关键词: 绿色作业车间, 高维多目标, 动态调度, 总能耗, IMOGWO算法

Abstract: Nowadays, environmental problems are becoming more and more serious, and green and intelligent manufacturing has attracted much attention. On the basis of the dynamic flexible job-shop, considering different machine status under the situation of energy consumption and energy-saving machine works, this paper builds the multi-objective dynamic flexible job-shop scheduling model with goals of total energy consumption, maximum completion time, machine total load and stability of product quality, and then develops an Improved Multi-objective Grey Wolf Optimizer (IMOGWO) to solve the model. Firstly, we use the reverse learning initialization population strategy to expand the population diversity. Sencondly, according to the multi-objective problem and characteristics of standard GWO algorithm, we propose multi-stage official leadership mechanism, and introduce POX crossover and reverse mutation operator. Finally, the elite retention strategy is improved to adapt to the multi-objective optimization algorithm. In order to prove the effectiveness of the algorithm, we designe two groups of simulation experiments to compare three algorithms respectively. The simulation results show that the improved IMOGWO algorithm has better convergence and distribution for solving multi-objective problems.

Key words: green job-shop, high dimensional multi-objective, dynamic scheduling, total energy consumption, IMOGWO algorithm