Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference (한국전기전자재료학회:학술대회논문집)

The Korean Institute of Electrical and Electronic Material Engineers (한국전기전자재료학회)
권호 표지

Quality prediction method by using ZnO thin film deposition process modeling

ZnO 박막 증착 공정 모델링에 의한 품질 예측 기법

  • Lim, Keun-Young (Wonkwang Univ. School of Electrical Electronic and Information Engineering) ;
  • Chung, Doo-Yeon (Wonkwang Univ. School of Electrical Electronic and Information Engineering) ;
  • Lee, Sang-Keuk (Kwangwoon university) ;
  • Park, Choon-Bae (Wonkwang Univ. School of Electrical Electronic and Information Engineering)
  • 임근영 (원광대학교 전기전자 및 정보공학부) ;
  • 정두연 (원광대학교 전기전자 및 정보공학부) ;
  • 이상극 (광운대학교) ;
  • 박춘배 (원광대학교 전기전자 및 정보공학부)
  • Published : 2006.06.22
Download PDF
⟨ Previous Next ⟩

Abstract

ZnO deposition parameters are not independent and have a nonlinear and complex properties respectively. Therefore, finding optimal process conditions are very difficult and need to do many experiments. To predict ZnO deposition result, neural network was used. To gather training data, Si, GaAs, and Glass were used for substrates, and substrate temperature, work pressure, RF power were $50-500^{\circ}C$, 15 mTorr, and 180-210 W respectively, and the purity of target was ZnO 4N. For predicting the result of ZnO deposition process exactly, sensitivity analysis and drawing a response surface was added. The temperature of substrate was evaluated as a most important variable. As a result, neural network could verify the nonlinear and complex relations of variables and find the optimal process condition for good quality ZnO thin films.

Keywords