Optimization and Simulation of Remanufacturing Production Scheduling under Uncertainties

This paper aims to develop a desirable optimization method for the remanufacturing production scheduling under uncertainties. For this purpose, a quality evaluation standard was proposed in light of the two uncertainties, i.e. randomness and ambiguity, of remanufacturing job scheduling. Inspired by the rough set theory and multi-objective approximation sorting algorithm, this evaluation standard can eliminate the redundant information in quality evaluation. On this basis, a remanufacturing production scheduling model was constructed under uncertainties, and solved by a hybrid algorithm developed from the double algorithm, backpropagation (BP) neural network and the genetic algorithm (GA). Simulation results show that the proposed algorithm excels in convergence, and its solution can lead to the minimal scheduling cost and makespan. This algorithm can effectively optimize the scheduling problem of remanufacturing production and processing. The research findings shed new light on the rapid evaluation of recycled resource quality and the optimal scheduling of remanufacturing production.