Browse > Article

Feature Based Decision Tree Model for Fault Detection and Classification of Semiconductor Process  

Son, Ji-Hun (Department of Information and Industrial Engineering, Yonsei University)
Ko, Jong-Myoung (Department of Information and Industrial Engineering, Yonsei University)
Kim, Chang-Ouk (Department of Information and Industrial Engineering, Yonsei University)
Publication Information
IE interfaces / v.22, no.2, 2009 , pp. 126-134 More about this Journal
Abstract
As product quality and yield are essential factors in semiconductor manufacturing, monitoring the main manufacturing steps is a critical task. For the purpose, FDC(Fault detection and classification) is used for diagnosing fault states in the processes by monitoring data stream collected by equipment sensors. This paper proposes an FDC model based on decision tree which provides if-then classification rules for causal analysis of the processing results. Unlike previous decision tree approaches, we reflect the structural aspect of the data stream to FDC. For this, we segment the data stream into multiple subregions, define structural features for each subregion, and select the features which have high relevance to results of the process and low redundancy to other features. As the result, we can construct simple, but highly accurate FDC model. Experiments using the data stream collected from etching process show that the proposed method is able to classify normal/abnormal states with high accuracy.
Keywords
semiconductor manufacturing; fault detection and classification; decision tree; wrapper based feature selection;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Fayyad, U. M. and Irani, K. B. (1993), Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning, In Proceedings of the 13th International Joint conference on Artificial Intelligence, 1022-1027
2 Guyon, I. and Elisseeff, A. (2003), An introduction to variable and feature selection, Journal of Machine Learning Research, 3, 1157-1182   DOI
3 Quinlan, J. R. (1986), Induction of decision trees, Machine Learning, 1(1), 81-106   ScienceOn
4 Kohavi, R. and John, G. (1997), Wrapper for feature subset selection, Artificial Intelligence, 19(1-2), 273-324
5 Lada, E. E., Lu, J-C., and Wilson, J. R. (2002), A Wavelet-Based Procedure for Process Fault, IEEE Transactions on Semiconductor Manufacturing, 15(1), 79-90   DOI   ScienceOn
6 Irani, K. B., Cheng, J., Fayyad, U. M., and Qian, Z. (1993), Applying machine learning to semiconductor manufacturing, IEEE Intelligent Systems and Their Applications, 8(1), 41-47   DOI   ScienceOn
7 Guo, H.-F., Spanos, C. J., and Miller, A. J. (1991), Real time statistical process control for plasma etching, In Proceedings of IEEE/SEMI International Semiconductor Manufacturing Science Symposium, 113-118   DOI
8 Choi, J. Y., Ko, J. M., Kim, C. O., Kang, Y. S., and Lee, S. J. (2007), Process start/end event detection and dynamic time warping algorithms for runby-run process fault detection, In Proceedings of International Symposium on Semiconductor Manufacturing, 1-4   DOI
9 Cherry, G. and Qin, S. J. (2006), Multiblock principal component analysis based on a combined index for semiconductor fault detection and diagnosis, IEEE Transactions on Semiconductor Manufacturing, 19(2), 159-172   DOI   ScienceOn
10 Goodlin, B. E., Boning, D. S., Sawin, H. H., and Wise, B. M. (2003), imultaneous Fault Detection and Classification for Semiconductor Manufacturing Tools, Journal of Electrochemical Society, 150(12), 778-784   DOI   ScienceOn
11 Salvador, S., Chan, P., Brodie, J. (2004), Learning States and Rules for Time Series Anomaly Detection. In Proceedings of the 17th International Florida Artificial Intelligence Research Symposium
12 Baek, J. G., Kim, C. O., and Kim, S. S. (2002), Online learing of the cause-and-effect knowledge of a manufacturing process, International Journal of Production Research, 40(14), 3275-3290   DOI   ScienceOn
13 Dunia, R., Qin, S. J., Edgar, T. F., and McAvoy, T. J. (1996), Identification of faulty sensors using principal component analysis, AIChE Journal, 42(10), 2797-2812   DOI   ScienceOn