Ig. Rosen et al., A neural-network-based approach to determining a robust process recipe forthe plasma-enhanced deposition of silicon nitride thin films, IEEE CON SY, 9(2), 2001, pp. 271-284
We consider the problem of locating a process recipe which produces outputs
which are, in some sense, least sensitive to small fluctuations in the pro
cess condition. Specifically, we determine the most robust process recipe f
or the plasma-enhanced chemical vapor deposition (PECVD) of silicon nitride
thin films having specified optical properties, An appropriate sensitivity
functional describing the relationship between the process inputs and outp
uts and their localized variability is defined in terms of response surface
s and the response surface gradients. Determining the most robust process r
ecipes which produce films with a given refractive index is then formulated
as a constrained minimization problem, The silicon nitride films are chara
cterized by spectroscopic ellipsometry and the requisite response surfaces
are obtained by training feedforward artificial neural networks with availa
ble data. Numerical findings are presented, validated via simulation, and d
iscussed.