Wafer Lot Output Time Prediction with a Hybrid Artificial Neural Network

To further enhance the accuracy of lot output time prediction in a wafer fab (fabrication plant), a hybrid artificial neural network is proposed in this study. At first, the concept of input classification is applied to Chen’s fuzzy back propagation network (FBPN) by pre-classifying input examples with the self-organization map (SOM) classifier before they are fed into the FBPN. Then, examples belonging to different categories are learned with the same FBPN but with different parameter values. Production simulation is also applied in this study to generate test examples. According to experimental results, the prediction accuracy of the proposed methodology was significantly better than those of three existing approaches, FBPN without example classification, case-based reasoning (CBR), and evolving fuzzy rules (EFR), in most cases by achieving a 15%~45% (and an average of 31%) reduction in the root-mean-squared-error (RMSE). Key-Words: Wafer fab; Output time prediction; Self-organization map; Fuzzy back propagation network