in plane graph space of building specialty based on deep learning | |
| Hwang et al. | Integrated Digital Delivery: Implementation status and project performance in the Singapore construction industry | |
| Choi et al. | Development of BIM-based evacuation regulation checking system for high-rise and complex buildings | |
| Leite et al. | Analysis of modeling effort and impact of different levels of detail in building information models | |
| Rausch et al. | Deploying 3D scanning based geometric digital twins during fabrication and assembly in offsite manufacturing | |
| KR20200081340A (en) | Method and apparatus for architectural drawing analysing | |
| Mani et al. | Estimating construction labor productivity frontier: Pilot study | |
| CN115797960A (en) | Analysis system and method based on engineering drawing | |
| CN111523167A (en) | BIM model generation method, device, equipment and storage medium | |
| CN114972659B (en) | Method and system for converting two-dimensional drawing into three-dimensional model for drawing examination | |
| CN113962000A (en) | Method for dynamically arranging smoke detectors in CAD (computer-aided design) drawing | |
| CN111161379A (en) | Indoor home automatic layout algorithm based on deep learning and empty house type feature detection | |
| CN113887508B (en) | Accurate identification method for central line of public corridor space in building professional residence plan | |
| CN111523169B (en) | Decoration scheme generation method and device, electronic equipment and storage medium | |
| CN115857413A (en) | Intelligent building safety monitoring system and method based on Internet of things | |
| Gholami et al. | Exploiting BIM in energy efficient domestic retrofit: evaluation of benefits and barriers | |
| Barco et al. | A recursive algorithm for building renovation in smart cities | |
| Tamke et al. | An automated approach to the generation of structured building information models from unstructured 3D point cloud scans | |
| Muhammad | The significance of building information modelling to the quantity surveying practices in the UAE construction industry | |
| CN112801620B (en) | Engineering information processing method, device, equipment and storage medium | |
| CN113901051A (en) | Method and device for generating WebGL data, storage medium and electronic equipment | |
| Drobnyi et al. | Deep-learning guided structural object detection in large-scale, occluded indoor point cloud datasets | |
| CN114550187A (en) | Method and device for identifying doors and windows in drawing, electronic equipment and storage medium | |
| Lambers et al. | Risk management strategies for common residential construction defects: the case of Queensland, Australia | |
| CN116578915B (en) | Structured house type analysis method and system based on graphic neural network |
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 |