基于小生境差分进化算法的预防性维修优化研究

A differential evolution algorithm based on niche for optimal application research of preventive maintenance

针对预防性维修问题,提出了一种基于小生境进化策略的改进差分进化算法.该算法采用DE/best/2/bin变异方式,变异个体由当前种群中的最优个体作引导,同时引入小生境进化策略,使算法具有局部搜索能力强和精度高的特点,也增强了算法的全局搜索能力,避免早熟现象的发生.将该算法应用于求解有限时间区间的预防性维修问题,仿真试验结果表明,该算法可行有效,其结果能对生产实践起到一定指导作用.

In view of the preventive maintenance problem, an improved differential evolution algorithm based on niche evolution strategy was presented. The algorithm takes the DE/best/2/bin mutation scheme, and the mutation individual is guided by the optimal individual in the current population, at the same time a strategy of niche evolutionary is introduced to make the algorithm has good performance of local searching ability and high convergence accuracy while enhancing the global searching ability and avoid the premature phenomena. Finally, the algorithm is used in preventive maintenance problem of finite time horizon, the simulation results show that the algorithm is feasible and efficient and can play a definite part in directing production.