A Hybrid SOM-BPN Approach to Lot Output Time Prediction in a Wafer Fab

Authors:
Toly Chen
Affiliations:
Department of Industrial Engineering and System Management, Feng Chia University, Taichung, Taiwan, R. O. C. 407
Venue:
Neural Processing Letters
Year:
2006

Citing 3
Cited 8

A hybrid neural network model in handwritten word recognition

Neural Networks
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
SOM Ensemble-Based Image Segmentation

Neural Processing Letters

Incorporating fuzzy c-means and a back-propagation network ensemble to job completion time prediction in a semiconductor fabrication factory

Fuzzy Sets and Systems
An intelligent mechanism for lot output time prediction and achievability evaluation in a wafer fab

Computers and Industrial Engineering
A hybrid intelligent approach for output projection in a semiconductor fabrication plant

Intelligent Data Analysis
A fuzzy-neural and multiple-bucket approach for estimating lot cycle time in a wafer fab with dynamic product mix

Computers and Industrial Engineering
A hybrid fuzzy-neural approach to job completion time prediction in a semiconductor fabrication factory

Neurocomputing
A fuzzy back propagation network ensemble with example classification for lot output time prediction in a wafer fab

Applied Soft Computing
Fuzzy-neural approaches with example post-classification for estimating job cycle time in a wafer fab

Applied Soft Computing
A Fuzzy Fluctuation Smoothing Rule for Job Dispatching in a Wafer Fabrication Factory: A Simulation Study

International Journal of Fuzzy System Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Output time prediction is a critical task to a wafer fab (fabrication plant). To further enhance the accuracy of wafer lot output time prediction, the concept of input classification is applied to the back propagation network (BPN) approach in this study by pre-classifying input examples with the self-organization map (SOM) classifier before they are fed into the BPN. Examples belonging to different categories are then learned with different BPNs but with the same topology. 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, case-based reasoning (CBR), BPN without example classification, and evolving fuzzy rules (EFR), in most cases by achieving a 13---46% (and an average of 30%) reduction in the root-mean-squared-error (RMSE) over the comparison basis --- BPN without example classification.