A fuzzy-neural and bi-objective scheduling system for job scheduling in a wafer fabrication factory

Abstract

This paper established a fuzzy-neural and bi-objective scheduling system to improve the performance of job scheduling in a wafer fabrication factory. First, by controlling the standard deviation of cycle time, the fuzzy-neural and bi-objective scheduling system facilitates the rapid assignment of the internal due date. Subsequently, based on a precise cycle time estimation using a fuzzy back propagation network, the system attempts to assign a tight due date if more time is allowed. After the jobs related with an order are released into the wafer fabrication factory, a bi-objective dispatching rule is used to shorten cycle time standard deviation, and at the same time, to ensure on-time delivery, which is distinct from the previous studies because the existing dispatching rules in this field were not designed for such purposes. According to the experimental results, the proposed methodology is better than some existing approaches in both due date assignment and on-time delivery.