DocumentCode :
1462838
Title :
Modeling of Silicon Carbide ECR Etching by Feed-Forward Neural Network and Its Physical Interpretations
Author :
Xia, Jing-Hua ; Rusli ; Kumta, Amit
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
Volume :
38
Issue :
5
fYear :
2010
fDate :
5/1/2010 12:00:00 AM
Firstpage :
1091
Lastpage :
1096
Abstract :
The behavior of electron cyclotron resonance etching of 4H-SiC based on SF6 + O2 plasma is studied using a three-layered feed-forward neural network model trained by the Broyden, Fletcher, Goldfarb, and Shanno optimization algorithm. The etch rate of 4H-SiC is modeled as a function of microwave power, dc bias, process pressure, and O2/(SF6 + O2) flow ratio referred to as the O2 fraction. The results clearly reveal the interaction of the various process parameters and their resultant effects on the etch rate. It is found that, by varying the O2 fraction and process pressure, optimized etch rate peaks can be achieved. Increasing dc bias and microwave power is found to result in the optimized etch rate peaks occurring at higher O2 fraction and process pressure, respectively. In addition, increasing dc bias or microwave power will increase the etch rate. However, there is saturation in the etch rate at higher dc bias, which does not occur with microwave power. Based on these modeling results, detailed physical interpretations of the etching process are given in terms of the chemical reaction of 4H-SiC with F, O, positive ion bombardment, etc.
Keywords :
electronic engineering computing; neural nets; optimisation; oxygen; plasma radiofrequency heating; semiconductor process modelling; silicon compounds; sputter etching; sulphur compounds; wide band gap semiconductors; DC bias; O2; SF6; SiC; electron cyclotron resonance etching; feed forward neural network; microwave power; optimization algorithm; physical interpretations; positive ion bombardment; process parameter; process pressure; Broyden, Fletcher, Goldfarb, and Shanno (BFGS) optimization algorithm; electron cyclotron resonance (ECR); modeling; neural network; plasma etching; silicon carbide;
fLanguage :
English
Journal_Title :
Plasma Science, IEEE Transactions on
Publisher :
ieee
ISSN :
0093-3813
Type :
jour
DOI :
10.1109/TPS.2010.2043858
Filename :
5443535
Link To Document :
بازگشت