基于置信区间的多元质量特性满意参数设计

Satisfactory parameter design approach based on confidence interval for multivariate quality characteristics

针对多元质量特性参数设计中模型不确定性问题,提出了一种基于置信区间的多元质量特性满意参数设计方法。首先,采用双响应曲面法建立各质量特性均值和标准差的近似模型,进而计算各质量特性均值和标准差的置信区间,在此基础上对质量特性指标在各自约束条件下的满意解集进行定义并对约束放宽策略进行设计,最终通过指标相容性分析得到满足所有约束条件的相容性解集。通过对实际工业案例进行分析,表明该方法能有效减小模型不确定性的影响,在满意解集中选取的满意解与传统稳健解相比更加可靠。

A satisfactory parameter design approach hased on confidence interval is proposed to solve the model uncertainty problem of multivariate quality characteristics. The response models of mean and standard de viation are built by using the dual response surface method, and then their confidence interval expressions are obtained. The satisfactory sets which make each quality characteristic satisfies the respective constraint are de- fined based on the confidence intervals, and the constraint relaxed strategy is then designed. The consistency set that satisfies all constraints is obtained through consistency analysis. A numerical example shows that the pro posed method can reduce the effect of model uncertainty and the satisfactory parameter is more reliable than the robust parameter which is obtained through the current method.