Browse > Article
http://dx.doi.org/10.4313/JKEM.2010.23.11.831

Modeling of PECVD Oxide Film Properties Using Neural Networks  

Lee, Eun-Jin (School of Information, Communications and Electronics Engineering, Catholic University)
Kim, Tae-Seon (School of Information, Communications and Electronics Engineering, Catholic University)
Publication Information
Journal of the Korean Institute of Electrical and Electronic Material Engineers / v.23, no.11, 2010 , pp. 831-836 More about this Journal
Abstract
In this paper, Plasma Enhanced Chemical Vapor Deposition (PECVD) $SiO_2$ film properties are modeled using statistical analysis and neural networks. For systemic analysis, Box-Behnken's 3 factor design of experiments (DOE) with response surface method are used. For characterization, deposited film thickness and film stress are considered as film properties and three process input factors including plasma RF power, flow rate of $N_2O$ gas, and flow rate of 5% $SiH_4$ gas contained at $N_2$ gas are considered for modeling. For film thickness characterization, regression based model showed only 0.71% of root mean squared (RMS) error. Also, for film stress model case, both regression model and neural prediction model showed acceptable RMS error. For sensitivity analysis, compare to conventional fixed mid point based analysis, proposed sensitivity analysis for entire range of interest support more process information to optimize process recipes to satisfy specific film characteristic requirements.
Keywords
PECVD; Oxide film; Neural network; Modeling; Sensitivity analysis;
Citations & Related Records
연도 인용수 순위
  • Reference
1 S. Cho, Y. Kim, Y. Seo, Y. Im, and D. Yoon, J. Kor. Ceram.. Soc. 38 1037 (2001).   과학기술학회마을
2 S. Kim, H. Kim, and K. Lim, Theory and App. Chem. Eng. 8, 5094 (2002).
3 S. Song, Y. Park, and D. Park, Theory and App. Chem. Eng. 9, 2690 (2003).
4 S. Han, M. Ceiler, A. Bidstrup, P. Kohl, and G. May, Trans. IEEE CPMT-Part A 17, 174 (1994).
5 S. Hong, J. Park, and S. Han, J. KIEEME 6, 262 (2005).