A Methodology for Predictive Maintenance in Semiconductor Manufacturing


  • Peter Scheibelhofer ams AG, Unterpremstätten, Austria Institute of Statistics, Graz University of Technology, Austria
  • Dietmar Gleispach ams AG, Unterpremstätten, Austria
  • Günter Hayderer ams AG, Unterpremstätten, Austria
  • Ernst Stadlober Institute of Statistics, Graz University of Technology, Austria




In order to occupy a competitive position in semiconductor industry the most important challenges a fabrication plant has to face are the reduction of manufacturing costs and the increase of production yield. Predictive maintenance is one possible way to address these challenges. In this paper we present an implementation of a universally applicable methodology based on the theory of regression trees and Random Forests to predict tool maintenance operations. We exemplarily show the application of the method by constructing a model for predictive maintenance of an ion implantation tool. To fit the
problem adequately and to allow a descriptive interpretation we introduce the remaining time until next maintenance as a response variable. By using R and adequately analyzing data acquired during wafer processing a Random Forest model is constructed. We can show that under typical production conditions
the model is able to predict a recurring maintenance operation sufficiently accurate. This example shows that better planning of maintenance operations allows for an increase in productivity and a reduction of downtime costs.


Berk, R. A. (2008). Statistical Learning from a Regression Perspective. Springer, New York.

Breiman, L. (1996). Bagging predictors. Machine Learning, 24, 123-140.

Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32.

Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. (1984). Classification and Regression Trees. Wadsworth, California.

Efron, B. (1979). Bootstrap methods: another look at the jackknife. The Annals of Statistics, 7, 1-26.

Hastie, T., Tibshirani, R., and Friedman, J. (2001). The Elements of Statistical Learning. Springer, New York.

Hothorn, T., Hornik, K., and Zeileis, A. (2006). Unbiased recursive partitioning: a conditional inference framework. Journal of Computational and Graphical Statistics, 15, 651-674.

Hothorn, T., and Zeileis, A. (2012). partykit; a toolkit for recursive partitioning [Computer software manual]. Available from http://CRAN.R-project.org/ package=partykit (R package version 0.1-3)

Liaw, A., andWiener, M. (2002). Classification and regression by randomForest. R News, 2, 18-22.

Meinshausen, N. (2006). Quantile regression forests. Journal of Machine Learning Research, 7, 983-999.

R Development Core Team. (2011). R: A language and environment for statistical computing [Computer software manual]. Vienna, Austria. Available from http://www.R-project.org/ (ISBN 3-900051-07-0)

Sandri, M., and Zuccolotto, P. (2006). Variable selection using random forests. In S. Zani, A. Cerioli, M. Riani, and M. Vichi (Eds.), Data Analysis, Classification and the Forward Search. Proceedings of the Meeting of the Classification and Data Analysis Group (CLADAG) of the Italian Statistical Society, University of Parma, June 6-8, 2005. Springer, Berlin.

Scheibelhofer, P. (2011). Tree-based Methods for Predictive Failure Detection in Semiconductor Fabrication. Unpublished master’s thesis, Institute of Statistics, Graz University of Technology.

Schellenberger, M., Roeder, G., Mattes, A., Pfeffer, M., Pfitzner, L., Knapp, A., et al. (2011). Developing a framework for virtual metrology and predictive maintenance. Future Fab International, 39, 32-37.

Therneau, T. M., and J., A. E. (1997). An introduction to recursive partitioning using the rpart routines (Tech. Rep. No. 61). Department of Health Science Research, Mayo Clinic, Rochester.

Wolf, S. (2003). Microchip Manufacturing. Lattice Press, Sunset Beach.



How to Cite

Scheibelhofer, P., Gleispach, D., Hayderer, G., & Stadlober, E. (2016). A Methodology for Predictive Maintenance in Semiconductor Manufacturing. Austrian Journal of Statistics, 41(3), 161–173. https://doi.org/10.17713/ajs.v41i3.171