Skip to main content

Neural network modeling of molecular beam epitaxy

Publication ,  Conference
Lee, KK; Brown, T; Dagnall, G; Bicknell-Tassius, R; Brown, A; May, G
Published in: ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)
January 1, 2000

This paper presents the systematic characterization of the molecular beam epitaxy (MBE) process to quantitatively model the effects of process conditions on film qualities. A five-layer, undoped AlGaAs and InGaAs single quantum well structure grown on a GaAs substrate is designed and fabricated. Six input factors (time and temperature for oxide removal, substrate temperatures for AlGaAs and InGaAs layer growth, beam equivalent pressure of the As source and quantum well interrupt time) are examined by means of a fractional factorial experiment. Defect density, x-ray diffraction, and photoluminescence are characterized by a static response model developed by training back-propagation neural networks. In addition, two novel approaches for characterizing reflection high-energy electron diffraction (RHEED) signals used in the real-time monitoring of MBE are developed. In the first technique, principal component analysis is used to reduce the dimensionality of the RHEED data set, and the reduced RHEED data set is used to train neural nets to model the process responses. A second technique uses neural nets to model RHEED intensity signals as time series, and matches specific RHEED patterns to ambient process conditions. In each case, the neural process models exhibit good agreement with experimental results.

Duke Scholars

Published In

ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)

DOI

ISBN

9780791826614

Publication Date

January 1, 2000

Volume

2000-U

Start / End Page

119 / 127
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Lee, K. K., Brown, T., Dagnall, G., Bicknell-Tassius, R., Brown, A., & May, G. (2000). Neural network modeling of molecular beam epitaxy. In ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE) (Vol. 2000-U, pp. 119–127). https://doi.org/10.1115/IMECE2000-1470
Lee, K. K., T. Brown, G. Dagnall, R. Bicknell-Tassius, A. Brown, and G. May. “Neural network modeling of molecular beam epitaxy.” In ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE), 2000-U:119–27, 2000. https://doi.org/10.1115/IMECE2000-1470.
Lee KK, Brown T, Dagnall G, Bicknell-Tassius R, Brown A, May G. Neural network modeling of molecular beam epitaxy. In: ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE). 2000. p. 119–27.
Lee, K. K., et al. “Neural network modeling of molecular beam epitaxy.” ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE), vol. 2000-U, 2000, pp. 119–27. Scopus, doi:10.1115/IMECE2000-1470.
Lee KK, Brown T, Dagnall G, Bicknell-Tassius R, Brown A, May G. Neural network modeling of molecular beam epitaxy. ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE). 2000. p. 119–127.

Published In

ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)

DOI

ISBN

9780791826614

Publication Date

January 1, 2000

Volume

2000-U

Start / End Page

119 / 127