Share Email Print
cover

Proceedings Paper

Modeling the properties of PECVD silicon dioxide films using neural networks
Author(s): Seung-Soo Han; Martin Ceiler; Sue Ann Bidstrup Allen; Paul A. Kohl; Gary Stephen May
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Silicon dioxide films deposited by plasma-enhanced chemical vapor deposition (PECVD) are useful as interlayer dielectric for metal-insulator structures such as MOS integrated circuits and multichip modules. The PECVD for SiO2 in a SiH4/N2O gas mixture yields films with excellent physical properties. However, due to the complex nature of particle dynamics within the plasma, it is difficult to determine the exact nature of the relationship between film properties and controllable deposition conditions. Previous modeling techniques such as first principles or statistical response surface methods are limited in either efficiency or accuracy. In this study, PECVD modeling using neural networks has been introduced. Neural networks have been shown to exhibit superior performance in both accuracy and prediction capability compared to statistical models.

Paper Details

Date Published: 15 February 1994
PDF: 10 pages
Proc. SPIE 2091, Microelectronic Processes, Sensors, and Controls, (15 February 1994); doi: 10.1117/12.167348
Show Author Affiliations
Seung-Soo Han, Georgia Institute of Technology (United States)
Martin Ceiler, Georgia Institute of Technology (United States)
Sue Ann Bidstrup Allen, Georgia Institute of Technology (United States)
Paul A. Kohl, Georgia Institute of Technology (United States)
Gary Stephen May, Georgia Institute of Technology (United States)


Published in SPIE Proceedings Vol. 2091:
Microelectronic Processes, Sensors, and Controls
Kiefer Elliott; John R. Hauser; James A. Bondur; Kiefer Elliott; John R. Hauser; Dim-Lee Kwong; Asit K. Ray; James A. Bondur, Editor(s)

© SPIE. Terms of Use
Back to Top