基于混合多值离散粒子群优化的混合极性Reed-Muller最小化算法  

Hybrid Multi-valued Discrete Particle Swarm Optimization Algorithm for Mixed-polarity Reed-Muller Minimization

作　　者：卜登立[1,2] 江建慧[1] 

机构地区：[1]同济大学软件学院上海201804 [2]井冈山大学电子与信息工程学院吉安343009

出　　处：《电子与信息学报》2013年第2期361-367,共7页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(60903033)资助课题

摘　　要：针对布尔函数系统的混合极性Reed-Muller(Mixed-Polarity Reed-Muller,MPRM)最小化问题,该文提出了一种混合多值离散粒子群优化算法。为解决多样性损失,改善优化结果,兼顾算法的效率和精度,算法采用多群协同优化方法,并提出了概率变异更新、没有重复的更新以及群间重复最优变异3种更新和变异策略。实验结果表明,和模拟退火遗传算法相比,所构造算法能够在获得基本相同优化结果的同时,提高MPRM最小化的时间效率。A novel hybrid multi-valued Discrete Particle Swarm Optimization （DPSO） algorithm for Mixed- Polarity Reed-Muller （MPRM） minimization of Boolean function system is proposed. To solve the problem of diversity loss, improve the optimized result and balance the efficiency and precision of DPSO, multi-swarm cooperative optimization is employed, and three update and mutation strategies of update with probabilistic mutation, update with no duplicates and mutation with best duplicates between swarms are proposed. The experimental results show that compared with Simulated Annealing Genetic Algorithm （SAGA）, the proposed algorithm can obtain similar optimized results and improve the time efficiency of MPRM minimization.

关 键 词：数字电路 布尔函数系统 混合极性Reed—Muller 多值离散粒子群优化 多群 更新和变异策略 

分 类 号：TP331.2[自动化与计算机技术—计算机系统结构] TP391.72[自动化与计算机技术—计算机科学与技术]