Share Email Print

Proceedings Paper

Automated fault detection and classification of etch systems using modular neural networks
Author(s): Sang Jeen Hong; Gary Stephen May; John Yamartino; Andrew Skumanich
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Modular neural networks (MNNs) are investigated as a tool for modeling process behavior and fault detection and classification (FDC) using tool data in plasma etching. Principal component analysis (PCA) is initially employed to reduce the dimensionality of the voluminous multivariate tool data and to establish relationships between the acquired data and the process state. MNNs are subsequently used to identify anomalous process behavior. A gradient-based fuzzy C-means clustering algorithm is implemented to enhance MNN performance. MNNs for eleven individual steps of etch runs are trained with data acquired from baseline, control (acceptable), and perturbed (unacceptable) runs, and then tested with data not used for training. In the fault identification phase, a 0% of false alarm rate for the control runs is achieved.

Paper Details

Date Published: 29 April 2004
PDF: 8 pages
Proc. SPIE 5378, Data Analysis and Modeling for Process Control, (29 April 2004); doi: 10.1117/12.536870
Show Author Affiliations
Sang Jeen Hong, Georgia Institute of Technology (United States)
Gary Stephen May, Georgia Institute of Technology (United States)
John Yamartino, Applied Materials (United States)
Andrew Skumanich, Applied Materials (United States)

Published in SPIE Proceedings Vol. 5378:
Data Analysis and Modeling for Process Control
Kenneth W. Tobin, Editor(s)

© SPIE. Terms of Use
Back to Top