Reactive ion etch modeling using neural networks and simulated annealing

Silicon dioxide films are useful as interlayer dielectrics for integrated circuits and multichip modules (MCM's), and reactive ion etching (RIE) in RF glow discharges is a popular method for forming via holes in SiO/sub 2/ between metal layers of an MCM. However, precise modeling of RIE is difficult due to the extremely complex nature of particle dynamics within a plasma. Recently, empirical RIE models derived from neural networks have been shown to offer advantages in both accuracy and robustness over more traditional statistical approaches. In this paper, a new learning rule for training back-propagation neural networks is introduced and compared to the standard generalized delta rule. This new rule quantifies network memory during training and reduces network disorder gradually over time using an approach similar to simulated annealing. The modified neural networks are used to build models of etch rate, anisotropy, uniformity, and selectivity for SiO/sub 2/ films etched in a chloroform and oxygen plasma. Network training data was obtained from a 2/sup 4/ factorial experiment designed to characterize etch variation with RF power, pressure, and gas composition. Etching took place in a Plasma Therm 700 series RIE system. Excellent agreement between model predictions and measured data was obtained.

[1]  Gary S. May,et al.  Advantages of plasma etch modeling using neural networks over statistical techniques , 1993 .

[2]  H. W. Lehmann,et al.  Mechanism of Dry Etching of Silicon Dioxide A Case of Direct Reactive Ion Etching , 1985 .

[3]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[4]  P. Culicover,et al.  Neural connections, mental computation , 1988 .

[5]  L. M. Loewenstein,et al.  Method for semiconductor process optimization using functional representations of spatial variations and selectivity , 1991, [1991 Proceedings] Eleventh IEEE/CHMT International Electronics Manufacturing Technology Symposium.

[6]  Thomas F. Edgar,et al.  Constructing a reliable neural network model for a plasma etching process using limited experimental data , 1994 .

[7]  George E. P. Box,et al.  Empirical Model‐Building and Response Surfaces , 1988 .

[8]  C. Steinbrüchel,et al.  Etch mechanism in the reactive ion etching of silicon nitride , 1991 .

[9]  C. Spanos,et al.  Statistical experimental design in plasma etch modeling , 1991 .

[10]  Edward A. Rietman,et al.  Use of neural networks in modeling semiconductor manufacturing processes: an example for plasma etch modeling , 1993 .

[11]  D. J. Economou,et al.  Parametric study of a radio‐frequency glow discharge using a continuum model , 1990 .

[12]  C. J. Mogab,et al.  Plasma etching of Si and SiO2—The effect of oxygen additions to CF4 plasmas , 1978 .

[13]  P. E. Riley,et al.  Comparison of etch rates of silicon nitride, silicon dioxide, and polycrystalline silicon upon O2 dilution of CF4 plasmas , 1989 .

[14]  J. Pelletier,et al.  Two-dimensional implications of a purely reactive model for plasma etching , 1991 .

[15]  Terry R. Turner,et al.  Etch process characterization using neural network methodology: a case study , 1992, Other Conferences.