改进质量损失函数的多响应稳健优化设计

伍建军; 谢周伟; 黄裕林; 吴小明

doi:10.13433/j.cnki.1003-8728.2017.0405

改进质量损失函数的多响应稳健优化设计

doi: 10.13433/j.cnki.1003-8728.2017.0405

1.
江西理工大学机电工程学院, 江西赣州 341000

基金项目:

国家自然科学基金项目（51365015）、省教育厅（GJJ13416）及省科技厅（20142BBE50058）科技项目资助

详细信息

作者简介:
伍建军(1974-),副教授,博士,硕士生导师,研究方向为质量与可靠性,391485400@qq.com

计量
- 文章访问数: 158
- HTML全文浏览量: 31
- PDF下载量: 12
- 被引次数: 0
出版历程
- 收稿日期: 2015-10-23
- 刊出日期: 2017-04-05

A New Method for Multi-response Robust Optimization based on Improved Quality Loss Function

1.
School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Jiangxi Ganzhou 341000, China

摘要

摘要: 针对传统的多响应优化方法很少同时考虑到优化结果的最优性与稳健性以及容易忽视各个响应质量损失的问题，通过引入双响应曲面法的思想，提出了一种基于改进质量损失函数的多响应稳健优化设计新方法。通过双响应曲面法与多变量质量损失函数的相互结合，同时考虑了各个响应的均值和方差，首先通过拟合各个响应的均值回归方程和方差回归方程并将其结合到多变量质量损失函数中，然后通过主客观权重法科学设置各响应均值和方差质量损失的权重，最后将多响应的稳健优化问题转化为求解综合质量损失最小值的问题。以细胞注射3自由度柔顺并联微动平台中的双曲柔性铰链为研究对象进行研究，结果表明，该方法能够有效地解决具有多个响应问题的稳健优化，为多响应稳健优化设计提供新的思路。
- 多变量质量损失函数 /
- 双响应曲面方法 /
- 主客观权重 /
- 多响应稳健优化
Abstract: Because the conventional multi-response optimization methods rarely consider the optimization and the robustness simultaneously and tend to overlook the quality loss of multiple responses, we propose a new method of multi-response robust optimization based on the improved quality loss function to achieve the robustness and optimization of multiple responses by introducing the dual response surface method. With the dual response surface method and the multivariate loss function combined, the new method considers both the mean and variance of multiple responses. Firstly, the regression equation of the mean and standard deviation of multiple responses are fitted and are incorporated into the multivariate quality loss function. Secondly, the subjective and objective weight theory is used to set the weights of quality losses of mean and standard deviations of each response. Finally, the multi-response robust and optimal problem is transformed into the minimization of overall quality loss. The hyperbolic flexure hinge in the cell injection 3-DOF compliant parallel micro motion platform is used to prove the effectiveness of the new method. The analysis results show that the new method can more effectively solve multi-response robust optimization problems.
- multivariate loss function /
- dual response surface method /
- subjective and objective weight theory /
- multiple-response robust optimization

HTML全文

参考文献(17)

[1]	陈入领,潘双夏,沈彤.稳健设计研究现状[J].机械设计,2003,20(8):1-3 Chen R L, Pan S X, Shen T. Current research status of steady design[J]. Journal of Machine Design, 2003,20(8):1-3 (in Chinese)
[2]	张流洋,马义中,汪建均,等.考虑协变量的相关多响应稳健优化设计[J].系统工程,2015,33(2):126-133 Zhang L Y, Ma Y Z, Wang J J, et al. Correlated multi-response robust design and optimization with considering covariates[J]. Systems Engineering, 2015,33(2):126-133 (in Chinese)
[3]	Pignatiello J J. Strategies for robust multiresponse quality engineering[J]. IIE Transaction, 1993,25(3):5-15
[4]	Khuri A I, Conlon M. Simultaneous optimization of multiple responses represented by polynomial regression functions[J]. Technometrics, 1981,23(4):363-375
[5]	Harrington E C. The desirability function[J]. Industrial Quality Control, 1965,21(10):494-498
[6]	Derringer G, Suich R. Simultaneous optimization of several response variables[J]. Journal of Quality Technology, 1980,12(4):214-219
[7]	Myers R H, Carter W H. Response surface techniques for dual response systems[J]. Technometrics, 1973,15(2):301-317
[8]	Dengiz B, Belgin O. Simulation optimization of a multi-stage multi-product paint shop line with Response Surface Methodology[J]. Simulation, 2014,90(3):265-274
[9]	欧阳林寒,马义中,汪建均,等.基于熵权理论和双响应曲面的稳健设计[J].管理工程学报,2014,28(2):191-195,190 Ouyang L H, Ma Y Z, Wang J J, et al. Robust design based on entropy weight and dual response surface[J]. Journal of Industrial Engineering Management, 2014,28(2):191-195,190 (in Chinese)
[10]	Yeniay D, Unal R, Lepsch R A. Using dual response surfaces to reduce variability in launch vehicle design: a case study[J]. Reliability Engineering & System Safety, 2006,91(4):407-412
[11]	Vining G G, Myers R H. Combining Taguchi and response surface philosophies: a dual response approach[J]. Journal of Quality Technology, 1990,22(1):38-45
[12]	Artiles-leon N. A pragmatic approach to multiple-response problems using loss functions[J]. Quality Engineering, 1996,9(2):213-220
[13]	马义中,程少华,李言俊.改进的多变量质量损失函数及其实证分析[J].系统工程,2002,20(4):54-58 Ma Y Z, Cheng S H, Li Y J. An improved multivariate loss function and positive analysis[J]. Systems Engineering, 2002,20(4):54-58 (in Chinese)
[14]	汪文革,王珍惜.一种主客观综合的训练评估指标权重的确定方法[J].舰船电子工程,2013,33(8):123-125 Wang W G, Wang Z X. A subjective and objective method for determining index weights of training evaluation[J]. Ship Electronic Engineering, 2013,33(8):123-125 (in Chinese)
[15]	张宪民,刘晗.3-RRR并联机器人含间隙的运动学标定及误差补偿[J].华南理工大学学报(自然科学版),2014,42(7):97-103 Zhang X M, Liu H. A clearance approach of kinematic calibration and error compensation for 3-RRR parallel robot[J]. Journal of South China University of Technology (Natural Science Edition), 2014,42(7):97-103 (in Chinese)
[16]	张艳君.基于ANSYS的二维微动平台的性能分析[J].机床与液压,2013,41(9):154-156,162 Zhang Y J. Performance analysis of 2D jiggle platform based on ANSYS[J]. Machine Tool & Hydraulics, 2013,41(9):154-156,162 (in Chinese)
[17]	胡俊峰,张宪民.3自由度精密定位平台的运动特性和优化设计[J].光学精密工程,2012,20(12):2686-2695 Hu J F, Zhang X M. Kinematical properties and optimal design of 3-DOF precision positioning stage[J]. Optics and Precision Engineering, 2012,20(12):2686-2695 (in Chinese)