An Improved Loss Function Approach for Multi-response Optimization Using Seemingly Unrelated Regressions

Abstract

Abstract:

Multi-response optimization with correlated responses in complex product or process is studied. The seemingly unrelated regression method is employed to improve traditional loss function approach. Correlations among responses are considered both in the model fitting phase and in the optimization phase. Illustrated example shows that the proposed approach can lead to an optimal solution with smaller expected quality loss. The approach overcomes the drawback of traditional method which ignores the correlation or only considers the correlation in the optimization phase. It is an important improvement on the conventional loss function method.

Key words: seemingly unrelated regressions, multiresponse optimization, loss function, response surface methodology, correlations among responses

ZHANG Xutao1,2，HE Zhen2, BI Hailing1. An Improved Loss Function Approach for Multi-response Optimization Using Seemingly Unrelated Regressions[J]. Industrial Engineering Journal .

References

［1］ARDAKANI M K, WULFF S S. An overview of optimization formulations for multiresponse surface problems ［J］. Quality and Reliability Engineering International, 2013, 29(1): 3-16. ［2］ZELLNER A. An efficient method of estimating seemingly unrelated regressions and tests for aggregation bias ［J］. Journal of the American Statistical Association, 1962, 57(298): 266-286.
［3］PIGNATIELLO J J. Strategies for robust mutiresponse quality engineering ［J］. IIE Transactions, 1993, 25(3): 5-15.
［4］VINING G G. A compromise approach to multiresponse optimization ［J］. Journal of Quality Technology, 1998, 30(4): 309.
［5］KO Y, KIM K, JUN C. A new loss functionbased method for multiresponse optimization ［J］. Journal of Quality Technology, 2005, 37(1): 50-59.
［6］OUYANG L, MA Y, BYUN J. An integrative loss function approach to multiresponse optimization ［J］. Quality and Reliability Engineering International, 2013, 31(2): 193204.
［7］汪建均，马义中，翟云焕. 相关多质量特性的优化设计［J］. 管理工程学报, 2011, 25(2): 66-73.
WANG J J, MA Y Z, ZHAI Y H. Optimization design of correlated multiple quality characteristics ［J］. Journal of Industrial Engineering and Engineering Management, 2011, 25(2): 66-73. ［8］YADAV O P, BHAMARE S S, RATHORE A. Reliabilitybased robust design optimization: a multiobjective framework using hybrid quality loss function ［J］. Quality and Reliability Engineering International, 2010, 26(1): 27-41.
［9］何桢，吕海利. 多元质量特性稳健性设计方法的优化研究［J］. 管理科学. 2007, 20(1): 2-7.
HE Z, LYU H. Optimization research on robust design with multiple quality characteristics ［J］. Journal of Management Sciences, 2007, 20(1): 2-7.
［10］SIBALIJA T V, MAJSTOROVIC V D. Multiresponse optimisation of thermosonic copper wirebonding process with correlated responses ［J］. The International Journal of Advanced Manufacturing Technology, 2009, 42(3-4): 363-371.
［11］SHAH H K, MONTGOMERY D C, CARLYLE W M. Response surface modeling and optimization in multiresponse experiments using seemingly unrelated regressions ［J］. Quality Engineering, 2004, 16(3): 387-397.
［12］PETERSON J J, MIROQUESADA G, DEL CASTILLO E. A Bayesian reliability approach to multiple response optimization with seemingly unrelated regression models ［J］. Quality Technology and Quantitative Management, 2009, 6(4): 353-369.

[1]	TU Xinyu, YIN Jiankang, YANG Fangyan, LI Maobo, LI Haodong, LI Sheng, SONG Hongwen. A Research on the Impact Factors of Recognition Rate of QR Code Label Based on RSM [J]. Industrial Engineering Journal, 2020, 23(6): 146-154.
[2]	ZHENG Yuqiao, ZHANG Chengcheng, MA Huidong, ZHANG Lu. A Research on the Quality Control of Wind Turbine Hub Assembly Process Based on Improved Taguchi Method [J]. Industrial Engineering Journal , 2019, 22(3): 37-43.
[3]	Fang Juntao1, He Zhen2, Song Linxi2, Zhang Yang2. The robust M-estimators in Response Surface Modeling [J]. Industrial Engineering Journal , 2012, 15(3): 98-103.
[4]	Zhang Yueyi1, Song Mingshun1, Han Zhijun2, Chen Xianglai3. Design of Quality Loss Function under the Smaller the Better Characteristic without Neglecting the Linear Term [J]. Industrial Engineering Journal , 2011, 14(6): 81-83.
[5]	Xue Li. Optimization Design of an EWMA Control Chart for NonNormal Data based on Taguchis Loss Function [J]. Industrial Engineering Journal , 2011, 14(5): 75-78.