This paper explores the use of neural networks for real-time, model-based f
eedback control of reactive ion etching (RIE). This objective is accomplish
ed in part by constructing a predictive model for the system that ran be ap
proximately inverted to achieve the desired control. An indirect adaptive c
ontrol (IAC) strategy is pursued. The IAC structure includes a controller a
nd plant emulator, which are implemented as two separate back-propagation n
eural networks. These components facilitate nonlinear system identification
and control, respectively. The neural network controller is applied to con
trolling the etch rate of a GaAs/AlGaAs metal-semiconductor-metal (MSM) str
ucture in a BCl3/Cl-2 plasma using a Plasma Therm 700 SLR series RIE system
, Results indicate that in the presence of disturbances and shifts in RIE p
erformance, the IAC neural controller is able to adjust the recipe to match
the etch rate to that of the target value in less than 5 s. These results
are shown to be superior to those of a more conventional control scheme usi
ng the linear quadratic Gaussian method with loop-transfer recovery, which
is based on a linearized transfer function model of the RIE system.