A neural-network-based approach to determining a robust process recipe forthe plasma-enhanced deposition of silicon nitride thin films

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.