Title :
Comparison of global nonlinear models and “model-on-demand” estimation applied to identification of a RTP wafer reactor
Author :
Braun, M.W. ; Rivera, D.E. ; Stenman, A. ; Foslien, W.
Author_Institution :
Dept. of Chem. Bio & Mater. Eng., Arizona State Univ., Tempe, AZ, USA
fDate :
6/21/1905 12:00:00 AM
Abstract :
“Model on demand” (MoD) simulation of the temperature dynamics in a simulated rapid thermal processing (RTP) reactor is compared against various types of global models (ARX, semiphysical, combined semiphysical with neural net). The identification data is generated from an m-level pseudo-random sequence input whose parameters are specified systematically using a priori information readily available to the engineer. The MoD estimator outperforms the ARX model and a two semi-physical models, while matching the performance of a combined semi-physical with neural net model. This makes MoD estimation an appealing alternative to global methods because of its reduced engineering effort and simplified a priori knowledge regarding model structure
Keywords :
identification; neural nets; process control; rapid thermal processing; sequences; ARX model; RTP wafer reactor; global models; global nonlinear models; m-level pseudo-random sequence input; model structure; model-on-demand estimation; neural net model; rapid thermal processing wafer reactor; reduced engineering effort; semiphysical model; temperature dynamics; Automatic control; Chemical technology; Inductors; Neural networks; Predictive models; Rapid thermal processing; Semiconductor device modeling; Semiconductor process modeling; State estimation; Systems engineering and theory;
Conference_Titel :
Decision and Control, 1999. Proceedings of the 38th IEEE Conference on
Conference_Location :
Phoenix, AZ
Print_ISBN :
0-7803-5250-5
DOI :
10.1109/CDC.1999.827976
