Abstract:

：Numerous studies indicated that amount of energy is consumed by machining job shops. Hence reducing the energy consumption of machining job shops is one of the strategies for sustainable manufacturing. The existing researches of scheduling method considering energy consumption for machining job shops focus on constant or partly flexible process plan, and the study considering multi flexibilities of process plan is scarce. A scheduling method for reducing energy consumption of machining job shops considering the flexible process plan is proposed which considers the influence that flexible process plan have on energy consumption. Based on the analysis of energy consumption characteristics of flexible process plan-oriented task scheduling, a mathematical model of task scheduling problem is formulated. The optimal objects of the model include total energy consumption of task, makespan and workload of machine. The Q-learning algorithm is improved to find the Pareto optimal solution of the multi-objective mathematical model. Finally, the experimental results indicate that the proposed model has energy saving potential and improved Q-learning algorithm is feasible.

Key words: energy consumption, improved Q-learning algorithm, pareto multi-object optimization, flexible process plan