Combined use of computational intelligence and materials data for on-line monitoring and control of MBE experiments

This paper describes the combined use of computational intelligence procedu res and materials data for monitoring and controlling the growth of thin fi lms using molecular beam epitaxy (MBE). Given ellipsometry data (Psi and De lta) at a specific wavelength, a genetic algorithm-like method is used to s olve an inverse problem, and estimate values of the complex refractive inde x and the deposition rate. Using a set of such values at different waveleng ths, and combining the use of multiwavelength spectroscopic materials data and computational intelligence procedures, it is then possible to provide a n optimal estimate of the composition of the material being deposited. Cont rol of the film growth is then accomplished through adjustments of cell tem peratures. This procedure is described in this paper, and examples of monit oring and control results are reported for the system of AlxGa1-xAs film on GaAs substrate. (C) 1998 Published by Elsevier Science Ltd. All rights res erved.