论文部分内容阅读
研究了协变量之间以及多响应之间同时存在相关性的问题,考虑了多响应的最优性与稳健性,提出了基于主成分分析与似然不相关回归相结合的方法解决含有多个协变量的多响应稳健设计问题。该方法分析了决策者在协变量概率取不同阈值的情况下,将相关多响应优化问题转化为求解相应情况下的综合满意度函数最大值的问题。并结合具体的实例进行分析研究,结果表明了本文所提出的方法能够有效地解决此类多响应稳健设计问题。
The coexistence of covariates and multiple responses are studied. The optimality and robustness of multiple responses are considered. Based on the combination of principal component analysis and likelihood uncorrelated regression, Multi-response covariance robust design problem. The method analyzes the problem that the decision maker transforms the related multi-response optimization problem into the maximum value of the comprehensive satisfaction function in the corresponding situation when the covariate probability takes different thresholds. The results show that the proposed method can effectively solve the robust design problem of multi-response.