A hybrid SOM-BPN approach to lot output time prediction in a wafer fab

Tin-Chih Chen*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

61 Scopus citations


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.

Original languageEnglish
Pages (from-to)271-288
Number of pages18
JournalNeural Processing Letters
Issue number3
StatePublished - 1 Dec 2006


  • Back propagation network
  • Hybrid approach
  • Output time prediction
  • Self-organization map
  • Wafer fab

Fingerprint Dive into the research topics of 'A hybrid SOM-BPN approach to lot output time prediction in a wafer fab'. Together they form a unique fingerprint.

Cite this