CN106182765A - 3D printer model scale error Forecasting Methodology based on support vector machine - Google Patents
3D printer model scale error Forecasting Methodology based on support vector machine Download PDFInfo
- Publication number
- CN106182765A CN106182765A CN201610523643.3A CN201610523643A CN106182765A CN 106182765 A CN106182765 A CN 106182765A CN 201610523643 A CN201610523643 A CN 201610523643A CN 106182765 A CN106182765 A CN 106182765A
- Authority
- CN
- China
- Prior art keywords
- model
- scale error
- printer
- print parameters
- vector machine
- 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
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
- 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 invention provides a kind of 3D printer model scale error Forecasting Methodology based on support vector machine, step includes: 1, threedimensional model design；2, set different print parameters and print；3, model key point, Most Vital Edge position determine；4, by obtaining scale error with master pattern Least squares matching；5, the model parameter obtained and corresponding print parameters are formed data base, data base is randomly divided into two classes: training group and prediction group；6, use training group that SVM model is trained, and use prediction group that the prediction accuracy of trained SVM model is verified, filter out satisfactory SVM model；7, using new print parameters as the scale error of input prediction model.The present invention can predict the scale error scope of this parameter series drag by print parameters, is conducive to improving printing effect, reduces unnecessary spillage of material.
Description
Technical field
The present invention relates to aided manufacturing techniques field, in particular it relates to one is based on support vector machine (Support
Vector Machine, SVM) 3D printer model scale error Forecasting Methodology.
Background technology
The purpose of 3D printer model size prediction is to be divided into printer model whether meeting the two big classes that scale error requires,
Auxiliary printing person before printing, set print parameters time consider print result, improve print quality, reduce consumptive material waste and the time
Loss.So far, 3D printer product emerges in an endless stream on the market, material for training the most continually, but 3D print printing knot
Fruit controls still to need the experience of printer operator, uses machine learning prediction algorithm based on support vector machine effectively to reduce
Requirement to printer operator, has good meaning for strengthening the economic and practical of 3D printer itself.
SVM is a kind of foundation linear classifier on the basis of Statistical Learning Theory, and its algorithm is a convex optimization problem,
Its locally optimal solution is globally optimal solution.Its feature is according to structural risk minimization, in limited sample information
Seek the most this between the complexity and extensive learning capacity of model, overlearning can be prevented effectively from or be absorbed in local optimum
Etc. shortcoming.As a example by 2-D data, two class data point distribution are in a two dimensional surface, and its ultimate principle is to be found by training
Can the classification county of two class data points in sunder.Classification line although it is so has a lot, but has and only demarcation line meets
To the classification line that two class data point distances are the shortest.For multidimensional data, data point distribution is in hyperspace, and SVM divides
What class device obtained is optimal separating hyper plane.
Through retrieval, Publication No. CN105643944A, the Chinese invention patent application of application number 201610200113.5, it is somebody's turn to do
Disclosure of the invention a kind of 3D printer stable control method and control system, the 3D printer stable control method of this invention and control
System processed, by the model of the optimum thresholding error amount of structure, chooses optimum in real time by the decaying integral equilibrium point recommending controlling value
Threshold error value, the recommendation controlling value that can preferably solve 3D printer forming process occurs along with the change of threshold value all
Weighing apparatus and the phenomenon of lack of balance decay, improve the stability of printer.But this patent lays particular emphasis on by solving printer apparatus
The stability problem of hardware components improves print quality, it is impossible to consider the impact of each factor in whole print procedure.
Summary of the invention
For defect of the prior art, it is an object of the invention to provide a kind of 3D printer model based on support vector machine
Scale error Forecasting Methodology, described method uses model construction of SVM to the relation of print parameters with moulded dimension error, right
Same model scale error situation under different parameters is arranged is predicted, be given this parameter arrange middle moulded dimension error surpass
The probability crossing threshold value predicts the outcome, and for printing person's reference, thus realizes optimizing print quality.
For realizing object above, the present invention provides a kind of 3D printer model scale error prediction side based on support vector machine
Method, described method comprises the steps:
The first step, threedimensional model design, and described threedimensional model is the threedimensional model of finished parts, is used for testing 3D printer and beats
Print level；
Second step, the threedimensional model first step obtained import 3D printer, and set different beating on 3D printer
Print parameter prints；
3rd step, threedimensional model key point, Most Vital Edge position determine and record cloud data；
The main geometric properties of the threedimensional model first step obtained carries out conclusion and determines, including the circular hole center of circle, circular arc arc
Degree, each length of side and intersection point thereof；The main geometric properties determined measures acquisition cloud data under measuring instrument；
4th step, by with master pattern Least squares matching obtain scale error；
The threedimensional model that 3rd step gained cloud data and the first step obtain is carried out Least squares matching, it is thus achieved that 3D prints
The scale error of machine printout part；
The corresponding print parameters shape that 5th step, the finished parts scale error the 4th step obtained and second step obtain
Become data base, and data base is divided into two classes by finished parts random packet: training group and prediction group；
SVM model is trained, and uses prediction group to trained SVM model by the 6th step, employing training group
Prediction accuracy is verified, filters out the satisfactory i.e. forecast model of SVM model；
7th step, using new print parameters as the scale error of input prediction model.
Preferably, in the first step, the geometric properties of described threedimensional model comprises the point, line, surface of common model, hole, and
It is easy to use optical measuring instrument or three-dimensional probe measurement.
Preferably, in the 4th step, described by obtaining scale error with master pattern Least squares matching, refer to: will
The cloud data that 3rd step obtains matches with the threedimensional model of the finished parts designed by the first step, to obtain minimum mean-square error
Value.
Preferably, in the 5th step, described random packet is for be repeatedly grouped, and packet is according to depending on data set sum.
Preferably, in the 5th step, described data base is a Multidimensional numerical, and it is made up of two parts: print parameters and
Label value.
Preferably, described forecast model exists independent of 3D printer as software system, or as algoritic module
Being built into 3D print parameters and arrange in system, the printing effect feedback after arranging as parameter, auxiliary direction printing person sets ginseng
Number.
Compared with prior art, the present invention has a following beneficial effect:
The scale error prediction of the present invention is built upon on whole print procedure, is to consider in print procedure each
The factor of printout part scale error may be affected, set up supporting vector machine model on this basis, and print based on history
Scale error prediction on data.
The method of the invention can predict, by print parameters, the finished product that under this parameter series, three dimensional model printing goes out
The scale error scope of part, is conducive to improving printing effect, reduces unnecessary spillage of material.
Accompanying drawing explanation
By the detailed description non-limiting example made with reference to the following drawings of reading, the further feature of the present invention,
Purpose and advantage will become more apparent upon:
Fig. 1 is the flow chart of one embodiment of the invention；
Fig. 2 is the three-dimensional model structure schematic diagram of one embodiment of the invention.
Detailed description of the invention
Below in conjunction with specific embodiment, the present invention is described in detail.Following example will assist in the technology of this area
Personnel are further appreciated by the present invention, but limit the present invention the most in any form.It should be pointed out that, the ordinary skill to this area
For personnel, without departing from the inventive concept of the premise, it is also possible to make some deformation and improvement.These broadly fall into the present invention
Protection domain.
As it is shown in figure 1, a kind of 3D printer model scale error Forecasting Methodology based on support vector machine, described method includes
Following steps:
Step 1, design threedimensional model
Described threedimensional model is the threedimensional model of finished parts, is used for testing 3D printer printing level；
Threedimensional model needs the geometric properties possessing usual workpiece, includes but not limited to a little: line (straight line, curve, arc), face
(curved surface, plane), hole (through hole, stepped hole) etc., as shown in Figure 2.
Step 2, threedimensional model step 1 obtained import 3D printer, and set different printings on 3D printer
Parameter prints；Described print parameters is the print parameters of threedimensional model, including: printing thickness, model is in print procedure
Angles, the parameter such as bearing height supported in model print procedure, support gradient, supporting construction and the contact surface of model
Long-pending, the density of supporting construction, ambient parameter such as temperature, humidity, material properties code name.
Under normal circumstances, as a example by SLA printer, relate to need arrange print parameters more than ten kinds, printing person
Can determine that crucial parameter is arranged by self judging, including but be not limited only to: print thickness, model angles,
The contact point size of support structure, structural point etc., environmental condition such as temperature, humidity etc., printed material such as model 1, model 2 etc..
Step 3, threedimensional model key point, Most Vital Edge position determine and record cloud data；
The main geometric properties of threedimensional model step 1 obtained carries out conclusion and determines, including the circular hole center of circle, circular arc arc
Degree, each length of side and intersection point thereof；The main geometric properties determined measures acquisition cloud data under measuring instrument；
Described three-dimensional key point, including: the starting point of line and terminal, the center of circle of circular arc, hole and the geometric properties of prominent post,
And the profile information of model, in specifically taking a little, radiographic measurement obtains cloud data by image procossing, and contact type measurement passes through
Set unit are cm2Or the quantity that takes in unit length cm obtains cloud data, general setting unit are cm2By matrix
Mode takes a little five or unit length cm and equidistantly takes a little ten.
Described Most Vital Edge is the limit playing a decisive role threedimensional model External Shape and function, including forming three-dimensional mould
The limit of type contours profiles such as straight line, circular arc, composition threedimensional model close keyhole, the profile circular arc formed on a certain perspective plane of post or
Straight line, curved side.
For key point, Most Vital Edge, contact-type image instrument is used to measure the cloud data that can obtain key point, Most Vital Edge,
Use contact type measurement such as probe measurement can obtain the cloud data of key point, Most Vital Edge；Wherein contact type measurement it needs to be determined that
The measure dot number amount of unit are or unit length.
Step 4, by with master pattern carry out Least squares matching obtain scale error；
The actual point, line, surface of step 3 gained cloud data Yu the threedimensional model of step 1 are carried out Least squares matching, obtains
Obtain the scale error result of 3D printer printout part.
The corresponding print parameters that step 5, finished parts scale error step 4 obtained and step 2 obtain is formed
Data base, and data base is divided into two classes by finished parts random packet: training group and prediction group；
Described data base is a Multidimensional numerical, and it is made up of two parts: print parameters and label value.Described label
What value obtained after being measured coupling by each group of print parameters correspondence finished parts scale error converts, and sets certain size
Error threshold, the scale error value that will be greater than this threshold value is set as-1, is set as+1 less than or equal to the scale error value of this threshold value,
Assume there be n print parameters, and have printed m model, then this data set is the matrix of m × (n+1).
Random packet will repeatedly random packet, packet, depending on data set sum situation, is typically chosen three groups, five groups etc.；
And the error result in step 4 is set as+1 (scale error is less than this threshold value) by certain threshold value ,-1 (scale error is more than
Equal to this threshold value).
Step 6, use training group that SVM model is trained, and use pre-to trained SVM model of prediction group
Survey accuracy to carry out verifying, filtering out the satisfactory i.e. forecast model of SVM model；
Different random packet results trains different SVM models, uses the test group of correspondence to survey SVM model
Examination, selects the SVM model that predictablity rate is high, and general accuracy rate is advisable greater than, equal to 85%.
Step 7, using new print parameters as the scale error of input prediction model；
The model of prediction accuracy high in step 6 is defined as forecast model, and the chi to new print parameters drag
Very little error is predicted, it is determined whether exceed the certain size error (size requiring situation to arrange according to actual end product quality
Error threshold) limit.
Said method of the present invention, analyzes and finished parts quality may rise in print procedure the factor of influence (include
Ambient parameter, model parameter and device parameter: the setup parameter before printer printing), it is proposed that consider whole printed
Journey also uses the method for mathematical statistics to establish the forecast model of factor of influence and finished parts scale error, can be as in equipment
Put software, it is possible to as peripheral hardware program predict in advance certain print parameters arrange under finished parts scale error situation, to printing
Quality carries out anticipation based on historical experience, improves the success rate of printout part.
The present invention can predict the scale error scope of this parameter series drag by print parameters, is conducive to improving
Printing effect, reduces unnecessary spillage of material.
Above the specific embodiment of the present invention is described.It is to be appreciated that the invention is not limited in above-mentioned
Particular implementation, those skilled in the art can make various deformation or amendment within the scope of the claims, this not shadow
Ring the flesh and blood of the present invention.
Claims (8)
1. a 3D printer model scale error Forecasting Methodology based on support vector machine, it is characterised in that described method includes
Following steps:
The first step, threedimensional model design, and described threedimensional model is the threedimensional model of finished parts, is used for testing 3D printer stamping ink
Flat；
Second step, the threedimensional model first step obtained import 3D printer, and set different printing ginsengs on 3D printer
Number prints；
3rd step, threedimensional model key point, Most Vital Edge position determine and record cloud data；
The main geometric properties of the threedimensional model first step obtained carries out conclusion and determines, including the circular hole center of circle, circular arc radian, each
The length of side and intersection point thereof；The main geometric properties determined measures acquisition cloud data under measuring instrument；
4th step, by with master pattern Least squares matching obtain scale error；
The threedimensional model that 3rd step gained cloud data and the first step obtain is carried out Least squares matching, it is thus achieved that 3D printer is beaten
The scale error of print finished parts；
The corresponding print parameters that 5th step, the finished parts scale error the 4th step obtained and second step obtain forms number
According to storehouse, and data base is divided into two classes by finished parts random packet: training group and prediction group；
SVM model is trained, and uses the prediction group prediction to trained SVM model by the 6th step, employing training group
Accuracy is verified, filters out the satisfactory i.e. forecast model of SVM model；
7th step, using new print parameters as the scale error of input prediction model.
A kind of 3D printer model scale error Forecasting Methodology based on support vector machine the most according to claim 1, it is special
Levying and be, in the first step, the geometric properties of described threedimensional model comprises the point, line, surface of common model, hole, and is easy to use
Optical measuring instrument or three-dimensional probe measurement.
A kind of 3D printer model scale error Forecasting Methodology based on support vector machine the most according to claim 1, it is special
Levying and be, in second step, described print parameters is the print parameters of threedimensional model, including: printing thickness, model is printed
Angles in journey, the parameter such as bearing height supported in model print procedure, support gradient, supporting construction and model
Contact area, the density of supporting construction, ambient parameter such as temperature, humidity, material properties code name.
A kind of 3D printer model scale error Forecasting Methodology based on support vector machine the most according to claim 1, it is special
Levying and be, in the 3rd step, described three-dimensional key point, including: the starting point of line and terminal, the center of circle of circular arc, hole and prominent post
Geometric properties, and the profile information of model, in specifically taking a little, radiographic measurement obtains cloud data, contact by image procossing
Measure by setting unit are cm2Or the quantity that takes in unit length cm obtains cloud data, typically set unit are
cm2Take a little five or unit length cm by matrix-style and equidistantly take a little ten；
Described Most Vital Edge, is the limit playing a decisive role threedimensional model External Shape and function, including composition threedimensional model
The limit of contours profiles, composition threedimensional model closes keyhole, the profile circular arc formed on a certain perspective plane of post or straight line, curved side.
A kind of 3D printer model scale error Forecasting Methodology based on support vector machine the most according to claim 1, it is special
Levying and be, in the 5th step, described random packet is for be repeatedly grouped, and packet is according to depending on data set sum.
6. according to a kind of based on support vector machine the 3D printer model scale error prediction side described in any one of claim 1-5
Method, it is characterised in that in the 5th step, described data base is a Multidimensional numerical, and it is made up of two parts: print parameters and mark
Label value.
A kind of 3D printer model scale error Forecasting Methodology based on support vector machine the most according to claim 6, it is special
Levy and be, what described label value obtained after being measured coupling by each group of print parameters correspondence finished parts scale error conversion and
Coming, set a scale error threshold value, the scale error value that will be greater than this threshold value is set as-1, misses less than or equal to the size of this threshold value
Difference is set as+1, it is assumed that has n print parameters, and have printed m model, then this data set is the matrix of m × (n+1).
8. according to a kind of based on support vector machine the 3D printer model scale error prediction side described in any one of claim 1-5
Method, it is characterised in that described forecast model exists independent of 3D printer as software system, or as in algoritic module
Put 3D print parameters and arrange in system, the printing effect feedback after arranging as parameter, auxiliary direction printing person's setup parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610523643.3A CN106182765B (en) | 2016-07-05 | 2016-07-05 | 3D printing model scale error prediction technique based on support vector machines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610523643.3A CN106182765B (en) | 2016-07-05 | 2016-07-05 | 3D printing model scale error prediction technique based on support vector machines |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106182765A true CN106182765A (en) | 2016-12-07 |
| CN106182765B CN106182765B (en) | 2019-05-24 |
Family
ID=57465654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610523643.3A Active CN106182765B (en) | 2016-07-05 | 2016-07-05 | 3D printing model scale error prediction technique based on support vector machines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106182765B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107672180A (en) * | 2017-09-06 | 2018-02-09 | 哈尔滨理工大学 | A kind of 3D printing accuracy checking method based on reverse Engineering Technology |
| CN108422670A (en) * | 2018-03-09 | 2018-08-21 | 西安交通大学 | A kind of paths planning method in discontinuous grid division three-dimensional point cloud face |
| CN109532021A (en) * | 2018-10-10 | 2019-03-29 | 浙江大学 | The molten product layer-by-layer detection method of defect of 3D printing based on the actinic abnormal point of structure |
| CN109773186A (en) * | 2019-01-30 | 2019-05-21 | 湖南华曙高科技有限责任公司 | For manufacturing the increasing material manufacturing method and its equipment, readable storage medium storing program for executing of three-dimension object |
| CN109814817A (en) * | 2019-01-29 | 2019-05-28 | 福建省纳金网信息技术有限公司 | A kind of 3D printing training data base construction method based on artificial intelligence technology |
| JP2020059494A (en) * | 2018-10-04 | 2020-04-16 | ザ・ボーイング・カンパニーＴｈｅ Ｂｏｅｉｎｇ Ｃｏｍｐａｎｙ | Methods of synchronizing manufacture of shimless assembly |
| CN111113903A (en) * | 2020-02-27 | 2020-05-08 | 杭州电子科技大学 | Automatic calibration method for 3D printing micro-nano device based on artificial intelligence |
| CN111941849A (en) * | 2020-06-28 | 2020-11-17 | 西安理工大学 | Size error compensation method for 3D printing cylindrical part |
| CN112004658A (en) * | 2018-04-26 | 2020-11-27 | 惠普发展公司，有限责任合伙企业 | Print production quality prediction |
| CN112097673A (en) * | 2019-06-18 | 2020-12-18 | 上汽通用汽车有限公司 | Virtual matching method and system for vehicle body parts |
| CN113059810A (en) * | 2021-05-19 | 2021-07-02 | 上海理工大学 | Triaxial 3D printer spatial error detection method based on test specimen |
| CN113536464A (en) * | 2021-07-21 | 2021-10-22 | 浙江吉利控股集团有限公司 | Dimension control method and dimension control system based on artificial intelligence |
| CN114274506A (en) * | 2021-02-19 | 2022-04-05 | 北京恒尚科技有限公司 | Method for 3D printing of spectacle frame and spectacle frame prepared by method |
| CN114425856A (en) * | 2022-01-19 | 2022-05-03 | 无锡学院 | Irregular target scanning and printing method based on three-dimensional camera |
| CN114929457A (en) * | 2020-01-16 | 2022-08-19 | 惠普发展公司，有限责任合伙企业 | Spatial arrangement of objects for additive manufacturing |
| CN115139531A (en) * | 2022-07-04 | 2022-10-04 | 深圳胜马优创科技有限公司 | 3D printing support structure construction method, device, equipment and storage medium |
| CN115534304A (en) * | 2022-09-29 | 2022-12-30 | 灰觋有限公司 | FDM printing device and automatic detection method for quality of printed product |
| CN117962314A (en) * | 2024-03-18 | 2024-05-03 | 江阴勰力机械科技有限公司 | Three-dimensional modeling method and system for 3D printer based on digital twin |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06126842A (en) * | 1992-10-16 | 1994-05-10 | Matsushita Electric Ind Co Ltd | Condition-establishing system in molding of optical molding model |
| JPH08156108A (en) * | 1994-12-07 | 1996-06-18 | Matsushita Electric Ind Co Ltd | Variable laminating pitch-shaping method |
| CN104400998A (en) * | 2014-05-31 | 2015-03-11 | 福州大学 | 3D printing detection method based on infrared spectroscopic analysis |
| CN105619818A (en) * | 2015-12-31 | 2016-06-01 | 浙江大学 | Fused deposition modeling 3D printing monitoring system based on acoustic emission |
-
2016
- 2016-07-05 CN CN201610523643.3A patent/CN106182765B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06126842A (en) * | 1992-10-16 | 1994-05-10 | Matsushita Electric Ind Co Ltd | Condition-establishing system in molding of optical molding model |
| JPH08156108A (en) * | 1994-12-07 | 1996-06-18 | Matsushita Electric Ind Co Ltd | Variable laminating pitch-shaping method |
| CN104400998A (en) * | 2014-05-31 | 2015-03-11 | 福州大学 | 3D printing detection method based on infrared spectroscopic analysis |
| CN105619818A (en) * | 2015-12-31 | 2016-06-01 | 浙江大学 | Fused deposition modeling 3D printing monitoring system based on acoustic emission |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107672180B (en) * | 2017-09-06 | 2019-10-01 | 哈尔滨理工大学 | A kind of 3D printing accuracy checking method based on reverse Engineering Technology |
| CN107672180A (en) * | 2017-09-06 | 2018-02-09 | 哈尔滨理工大学 | A kind of 3D printing accuracy checking method based on reverse Engineering Technology |
| CN108422670A (en) * | 2018-03-09 | 2018-08-21 | 西安交通大学 | A kind of paths planning method in discontinuous grid division three-dimensional point cloud face |
| 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 |
| CN112004658A (en) * | 2018-04-26 | 2020-11-27 | 惠普发展公司，有限责任合伙企业 | Print production quality prediction |
| US11376793B2 (en) | 2018-04-26 | 2022-07-05 | Hewlett-Packard Development Company, L.P. | Printing production quality prediction |
| JP7508209B2 (en) | 2018-10-04 | 2024-07-01 | ザ・ボーイング・カンパニー | How to synchronize the manufacture of shimless assemblies. |
| JP2020059494A (en) * | 2018-10-04 | 2020-04-16 | ザ・ボーイング・カンパニーＴｈｅ Ｂｏｅｉｎｇ Ｃｏｍｐａｎｙ | Methods of synchronizing manufacture of shimless assembly |
| CN109532021A (en) * | 2018-10-10 | 2019-03-29 | 浙江大学 | The molten product layer-by-layer detection method of defect of 3D printing based on the actinic abnormal point of structure |
| CN109814817A (en) * | 2019-01-29 | 2019-05-28 | 福建省纳金网信息技术有限公司 | A kind of 3D printing training data base construction method based on artificial intelligence technology |
| CN109773186B (en) * | 2019-01-30 | 2021-07-02 | 湖南华曙高科技有限责任公司 | Additive manufacturing method for manufacturing three-dimensional object, apparatus thereof, and readable storage medium |
| CN109773186A (en) * | 2019-01-30 | 2019-05-21 | 湖南华曙高科技有限责任公司 | For manufacturing the increasing material manufacturing method and its equipment, readable storage medium storing program for executing of three-dimension object |
| CN112097673B (en) * | 2019-06-18 | 2022-11-15 | 上汽通用汽车有限公司 | Virtual matching method and system for vehicle body parts |
| CN112097673A (en) * | 2019-06-18 | 2020-12-18 | 上汽通用汽车有限公司 | Virtual matching method and system for vehicle body parts |
| CN114929457A (en) * | 2020-01-16 | 2022-08-19 | 惠普发展公司，有限责任合伙企业 | Spatial arrangement of objects for additive manufacturing |
| CN111113903A (en) * | 2020-02-27 | 2020-05-08 | 杭州电子科技大学 | Automatic calibration method for 3D printing micro-nano device based on artificial intelligence |
| CN111941849A (en) * | 2020-06-28 | 2020-11-17 | 西安理工大学 | Size error compensation method for 3D printing cylindrical part |
| CN114274506A (en) * | 2021-02-19 | 2022-04-05 | 北京恒尚科技有限公司 | Method for 3D printing of spectacle frame and spectacle frame prepared by method |
| CN114274506B (en) * | 2021-02-19 | 2024-03-26 | 北京恒尚科技有限公司 | Method for printing glasses frame in 3D mode and prepared glasses frame |
| CN113059810A (en) * | 2021-05-19 | 2021-07-02 | 上海理工大学 | Triaxial 3D printer spatial error detection method based on test specimen |
| CN113536464B (en) * | 2021-07-21 | 2024-03-08 | 浙江吉利控股集团有限公司 | Dimension control method and dimension control system based on artificial intelligence |
| CN113536464A (en) * | 2021-07-21 | 2021-10-22 | 浙江吉利控股集团有限公司 | Dimension control method and dimension control system based on artificial intelligence |
| CN114425856A (en) * | 2022-01-19 | 2022-05-03 | 无锡学院 | Irregular target scanning and printing method based on three-dimensional camera |
| CN115139531B (en) * | 2022-07-04 | 2024-01-30 | 深圳胜马优创科技有限公司 | 3D printing support structure construction method, device, equipment and storage medium |
| CN115139531A (en) * | 2022-07-04 | 2022-10-04 | 深圳胜马优创科技有限公司 | 3D printing support structure construction method, device, equipment and storage medium |
| CN115534304A (en) * | 2022-09-29 | 2022-12-30 | 灰觋有限公司 | FDM printing device and automatic detection method for quality of printed product |
| CN117962314A (en) * | 2024-03-18 | 2024-05-03 | 江阴勰力机械科技有限公司 | Three-dimensional modeling method and system for 3D printer based on digital twin |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106182765B (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106182765A (en) | 3D printer model scale error Forecasting Methodology based on support vector machine | |
| CN107564002A (en) | Plastic tube detection method of surface flaw, system and computer-readable recording medium | |
| CN108564563A (en) | A kind of tire X-ray defect detection method based on Faster R-CNN | |
| CN108399287A (en) | Using the appraisal procedure of the machine tool beam design scheme of Fuzzy Level Analytic Approach | |
| CN106041344B (en) | A kind of laser peening school form quality amount control method for aeroplane engine machine support | |
| CN107067044A (en) | A kind of finance reimbursement unanimous vote is according to intelligent checks system | |
| CN104626583B (en) | Generation system and generation method that a kind of 3 D-printing is supported | |
| CN109213866A (en) | A kind of tax commodity code classification method and system based on deep learning | |
| CN109458936A (en) | A kind of power transmission line sag accurate measurement method based on laser point cloud data | |
| CN103076334B (en) | Method for quantitatively evaluating perceived quality of digital printed lines and texts | |
| CN107679089A (en) | A kind of cleaning method for electric power sensing data, device and system | |
| CN105787980A (en) | Method and system for detecting field angle of virtual reality display device | |
| CN110069776A (en) | Customer satisfaction appraisal procedure and device, computer readable storage medium | |
| US12053931B1 (en) | Method, device, and electronic device for controlling 3D printing | |
| CN110706203A (en) | Method and system for automatically detecting key points of lateral skull tablets based on deep learning | |
| CN117922017B (en) | Multichannel 3D printing method and 3D printing system | |
| CN107247954A (en) | A kind of image outlier detection method based on deep neural network | |
| CN107357941A (en) | A kind of system and method that watermark protocol data can be tested in real time | |
| CN118288386B (en) | Prefabricated box Liang Liangmian cloth vibration integrated intelligent integrated control system | |
| CN106886917A (en) | A kind of method and device for generating advertisement | |
| CN108319776A (en) | Simulation Parameters decision-making technique based on the soft collection of group's generalized interval intuitionistic fuzzy | |
| CN108681757A (en) | A kind of machining steel management method based on Quick Response Code | |
| CN109978250A (en) | A kind of qualitative forecasting method of battery pole piece coating production surface density | |
| CN109829879A (en) | The detection method and device of vascular bundle | |
| KR101268444B1 (en) | Configuration Method of the optimal water quality Monitoring Network And Decision Supporting System the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |