面向可持续生产中多任务调度的双重增强模因算法

Dual-enhanced Memetic Algorithm for Multi-task Scheduling in Sustainable Production

从经济、环境和社会3个维度,全面提升生产调度方案的可持续性具有重要意义.针对并行机生产场景,建立考虑机器指派、加工顺序、人员安排以及开关机控制等4种决策任务的调度模型.为实现对复杂决策空间的高效寻优,提出一种融合两种局部优化策略的双重增强模因算法(Dual-enhanced memetic algorithm, DMA)求解模型.从随机更新角度,针对不同决策任务,构造单步变邻域搜索(One-step variable neighborhood search, 1S-VNS)策略.从定向优化角度,分析目标和关键任务之间的匹配关系,提出一种可持续目标导向策略(Sustainable goals-oriented strategy, SGS).考虑到两种优化策略的不同特点,单步变邻域搜索策略作用于整个种群,目标导向策略强化种群中的精英个体,实现对输出解集的双重优化.仿真实验结果表明,双重优化策略能有效地增强算法性能,并且所提算法在非支配解的多样性和收敛性上具有优越性.

It is of great significance to comprehensively enhance the sustainability of production scheduling with economic,environmental and social demand.A scheduling model for parallel machine production is established with consideration of four decision tasks:Machine assignment,processing sequence,personnel arrangement,and on/off machine control.To solve this complex problem,a dual-enhanced memetic algorithm(DMA)that integrates two local optimization strategies is proposed.In a random manner,a one-step variable neighborhood search(1S-VNS)suitable for decision-making tasks is designed.For targeted optimization,a sustainable goals-oriented strategy(SGS)is constructed after analyzing the matching relationship between objectives and key tasks.Based on the different characteristics of the two optimization strategies,the 1S-VNS acts on the entire population,and the SGS strengthens the elite individuals,achieving dual optimization of the output solution set.The simulation experimental results show that the dual optimization strategies effectively enhance the algorithm performance,and the proposed DMA has superiority in diversity and convergence of non-dominated solutions.