CN110969111A - Automatic identification and classification method for mechanical part digital drawing - Google Patents
Automatic identification and classification method for mechanical part digital drawing Download PDFInfo
- Publication number
- CN110969111A CN110969111A CN201911189276.8A CN201911189276A CN110969111A CN 110969111 A CN110969111 A CN 110969111A CN 201911189276 A CN201911189276 A CN 201911189276A CN 110969111 A CN110969111 A CN 110969111A
- Authority
- CN
- China
- Prior art keywords
- graph
- mechanical
- rule
- rule database
- graphs
- 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.)
- Withdrawn
Links
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Library & Information Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses an automatic identification and classification method of a mechanical part digital drawing, which comprises the steps of screening and classifying key words by setting first-level classification, comparing a graph with a graph rule database by second-level classification, and comparing the graph with the graph rule database by drawing parameters of the drawing by third-level classification, so as to accurately classify the items of the drawing; setting abnormal analysis, performing manual intervention on the graphs which cannot be matched, greatly reducing the intensity of manual operation, and supplementing and correcting a graph rule database in time; the convenience is brought to technicians to search corresponding drawings in time, and the operation time is saved. The invention improves the working efficiency of technicians.
Description
Technical Field
The invention belongs to the technical field of drawing classification, and particularly relates to an automatic identification and classification method for a digital drawing of a mechanical part.
Background
In the field of industrial manufacturing, there are a large number of electronic drawings of mechanical equipment in various file formats. The three-dimensional mechanical model can be reconstructed based on the mechanical part diagram, so that the graph recognition and data extraction based on the electronic mechanical diagram have important market prospect. The information in the mechanical diagram has various categories such as graphs, texts and symbols, and needs to be extracted step by step based on different methods, so that the mechanical data model needs to have a professional, hierarchical and staged organization mode, and the common requirements of data extraction and management are met. At present, most of electronic mechanical drawings adopt a manual drawing recognition mode, the mode is easily influenced by subjective factors, quality problems of misreading and missed reading of information can be caused, and meanwhile, the recognition efficiency is low.
Classify, handle, accomodate a large amount of mechanical drawings is a very loaded down with trivial details process, secondly, also need certain cycle's flow when designer or production workman need borrow the drawing, like this when actual application, will lead to the cycle extension of production for work becomes loaded down with trivial details.
Disclosure of Invention
The invention aims to solve the technical problems and provides an automatic identification and classification method of mechanical part digital drawings, so that the mechanical electronic drawings are automatically identified and classified. In order to achieve the purpose, the technical scheme of the invention is as follows:
the automatic identification and classification method of the mechanical part digital drawing comprises the following steps
S1, identifying a graph rule, wherein the mechanical drawing rule comprises a rule set in a drawing making stage, the construction objects of the mechanical drawing are point, line and surface attributes, and the mechanical drawing is divided based on different parts and detail compositions of parts, characters, tables and the like in the mechanical drawing; establishing all relations among the graphs as a graph rule database by using graph rule association;
s2, drawing information extraction, namely identifying character information of general mechanical parts in the drawing and extracting keywords;
s3, classifying the corresponding drawings under each label by the extracted keywords, and naming the labels by the keywords;
s4, matching the graph rules in the graph rule database according to the drawings in each label, and distributing the same part connection relation into the sub-labels;
s5, verifying the graph, and checking whether the drawing parameters in the mechanical drawing are in accordance with the standard in the graph rule database;
and S6, carrying out abnormal analysis, carrying out manual processing on graphs with wrong drawing parameters of the drawing and graphs which cannot be matched with the graph rule database.
Specifically, in step S1, all the graphic objects are located in a unified coordinate system by the graphic movement method;
and classifying the basic drawing elements, and uniquely identifying the extracted basic information such as points, lines, surfaces, image blocks, textures, colors, tables, image layers and the like to prepare a graphic rule.
Compared with the prior art, the automatic identification and classification method of the mechanical part digital drawing has the advantages that:
the keywords are screened and classified through setting first-level classification, the graphs are compared with a graph rule database through second-level classification, and the graph drawing parameters are compared with the graph rule database through third-level classification, so that the items of the graphs are accurately classified; setting abnormal analysis, performing manual intervention on the graphs which cannot be matched, greatly reducing the intensity of manual operation, and supplementing and correcting a graph rule database in time; the convenience is brought to technicians to search corresponding drawings in time, the operation time is saved, and the work efficiency is improved.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments.
Example (b):
the embodiment is an automatic identification and classification method of a mechanical part digital drawing, which comprises the following steps:
s1, identifying a graph rule, wherein the mechanical drawing rule comprises a rule set in a drawing making stage, the construction objects of the mechanical drawing are point, line and surface attributes, and the mechanical drawing is divided based on different parts and detail compositions of parts, characters, tables and the like in the mechanical drawing; and all the graphic objects are in a unified coordinate system in a graphic movement mode.
And classifying the basic drawing elements, and uniquely identifying the extracted basic information such as points, lines, surfaces, image blocks, textures, colors, tables, image layers and the like to prepare a graphic rule. And establishing all relations among the graphs as a graph rule database by using the graph rule association.
S2, drawing information extraction, namely identifying character information of general mechanical parts in the drawing and extracting keywords; such as mechanical assembly drawing, component structure assembly drawing, screw mounting structure assembly drawing and the like
S3, classifying the corresponding drawings under each label by the extracted keywords, and naming the labels by the keywords;
s4, matching the graph rules in the graph rule database according to the drawings in each label, and distributing the same part connection relation into the sub-labels;
s5, verifying the graph, checking whether the drawing parameters in the mechanical drawing are in accordance with the standard in the graph rule database, verifying the accuracy of the drawing parameters, and verifying the integrity of the graph rule database;
and S6, performing exception analysis, wherein although the graphic features in the mechanical drawing are identified by the graphic rule database and summarized into the sub-labels, drawing parameters or wrong graphics exist, and the graphics which cannot be matched with the graphic rule database are manually processed.
When the method is applied, the keywords are screened and classified by setting the first-level classification, the graph is compared with the graph rule database by the second-level classification, the graph drawing parameters are compared with the graph rule database by the third-level classification, and the items of the graph are accurately classified; setting abnormal analysis, performing manual intervention on the graphs which cannot be matched, greatly reducing the intensity of manual operation, and supplementing and correcting a graph rule database in time; the convenience is brought to technicians to search corresponding drawings in time, the operation time is saved, and the work efficiency is improved.
What has been described above are merely some embodiments of the present invention. It will be apparent to those skilled in the art that various changes and modifications can be made without departing from the inventive concept thereof, and these changes and modifications can be made without departing from the spirit and scope of the invention.
Claims (2)
1. The automatic identification and classification method of the mechanical part digital drawing is characterized by comprising the following steps
S1, identifying a graph rule, wherein the mechanical drawing rule comprises a rule set in a drawing making stage, the construction objects of the mechanical drawing are point, line and surface attributes, and the mechanical drawing is divided based on different parts and detail compositions of parts, characters, tables and the like in the mechanical drawing; establishing all relations among the graphs as a graph rule database by using graph rule association;
s2, drawing information extraction, namely identifying character information of general mechanical parts in the drawing and extracting keywords;
s3, classifying the corresponding drawings under each label by the extracted keywords, and naming the labels by the keywords;
s4, matching the graph rules in the graph rule database according to the drawings in each label, and distributing the same part connection relation into the sub-labels;
s5, verifying the graph, and checking whether the drawing parameters in the mechanical drawing are in accordance with the standard in the graph rule database;
and S6, carrying out abnormal analysis, carrying out manual processing on graphs with wrong drawing parameters of the drawing and graphs which cannot be matched with the graph rule database.
2. The automatic identification and classification method for the mechanical part digital drawing according to claim 1, characterized in that: in step S1, all the graphic objects are placed in a unified coordinate system by a graphic movement method;
and classifying the basic drawing elements, and uniquely identifying the extracted basic information such as points, lines, surfaces, image blocks, textures, colors, tables, image layers and the like to prepare a graphic rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911189276.8A CN110969111A (en) | 2019-11-28 | 2019-11-28 | Automatic identification and classification method for mechanical part digital drawing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911189276.8A CN110969111A (en) | 2019-11-28 | 2019-11-28 | Automatic identification and classification method for mechanical part digital drawing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110969111A true CN110969111A (en) | 2020-04-07 |
Family
ID=70032028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911189276.8A Withdrawn CN110969111A (en) | 2019-11-28 | 2019-11-28 | Automatic identification and classification method for mechanical part digital drawing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110969111A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417996A (en) * | 2020-11-03 | 2021-02-26 | 珠海格力电器股份有限公司 | Information processing method and device for industrial drawing, electronic equipment and storage medium |
| CN113989808A (en) * | 2021-10-25 | 2022-01-28 | 广东宏远新科自动化技术开发有限公司 | Method and system for selecting specifications of mechanical manufacturing materials based on drawing information processing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140214758A1 (en) * | 2013-01-29 | 2014-07-31 | Transbit Technologies Software Private Limited | Method and system for automatic processing and management of technical digital documents and drawings |
| CN107045526A (en) * | 2016-12-30 | 2017-08-15 | 许昌学院 | A kind of pattern recognition method of electronics architectural working drawing |
| CN110399509A (en) * | 2019-06-10 | 2019-11-01 | 万翼科技有限公司 | It is a kind of intelligently to know drawing system and method |
-
2019
- 2019-11-28 CN CN201911189276.8A patent/CN110969111A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140214758A1 (en) * | 2013-01-29 | 2014-07-31 | Transbit Technologies Software Private Limited | Method and system for automatic processing and management of technical digital documents and drawings |
| CN107045526A (en) * | 2016-12-30 | 2017-08-15 | 许昌学院 | A kind of pattern recognition method of electronics architectural working drawing |
| CN110399509A (en) * | 2019-06-10 | 2019-11-01 | 万翼科技有限公司 | It is a kind of intelligently to know drawing system and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112417996A (en) * | 2020-11-03 | 2021-02-26 | 珠海格力电器股份有限公司 | Information processing method and device for industrial drawing, electronic equipment and storage medium |
| CN112417996B (en) * | 2020-11-03 | 2024-06-14 | 珠海格力电器股份有限公司 | Information processing method and device for industrial drawing, electronic equipment and storage medium |
| CN113989808A (en) * | 2021-10-25 | 2022-01-28 | 广东宏远新科自动化技术开发有限公司 | Method and system for selecting specifications of mechanical manufacturing materials based on drawing information processing |
| CN113989808B (en) * | 2021-10-25 | 2022-11-18 | 广东宏远新科自动化技术开发有限公司 | Method and system for selecting specifications of mechanical manufacturing materials based on drawing information processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110992317B (en) | PCB defect detection method based on semantic segmentation | |
| CN109711659B (en) | Yield improvement management system and method for industrial production | |
| CN106021545B (en) | Method for vehicle remote diagnosis and spare part retrieval | |
| US8346773B2 (en) | Product classification system | |
| CN107016018B (en) | Database index creation method and device | |
| CN110704880B (en) | Correlation method of engineering drawings | |
| CN112163553B (en) | Material price accounting method, device, storage medium and computer equipment | |
| CN109598705B (en) | Automatic generation method of inspection procedure based on detection characteristics | |
| CN111127068B (en) | Automatic pricing method and device for engineering quantity list | |
| CN113569310B (en) | Intelligent design method for industrial product model | |
| CN105205038A (en) | Complete material list table generation method and device | |
| CN108241925A (en) | A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection | |
| CN110969111A (en) | Automatic identification and classification method for mechanical part digital drawing | |
| CN111932394A (en) | Bad root cause path analysis method and system based on association rule mining | |
| CN117056688A (en) | New material production data management system and method based on data analysis | |
| CN111652259B (en) | Method and system for cleaning data | |
| CN115982655A (en) | Missing data flow abnormity prediction method based on decision tree | |
| CN105677723A (en) | Method for establishing and searching data labels for industrial signal source | |
| CN110688445B (en) | Digital archive construction method | |
| CN112598142A (en) | Wind turbine generator overhaul work quality examination assisting method and system | |
| CN113781011B (en) | Auditing method and system for power distribution network engineering cost | |
| CN110807082A (en) | Quality spot check item determination method, system, electronic device and readable storage medium | |
| CN116303402A (en) | Data cleaning method based on data warehouse | |
| CN106056223B (en) | Platform for vehicle remote diagnosis and spare part retrieval | |
| CN111209397B (en) | Method for determining enterprise industry category |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200407 |