CN107696499B - The detection of 3D printing product quality and restorative procedure that threedimensional model is combined with machine vision - Google Patents
The detection of 3D printing product quality and restorative procedure that threedimensional model is combined with machine vision Download PDFInfo
- Publication number
- CN107696499B CN107696499B CN201710886339.XA CN201710886339A CN107696499B CN 107696499 B CN107696499 B CN 107696499B CN 201710886339 A CN201710886339 A CN 201710886339A CN 107696499 B CN107696499 B CN 107696499B
- Authority
- CN
- China
- Prior art keywords
- product
- point
- error
- group
- printing
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y40/00—Auxiliary operations or equipment, e.g. for material handling
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y50/00—Data acquisition or data processing for additive manufacturing
- B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Materials Engineering (AREA)
Abstract
The 3D printing product quality detection that threedimensional model is combined with machine vision is related to the fields such as intelligentized control method with restorative procedure.This method carries out post-processing primarily directed to 3D printing product, improves surface accuracy.Steps are as follows: the acquisition of point cloud data: the part obtains the corresponding point cloud data of object by the scanning to object;The quality evaluation of product: the part first has to progress point cloud data model corresponding with 3D printing object and is aligned, and provides product surface error condition;Product space initialization: the part is the position of world coordinates of the practical printed product in mechanical system in order to obtain;By world coordinate point and model coordinate point alignment: the part is that the error that will have been obtained corresponds on world coordinates;Path planning, which is realized, to be repaired: the part is selected according to the specific situation for needing to repair product surface and specifically repairs algorithm, realizes repair.The present invention is suitable for the repair of the 3D printing product of plane and curved surface.
Description
Technical field
The present invention relates to intelligentized control method, machine vision, the methods of path planning.It is scanned more particularly to 3D printing product
The point cloud data and model obtained afterwards compares;Product Quality Evaluation;It plans repair path, realizes the quality testing of 3D printing product
With reparation.
Background technique
The fast development of 3D printing technique, 3D printing product are also applied to every field, this is just to the quality of printed product
More stringent requirements are proposed.Due to the influence of moulding mechanism and material etc., 3D printing product surface inevitably have it is raised or sunken,
The precision of printed product still has gap compared to traditional machining precision.Presently, there are the later period to 3D printing product at
Reason is mostly be it is direct carry out smooth surface, such as common sand paper polishing, bead-blast, steam are smooth.But due to 3D printing product
The random error on surface is not accidentally unified difference, directly carries out unified smoothing to surface using manual formula operation,
Quantization reparation is not carried out, and the reparation situation to surface is also only on the basis of resting on qualitatively.Based on these, 3D is beaten
The detection that product carries out quality is printed, it is necessary for then carrying out quantitative repair.
When 3D printing, the material of selection is usually photosensitive resin, metal powder, thermoplastic etc..Particularly, for using
Printed material be thermoplastic fused glass pellet 3D printing technique for, due to printed product precision by printed material,
The combined influence of melting temperature, cooling velocity carries out quality of research detection to it and has more realistic meaning with repair system and answer
With value.
Summary of the invention:
The embodiment of the present invention will provide the process and method of a whole set of quality testing and reparation, according to reparation algorithm to 3D
Printed product is repaired, and the 3D printing product of high quality is obtained.Detailed process the following steps are included:
100, quality evaluation is carried out to 3D printing object.3D printing product is scanned first during this, is produced
The corresponding point cloud data of product is then soft in Geomagic quality by the point cloud of the corresponding STL model of printed product and scanning
It is aligned under part, obtains the error between model and point cloud data.
200,3D printing product space initializes.After product space initialization determines that printed product is put into mechanical system
The world coordinate point of product space.
300, world coordinate point and model coordinate point alignment.STL model and point cloud data are carried out pair in step 100
Than obtaining error, world coordinate point and model coordinate point alignment correspond to error dot in world coordinate point.
400, according to world coordinate point and error amount, the error condition of visualization display product produces flatness 3D printing
Product path planning scheme corresponding with curved surface 3D printing product selection is realized and is repaired.Repairing includes two aspects, to deficient printing
Partial increases, and the reduction to print area is crossed, two class repair path algorithms are the same, only to carry out to the reduction for crossing printing portion
Explanation.
Wherein in step 400, only to the 3D printing product of planarization and curving 3D printing product specific aim reparation.
The precision of graver straight knife fix tool is 0.1mm, and the point set for being less than fix tool precision to error is not repaired.By 3D printing
Product is divided into two classes and is handled.
For the 3D printing product of planarization, when being repaired, to avoid collision, layered shaping is carried out first, it will be in phase
It is divided into one group with the point set on separation.
For printed product itself, the position of concave-convex intersection, to avoid fix tool from colliding, since fix tool is upward
Width is 0.3mm-0.5mm, is rejected to the point set within the scope of product bumps intersection 0.5mm, not repair process.
For the continuity for guaranteeing repair, we have carried out continuous treatment to the point set of sustained height.
It is 0.1mm, institute due to repairing tool precision first by the X-coordinate of all point sets according to being ranked up from small to large
To be grouped with the interval of 0.1mm according to X-direction, obtain in the X-axis direction with multiple groupings from small to large, Mei Gefen
Point set in group comprising needing to repair.In the group divided, sort from small to large again according to Y direction.
For guarantee repair when continuity, and repair cutter precision be 0.1mm, will group between points distance with
0.1mm is compared, and will be spaced between points and is divided into one group less than or equal to 0.1mm.
When repairing to 3D printing product, mechanical system is raised into initial position in short transverse (Z-direction) first
At a distance from printing starting point difference in height, it is under normal conditions 10mm-20mm, avoids colliding in repair process.Find out group
Interior point concentrates the maximum value of error, and keeps a record.Mechanical system is moved to the starting point printed in group in X, Y direction, then
Mechanical system is declined into the distance raised at a distance from the max value of error difference in Z-direction, ensure that from error most
Height, which starts to cut down, to be repaired.During polishing is repaired and cut down, fix tool moves to the end in group from the starting point in the group divided
Point, to guarantee repair fineness, is usually declined with the step distance of 0.02mm, is followed since fix tool precision is 0.1mm
Ring carries out this process, moves to next group until error component reparation is finished.
When being looped to determine, mechanical system declines the distance of 0.02mm every time, and decline accumulated value is possible to bigger
It judges whether to move on to next group in max value of error Shi Caineng and be repaired, to avoid tiring out caused by increasing with a group number
Product error is excessive, after every group of point set is repaired, carry out the height for judge mechanical system accumulation decline and max value of error it
Between difference, both raise the distance of difference to mechanical system according to difference to compensate.
For curving 3D printing product, curved surface reparation will not relate to collision problem.In point set pretreatment, it is only necessary to
The point set for being less than reparation precision 0.1mm to error amount is rejected.
To improve remediation efficiency, curved surface repair path algorithm is to combine plane reparation with curved surface reparation to complete
, the protrusion of curved surface highest point is higher than for printed product, is repaired according to the reparation rule of above-mentioned plane, until to repairing
Until curved surface highest point;Remaining is lower than error existing for the point set of curved surface highest point and is then repaired in the following manner.
Similarly, it in order to guarantee the continuity repaired, needs to be grouped the point set of curved surface.The method and plane of grouping
It is similar, first all point sets are ranked up from small to large according to X, are grouped according still further to X-direction every 0.1mm, then
The point set Y value in group is ranked up from small to large again, is carried out after being compared according to distance between points with 0.1mm thin
Grouping.
Curved surface reparation and plane reparation difference are that mechanical system repair the curved surface path of walking.It will be above curved surface most
High point tolerance uses plane reparation, then mechanical system is raised to the distance of 10mm-20mm, avoids touching when repairing mobile
It hits.Find the sum of Z value coordinate of the error amount of point set and point maximum value, the Z coordinate of recording error value and the point in group.With this
Point is separation, is grouped again.Using the sum of the Z coordinate of error amount and the point in organizing maximum as starting point, carries out curved surface and beat
Mill is repaired.
To guarantee that when repairing be curved surface path, in repair process, according to Y direction distance between points in group with
Z-direction distance, mechanical system while mobile two axis, are declined with the step distance of 0.02mm every time, carry out circulation reparation, until
The grouping error reparation will be needed to finish, into next group of reparation.
Similarly, curved surface reparation can also encounter the accumulation falling head of mechanical system slightly larger than repairing error, using similar
Compensation way in plane reparation carries out raising mechanical system compensation.
This patent additionally provides the detection of a whole set of scanning quality and the flow system repaired, and specifically includes following mould
Block: product point cloud data acquisition, quality evaluation, visualization display error, path planning reparation.
Product point cloud data acquisition is to be scanned to obtain corresponding point cloud data to 3D printing product;Quality evaluation portion
Dividing is compared using obtained point cloud data STL model corresponding with printed product, is obtained in Geomagic quality
Take the quality of printed product;Visualization display error shows that point cloud data is corresponding with printed product by visualization interface
STL model compares rear error map;Path planning part is selected according to printed product surface plane curved surface situation
Unused path planning algorithm.
The detection of 3D printing product quality and restorative procedure that the threedimensional model of the embodiment of the present invention is combined with machine vision
It has the advantages that
1) it quantitatively analyzes the print quality of product and is quantitatively repaired, it is different from traditional post-processing, it is right
3D printing product, it is quantitative pointedly to repair product error, improve precision.
2) convenience proposes a whole set of reparation flow system;By the acquisition of product point cloud data, quality evaluation, can
Depending on changing display error, for path planning repair set into a process, it is more convenient to operate.
3) diversity proposes different recovery scenarios from curved surface to plane, can be to a variety of different 3D printing products
Carry out feasibility reparation.
Detailed description of the invention:
The flow chart of Fig. 1 product quality detection and repair system
Fig. 2 plane repair path flow chart
Fig. 3 curved surface repairs segmentation figure
Specific embodiment
Embodiments herein is described in detail below in conjunction with attached drawing, it should be noted that is do not conflicted
In the case of, point cloud data, quality evaluation and the path planning reparation of the acquisition product of the application are suitable for most of planes and song
Surface model.
The 3D printing product quality detection combined present applicant proposes a kind of threedimensional model with machine vision and reparation side
Method realizes that the quality testing to 3D printing product is evaluated, is targetedly repaired to error existing for product surface, beat 3D
The post-processing repair of print product has reached the standard of quantification.
Fig. 1 is shown according to the quality testing of the 3D printing product of embodiments possible of the application a kind of and restorative procedure
Detailed process.Two classes can be roughly divided into for the region for entirely needing to repair: to the reduction of printing portion excessively, to deficient printing portion
That divides increases, and for the two, test and evaluation methods, the algorithm of repair path of printed product are the same, we are only with right herein
It crosses for the polishing reparation of printing portion and sketches the detection of 3D printing product quality and repair process based on machine vision.Specifically
The following steps are included:
Step 100: acquisition point cloud data is scanned to 3D printing product
Step 200: the point cloud data of scanning STL model corresponding with product is aligned
Step 300: forming the quality evaluation result to product
Step 400: visualization display product and point cloud data comparing result figure on interface
Step 500: judging 3D printing product surface situation, select plane or curved surface repair path algorithm, realize and repair.
It may be noted that in step 100, in order to obtain the complete point cloud data of printed product, after sticking sign point, carry out
Multiple-Scan, to guarantee the splicing between scanning twice, the angle that turntable rotates every time is typically chosen in 10 degree of -15 degree, obtains
Take the complete point cloud data of printed product.
Object point cloud data scanning finishes, in step 200, it should be pointed out that for scanning point set beyond at software
Manage the carry out uniform sampling processing of range.
Optionally, the step 100 includes following sub-steps:
Sub-step 110, in turntable or object itself sticking sign point.
Sub-step 120, opening scanner are scanned product, every run-down object, 10 degree of control turntable rotation-
15 degree, the point cloud data of automatic Mosaic twice sweep in 3D scan software.
Further, include following sub-step in step 200:
Sub-step 210 handles point cloud data, i.e., to deviate in the obtained point cloud data of scanning the point set of object into
Row is rejected.
Sub-step 220, point cloud data are aligned with 3D printing model, after point cloud data is pre-processed.?
In Geomagic quality software, 3D printing model (STL model) is selected as reference model, point cloud data is set as test mould
Type, the global error to guarantee the two alignment is minimum, selects best fit alignment.
Further, include following sub-step in step 300:
Sub-step 310 obtains Product Quality Evaluation result in Geomagic quality.
Sub-step 320 saves the coordinate points after STL model is aligned with point cloud data and error data value.
The step 400 includes:
The Error Graph after comparing between 3D printing model and point cloud data is intuitively shown on the visualization interface of foundation,
Facilitate error of observation distribution.
The step 500 includes:
Sub-step 510 judges the product surface situation to be repaired, and according to being plane or curved surface, selects
Corresponding repair path algorithm.
Sub-step 520,
As shown in Figure 2.Product surface is subjected to layered shaping, that is to say and the point set on identical separation is divided into one
In a big group, then point set sorted from small to large according to X value, to be grouped every 0.1mm, then will in group point according to Y value from it is small to
Big sequence, then carries out continuity subdivision group with 0.1mm.Maximum error dot in group is found out, group is moved to by the first point in group
Interior last point, what is moved in circles is successively repaired.In repair process, the current point set of reparation and the mistake of reparation are constantly shown
Difference.It repairs and finishes in group, according to the difference of decline Cumulative Distance and error, adjust mechanical system.
Sub-step 530,
Reparation for curved surface class printed product, as shown in figure 3, curve a is the boundary line of the object actually printed, it is bent
Line b is the boundary during model is corresponding, and the part on curve b and under curve a is polish the region of reparation.Straight line
C is the corresponding horizontal line position in highest point of curved surface.The reparation of entire curved surface is divided into two parts, i.e., on straight line c
And the part under curve a, it is denoted as M;Part under straight line c and on curve b, is denoted as N;This two parts is using different
Product recovery scenario.The method that the part M uses straight line repair path carries out polishing reparation.For N section, first to
Product coordinate points obtained in Geomagic quality are handled with error dot, i.e., first by point set according to X value from small to large
Sequence is clicked through with being grouped every 0.1mm to the Z value error corresponding to this point for organizing interior all point sets and with the Z value maximum in group
Row compares.If being less than the point of Z value maximum value, retains original point and error is constant;More than or equal to Z value maximum point, then the point
Coordinate remains unchanged, but corresponding error amount becomes the difference of Z value maximum point and the point Z value in group.To all point sets into
After row arranges, algorithm is repaired according to above-mentioned curved surface, realizes curved surface reparation.
The detection of 3D printing product quality and restorative procedure that the threedimensional model of the embodiment of the present invention is combined with machine vision
It has the advantages that
1) it quantitatively analyzes the print quality of product and is quantitatively repaired, it is different from traditional post-processing, it is right
3D printing product, it is quantitative pointedly to repair product error, improve precision.
2) convenience proposes a whole set of reparation flow system;By the acquisition of product point cloud data, quality evaluation, can
Depending on changing display error, for path planning repair set into a process, it is more convenient to operate.
3) diversity proposes different recovery scenarios from curved surface to plane, can be to a variety of different 3D printing products
Carry out feasibility reparation.
Claims (5)
1. the detection of 3D printing product quality and restorative procedure that threedimensional model is combined with machine vision, which is characterized in that including
Following steps:
100, quality evaluation is carried out to 3D printing product, 3D printing product is scanned first, obtains corresponding cloud of product
The corresponding STL model of printed product is aligned to obtain quality evaluation and model and point cloud data by data with the point cloud of scanning
Between error;
200, product space initializes, and product space initialization determines that printed product is put into the corresponding world of mechanical system and is sat
Under mark;
300, world coordinates is aligned with model coordinate, the error between model and point cloud data is corresponded under world coordinates;
400, the error according to obtained world coordinates and corresponding error, between visualization display product model and point cloud data
Distribution, and corresponding path planning is selected to different 3D printing products, it realizes and repairs, specific as follows:
Two classes: plane class repair path algorithm, curved surface class repair path algorithm are divided into for the reparation of 3D printing product;
For the 3D printing product of plane class, first progress layered shaping, the point set on identical separation is divided into one group;
For printed product itself, the point set within the scope of product bumps intersection 0.5mm is rejected, not repair process;
For the continuity for guaranteeing repair, continuous treatment is carried out to the point set of sustained height: first by the X of all point sets
Coordinate is 0.1mm due to repairing tool precision, so with the interval of 0.1mm according to X-direction according to being ranked up from small to large
It is grouped, obtains in the X-axis direction with multiple groupings from small to large, the interior point set comprising needing to repair of each grouping;?
In the group divided, sort from small to large again according to Y direction;
Continuity when being repaired for guarantee, and the precision for repairing cutter is 0.1mm, it will group interior distance and 0.1mm between points
It is compared, will be spaced between points and be divided into one group less than or equal to 0.1mm;
When repairing to 3D printing product, mechanical system is raised into certain distance in short transverse, that is, Z-direction first, it should be away from
From for initial position and printing starting point difference in height;It finds out point in group and concentrates the maximum value of error, and keep a record;Mechanical system is existed
X, the starting point printed in group, then distance and the mistake that mechanical system has been raised in Z-direction decline are moved in Y direction
The distance of poor maximum value difference ensure that cut down since error highest and repair;During polishing is repaired and is cut down, fix tool
The terminal in group is moved to from the starting point in the group divided, since fix tool precision is 0.1mm, with the step distance of 0.02mm
Decline, circulation carry out this process, move to next group until error component reparation is finished;
When being looped to determine, after every group of point set is repaired, the height and mistake that judge mechanical system accumulation decline are carried out
Difference between poor maximum value raises the distance of difference to compensate;
For the 3D printing product of curved surface class, in point set pretreatment, it is only necessary to be less than the point for repairing precision 0.1mm to error amount
Collection is rejected;
Curved surface repair path algorithm is to combine plane reparation with curved surface reparation to complete, and is higher than song for printed product
The protrusion of face highest point is repaired according to the reparation rule of above-mentioned plane, until the error repaired until until highest point;
Remaining is lower than error existing for the point set of curved surface highest point and is then repaired in the following manner;
First all point sets are ranked up from small to large according to X, are grouped according still further to X-direction every 0.1mm, then again
Point set Y value in group is ranked up from small to large, is finely divided after being compared according to distance between points with 0.1mm
Group;
Curved surface highest point tolerance be will be above using plane reparation, then mechanical system is raised to the distance of 10mm-20mm, avoided
Collision when repairing mobile;Find the sum of Z value coordinate maximum value of the error amount of point set and the point in group, recording error value be somebody's turn to do
The Z coordinate of point is grouped again using this point as separation;It is to organize interior error amount with the sum of the Z coordinate of point maximum
Point carries out curved surface polishing and repairs;
In repair process, according to the Y direction distance and Z-direction distance in group between points, the same time shift of mechanical system
Dynamic Y-axis and Z axis, are declined with the step distance of 0.02mm every time, carry out circulation reparation, until the grouping error will be needed to have repaired
Finish, into next group of reparation;
After every group of point set is repaired, judge the difference between the height and max value of error of mechanical system accumulation decline
Value, raises the distance of difference to compensate.
2. the method according to claim 1, wherein step 100 includes:
Before product carries out quality evaluation, needs to carry out the scanning of 3D printing product and obtain point cloud data, which is to utilize machine
The automatic scanning of tool system;To 3D printing product carry out point cloud data acquisition when, control mechanical system rotate every time 10 degree-
15 degree, realize that point cloud data obtains.
3. the method according to claim 1, wherein step 200 includes:
Before product is repaired, it is thus necessary to determine that specific location of the product in mechanical system that is to say that product space is initial
Change;Product space initialization is: calibration binocular camera first, then utilizes under binocular camera between pixel coordinate and world coordinates
Relationship obtain world coordinates.
4. the method according to claim 1, wherein step 300 includes:
According to four-tuple method, by model coordinate systems and printed product coordinate system be aligned, the world coordinates of product can be obtained
It puts and corresponding error.
5. the method according to claim 1, wherein step 400 includes:
Visually show the error comparison diagram between 3D printing product and model, error map is indicated according to different colors
Error size is different;Entire interface visualization display error comparison diagram, intuitively holds the error condition of product;According to 3D
Printed product surface is that plane or curved surface carry out selecting corresponding repair mode reparation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710886339.XA CN107696499B (en) | 2017-09-27 | 2017-09-27 | The detection of 3D printing product quality and restorative procedure that threedimensional model is combined with machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710886339.XA CN107696499B (en) | 2017-09-27 | 2017-09-27 | The detection of 3D printing product quality and restorative procedure that threedimensional model is combined with machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107696499A CN107696499A (en) | 2018-02-16 |
CN107696499B true CN107696499B (en) | 2019-07-16 |
Family
ID=61175964
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710886339.XA Active CN107696499B (en) | 2017-09-27 | 2017-09-27 | The detection of 3D printing product quality and restorative procedure that threedimensional model is combined with machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107696499B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108422670B (en) * | 2018-03-09 | 2019-12-24 | 西安交通大学 | Path planning method for non-continuous grid division of three-dimensional point cloud surface |
CN110961633A (en) * | 2018-09-28 | 2020-04-07 | 安世亚太科技股份有限公司 | Three-dimensional printing method and device |
CN109532021B (en) * | 2018-10-10 | 2020-08-25 | 浙江大学 | 3D printing fused deposition defect layer-by-layer detection method based on structural light property abnormal points |
CN110470213A (en) * | 2018-12-19 | 2019-11-19 | 中联认证中心(北京)有限公司 | A kind of online assessment device of 3D printing drip molding precision |
CN111435400A (en) * | 2018-12-26 | 2020-07-21 | 沈阳新松机器人自动化股份有限公司 | Part repairing method and device and 3D printer |
CN109910294A (en) * | 2019-03-28 | 2019-06-21 | 哈尔滨理工大学 | A kind of 3D printing formed precision detection method based on machine vision |
WO2020238133A1 (en) * | 2019-05-24 | 2020-12-03 | 杭州捷诺飞生物科技股份有限公司 | 3d printer and 3d printing method |
CN110293685A (en) * | 2019-07-31 | 2019-10-01 | 江苏安全技术职业学院 | A kind of daily necessities 3D printing speed data processing method |
CN111391327B (en) * | 2020-03-11 | 2022-09-16 | 先临三维科技股份有限公司 | Printing error determination method, printing error determination device, electronic equipment and storage medium |
CN111674048B (en) * | 2020-05-13 | 2022-05-06 | 广东工业大学 | 3D printer broken wire alarm device and alarm method based on machine vision |
CN112917921A (en) * | 2021-01-26 | 2021-06-08 | 贵州航天天马机电科技有限公司 | 3D prints photosensitive resin part defect repair system |
CN113962188B (en) * | 2021-11-01 | 2024-04-02 | 西安交通大学 | Path planning method for conformal printing of multi-scale circuit on free-form surface |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9554910B2 (en) * | 2011-10-27 | 2017-01-31 | Biomet Manufacturing, Llc | Patient-specific glenoid guide and implants |
US9421716B2 (en) * | 2012-08-08 | 2016-08-23 | Makerbot Industries, Llc | Photo booth for three-dimensional images |
CN103341929B (en) * | 2013-06-27 | 2015-07-22 | 信义汽车玻璃(深圳)有限公司 | Method for manufacturing injection product model |
US9857784B2 (en) * | 2014-11-12 | 2018-01-02 | International Business Machines Corporation | Method for repairing with 3D printing |
CN104908327B (en) * | 2015-07-07 | 2017-06-27 | 杭州先临三维科技股份有限公司 | A kind of 3D printing product |
CN105172152B (en) * | 2015-10-28 | 2017-06-20 | 深圳晗竣雅科技有限公司 | 3D forming methods based on profile injection moulding |
CN106182643B (en) * | 2016-08-11 | 2018-07-17 | 富泰克精密注塑(苏州)有限公司 | A kind of spur gear injection mold gear compensating approach method |
CN106915088A (en) * | 2017-02-10 | 2017-07-04 | 河南理工大学 | A kind of technique processing method based on the colouring of 3D printing product surface |
-
2017
- 2017-09-27 CN CN201710886339.XA patent/CN107696499B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107696499A (en) | 2018-02-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107696499B (en) | The detection of 3D printing product quality and restorative procedure that threedimensional model is combined with machine vision | |
CN112326673B (en) | Injection molding surface defect detection method and device based on machine vision | |
CN108760766B (en) | Image splicing method for detecting surface micro-defects of large-caliber optical crystal | |
CN103175469B (en) | Enhanced edge focusing instrument and the focus method using the instrument | |
CN114041168A (en) | Automated 360-degree dense point object inspection | |
JP3596753B2 (en) | Apparatus and method for generating part program for image measuring device | |
CN101526484B (en) | Bearing defect detecting technique based on embedded-type machine vision | |
US9182583B2 (en) | Structured illumination microscopy optical arrangement including projection artifact supression element | |
CN108496124A (en) | The automatic detection and robot assisted processing of surface defect | |
CN114571326B (en) | Method, device and system for grinding deformed curved surface based on computer vision | |
CN102455171B (en) | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof | |
CN102135417A (en) | Full-automatic three-dimension characteristic extracting method | |
JP5395470B2 (en) | Shape recognition device | |
Milroy et al. | Automated laser scanning based on orthogonal cross sections | |
CN110555385B (en) | Welding seam characteristic point solving method based on variable step length curvature filtering | |
CN109532245A (en) | Laser marking partition bonding device and method thereof | |
CN101425178B (en) | Method for repairing edge contour image of columnar injection deposition blank | |
CN116958178A (en) | Autonomous planning method and system for weld polishing based on laser vision | |
CN110044296A (en) | The automatic tracking method and measuring machine of 3D shape | |
Zou et al. | Laser-based precise measurement of tailor welded blanks: a case study | |
JP5218957B2 (en) | Shape measuring device, shape measuring method, and shape measuring program | |
CN115453839A (en) | Single light source horizontal calibration method for DLP3D printing | |
CN105654499B (en) | A kind of image evaluation method of laser surface modification | |
CN103871048A (en) | Straight line primitive-based geometric hash method real-time positioning and matching method | |
KR100514115B1 (en) | Roughing information measuring method for shoes |
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 |