用改进的混合遗传算法进行器件模型参数提取

Model parameter extraction for semiconductor devices based on a hybrid genetic algorithm

本文研究了使用混合遗传算法的器件模型参数提取。该混合遗传算法结合了全局寻优的遗传算法和局部寻优的Powell算法,以改善单纯使用遗传算法局部收敛速度较慢这一不足。为了进一步加快算法的速度,提出了在混合算法开始阶段控制Powell迭代次数的策略。文中以GaAs MESFET小信号模型的参数提取为例,说明了算法的效果。

In this paper a hybrid algorithm that incorporates the genetic algorithm and the traditional Powell algorithm with the applications to the semiconductor device model parameter extraction is presented. Improved strategy to reduce the computational cost is proposed, The performance of the algorithm is illustrated by a practical GaAs MESFET small signal model parameter extraction problem.