Acquisition of Dispatching Rules for Job-Shop Scheduling Problem by Artificial Neural Networks Using PSO

Abstract

A Job-shop Scheduling Problem (JSP) constitutes the basic scheduling problem that is observed in manufacturing systems. In conventional JSP, feature values of work and queue times are used to formulate dispatching rules for scheduling. In this paper, an Artificial Neural Network (ANN) is used to create an index for job priority. Furthermore, in order to optimize the output of the ANN, Particle Swarm Optimization (PSO) is used in unsupervised learning of the synaptic weights for the ANN. The functions of the proposed method are discussed in this paper.