USING NEURAL NETWORKS TO DETERMINE INTERNALLY-SET DUE-DATE ASSIGNMENTS FOR SHOP SCHEDULING

The production control system for a shop can be viewed as consisting o f three sequential stages, the order-promising stage, the order-releas e stage, and the dispatching (or shop floor) stage. The first stage, w herein a customer's job arrives and is assigned a due date, provides t he focus for this research. In particular, the performance of six regr ession-based due-date assignment rules found in the literature is comp ared with due dates determined by a neural network. The purpose is to see whether neural networks hold any promise for application in this a rea. For the particular shop and the conditions studied, it is found t hat the neural network outperforms all six conventional rules accordin g to mean-absolute-deviation (MAD) and standard-deviation-of-lateness (SDL) criteria, although for one rule on the latter criterion, the dif ference is not statistically significant. Further analysis indicates t hat this conclusion generally holds both when the amount of data avail able is varied and a second, more structured shop is studied. On a thi rd shop with random routings, the neural network outperforms the best conventional method according to the MAD measure, but results are mixe d for the SDL criterion. The superior performance of the neural networ k leads us also to evaluate a regression model nonlinear in its indepe ndent variables, a case not considered in the due-date literature. The nonlinear model generally outperforms the conventional rules on MAD a nd SDL. The neural network outperforms the nonlinear model on MAD, whi le the results for SDL are not as clear.