System Reliability Analysis for Nonnormal Distributions and Optimization Using Experimental Design Technique

실험계획법을 이용한 비정규 분포에 대한 신뢰도 계산 방법과 최적 설계에의 적용

An experimental design technique is developed for estimating the moments of system response functions. It is easy to implement and provides accurate results compared with other traditional methods. It is based on the work of Taguchi, later improved by D'Errico and Zaino. The existing experimental techniques, however, is applicable only for normally distributed cases. In this article the three-level Taguchi method is extended to obtain optimum choice for levels and weights to handle nonnormal distributions. A systematic procedure for reliability analysis is then proposed by using the Pearson system and the narrow system reliability bounds. Illustrative examples including a tolerance optimization problem are shown very accurate comparing with those by Monte-Carlo simulations and the first-order reliability method.