基于混合粒子群优化算法的多组合设备调度方法研究

Research on Scheduling Method of Multi-Cluster Tools Based on Hybrid Particle Swarm Optimization Algorithm

半导体晶圆制造系统是当今最复杂的制造系统之一,具有规模庞大、设备昂贵、多品种混合生产等复杂特征。如何有效地优化调度与控制方法对于缩短生产周期、提高设备利用率至关重要。近年来,多组合设备逐渐应用于晶圆加工,由于存在晶圆滞留时间约束,多组合设备的调度问题变得极为复杂且具有挑战性。以最小化生产周期为目标,提出了一种混合粒子群优化算法来解决多组合设备的调度问题,对粒子群优化算法的参数进行自适应混沌优化,实现全局搜索与局部搜索间的有效平衡,同时引入不可行解修复策略,对不可行解进行自适应修复,有效地提高了搜索效率和求解质量。最后基于实际生产数据进行仿真实验,计算结果表明,所提出的混合粒子群优化算法对解决多组合设备调度问题具有有效性和高效性。

In recent years,multi-cluster tools are gradually applied to wafer processing,due to the existence of wafer residency time constraints,multi-cluster tools scheduling problems become extremely complex and challenging.A hybrid particle swarm optimization algorithm is proposed to solve the scheduling problem of multi-cluster tools with the goal of minimizing the production cycle time.Adaptive chaos optimization is carried out on the parameters of the particle swarm optimization algorithm to achieve an effective balance between global and local search,and at the same time,an infeasible solution repair strategy is introduced to carry out adaptive repair on infeasible solutions,which effectively improves the search efficiency and the quality of the solution.