CASE-STUDIES ON MODELING MANUFACTURING PROCESSES USING ARTIFICIAL NEURAL NETWORKS

The modeling capability of an artificial neural network is studied thr ough three different manufacturing processes. The first case study is a linear separable pattern classification problem in manufacturing pro cess diagnosis. The performance between the neural network and the pro bability voting classifier is compared. The second case study uses a d esign of experiment to study an SMC compression molding process. Model ing and predicting performances between a regression model and a neura l network model are compared in linear as well as nonlinear cases. The third case study investigates correlation models between the operatin g conditions and product quality defects of an automotive painting pro cess. Results from a neural network model are compared with those of a probability voting classifier. An ad hoc modification named focused l earning paradigm on the back-propagation algorithm is also introduced to speed up network learning.