Improvement of Process Capability Through Neural Networks and Robust Design: A Case Study

摘要

This study applies an integrated method using neural network and robust design methods for im- proving the process capability by optimizing multiple quality characteristics. The neural network is used first to pro- vide a nonlinear relationship between process parameters and the corresponding responses; in doing so, the optimum parameter settings can e obtained. A computerized simulation using Taguchi's approach is then conducted to help the manufacturer identify critical parameters with respect to multiple responses in order to ensure efficient process con- trol. The implementation of this case study is carried out via a polymerization process in a silicon-filter manufacturing factory. The results show the practicality of the proposed approach.