基于神经网络和遗传算法的三维打印工艺参数优化

李淑娟; 陈文彬; 刘永; 符柳

doi:10.13433/j.cnki.1003-8728.2014.1116

基于神经网络和遗传算法的三维打印工艺参数优化

doi: 10.13433/j.cnki.1003-8728.2014.1116

1.
西安理工大学机械与精密仪器工程学院, 西安 710048

基金项目:

国家973项目(2009CB724406)

陕西省工业攻关项目(2012K07-25)资助

详细信息

作者简介:
李淑娟(1965- ),教授,博士生导师,研究方向为直接数字制造技术,shujuanli2009@gmail.com。

计量
- 文章访问数: 228
- HTML全文浏览量: 41
- PDF下载量: 6
- 被引次数: 0
出版历程
- 收稿日期: 2013-04-10

Optimization of the 3DP Printing Parameters Based on the Neural Networks and Genetic Algorithm

1.
School of Mechanical and Instrument Engineering, Xi'an University of Technology, Xi'an 710048

摘要

摘要: 分析了粉末材料三维打印(three dimensional printing,3DP)过程中影响成型精度的因素,采用试验的方法确定打印过程中的三维制件的收缩率范围.以“H”型工件为标准,建立了基于神经网络(neural network,NN)的制件尺寸精度误差和打印工艺参数之间关系的模型.以制件最小尺寸误差为目标,采用遗传算法(genetic algorithm,GA)对3DP中的工艺参数如饱和度、层厚和X、Y、Z这3个方向的收缩补偿值进行优化,获得了相应的打印工艺参数.采用3DP默认的打印参数、打印参数的最小值、最大值以及NN-GA得到的参数进行对比试验.结果表明:采用NN-GA获得的工艺参数打印的制件的尺寸误差最小,可以预测3DP成型制件相对尺寸误差.
- 3DP /
- 神经网络 /
- 遗传算法 /
- 参数优化 /
- 尺寸精度
Abstract: The factors affect the printing accuracy for powdery materials is analyzed in three dimensional printing(3DP) process,the experiment is used to determine the range of shrinkage of the printing process for the threedimensional components. The "H" type component as the test specimen,the neural network(NN) is used to describe the complicated relationship between the dimensional accuracy of component and printing processing parameters. As the goal of the minimum dimensional accuracy of specimen,the genetic algorithm(GA) is used to optimize the 3DP printing parameters such as saturation,the layer thickness and compensation in three directions X,Y and Z respectively. The comparing experiments for 3DP using default parameters of printer,the minimum and maximum value in the range of printing parameters,and the NN-GA obtained parameters are conducted,and the results show that the dimensional accuracy is the best using the printing processing parameters of the NN-GA obtained,which show that the NN-GA can predict the dimensional accuracy for 3DP printing processing and provide the reference for other similar fabrication method.
- constrained optimization /
- design of experiments /
- dimensional accuracy /
- forecasting /
- genetic algorithms

HTML全文

参考文献(17)

[1]	Terry WAdditive manufactauring and 3D printing stateof the industry[R]Annual Worldwide ProgressReport,2011
[2]	Turker M,Godlinski D. Elfecta of productaion parameterson the properties of IN 718 super alloy by three-dimensional printing[J]Materials Charactaerization,2008,59:1728-1735
[3]	Suwanprateeb J. Improvement in mechanical propertiesof three-dimensional printing parts made from naturalpolymers reinforced by acrylate resin for biomedicalapplications:a double infiltration approach[J]. PolymerInternational, 2006; 55; 57-62
[4]	Suwanprateeb J, Suwanpreuk W Development of translucentand strong three dimensional printing models[J}. RapidPrototyping Journa1,2009:52-58
[5]	Lam C X F, Mo X M. Scalfold development using 3Dprinting with a starch-based polymer[J]MaterialsSeience and Engineering,2002, C20;49-56
[6]	Mohammad V,Chee K C. Elfectas of layer thicknessand binder saturation level parameters on 3D printingprocess[J]The International Journal of AdvancedManufactauring Technology,2010,53;275-284
[7]	Li S J, Cao S. Print parameters inlluence on parts'quality and calibration with 3DP-part I:Print parametersinlluence on parts'surface topography[J]AdvancedMaterials Research,2012,399:1639-1645
[8]	Li S J, Cao S. Print parameters inlluence on parts'quality and calibration with 3DP-part II; Printparameters calibration and contour aecuracy control } JAdvanced Materials Researc:h,2012,399:1687-1692
[9]	曹珊,李淑娟三维打印技术工艺参数对制件表面形貌的影响[J]机械科学与技术,2012, 31 (7);1081-1084Cao S, Li S J. The influence of 3DP processingparameters on the parts'surfacta topography[J]Mechanical Seience and Technology for AerospaceEngineering, 2012, 31(7):1081-1084(in Chinese)
[10]	符柳,李淑娟,胡超基于RSM的三维打印参数对材料收缩率的影响[J]机械科学与技术,2013, 32(12):1835-1840Fu L, Li S J, Hu C. Elfecta of the 3DP printingparameters on the material contractaion ratio based on theRSM method[J]Mechanical Science and Technologyfor Aerospace Engineering, 2013,32(12):1835-1840(in Chinese)
[11]	Lu K,ReynoldsW T. 3DP process for fine meshstructaure printing[J]Powder Technology, 2008,187:11-18
[12]	Cho H S, Park W S. Determining optimal parametersfor stereolithography processes via genetic: algorithmpark [J]. Journal of Manufactauring Systems, 2000:18-27
[13]	Maslov I V, Izidor G. Using neural network to improvethe performance of the hybrid evolutionary algorithm inimage registration[C]//Proceedings of SPIE-TheInternational Society for Optical Engineering, 2003,5015 55-65
[14]	董世钢数控加工切削参数优化的研究[D]长春:长春理工大学,2009Dong S G. Research on optimization of NC machingcutting parameters[D]Changchun:ChangchunUniversity of Science and Technology, 2009(in Chinese)
[15]	Li S J, Li Y, Liu Y. A GA-based NN approach formakespan estimation international[J]Journal ofApplied Mathematicsand Computation,2007,185(2):1003-1014
[16]	张德丰MATLAB神经网络应用设计[M]北京:机械工业出版社,2009Zhang D F. Application design of MATLAB neuralnetwerk[M]Beijing; China Machine Press, 2009(in Chinese)
[17]	Sarimveis,Haralambos. A new algorithm for developingdynaic radial basic: functaion neural network models basedon genetic: algorithms[J]Computers and ChemicalEngineering,2004;209-217