Abstract
We describe an automated system for improving yield, power consumption and speed characteristics in the manufacture of semiconductors. Data are continually collected in the form of a history of tool usage, electrical and other real-valued measurements—a dimension of tens of thousands of features. Unique to this approach is the inference of patterns in the form of binary regression rules that demonstrate a significantly higher or lower performance value for tools relative to the overall mean for that manufacturing step. Results are filtered by knowledge-based constraints, increasing the likelihood that empirically validated rules will prove interesting and worth further investigation. This system is currently installed in the IBM 300 mm fab, manufacturing game chips and microprocessors. It has detected numerous opportunities for yield and performance improvement, saving many millions of dollars.
Similar content being viewed by others
References
Goodwin R, Miller R, Tuv E, Borisov A, Janakiram M, Louchheim S (2004) Advancements and applications of statistical learning/data mining in semiconductor manufacturing. Intel Technol J 8(4):325–336
Harding J, Shahbaz M, Srinivas Kusiak A (2006) Data mining in manufacturing: A review. Manuf Sci Engin 128(4):969–976
Melzner H (2002) Statistical modeling and analysis of wafer test fail counts. In: Advanced semiconductor manufacturing 2002 IEEE/SEMI conference and workshop, pp 266–271
Weber C (2004) Yield learning and the sources of profitability in semiconductor manufacturing and process development. IEEE Trans Semicond Manuf 17(4):590–596
Kong G (2004) Tool commonality analysis for yield enhancement. In: Proceedings of IEEE conference and workshop on advanced semiconductor manufacturing, pp 202–205
Chen W, Tseng S, Hsiao K, Liu C (2004) A data mining project for solving low-yield situations of semiconductor manufacturing. In: Proceedings of IEEE conference and workshop on advanced semiconductor manufacturing, pp 129–134
Irani KB, Cheng J, Fayyad UM, Qian Z (1993) Applying machine learning to semiconductor manufacturing. IEEE Expert: Intell Syst Appl 8(1):41–47
Apte C, Weiss S, Grout G (1993) Predicting defects in disk drive manufacturing: A case study in high-dimensional classification. In: IEEE CAIA (93), pp 212–218
Fountain T, Dietterich T, Sudyka B (2000) Mining ic test data to optimize vlsi testing. In: Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 18–25
Campbell S (2007) Fabrication engineering at the micro and nanoscale. Oxford University Press, London
Shahbaz M, Srinivas Harding J (2004) Knowledge extraction from manufacturing process and product databases using association rules. In: Proceedings of conference on product data technology Europe, pp 145–153
Kusiak A (2001) Rough set theory: a data mining tool for semiconductor manufacturing. IEEE Trans Electron Packag Manuf 24(1):44–50
Lian-Yin Z, Li-Pheng K, Sai-Cheong F (2002) Derivation of decision rules for the evaluation of product performance using genetic algorithms and rough set theory. In: Data mining for design and manufacturing: methods and applications. Kluwer Academic, Dordrecht, pp 337–353
Sadoyan H, Zakarian A, Mohanty P (2006) Data mining algorithm for manufacturing process control. Int J Adv Manuf Technol 28(3/4):342–350
Hrycej T, Strobel C (2008) Extraction of maximum support rules for the root cause analysis. Comput Intell Automot Appl 132: 89–99
Chen R, Yeh K, Chang C, Chien H (2006) Using data mining technology to improve manufacturing quality—a case study of lcd driver ic packaging industry. In: Seventh ACIS international conference on software engineering, artificial intelligence, networking, and parallel/distributed computing, pp 115–119
Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth, Belmont
Gardner M, Bieker J (2000) Data mining solves tough semiconductor manufacturing problems. In: Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 376–383
Chien C, Wang W, Cheng J (2007) Data mining for yield enhancement in semiconductor manufacturing and an empirical study. Expert Syst Appl 33(1):192–198
Rokach L (2008) Mining manufacturing data using genetic algorithm-based feature set decomposition. Int J Intell Syst Technol Appl 4(1/2):57–78
Weiss S, Indurkhya N (2001) Solving regression problems with rule-based ensemble classifiers. In: Proceedings of KDD-2001
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Weiss, S.M., Baseman, R.J., Tipu, F. et al. Rule-based data mining for yield improvement in semiconductor manufacturing. Appl Intell 33, 318–329 (2010). https://doi.org/10.1007/s10489-009-0168-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-009-0168-9