针对现有进化算法在进行逻辑电路设计时存在的进化缓慢和容易陷入局部解等问题,提出一种自适应免疫进化算法(adaptive immune evolutionary algorithm, AIEA)。该算法引入了免疫记忆机制和抗体差异调节算子,能够很好地保证个体的多样性,有利于跳出局部最优解;通过采用自适应交叉率和变异率,提高了算法的搜索能力和收敛速度。通过与多目标进化算法(MOEA)、简单免疫算法(SIA)的实验比较,证明了该自适应免疫进化算法的有效性。
To solve the problems of traditional evolution algorithm, such as slowness evolution speed and premature convergence, this paper presened an adaptive immune evolutionary algorithm (AIEA) for combinational logic circuit design. The AIEA draws into the mechanisms existing in biological immune system such as immune memory, immune regulation, and antibody diversity. Besides, the AIEA featured an adaptation strategy that enabled crossover probability and mutation probability to vary with genetic-search process. The results were compared with those produced by the multi-objective evolutionary algorithm (MOEA) and by the simple immune algorithm (SIA). The simulation results show that AIEA overcomes the disadvantages of premature convergence, and improve the global searching efficiency and capability.