Multi-response Robust Design based on Comprehensive Weight and Quality Loss
-
摘要: 针对多元稳健设计中如何确定权重和建立优化模型的问题,提出了考虑主客观权重和质量损失函数的多元稳健设计模型。在利用质量损失度量多质量特性稳健性的基础上,利用Kendall协同系数检验的方法对专家打分的分数进行一致性检验,其次根据通过检验的分数计算各质量特性的主观权重;同时,利用熵权理论确定不同质量特性的客观权重;然后将主观权重与客观权重线性加权得到综合权重。另外,在拟合回归模型时充分考虑了拟合模型的有效性及回归系数的显著程度。通过实例说明该方法可以突破试验范围的限制,寻找全局最优解。
-
关键词:
- 稳健设计 /
- Kendall协同系数检验 /
- 熵权 /
- 质量损失 /
- 回归模型
Abstract: Based on comprehensive weight and quality loss, we present a method for robust design that has multiple quality characteristics to solve the weight and optimization problems. Firstly, we employ the quality loss to measure the robustness of multiple quality characteristics. Secondly, the subjective weight is calculated according to the data which passed the Kendall's concordance coefficient test. Meanwhile, the concept of entropy weight is introduced to calculate the objective weight by considering the information on responses. Then the comprehensive weights can be determined by the above two kinds of weight. Thirdly, the validity of the method and the significance of the coefficient are taken into consideration when conducting the regression analysis. Finally, a case study is given to illustrate that the improved method can find the optimal solution in the global range. -
[1] Robinson T J, Borror C M, Myers R H. Robust parameter design: a review[J]. Quality and Reliability Engineering International, 2004,20(1):81-101 [2] Shilpa M, Naidu N V R. Quantitative evaluation of quality loss for fraction defective case using Taguchi's quality loss function[J]. International Journal of Logistics Systems and Management, 2015,18(1):126-138 [3] Pal S, Gauri S K. Multi-response optimization using multiple regression-based weighted signal-to-noise ratio (MRWSN)[J]. Quality Engineering, 2010,22(4):336-350 [4] Gauri S K. Optimization of multi-response dynamic systems using principal component Analysis (PCA)-based utility theory approach[J]. International Journal of Industrial Engineering Computations, 2014,5(1):101-114 [5] 魏世振,韩玉启,陈传明.基于信噪比的多元质量损失函数研究[J].管理工程学报,2004,18(2):4-7 Wei S Z, Han Y Q, Chen C M. A study on multivariate quality loss functions based on signal-to-noise ratios[J]. Journal of Industrial Engineering/Engineering Management, 2004,18(2):4-7 (in Chinese) [6] Chen L H. Designing robust products with multiple quality characteristics[J]. Computers & Operations Research, 1997,24(10):937-944 [7] 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, Lv H L. Optimization research on robust design with multiple quality characteristics[J]. Journal of Management Sciences, 2007,20(1):2-7 (in Chinese) [8] 徐兰,方志耕.基于质量损失的交叉质量结构参数设计方法[J].管理工程学报,2011,25(3):106-110 Xu L, Fang Z G. A method of parameter design for crossed quality structure based on quality loss[J]. Journal of Industrial Engineering/Engineering Management, 2011,25(3):106-110 (in Chinese) [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/Engineering Management, 2014,28(2):191-195,190 (in Chinese) [10] 张流洋,马义中,汪建均,等.考虑主客观权重的多响应稳健优化设计[J].系统工程,2014,(4):87-95 Zhang L Y, Ma Y Z, Wang J J, et al. Balancing the subjective weight and objective weight for multi-response robust design and optimization[J]. Systems Engineering, 2014,(4):87-95 (in Chinese) [11] 吴喜之, 赵博娟. 非参数统计[M]. 4版. 北京: 中国统计出版社, 2013:10 Wu X Z, Zhao B J. Non-parameter Statistics[M]. 4th ed. Beijing: China Statistics Press, 2013:10 (in Chinese) [12] Wang Q, Wu C, Sun Y. Evaluating corporate social responsibility of airlines using entropy weight and grey relation analysis[J]. Journal of Air Transport Management, 2015,42:55-62 [13] Li Y C, Zhao L, Suo J J. Comprehensive assessment of marine ecological environment based on entropy weight model[J]. Polish Journal of Environmental Studies, 2015,24(1):151-155 [14] Chen C H, Chou C Y, Kan C C. Modified economic production and raw material model with quality loss for conforming product[J]. Journal of Industrial and Production Engineering, 2015,32(3):196-203 [15] Antony J. Multi-response optimization in industrial experiments using Taguchi's quality loss function and principal component analysis[J]. Quality and Reliability Engineering International, 2000,16(1):3-8 [16] Su C T, Tong L I. Multi-response robust design by principal component analysis[J]. Total Quality Management, 1997,8(6):409-416
点击查看大图
计量
- 文章访问数: 125
- HTML全文浏览量: 15
- PDF下载量: 5
- 被引次数: 0