A hybrid computer simulation-adaptive neuro-fuzzy inference system algorithm for optimization of dispatching rule selection in job shop scheduling problems under uncertainty

Abstract

Unstable environment of industrial systems is a source of various uncertainties in production features such as processing times. Moreover, selecting appropriate dispatching rules is a complex and significant issue in practical problems under uncertainty. Most previous studies have pointed out that using a single dispatching rule does not necessarily result in an optimal schedule. This study proposes a novel hybrid algorithm based on computer simulation and adaptive neuro-fuzzy inference system (ANFIS) to select optimal dispatching rule for each machine in job shop scheduling problems (JSSPs) under uncertain conditions so that makespan is minimized. It captures uncertainty using fuzzy set theory and assumes that processing times are in the form of fuzzy numbers. This algorithm contributes to the previous works in two important ways. First, the inherent uncertainty of JSSPs is reflected in fuzzy processing times. Second, this is the first study that develops an approach based on computer simulation and ANFIS for selecting the optimal dispatching rules and minimizing the makespan in JSSPs under uncertainty. The computational results demonstrate the superiority of this algorithm over the previous studies in the literature.