计算机科学

计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 638-643.doi: 10.11896/jsjkx.210300080

• 交叉& 应用 • 上一篇    下一篇

基于IPSO-WRF的选择性激光烧结件气泡溶解时间预测模型

张天瑞1,2, 魏铭琦1, 高秀秀1   

  1. 1 沈阳大学机械工程学院 沈阳110041
    2 东北大学机械工程与自动化学院 沈阳110819
  • 出版日期:2021-11-10 发布日期:2021-11-12
  • 通讯作者: 魏铭琦(weimingqi111@163.com)
  • 作者简介:tianjiangruixue@126.com
  • 基金资助:
    工信部重大专项(201675514);辽宁省自然科学基金计划项目(20180551001)

Prediction Model of Bubble Dissolution Time in Selective Laser Sintering Based on IPSO-WRF

ZHANG Tian-rui1,2, WEI Ming-qi1, GAO Xiu-xiu1   

  1. 1 School of Mechanical Engineering,Shenyang University,Shenyang 110041,China
    2 School of Mechanical Engineering and Automation,Northeastern University,Shenyang 110819,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:ZHANG Tian-rui,born in 1985,Ph.D,associate professor,master supervisor.His main research interests include operational reasearch and optimization.
    WEI Ming-qi,born in 1995,postgraduate master.His main research interests include quality prediction and supply chain management.
  • Supported by:
    Major Master of MIT(201675514) and National Natural Science Foundation of Liaoning Province(20180551001).

PDF (PC)

478

摘要： 针对选择性激光烧结(Selective Laser Sintering,SLS)件成型过程中因气泡导致的质量缺陷问题,提出一种基于改进粒子群(Improved Particle Swarm Optimization,IPSO)算法优化的加权随机森林(Weighted Random Forest,WRF)预测方法,用于实现气泡溶解时间的有效预测。该方法利用IPSO算法优化WRF分裂属性个数和决策树数量两个关键参数,构建IPSO-WRF预测模型。数值实例表明,与PSO-RF,PSO-KELM预测模型的预测结果相比,基于相同的训练样本和测试样本,气泡溶解时间IPSO-WRF的预测模型能够获得误差更小且更接近于实际值的输出结果。MAE,MAPE,RMSE指标表明,IPSO-WRF预测模型具有比PSO-RF模型和PSO-KELM模型更高的非线性拟合能力和预测精度。最后,通过敏感性分析确定对气泡溶解时间影响最显著的输入参数,为SLS技术的发展提供理论依据。

关键词: 参数敏感性分析, 改进粒子群算法, 加权随机森林, 气泡溶解时间, 选择性激光烧结

Abstract: In order to solve the problem of mass defects caused by bubbles during selective laser sintering (SLS),a weighted random forest (WRF) prediction method based on improved particle swarm optimization algorithm (IPSO) was proposed to predict the dissolution time of bubbles effectively.In this method,two key parameters of WRF,the number of split attributes and the number of decision trees,were optimized by IPSO algorithm to construct the prediction model of IPSO-WRF.Numerical examples show that compared with the prediction results of PSO-RF and PSO-KELM prediction models,IPSO-WRF prediction model based on the same training samples and test samples can get the output results of bubble dissolution time with smaller error and closer to the actual value.MAE,MAPE and RMSE indexes show that IPSO-WRF prediction model has higher nonlinear fitting ability and prediction accuracy than PSO-RF model and PSO-KELM model.Finally,the most significant input parameters affecting the bubble dissolution time are determined by sensitivity analysis,which provides a theoretical basis for the development of SLS technology.

Key words: Bubble dissolution time, Improved particle swarm optimization algorithm, Parameter sensitivity analys, Selective laser sintering, Weighted random forest

中图分类号: 

  • TH164
[1]NELSON J C.Selective laser sintering:A Definition of theProcess and an Empirical Sintering Moder[D].Austin:University of Texas at Austin:1993.
[2]WEI Q,ZHONG J,XU Z,et al.Microstructure Evolution and Mechanical Properties of Ceramic Shell Moulds for Investment Casting of Turbine Blades by Selective Sintering[J].Ceram Int,2018,44(1):12088-12097.
[3]SHI Y S,HUANG S H,PAN C Y.Research on Intelligent Optimization Method of Selective Laser Sintering Process Parameters[J].Mechanical Science and Technology,2003,22(2):259-263.
[4]BOURELL D L,WATT T J,LEIGH D K,et al.PerformanceLimitations in Polymer Laser Sintering[J].Physicals Proceeds,2014,56(3):147-156.
[5]KONTOPOULOU M,VLACHOPOULOS J.Bubble Dissolution in Molten Polymers and Its Role in Rotational Molding[J].Polym Engineering,1999,39(6):1189-1198.
[6]LIU Z P,WANG H S,XIE H P.Precision prediction of selectivelaser sintering of coated sand based on BP neural network[J].Hot Working Technology,2016,45(21):91-93.
[7]REN J W,YIN J J,DONG L J.Precision prediction of selective laser sintering of coated sand based on BP neural network[J].Mechine Tool&Hydraulics,2016,45(21):15-18.
[8]CAI C Z,PEI J F,WEN Y F.Support vector regression prediction of selective laser sintering molding density[J].Acta Physica Sinica,2009,58(special issue):8-14.
[9]BREIMAN L.Random Forests[J].Machine Learning,2001,45(1):5-32.
[10]WEN B E,DONG W H,XIE W J.Parameter optimization of random forest based on improved grid search algorithm[J].Computer Engineering and Applications,2018,54(10):154-157.
[11]LAI C G,CHEN X H,ZHAO S W.Flood risk assessment model based on random forest and its application[J].Journal of Hydraulic Engineering,2015,46(1):58-53
[12]LU W X,WU H C,WAN L Y.Prediction of Precipitation by PLS Based on Fusion of Random Forest Algorithm[J].Statistics & Decision,2020,18(3):27-31.
[13]JI Y J,YONG X Y,LIU Y L.Quality analysis and prediction method of hot rolled strip steel based on random forest[J].Journal of Northeast University,2019,40(1):11-15.
[14]ZHAO T,WANG L T,ZHANG Y.Recognition of user power consumption related factors and power consumption prediction method using mutual information and random forest algorithm[J].Proceedings of the CSEE,2016,36(3):604-614.
[15]HE J,WEN X T,NIE W X.Using Random Forest Algorithm to Predict Crack Development Zone[J].Oil Geophysical Prospecting,2020,55(1):161-166.
[16]WEN T X,ZHANG B,SHAO L S.Random forest model of coal and gas outburst prediction[J].Computer Engineering and Applications,2014,50(10):233-237.
[17]CHEN Y P,LUO M,PENG J H.Land use classification of industrial and mining reclamation areas based on network search random forest algorithm[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(14):250-257.
[18]YANG X Y,GUAN W Y,LIU Y Q.Wind power interval prediction method based on particle swarm optimization kernel extreme learning machine model[J].Proceedings of CSEE,2015,35(supplement):146-153.
[19]LI W T,BIAN S F,REN Q Y.Beidou ultra-fast clock error prediction based on particle swarm optimization kernel extreme learning machin[J].Journal of Astronautics,2019,40(9):1080-1088.
[20]KANG S A,YU J C,ZHANG J.Direct Route Drag Prediction of Chain-structured Underwater Vehicle Based on Neural Network Optimized by Particle Swarm Optimization[J].Journal of Mechanical Engineering.2019,55(21):32-38.
[21]WANG X X,BIAN S F,REN Q Y.Motor Fault DiagnosisMethod Based on Particle Swarm Optimization and Random Forest[J].Small & Special Electrical Machines,2019,47(10):42-45.
[22]KISI O,KHOSRAVINIA P,HEDDAM S,et al.Modeling wetting front redistribution of drip irrigation systems using a new machine learning method:Adaptive neuro- fuzzy system improved by hybrid particle swarm optimization-Gravity search algorithm[J].Agricultural Water Management.2021,256(12):107067-107083.
[1] 张旭, 王莉莉, 杨博韬.
带有一刀切约束的二维非规则装箱算法
Heuristic Algorithms for Two-dimensional Irregular Bin Packing Problem with GuillotineConstraints
计算机科学, 2020, 47(5): 212-216. https://doi.org/10.11896/jsjkx.190400078
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发