论文部分内容阅读
本文利用蒙特卡罗法估计电路产品合格率对元件参数中心值的一、二阶偏导数,再与牛顿最优化方法结合得到了一个电路中心设计的算法,为了提高偏导数估计值的精度,文中又给出了利用“失败”样本点的估计式。为了减少电路分析次数,作者提出了适用于蒙特卡罗分析的采样频率按权排序法,理论分析和算例表明:本文算法是成功的,适用于非凸、非单连通可行域,可进行中等规模电路的产品合格率估计和中心设计。
In this paper, the Monte Carlo method is used to estimate the first and second order partial derivatives of the pass rate of the circuit product to the center value of the component parameters. A circuit center design algorithm is obtained by combining with Newton’s optimization method. In order to improve the accuracy of partial derivative estimation, Also given the use of “failure” sample points of the formula. In order to reduce the number of circuit analysis, the authors propose a weighted ordering of sampling frequencies for Monte Carlo analysis. The theoretical analysis and examples show that the proposed algorithm is successful and suitable for non-convex and non-single-connected feasible domains. Scale circuit product qualification rate estimation and center design.