CN102789651A - Three-dimension model base constructing method for chemical easily-leaked part - Google Patents
Three-dimension model base constructing method for chemical easily-leaked part Download PDFInfo
- Publication number
- CN102789651A CN102789651A CN2012102250337A CN201210225033A CN102789651A CN 102789651 A CN102789651 A CN 102789651A CN 2012102250337 A CN2012102250337 A CN 2012102250337A CN 201210225033 A CN201210225033 A CN 201210225033A CN 102789651 A CN102789651 A CN 102789651A
- Authority
- CN
- China
- Prior art keywords
- cloud
- model
- checked
- point cloud
- bunch
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000000126 substance Substances 0.000 title claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 claims abstract description 9
- 230000015572 biosynthetic process Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000000383 hazardous chemical Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010937 topological data analysis Methods 0.000 description 1
Images
Landscapes
- Examining Or Testing Airtightness (AREA)
Abstract
The invention discloses a three-dimension model base constructing method for a chemical easily-leaked part. The method comprises the following steps: 1, construction analysis for a to-be-detected model, that is, performing construction analysis on the chemical easily-leaked part and performing semantic annotation on the to-be-detected part; 2, formation of point cloud data, that is, acquiring three-dimension point cloud information of the to-be-detected chemical easily-leaked part to form the point cloud data; 3, point cloud noise reduction treatment, that is, reading the scattered three-dimension point cloud data of the to-be-detected chemical easily-leaked part and performing noise reduction treatment on the point cloud data; 4, construction of part feature structures, that is, extracting a key point capable of expressing a feature of the to-be-detected part in boundary points, and reconnecting the key point to form a point cloud cluster according to an analyzed topological structure of each feature part of the to-be-detected model and the semantic annotation built in the step 1; and 5, establishment of a three-dimension point cloud model base, that is, building the three-dimension point cloud model base according to the representation of the cluster topological structure of the point cloud cluster.
Description
Technical field
The present invention relates to the chemical plant leak detection technology, be specially the 3 d model library method for building up that a kind of chemical industry that is used for the petrochemical industry crusing robot is prone to reveal parts.
Background technology
Various countries pay much attention to government utilities such as national security, social securities; In petrochemical industry; The Leak Detection of all kinds of chemical reaction containers and conveyance conduit has become the gordian technique that accident is avoided in petrochemical industry with repairing; According to the relevant regulations of petrochemical equipment leakage monitoring, must detect 8 kinds of positions of chemical reactor and near pipeline thereof, i.e. butt junction, valve, mechanical seal, pad, airtight and watertight padding, glass observation window, inspection socket and measuring instrument detect.Leak Detection for chemical plant also rests on manual detection or online Equipment Inspection at present.Because the singularity (dangerous harmful gas) of petrochemical industry can injure the human body generation for manual detection, and online equipment is too high owing to being prone to the too much feasible detection cost of leakage equipment point, the detection position precision is not high in addition.The mobile robot who at present adopts petrochemical industry to patrol and examine can carry out the detection of leak, but in testing process, adopt be utilize the target object image information as: information such as color, shape and smell information of sending or frequency response are comprehensively judged.Use for this robotlike's image information, also only rest on based on two-dimensional signal analysis and judgement to target object, and more than two dimensional image owing to having, the abundanter visually-perceptible details of three-dimensional model, thereby can improve the accuracy of search greatly.How fast and accurately this base part to be carried out Leak Detection, thereby confirm that hazardous chemical gas leakage source or suspicious object still exist some key issues and need to solve.Robot with target search station-keeping ability has higher utility.Therefore based on a kind of recognition technology of 3 d model library, and can be applied to the mobile robot, will have higher actual value and be worth with theoretical in the suspicious object search.
At present, the foundation of object dimensional model bank mainly contains following several method:
1) utilize traditional geometry Modeling Technology intuition to set up model:
2) utilize 3-D scanning equipment that real-world object is scanned, and then reconstruct model:
3) utilization is to the image reconstruction model (IBMR technology) at a plurality of visual angles of real-world object.
The point cloud information structuring object dimensional model bank of utilizing the binocular solid camera to obtain belongs to the image reconstruction modelling technique.The method of carrying out modeling usually is that a plurality of visual angles of object are scanned, thereby realizes three-dimensional model foundation.But the data volume that this method relates to is bigger, and is bigger for subsequent applications, the desired calculated amount of processing of model bank, causes efficient low, and real-time is poor, can not satisfy actual needs.Therefore seek a kind of suitable, effectively information extraction and method for reconstructing seem particularly important.
Summary of the invention
To the deficiency of prior art, the technical matters that quasi-solution of the present invention is determined is to propose the 3 d model library method for building up that a kind of chemical industry is prone to reveal parts.This method realizes the three-dimensional point cloud model input to object through simple input equipment; And the inner topology of the local feature through object relation is set up some cloud bunch; Then set up 3 d model library according to the topological relation between the cloud bunch-bunch, method is easy, is convenient to practical application.
The technical scheme that the present invention solve the technical problem is, designs the 3 d model library method for building up that a kind of chemical industry is prone to reveal parts, and the step that this method adopted is:
(1) model conformational analysis to be checked: chemical industry is prone to leak carries out conformational analysis, parts to be checked are carried out semantic annotations;
(2) form cloud data: obtain the three-dimensional point cloud information that chemical industry to be checked is prone to reveal parts, form cloud data;
(3) some cloud denoising: read the three dimensional point cloud at random that chemical industry to be checked is prone to reveal parts, cloud data is carried out denoising, thereby simplify cloud data; According to the curvature of curved surface that the cloud data neighborhood of a point is asked for, extract the frontier point that chemical industry to be checked is prone to reveal parts;
(4) component feature structure construction: extract the key point that to represent component feature to be checked in the frontier point; Semantic annotations according to being set up in the topological structure of analyzing gained each characteristic of model to be checked and the step (1) connects key point again; Form some cloud bunch, and then form the component feature structure construction;
(5) set up the three-dimensional point cloud model bank: the some cloud bunch topological structure with corresponding model that will represent each characteristic portion of model to be checked characterizes, thereby some cloud bunch-bunch topological structure of accomplishing model to be checked characterizes; Set up the three-dimensional point cloud model bank according to a cloud bunch-bunch topological structure sign.
Compared with prior art; Chemical industry of the present invention is prone to the 3 d model library method for building up of leak because adopted the simplification point cloud bunch with local topology relation--the method for bunch topology; Set up the three-dimensional point cloud model bank that petrochemical industry or chemical plant are prone to leak; Thereby can accurately express the information of model to be checked, and be not subject to the influence of angle, light to parts to be checked, improved the accuracy and the convenience that detect; The data volume that is used to simultaneously to handle is less, can satisfy the high characteristics of petrochemical industry robot online detection requirements real-time.
Description of drawings
Fig. 1 is prone to the process flow diagram of a kind of embodiment of 3 d model library method for building up of leak for chemical industry of the present invention;
Fig. 2 is prone to a kind of embodiment of 3 d model library method for building up of leak for chemical industry of the present invention foundation point cloud bunch is set up the detail flowchart of process and bunch-bunch topological process;
Fig. 3 is prone to the pipe joint three-dimensional stereo model storehouse method for building up process flow diagram of a kind of embodiment of 3 d model library method for building up of leak for chemical industry of the present invention.
Embodiment
Existing is that pipe joint is embodiment with a kind of easy leak in the petrochemical equipment, and combines its accompanying drawing, to 3 d model library method for building up of the present invention further explain.
The chemical industry of the present invention's design is prone to 3 d model library method for building up (the abbreviation method of leak; Referring to Fig. 1-3); Be to be prone on the morphosis characteristic basis of leak,, accomplish its complete configuration is described through semantic annotations at research petroleum chemical enterprise chemical industry; Thereby can be used in petrochemical industry and patrol and examine the mobile robot, it is that suspicious target is accomplished search check fast that chemical industry is prone to reveal parts.The concrete steps of said method are:
1, model to be checked (pipe joint parts) conformational analysis
Because the present invention is used for the three-dimensional detection that the key of petrochemical industry is prone to leak; And its parts have certain feature structure, thereby the pipe joint parts are carried out conformational analysis, characteristic features that can the bonded block shape; The sign of utilizing the general petrochemical industry of having set up to be prone to leak is resolved note; Thereby accomplish the language notation that the pipe joint parts is used for the stereoscopic model storehouse,, can effectively describe the architectural feature of the different parts of other petrochemical equipments through the method.
2, form cloud data
Through the stereoscopic vision video camera pipe joint parts to be checked are carried out the off-line collection, thereby generate the cloud data file, this cloud data file description the volume coordinate and the colouring information of parts to be checked and peripheral part environment point thereof.
3, some cloud denoising
The cloud data of pipe joint parts to be checked is read in a cloud messaging software, set up the topological relation between the some cloud, the traversal cloud data utilizes curvature method to judge whether to be frontier point, if keep frontier point; If not, then travel through next point, judge whether it is frontier point, is embodied as to set up the cloud data chained list, and from this chained list, travel through cloud data, judge whether to be frontier point, if then keep frontier point; If not, then travel through again; Retrain the whole cloud datas of traversal with this.Seek the unique point in the frontier point according to the architectural feature of analyzing pipeline to be checked, judge whether the point in the frontier point storehouse that keeps is the sign point of characteristic,, unique point is all extracted if then keep.
4, component feature structure construction
The topological structure meaning of one's words note of the pipe joint of having set up according to step 1; Pipe joint parts boundary characteristic to be checked according to step 3 gained; Mostly coupling part like pipe joint is flange-type structure, that is to say by the porose disk in edge to form, and the point to same characteristic carries out the topology connection in view of the above; Disk end face and outer rim circular hole are carried out a cloud respectively cluster, thereby form some cloud bunch with inner topology characteristic separately.The frontier point that is embodied as retaining carries out the characteristic topological analysis; Satisfy then being retained of configuration for unique point; Ungratified then is not thereby that unique point is removed; Unique point according to retaining is set up topological relation, thereby forms local feature point cloud bunch, and then formation component feature structure construction;
5, set up the three-dimensional point cloud model bank
The overall topology of analysis conduit; Each several part is put cloud bunch also to be coupled together according to topological mode; As the some cloud of disk end face point cloud in the conduit coupling in this example bunch and disk outer rim circular hole bunch; These two kinds of some clouds bunch are carried out the integral body topology connect, thereby form complete three-dimensional point cloud bunch-bunch topological structure of pipe joint.Bunch-bunch topological structure of this some cloud promptly is the 3 d model library that utilizes the pipe joint to be checked that the inventive method obtains.
Though the inventive method is that pipe joint is that embodiment specifies with a kind of leak, its principle and process are applicable to that other chemical industry are prone to the 3 d model library foundation of leak.
The present invention does not address part and is applicable to prior art.
Claims (1)
1. a chemical industry is prone to reveal the 3 d model library method for building up of parts, and the step that this method adopted is:
(1) model conformational analysis to be checked: chemical industry is prone to leak carries out conformational analysis, parts to be checked are carried out semantic annotations;
(2) form cloud data: obtain the three-dimensional point cloud information that chemical industry to be checked is prone to reveal parts, form cloud data;
(3) some cloud denoising: read the three dimensional point cloud at random that chemical industry to be checked is prone to reveal parts, cloud data is carried out denoising, thereby simplify cloud data; According to the curvature of curved surface that the cloud data neighborhood of a point is asked for, extract the frontier point that chemical industry to be checked is prone to reveal parts;
(4) component feature structure construction: extract the key point that to represent component feature to be checked in the frontier point; Semantic annotations according to being set up in the topological structure of analyzing gained each characteristic of model to be checked and the step (1) connects key point again; Form some cloud bunch, and then form the component feature structure construction;
(5) set up the three-dimensional point cloud model bank: the some cloud bunch topological structure with corresponding model that will represent each characteristic portion of model to be checked characterizes, thereby some cloud bunch-bunch topological structure of accomplishing model to be checked characterizes; Set up the three-dimensional point cloud model bank according to a cloud bunch-bunch topological structure sign.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210225033.7A CN102789651B (en) | 2012-07-03 | 2012-07-03 | Three-dimension model base constructing method for chemical easily-leaked part |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210225033.7A CN102789651B (en) | 2012-07-03 | 2012-07-03 | Three-dimension model base constructing method for chemical easily-leaked part |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102789651A true CN102789651A (en) | 2012-11-21 |
| CN102789651B CN102789651B (en) | 2015-03-11 |
Family
ID=47155048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210225033.7A Expired - Fee Related CN102789651B (en) | 2012-07-03 | 2012-07-03 | Three-dimension model base constructing method for chemical easily-leaked part |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102789651B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114025701A (en) * | 2019-06-20 | 2022-02-08 | 索尼集团公司 | Surgical tool tip and orientation determination |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1374620A (en) * | 2002-03-27 | 2002-10-16 | 深圳市特得维技术有限公司 | Computerized 3D visual color scan system and its scanning mode |
| CN101650835A (en) * | 2009-09-09 | 2010-02-17 | 哈尔滨工业大学 | Method for establishing three-dimensional geometrical structure of dog left ventricle conduction system based on local linear embedding method |
| US20110304628A1 (en) * | 2010-06-10 | 2011-12-15 | Autodesk, Inc. | Pipe reconstruction from unorganized point cloud data |
| US20120136860A1 (en) * | 2006-08-31 | 2012-05-31 | Drexel University | Multi-scale segmentation and partial matching 3d models |
-
2012
- 2012-07-03 CN CN201210225033.7A patent/CN102789651B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1374620A (en) * | 2002-03-27 | 2002-10-16 | 深圳市特得维技术有限公司 | Computerized 3D visual color scan system and its scanning mode |
| US20120136860A1 (en) * | 2006-08-31 | 2012-05-31 | Drexel University | Multi-scale segmentation and partial matching 3d models |
| CN101650835A (en) * | 2009-09-09 | 2010-02-17 | 哈尔滨工业大学 | Method for establishing three-dimensional geometrical structure of dog left ventricle conduction system based on local linear embedding method |
| US20110304628A1 (en) * | 2010-06-10 | 2011-12-15 | Autodesk, Inc. | Pipe reconstruction from unorganized point cloud data |
Non-Patent Citations (2)
| Title |
|---|
| SURYA GANGULI等: "Compressed Sensing，Sparsity,and Dimensionality in Neuronal Information Processing and Data Analysis", 《NEUROSCIENCE》 * |
| 张义宽等: "3D点云的拓扑结构表征与计算技术", 《中国图象图形学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114025701A (en) * | 2019-06-20 | 2022-02-08 | 索尼集团公司 | Surgical tool tip and orientation determination |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102789651B (en) | 2015-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112241997B (en) | Three-dimensional model building and repairing method and system based on multi-scale point cloud up-sampling | |
| EP2948916B1 (en) | Inspection data graphical filter | |
| Patil et al. | An adaptive approach for the reconstruction and modeling of as-built 3D pipelines from point clouds | |
| CN109035224B (en) | Submarine pipeline detection and three-dimensional reconstruction method based on multi-beam point cloud | |
| Lee et al. | Skeleton-based 3D reconstruction of as-built pipelines from laser-scan data | |
| Bosché et al. | The value of integrating Scan-to-BIM and Scan-vs-BIM techniques for construction monitoring using laser scanning and BIM: The case of cylindrical MEP components | |
| KR101794282B1 (en) | The method of creating 2d piping cad data to 3d piping cad modeling data | |
| US20230154037A1 (en) | Method for detecting leakage of water supply pipe based on ground-penetrating radar three-dimensional image attribute analysis | |
| US9620107B2 (en) | Voice inspection guidance | |
| CN103065356B (en) | A kind of method for building up of offshore oil facility three-dimensional model | |
| CN107103640B (en) | Three-dimensional modeling method and system for urban underground pipeline | |
| US20140207406A1 (en) | Self-directed inspection plan | |
| CN104937617B (en) | Provision of inspection data | |
| Wang et al. | Gas leak location detection based on data fusion with time difference of arrival and energy decay using an ultrasonic sensor array | |
| CN104181548A (en) | Method for monitoring water and soil conservation condition based on three-dimensional laser scanning technology | |
| Chen et al. | A review of detection technologies for underwater cracks on concrete dam surfaces | |
| CN104268940B (en) | MEMS structure reconstruction and detection method based on CT scanned images | |
| Osadcha et al. | Geometric parameter updating in digital twin of built assets: A systematic literature review | |
| Hongbin et al. | Feature preserving holes filling of scattered point cloud based on tensor voting | |
| Ahmed et al. | Autonomous modeling of pipes within point clouds | |
| Lin et al. | A novel detection and assessment method for operational defects of pipe jacking tunnel based on 3D longitudinal deformation curve: a case study | |
| CN111767619A (en) | Rapid modeling method for existing municipal engineering pipeline model | |
| Fahle et al. | Development and testing of octree-based intra-voxel statistical inference to enable real-time geotechnical monitoring of large-scale underground spaces with mobile laser scanning data | |
| CN102789651B (en) | Three-dimension model base constructing method for chemical easily-leaked part | |
| CN105574930B (en) | A kind of Chinese character three-dimensional data Collection ＆ Processing System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150311 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |