CN110502771A - A kind of prefabricated components point cloud automatic die assembly method based on particle swarm algorithm variable domain search match point - Google Patents
A kind of prefabricated components point cloud automatic die assembly method based on particle swarm algorithm variable domain search match point Download PDFInfo
- Publication number
- CN110502771A CN110502771A CN201910341005.3A CN201910341005A CN110502771A CN 110502771 A CN110502771 A CN 110502771A CN 201910341005 A CN201910341005 A CN 201910341005A CN 110502771 A CN110502771 A CN 110502771A
- Authority
- CN
- China
- Prior art keywords
- point
- prefabricated components
- point cloud
- bim
- bim model
- 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 31
- 239000002245 particle Substances 0.000 title claims abstract description 21
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 238000013461 design Methods 0.000 claims abstract description 8
- 238000013519 translation Methods 0.000 claims description 20
- 238000012952 Resampling Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 5
- 238000000465 moulding Methods 0.000 abstract description 17
- 238000012372 quality testing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 239000012141 concentrate Substances 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Moulds For Moulding Plastics Or The Like (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Invention provides a kind of prefabricated components point cloud automatic die assembly method based on particle swarm algorithm variable domain search match point.The automatic die assembly method include input prefabricated components point cloud, corresponding BIM model index, the discrete Extract contour point cloud data of BIM model, resample, thick matching judgment, BIM model significant points classification, matching point search pairing, spatial position optimization and etc..It designs a model automatically with BIM the technical method molded the present invention provides prefabricated components point cloud, prefabricated components are efficiently solved in quality testing, the problem of carrying out a large amount of human interventions is needed with the molding of BIM model, method is provided for the estimation of later period dimension data and supports.
Description
Technical field
It is the present invention relates to building safety management field, in particular to a kind of that match point is searched for based on particle swarm algorithm variable domain
Prefabricated components point cloud automatic die assembly method.
Background technique
In assembled architecture industry, in order to guarantee the successful installation of prefabricated components at the construction field (site), need in transport
It is preceding to carry out stringent quality testing.And currently used quality determining method is traditional manual measurement method.Manual measurement is pre-
Component processed have the shortcomings that it is obvious, such as: personnel attrition is big in detection process, time monetary cost is high, once workload is excessive
Easily cause artificial detection mistake.Therefore, it when in face of prefabricated components quantity is more, component form is complicated, is swept using three-dimensional laser
Retouching measuring technique can be effectively solved these problems.
Currently, the method that technical staff when carrying out error-detecting to prefabricated components point cloud data, generallys use is molding
Detection.Molding detection, which refers to designing a model prefabricated components point cloud data with BIM, to be carried out in conjunction with matching, to reach observation
To the purpose of ratio error.Current generation, the process for carrying out molding detection needs artificially specified match point, due to artificially selecting
As a result, match point inherently has error, it is more unreliable that this will lead to molding result.
Therefore, to make clamping process no longer have human intervention, match point, and iteration can be automatically selected by needing to develop one kind
Update the automatic die assembly method of match point.
Summary of the invention
The object of the present invention is to provide a kind of prefabricated components point Yun Zidong based on particle swarm algorithm variable domain search match point
Closing method, to solve problems of the prior art.
To realize the present invention purpose and the technical solution adopted is that such, one kind is matched based on the search of particle swarm algorithm variable domain
To the prefabricated components point cloud automatic die assembly method of point, comprising the following steps:
1) prefabricated components point cloud data is inputted.
2) it in BIM database, finds the corresponding BIM of prefabricated components and designs a model, and BIM is designed a model and is converted into
Desired point cloud.
3) BIM is obtained to design a model profile point set.
4) using Max Leverage resampling algorithm in the BIM model silhouette point set and step 1) obtained in step 3)
The prefabricated components point cloud data of input is resampled respectively
5) 4PCS algorithm is utilized, rough registration is carried out to BIM model silhouette resampling point set and prefabricated components resampling point set.
Calculate Rigid Body In Space transformation matrix.
6) utilize step Rigid Body In Space transformation matrix by complete BIM model silhouette point set and complete prefabricated components point cloud
Carry out rough registration.
7) according to prefabricated components feature, the BIM model silhouette point set in step 6) is divided into n grades.According to BIM model
It includes points that profile point collection sum, which calculates at different levels, and it is each to carry out BIM model silhouette point set using Max Leverage resampling algorithm
Grade points sampling, and different search neighborhoods is set and calculates match point.
8) using between particle swarm algorithm iterative calculation BIM model silhouette point set and prefabricated components point cloud data match point
Translation vector and quaternary number carry out the coordinate transform of prefabricated components point cloud data according to the translation vector of calculating and quaternary number, directly
Stop after to optimization M times.
9) output BIM model silhouette point set and prefabricated components point cloud data mold result.
Further, in step 7), BIM model silhouette point lump points are Num.BIM model silhouette point set presses significance level
It is divided into 4 grades.The Base search radius of neighbourhood is tr.The i-stage radius of neighbourhood is (5-i) tr.Wherein, i=1,2,3,4.According to BIM
Model silhouette point concentrates the three-dimensional coordinate (x, y, z) and unit normal vector (n of each pointx,ny,nz) coordinate, cycle calculations are all
The lever value of point, and it is arranged from big to small.Maximum lever value point is taken out every time, and judges whether off-take point number reaches point
Grade data point number 0.25Num, is classified update if reaching.When all the points are removed and are classified completion, then stop.
Further, in step 7), prefabricated components point cloud data is established into Kd-Tree data structure.Search for all BIM models
Profile point concentrates each point to the nearest neighbor point in prefabricated components point cloud data, chooses where nearest neighbor point distance is less than the point and sets
The point building model-cloud match point pair for setting the classification radius of neighbourhood, screens the model-cloud match point pair repeated, so that
Match point corresponds.
Further, in step 8), the translation vector and quaternary number between the match point that step 7) obtains are calculated.
Arbitrary point p (x, y, z) is according to any quaternary number q (q0,q1,q2,q3) rotation computation rule:
Wherein, p ' is institute's invocation point after rotation.
With translation vector t (t1, t2, t3) 3 translation variables are used as, by optimization object function
q0,q1,q2,q3,t1,t2,t3∈(-1,1)
Setting are as follows:
Wherein R (q) indicates rotation translation calculation, and N indicates the number of match point, and all Variable Controls are between -1 to 1.
The solution have the advantages that unquestionable:
A. optimize repeatedly using particle swarm algorithm and calculate the pairing of BIM model silhouette point set Yu prefabricated components point cloud data
Point, to complete automation molding;
It B. include thick matching and Optimized Matching step in clamping process, BIM model and prefabricated components point cloud are completed in thick matching
The substantially positioning of data, Optimized Matching can carry out different degrees of pairing according to the significance level of different parts in BIM model
Point search, so that molding result is more accurate;
C. it efficiently solves and manually chooses the unreliable and uncertain of match point in traditional clamping process, so that molding
Cheng Bianwei automation no longer needs human intervention, is that the prefabricated components point cloud error in later period compares providing method support.
Detailed description of the invention
Fig. 1 is method flow diagram;
Fig. 2 is the profile point set schematic diagram of prefabricated components point cloud data and BIM model extraction;
Fig. 3 is 10% resampling effect diagram of Max Leverage;
Fig. 4 is to carry out thick matching effect schematic diagram automatically using 4PCS;
Fig. 5 is BIM profile point set significance level automatic classification schematic diagram;
Fig. 6 is automatic die assembly result schematic diagram;
Fig. 7 is that algorithm iteration restrains result.
Specific embodiment
Below with reference to embodiment, the invention will be further described, but should not be construed the above-mentioned subject area of the present invention only
It is limited to following embodiments.Without departing from the idea case in the present invention described above, according to ordinary skill knowledge and used
With means, various replacements and change are made, should all include within the scope of the present invention.
Embodiment 1:
Referring to Fig. 1, the present embodiment lower, knot for the degree of automation present in existing prefabricated components molding detection technique
Do not have the problems such as operability when fruit reliability is lower and amount detection is larger, it is open a kind of based on particle swarm algorithm variable domain
Search for the prefabricated components point cloud automatic die assembly method of match point, comprising the following steps:
1) prefabricated components point cloud data is inputted.
2) it in BIM database, finds the corresponding BIM of prefabricated components and designs a model, and BIM is designed a model and is converted into
Desired point cloud.
3) referring to fig. 2, discrete BIM designs a model, and obtains BIM and designs a model profile point set.Wherein, 2a is concrete exterior wall
Plate point cloud data, 2b are BIM model outer profile point set.
4) using Max Leverage (maximum lever value) resampling algorithm to the BIM model silhouette point obtained in step 3)
Collect and resamples respectively with the prefabricated components point cloud data inputted in step 1).Wherein, Max Leverage resampling is calculated
Method basic principle description are as follows: according to cloud three-dimensional coordinate (x, y, z) and unit normal vector coordinate (nx,ny,nz), cycle calculations institute
Lever value (Leverage value) a little, and it is arranged from big to small, maximum lever value point is taken out every time, and judges to take
Whether point set reaches quantity of sampling quantity standard out, stops circulation after reaching quantity of sampling quantity standard, exports point set after resampling.
In the present embodiment, the data volume of resampling accounts for the 10% of former data volume.Take less data amount that can reduce thick
The match point selection matched improves computational efficiency to reduce calculation amount.Referring to Fig. 3, sample point substantially prefabricated components entirety ruler
Very little angle point range.
5) 4PCS (4-Point Congruent Set, four point congruence set) algorithm is utilized, BIM model silhouette is refetched
Sampling point collection and prefabricated components resampling point set carry out rough registration.Calculate Rigid Body In Space transformation matrix.The 4PCS algorithm is substantially former
Reason description are as follows: firstly, concentrating two pairs of space intersection data points of search in template point, calculate separately the length of each pair of data point;
Secondly, all data points pair concentrated search to meet two groups of length in match point and intersected;Finally, carrying out model point set and matching
To the space coordinate transformation of point set, successful matching is detected whether, and recycled repeatedly, export optimal spatial rigid body translation matrix.
6) utilize step Rigid Body In Space transformation matrix by complete BIM model silhouette point set and complete prefabricated components point cloud
Carry out rough registration.Such as Fig. 4, provides and knot is matched with the thick of prefabricated components point cloud data using 4PCS algorithm BIM model silhouette point set
Fruit.In figure, 4a slightly matches schematic diagram with BIM model silhouette for prefabricated components point cloud, and 4b and 4c are thick matching detailed schematic.
4b and 4c can be seen that profile point set is only substantially matching out at the long edge of component, and built-in fitting or component corner matching gap compared with
Greatly.In actual production, the case where might have prefabricated components size and BIM model silhouette point set there are size differences.
7) it calculates the lever value of BIM model silhouette point set and arranges from big to small, lever is divided according to different component feature
It is worth grade, and different search neighborhoods is set and calculates match point.
According to BIM model silhouette point lump points N um, profile point set significance level is classified as 1-4 grades.
The setting Base search radius of neighbourhood is tr, the radius of neighbourhood at different levels are (5-i) tr, as shown in figure 5, different colours table
Show different classifications, in the present embodiment tr=5mm.
The three-dimensional coordinate (x, y, z) and unit normal vector (n of each point are concentrated according to BIM model silhouette pointx,ny,nz) sit
Mark, the lever value of cycle calculations all the points, and it is arranged from big to small;Maximum lever value point is taken out every time, and judges to take out
Whether point number reaches ranked data point number 0.25Num, update is classified if reaching, when all the points are removed and have been classified
At then stopping.
Prefabricated components point cloud data is established into Kd-Tree data structure, it is each to search for all BIM model silhouette points concentrations
Point chooses the setting classification radius of neighbourhood where nearest neighbor point distance is less than the point to the nearest neighbor point in prefabricated components point cloud data
Point construct model-cloud match point pair, screen the model-cloud match point pair repeated so that match point correspond.
8) BIM model is iterated to calculate using PSO (Particle Swarm Optimization, particle swarm optimization algorithm)
Translation vector and quaternary number between profile point set and prefabricated components point cloud data match point, according to the translation vector of calculating and four
First number carries out the coordinate transform of prefabricated components point cloud data, until stopping after optimization M times.
To the match point that step 7) obtains, translation vector and quaternary number between match point are calculated.It is replaced with quaternary number
9 known variables of spin matrix can be reduced to 4 known variables by spin matrix, significantly reduce calculation amount.
Arbitrary point p (x, y, z) is according to any quaternary number q (q0,q1,q2,q3) rotation computation rule:
Wherein, p' is institute's invocation point after rotation.
With translation vector t (t1,t2,t3) 3 translation variables are used as, therefore optimization object function can be arranged are as follows:
q0,q1,q2,q3,t1,t2,t3∈(-1,1)
Wherein R (q) indicates rotation translation calculation, and N indicates the number of match point, and all Variable Controls are between -1 to 1.
The basic principle of particle swarm algorithm are as follows: use simple speed --- position model, pass through conjunction individual between population
Make to realize the solution to optimization problem with competition.
Wherein problem setting search space is D=7 dimension space, and population number is Np:
The position of Arbitrary Particles i indicates are as follows: Xi=(xi1,xi2,...,xiD);
The flying speed of Arbitrary Particles i are as follows: Vi=(vi1,vi2,...,viD);
The history optimum position of Arbitrary Particles i are as follows: Pi=(pi1,pi2,...,piD);
The global optimum position of population: Pg=(pg1,pg2,...,pgD);
Speed updates:
vij(t+1)=ω vij(t)
+c1×Rand()×(pij(t)-xij(t))+c2×Rand()(pgj(t)-xij(t))
Wherein its inertia weight of ω, c1With c2For Studying factors;
Location updating: xij(t+1)=xij(t)+vij(t+1);
Constraint condition control is -1≤vij≤ 1 and -1≤xij≤1;
History is optimal to be updated with global optimum:
Specified optimization number M, every suboptimization obtains translation vector and quaternary number will be directly to prefabricated components point cloud data
Coordinate is converted, and every suboptimization repeats step 7) and step 8), updates match point and coordinate position, optimization object function M times
After stop.As shown in fig. 6, providing final molding as a result, population quantity N is arranged in embodimentp=50, the number of iterations is
3000 times, optimize number M=20 times.6a is prefabricated components point cloud and the molding of BIM model silhouette as a result, 6b and 6c are molding details
Schematic diagram.From the point of view of integrally molding situation, prefabricated components point cloud data and BIM model outer profile data molding situation are fine, knot
The lever value stage division of BIM model is closed, payes attention to angular point portions and built-in fitting part in point cloud data, mitigates component middle section
The significance level of data allows clamping process so that different model area is not identical for the attraction of prefabricated components point cloud data
It is more in line with the testing requirements of prefabricated components.Fig. 7 is that algorithm iteration restrains result.Fig. 7 a indicates optimized evaluation curve, wherein horizontal
Coordinate representation optimizes number, and ordinate is valuation functions value, when final output is assessed value highest, when optimization number is 18
Result.Fig. 7 b is the convergence precision in 20 suboptimization each time, and ordinate indicates convergence precision, and abscissa indicates that population number multiplies
With the number of iterations, it can be seen that convergence precision when every suboptimization can reach 10-4.The present embodiment algorithm is effective.
9) output BIM model silhouette point set and prefabricated components point cloud data mold result.
It is worth noting that the present embodiment is classified according to BIM model silhouette point lever value, it can be with automatic distinguishing component
The significance level of different piece, so that clamping process is more accurate., the present embodiment completes 4PCS from after matching of using force, in BIM mould
Biggish region of search is arranged in type lever value larger part (turning etc.), increases the search capability of its match point in the overall situation.It recycles
Particle swarm algorithm goes to self-optimizing model position, and constantly updates match point, iteration optimization.Final purpose is BIM profile to be allowed
Point set is in a suitable position in prefabricated components point cloud, for size comparison later.The present embodiment is using heuristic
Searching algorithm optimizes marriage problem, obtains the molding of prefabricated components point cloud data and BIM model silhouette point set as a result, reality
The automation molding for having showed prefabricated components point cloud data, avoids more manual operations, solves manual method molding not
Reliability, so that the scale error assessment for prefabricated components provides method support.
Claims (4)
1. a kind of prefabricated components point cloud automatic die assembly method based on particle swarm algorithm variable domain search match point, which is characterized in that
The following steps are included:
1) prefabricated components point cloud data is inputted;
2) it in BIM database, finds the corresponding BIM of prefabricated components and designs a model, and BIM is designed a model and is converted into desired point
Cloud;
3) BIM is obtained to design a model profile point set;
4) using Max Leverage resampling algorithm to input in the BIM model silhouette point set and step 1) obtained in step 3)
Prefabricated components point cloud data resample respectively
5) 4PCS algorithm is utilized, rough registration is carried out to BIM model silhouette resampling point set and prefabricated components resampling point set;It calculates
Rigid Body In Space transformation matrix;
6) utilize step Rigid Body In Space transformation matrix by complete BIM model silhouette point set and complete prefabricated components point Yun Jinhang
Rough registration;
7) according to prefabricated components feature, the BIM model silhouette point set in step 6) is divided into n grades;According to BIM model silhouette point
It includes points that collection sum, which calculates at different levels, carries out BIM model silhouette point set points at different levels using Max Leverage resampling algorithm
Sampling, and different search neighborhoods is set and calculates match point;
8) using the translation between particle swarm algorithm iterative calculation BIM model silhouette point set and prefabricated components point cloud data match point
Vector and quaternary number carry out the coordinate transform of prefabricated components point cloud data according to the translation vector of calculating and quaternary number, until excellent
Stop after changing M times;
9) output BIM model silhouette point set and prefabricated components point cloud data mold result.
2. the prefabricated components point cloud automatic die assembly method according to claim 1 based on particle swarm algorithm, it is characterised in that:
In step 7), BIM model silhouette point lump points are Num;BIM model silhouette point set is divided into 4 grades by significance level;Base search
The radius of neighbourhood is tr;The i-stage radius of neighbourhood is (5-i) tr;Wherein, i=1,2,3,4;It is concentrated according to BIM model silhouette point each
The three-dimensional coordinate (x, y, z) and unit normal vector (n of a pointx,ny,nz) coordinate, the lever value of cycle calculations all the points, and by its
It arranges from big to small;Maximum lever value point is taken out every time, and judges whether off-take point number reaches ranked data point number
0.25Num is classified update if reaching;When all the points are removed and are classified completion, then stop.
3. the prefabricated components point cloud automatic die assembly method according to claim 2 based on particle swarm algorithm, it is characterised in that:
In step 7), prefabricated components point cloud data is established into Kd-Tree data structure;It is each to search for all BIM model silhouette points concentrations
Point chooses the setting classification radius of neighbourhood where nearest neighbor point distance is less than the point to the nearest neighbor point in prefabricated components point cloud data
Point construct model-cloud match point pair, screen the model-cloud match point pair repeated so that match point correspond.
4. the prefabricated components point cloud automatic die assembly method according to claim 1 based on particle swarm algorithm, it is characterised in that:
In step 8), the translation vector and quaternary number between the match point that step 7) obtains are calculated;Arbitrary point p (x, y, z) is according to any
Quaternary number q (q0,q1,q2,q3) rotation computation rule such as following formula:
In formula, p' is institute's invocation point after rotation.
With translation vector t (t1,t2,t3) 3 translation variables are used as, optimization object function is arranged are as follows:
q0,q1,q2,q3,t1,t2,t3∈(-1,1)
In formula, R (q) indicates rotation translation calculation, and N indicates the number of match point, and all Variable Controls are between -1 to 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910341005.3A CN110502771B (en) | 2019-04-25 | 2019-04-25 | Prefabricated part point cloud automatic die closing method based on particle swarm algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910341005.3A CN110502771B (en) | 2019-04-25 | 2019-04-25 | Prefabricated part point cloud automatic die closing method based on particle swarm algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110502771A true CN110502771A (en) | 2019-11-26 |
CN110502771B CN110502771B (en) | 2021-04-27 |
Family
ID=68585251
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910341005.3A Active CN110502771B (en) | 2019-04-25 | 2019-04-25 | Prefabricated part point cloud automatic die closing method based on particle swarm algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110502771B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112489188A (en) * | 2020-11-17 | 2021-03-12 | 上海建工四建集团有限公司 | Prefabricated part point cloud and design model mold closing method |
CN115222787A (en) * | 2022-09-20 | 2022-10-21 | 天津中科智能技术研究院有限公司 | Real-time point cloud registration method based on mixed retrieval |
CN115270250A (en) * | 2022-07-19 | 2022-11-01 | 中国建筑西南设计研究院有限公司 | BIM-based automatic checking method, system and medium for basic big sample detail drawing |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103770216A (en) * | 2014-01-09 | 2014-05-07 | 周兆弟 | Upper die and lower die clamping mechanism for prefabricated part forming die and die clamping and opening method |
US20160274025A1 (en) * | 2015-03-20 | 2016-09-22 | SMS Sensors Incorporated | Systems and Methods for Detecting Gases, Airborne Compounds, and Other Particulates |
CN106370670A (en) * | 2016-10-12 | 2017-02-01 | 上海建工集团股份有限公司 | 3D laser scanning based building prefabricated part quality detection system and method |
CN109118500A (en) * | 2018-07-16 | 2019-01-01 | 重庆大学产业技术研究院 | A kind of dividing method of the Point Cloud Data from Three Dimension Laser Scanning based on image |
-
2019
- 2019-04-25 CN CN201910341005.3A patent/CN110502771B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103770216A (en) * | 2014-01-09 | 2014-05-07 | 周兆弟 | Upper die and lower die clamping mechanism for prefabricated part forming die and die clamping and opening method |
US20160274025A1 (en) * | 2015-03-20 | 2016-09-22 | SMS Sensors Incorporated | Systems and Methods for Detecting Gases, Airborne Compounds, and Other Particulates |
CN106370670A (en) * | 2016-10-12 | 2017-02-01 | 上海建工集团股份有限公司 | 3D laser scanning based building prefabricated part quality detection system and method |
CN109118500A (en) * | 2018-07-16 | 2019-01-01 | 重庆大学产业技术研究院 | A kind of dividing method of the Point Cloud Data from Three Dimension Laser Scanning based on image |
Non-Patent Citations (3)
Title |
---|
YUQIN GE等: "A point cloud registration method combining enhanced particle swarm optimization and iterative closest point method", 《IEEE XPLORE》 * |
刘鹏坤等: "BIM技术在装配式建筑中的应用——以中科大厦为例", 《土木建筑工程信息技术》 * |
韩贤权等: "散乱点云数据精配准的粒子群优化算法", 《武汉大学学报.信息科学版》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112489188A (en) * | 2020-11-17 | 2021-03-12 | 上海建工四建集团有限公司 | Prefabricated part point cloud and design model mold closing method |
CN115270250A (en) * | 2022-07-19 | 2022-11-01 | 中国建筑西南设计研究院有限公司 | BIM-based automatic checking method, system and medium for basic big sample detail drawing |
CN115222787A (en) * | 2022-09-20 | 2022-10-21 | 天津中科智能技术研究院有限公司 | Real-time point cloud registration method based on mixed retrieval |
CN115222787B (en) * | 2022-09-20 | 2023-01-10 | 宜科(天津)电子有限公司 | Real-time point cloud registration method based on hybrid retrieval |
Also Published As
Publication number | Publication date |
---|---|
CN110502771B (en) | 2021-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110502771A (en) | A kind of prefabricated components point cloud automatic die assembly method based on particle swarm algorithm variable domain search match point | |
CN102750739B (en) | Construction method of three-dimensional geologic model | |
Fu et al. | Integrated thermal error modeling of machine tool spindle using a chicken swarm optimization algorithm-based radial basic function neural network | |
CN108595763A (en) | Die assembly design method based on model index technology | |
CN109344524B (en) | Method for optimizing distribution of reinforcing ribs of thin plate structure | |
CN108958238B (en) | Robot point-to-area path planning method based on covariant cost function | |
CN105956762A (en) | Engineering budgeting price combination method based on BIM and cloud platform | |
CN112417573A (en) | Multi-objective optimization method for shield tunneling underneath existing tunnel construction based on GA-LSSVM and NSGA-II | |
CN109284531A (en) | An a kind of two-dimentional hydrodynamics coupling process based on space topological | |
WO2020134388A1 (en) | Blade high-rigidity design method based on random isogeometric analysis | |
CN106446343B (en) | Automatic extraction method for parameterized profile of straight-line blade of radial-flow impeller | |
CN103544343A (en) | Serialized and parameterized modeling method of power chuck | |
CN113343427B (en) | Structural topology configuration prediction method based on convolutional neural network | |
Maheri | Multiobjective optimisation and integrated design of wind turbine blades using WTBM-ANSYS for high fidelity structural analysis | |
CN108073747A (en) | Aircraft structure Three Dimensional Design Model quality detecting system and method | |
CN108230452A (en) | A kind of model filling-up hole method based on textures synthesis | |
CN109977526A (en) | A method of the adjustment wing finite element model based on three-dimensional CST technology | |
CN108595631A (en) | Three-dimensional CAD model bilayer search method based on Graph Spectral Theory | |
CN107066644A (en) | A kind of special-shaped furred ceiling automatic modeling method | |
CN109388875A (en) | A kind of design implementation method of elastic element module | |
CN103294847B (en) | Water supply network model Fuzzy Identification based on waterpower adjustment | |
CN108074019A (en) | A kind of photovoltaic power generation power prediction method based on support vector machines | |
CN110322297A (en) | Medium-and-large-sized stamping die quotation prediction technique based on BP neural network | |
Tyurin | Methods of computer modeling of cost models for buildings | |
CN108830744B (en) | Dynamic verification method for external network equivalent model of designated area in power system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |