Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

An Algorithm Study to Detect Mass Flow Controller Error in Plasma Deposition Equipment Using Artificial Immune System

인공면역체계를 이용한 플라즈마 증착 장비의 유량조절기 오류 검출 실험 연구

  • You, Young Min (Department of Electronics Engineering, Myongji University) ;
  • Jeong, Ji Yoon (Department of Electronics Engineering, Myongji University) ;
  • Ch, Na Hyeon (Department of Electronics Engineering, Myongji University) ;
  • Park, So Eun (Department of Industrial and Management Engineering, Myongji University) ;
  • Hong, Sang Jeen (Department of Electronics Engineering, Myongji University)
  • 유영민 (명지대학교 공과대학 전자공학과) ;
  • 정지윤 (명지대학교 공과대학 전자공학과) ;
  • 조나현 (명지대학교 공과대학 전자공학과) ;
  • 박소은 (명지대학교 공과대학 산업경영공학과) ;
  • 홍상진 (명지대학교 공과대학 전자공학과)
  • Received : 2021.12.06
  • Accepted : 2021.12.16
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Errors in the semiconductor process are generated by a change in the state of the equipment, and errors usually arise when the state of the equipment changes or when parts that make up the equipment have flaws. In this investigation, we anticipated that aging of the mass flow controller in the plasma enhanced chemical vapor deposition SiO2 thin film deposition method caused a minute flow rate shift. In seven cases, fourier transformation infrared film quality analysis of the deposited thin film was used to characterize normal and pathological processes. The plasma condition was monitored using optical emission spectrometry data as the flow rate changed during the procedure. Preprocessing was used to apply the collected OES data to the artificial immune system algorithm, which was then used to process diagnosis. Through comparisons between datasets, the learning algorithm compared classification accuracy and improved the method. It has been confirmed that data characterized as a normal process and abnormal processes with differing flow rates may be discriminated by themselves using the artificial immune system data mining method.

Keywords

Acknowledgement

본 논문은 2021년도 (재)한국과학창의재단 학생연구프로젝트(URP; GID: 20211077103)의 지원으로 수행된 결과임.

References

  1. E. Kim, S. Cho, B. Lee, M. Cho, "Fault Detection an d diagnosis Using Self-Attentive Convolutional Neural Networks for Variable-length Sensor Data in Se-mi conductor Manufacturing", IEEE Trans. Semi. Manuf., Vol. 32, No. 3, pp. 302-309, 2019. https://doi.org/10.1109/tsm.2019.2917521
  2. H. Wang, H. Seo, "Showerhead Surface Temperature Monitoring Method of PECVD Equipment", Journal of the Semiconductor & Display Technology, Vol. 19, No. 2, pp. 16-21, 2020.
  3. H. Park, J. Choi, D. Kim, and S. Hong, "Artificial Immune System for Fault Detection and Classification of Semiconductor Equipment", Electronics, Vol. 10, No. 8, pp. 944-957, 2021. https://doi.org/10.3390/electronics10080944
  4. S. Hong, W. Lim, T. Cheong, G. May, "Fault Detection and Classification in Plasma Etch Equipment for Semiconductor Manufacturing e-Diagnostics", IEEE Trans. Semi. Manuf., Vol. 25, No. 1, pp. 83-93, 2012. https://doi.org/10.1109/TSM.2011.2175394
  5. F. A. Gonzalez, D. Dasgupta, and L. F. Nino, ''A randomized real-valued negative selection algorit-hm,'' in Proc 2nd Int. Conf. Artif. Immune Syst., pp. 261-272, 2003.
  6. Doering, Y. Nishi, "Handbook of Semiconductor Manufacturing Technology", Boca Raton, 2008.
  7. K. Kim, J. Choi, S. Hong, "Surface Properties of ACL Thin Films Depending on Process Conditions", Journal of the Semiconductor & Display Technology, Vol. 18, No. 2, pp. 44-46, 2019.
  8. D. Jang, S. Hong, "In-situ monitoring of multiple oxide/nitride dielectric stack PECVD deposition process", Transactions on Electrical and Electronic Materials, Vol. 19, No. 1, pp. 21-26, 2018. https://doi.org/10.1007/s42341-018-0005-0
  9. A.G. Revesz, "The Role of Hydrogen in SiO2 Films on Silicon", Journal of The Electrochemical Society, Vol. 126, No.1, pp. 122-130, 1979. https://doi.org/10.1149/1.2128967