반도체디스플레이기술학회지 (Journal of the Semiconductor & Display Technology)

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

Neural Network-based Time Series Modeling of Optical Emission Spectroscopy Data for Fault Prediction in Reactive Ion Etching

  • Sang Jeen Hong (Department of Semiconductor Engineering, Myongji University)
  • 투고 : 2023.11.30
  • 심사 : 2023.12.18
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Neural network-based time series models called time series neural networks (TSNNs) are trained by the error backpropagation algorithm and used to predict process shifts of parameters such as gas flow, RF power, and chamber pressure in reactive ion etching (RIE). The training data consists of process conditions, as well as principal components (PCs) of optical emission spectroscopy (OES) data collected in-situ. Data are generated during the etching of benzocyclobutene (BCB) in a SF6/O2 plasma. Combinations of baseline and faulty responses for each process parameter are simulated, and a moving average of TSNN predictions successfully identifies process shifts in the recipe parameters for various degrees of faults.

키워드

과제정보

This work was supported by Korean Evaluation Institute of Industrial Technology (G01002665681).

참고문헌

  1. D. Montgomery, Introduction to Statistical Quality Control, New York: John Wiley & Sons, Inc., 3rd Ed. 1997.
  2. M. Baker, C. Himmel, and G. May, "Time Series Modeling of Reactive Ion Etching Using Neural Networks," IEEE Trans. Semi. Manufac., vol. 8, no. 1, pp. 62-71, Feb., 1995. https://doi.org/10.1109/66.350758
  3. D. Kim, S. J. Hong, "Use of Plasma Information in Machine-Learning-Based Fault Detection and Classification for Advanced Process Control," IEEE Trans. Semi. Manufac. vol. 34, no. 3, pp. 408-419, Aug., 2021. https://doi.org/10.1109/TSM.2021.3079211
  4. J. E. Choi, H. Park, Y. H. Lee, and S. J. Hong, "Virtual Metrology for Etch Profile in Silicon Trench Etching with SF6/O2/Ar Plasma, IEEE Trans. Semi. Manufac. vol. 35, no. 35, pp. 128-137, Feb., 2022. https://doi.org/10.1109/TSM.2021.3138918
  5. A. A. Nuhu, Q. Zeeshan, B. Safaei, and M. A. Shahzad, "Machine Learning-based Techniques for Fault Diagnosis in the Semiconductor Manufacturing Process: A Comparative Study," The Journal of Supercomputing, vol. 79, pp. 2031-2081, Feb., 2023. https://doi.org/10.1007/s11227-022-04730-x
  6. B. Roger, M. Berry, I. Turlik, P. Garrow and D. Castillo, "Soft Mask for Via Patterning in Benzocyclobutene," Int. J. Micro. and Elect. Packaging, vol 17, no. 3, pp. 210-218, 3rd Quarter, 1994.
  7. D. White, D. Boning, S. Butler and G. Barna, "Spatial Characterization of Wafer State Using Principal Component Analysis of Optical Emissions Spectra in Plasma Etch," IEEE Trans. Semi. Manufac., vol. 10, no. 1, Feb., 1997.
  8. S. Hong and G. May, "Neural Network Modeling of Reactive Ion Etching Using Principal Component Analysis of Optical Emission Spectroscopy Data," IEEE/SEMI Adv. Semi Manufac. Conf., Boston, MA, pp. 415-420, April 2002.
  9. G. May, "Manufacturing ICs the Neural Way," IEEE Spectrum, pp.47-51, Sept. 1994.