Multi-objective optimization scheduling for manufacturing process based on virtual workflow models

Currently, processing time, energy consumption and processing quality are three significant optimization objectives for manufacturing process. The variety of optimization objectives and the constraints of processes make the production scheduling an NP-hard problem. To improve processing quality, feedback processing is requisite in productive process, but the nonlinearity of feedback process causes further scheduling complexity. The purpose of this research is to realize the multi-objective optimization scheduling of manufacturing process with feedback process. To solve these problems, a virtual workflow modeling method for parallel manufacturing process of manifold varieties of jobs is proposed in this study, and based on the models, a Multi-Objective Virtual Workflow Scheduling Algorithm (MOVWSA) is contributed. In MOVWSA, the genetic evolution based on two-dimensional chromosome coding and weighted elite retention metrics is employed to select processing equipment for processes, and a sequence-selective strategy is proposed to specify processing order and starting time of each process. It is shown from the comparative test results on flexible job shop scheduling benchmark instances (MK01–MK10) that the proposed MOVWSA can provide more dominant static solutions for multi-objective optimization scheduling. The simulation test illustrates that MOVWSA with virtual workflow modeling is capable of dynamically adjusting the processing plans when reprocessing events occur to ensure the stability of processing with makespan and energy consumption. Consequently, the method contributed in this paper achieves the static and dynamic multi-objective optimization scheduling for manufacturing process with nonlinear feedback process by the two mechanisms of virtual modeling and evolutionary optimization.