针对装配序列规划问题提出了一种模拟生物免疫系统的免疫算法,并给出了亲和力计算、抗体生成、免疫选择、记忆细胞更新等的具体实现方法。实例仿真结果表明,免疫算法在装配序列规划问题的求解中充分体现了免疫系统的多样性、免疫自我调节、免疫记忆和分布式并行等特点。免疫算法较遗传算法具有更强的全局搜索能力和更快的收敛速度,有效地改善了全局收敛性能和收敛速度。
A novel immune algorithm simulating the biological immune system was proposed to solve the Assembly Sequence Planning (ASP) problem. Implementation methods such as appetency computation, antibody generation, immunity selection, and memory cell update were provided. The immune algorithm in sequence planning problem solving reflected characteristics such as diversity, immune self-adjustment, immune memory and distributed parallel of the immune system. The immune algorithm was superior to those genetic algorithms in both global search capability and convergence speed. As a result, the immune algorithm was a prospective and efficient way to tackle ASP.