摘要
针对相关多绩效响应的供应链质量设计问题,笔者将主成分分析法与基于Kriging元模型的双响应曲面法相结合,提出一种同时考虑综合绩效均值效应和方差效应的稳健优化策略。首先,通过主成分分析,将多个相关绩效响应的位置特性和散度特性转化为供应链绩效的主成分综合得分;其次,分别构建多个绩效响应的位置特性和散度特性的Kriging元模型,进而得到基于Kriging元模型的综合绩效的主成分综合得分模型;最后,结合供应链仿真案例分析所构建优化策略的有效性。
As to the quality design of supply chain with correlated multi-performances, a robust optimization strategy with the consideration of mean effect and variance effect of overall performance based on principal component analysis(PCA) and Kriging meta-model. Firstly, the principal component analysis was used to transform the location and dispersion of each supply chain performance into the principal component score. Secondly, the Kriging meta-models were used to construct the relationship between the decision factors and the location of all the responses, and then the optimization strategy based on the weighted sum of the composite score through Kriging meta-model was given to identify the optimal levels of these decision factors. Finally, the effectiveness of the proposed optimization strategy was illustrated by a simulation case of supply chain.
作者
朱连燕
ZHU Lianyan(Department of Education and Science,Nanjing Polytechnic Institute,Nanjing Jiangsu 210048,China)
出处
《信息与电脑》
2021年第18期59-62,共4页
Information & Computer
基金
江苏省教育厅高校哲学社会科学研究基金项目(项目编号:2018SJA0626)。
关键词
供应链质量
相关多绩效响应
Kriging元模型
稳健参数设计
主成分分析
supply chain quality
correlated multi performance responses
Kriging meta-model
robust parameter design
principal component analysis
