Neural network and genetic algorithm-based hybrid approach to dynamic job shop scheduling problem

Abstract

In this paper, we analyze the characteristics of the dynamic job shop scheduling problem when machine breakdown and new job arrivals occur. A hybrid approach involving neural networks(NNs) and genetic algorithm(GA) is presented to solve the dynamic job shop scheduling problem as a static scheduling problem. The objective of this kind of job shop scheduling problem is minimizing the completion time of all the jobs, called the makespan, subject to the constraints. The result shows that the hybrid methodology which has been successfully applied to the static shop scheduling problems can be also applied to solve the dynamic shop scheduling problem efficiency.