Silicon carbide (SiC) was etched in a inductively coupled plasma. The etch process was modeled by using a neural network called generalized regression neural network (GRNN). For modeling, the process was characterized by a full factorial experiment with one center point. To test model appropriateness, additional test data of 16 experiments were conducted. The GRNN prediction performance was optimized by means of a genetic algorithm (GA). Compared to a conventional GRNN model, the GA-GRNN model demonstrated a significant improvement of more than 85%. Predicted model behaviors were highly consistent with actual measurements. From the GA-optimized model, several plots were predicted to examine etch mechanisms. The model predicted that parameter effects are a complex function of plasma conditions. The etch rate was strongly correlated to the variations in the pressure-induced dc bias. This was also illustrated for the variations in the gas ratio.
Skip Nav Destination
Article navigation
November 2004
Research Article|
November 01 2004
Prediction of SiC etching in a plasma using neural network
Byungwhan Kim;
Byungwhan Kim
a)
Department of Electronic Engineering
, Bio Engineering Research Center, Sejong University 98, Goonja-Dong, Kwangjin-Gu, Seoul, 143-747, Korea
Search for other works by this author on:
Byung Teak Lee
Byung Teak Lee
Department of Materials Science and Engineering
, Chonnam National University 300, Yongbong-Dong, Buk-Ku, Kwangju-Si, 500-757, Korea
Search for other works by this author on:
a)
Electronic mail: [email protected]
J. Vac. Sci. Technol. A 22, 2517–2522 (2004)
Article history
Received:
May 27 2004
Accepted:
September 07 2004
Citation
Byungwhan Kim, Byung Teak Lee; Prediction of SiC etching in a plasma using neural network. J. Vac. Sci. Technol. A 1 November 2004; 22 (6): 2517–2522. https://doi.org/10.1116/1.1810169
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
Low-temperature etching of silicon oxide and silicon nitride with hydrogen fluoride
Thorsten Lill, Mingmei Wang, et al.
Atomic layer deposition of nanofilms on porous polymer substrates: Strategies for success
Brian C. Welch, Jeanne Casetta, et al.
Surface passivation approaches for silicon, germanium, and III–V semiconductors
Roel J. Theeuwes, Wilhelmus M. M. Kessels, et al.
Related Content
Prediction of silicon oxynitride plasma etching using a generalized regression neural network
J. Appl. Phys. (August 2005)
Modeling SiC surface roughness using neural network and atomic force microscopy
J. Vac. Sci. Technol. B (October 2004)
Forecasting of heavy metal distribution based on co-kriging and generalized regression neural network with co-elements concentration as input data
AIP Conference Proceedings (July 2018)
Modeling of surface dust concentrations using neural networks and kriging
AIP Conference Proceedings (December 2016)
Forecasting of chromium distribution in subarctic noyabrsk using generalized regression neural networks and multilayer perceptron
AIP Conference Proceedings (July 2018)