求解混流集束型装备调度问题的差分进化算法

Improved Differential Evolution for Cluster Tool Scheduling Problem with Mixed-wafer Processing

针对带滞留时间约束的混流集束型晶圆制造装备调度问题,为了优化晶圆加工排序和机械手搬运作业排序,提出了改进差分进化算法.通过定义机械手搬运作业,将双排序问题转换为单排序问题,并将其应有到染色体编码中;设计基于禁止区间法的启发式构造算法以生成初始种群,避免了不可行染色体的产生;给出可行解必须满足的条件,将其应用到差分变异和差分交叉算子设计中,避免冗余迭代和陷入局部最优等现象.与差分进化算法、遗传禁忌混合算法、粒子群算法的仿真实验比较,验证了提出算法的有效性和鲁棒性.

Aiming at the scheduling problem of mixed-wafer clustered wafer manufacturing equipment with residence time constraints,an improved differential evolution algorithm is proposed to optimize both wafer input sequence and robotic move sequence.By defining the robot task operation,the problem is changed from a double sorting problem was to a single one,which is applied to chromosome coding later.Design a heuristic construction algorithm based on the forbidden interval method to generate the initial population and avoid the generation of infeasible chromosomes.Aiming to avoid redundant iterations and local optimization,the conditions that a feasible solution must meet are given and applied to design differential mutation and differential crossover operators.At last,the effectiveness and robustness of the proposed algorithm are verified by comparing with the simulation experiments of differential evolution algorithms,genetic tabu hybrid algorithms,and particle swarm optimization algorithms.