论文信息 - Comparison of global nonlinear models and "model-on-demand" estimation applied to identification of a RTP wafer reactor

Comparison of global nonlinear models and "model-on-demand" estimation applied to identification of a RTP wafer reactor

"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.

[1] Keith R. Godfrey,et al. Perturbation signals for system identification , 1993 .

[2] Asit K. Ray. RTP temperature control requirement for submicron device fabrication , 1993, Other Conferences.

[3] Urban Forssell,et al. Combining Semi-Physical and Neural Network Modeling: An Example ofIts Usefulness , 1997 .

[4] Fredrik Gustafsson,et al. Just in time models for dynamical systems , 1996, Proceedings of 35th IEEE Conference on Decision and Control.

[5] Dale E. Seborg,et al. Nonlinear Process Control , 1996 .

[6] Daniel E. Rivera,et al. Multi-level pseudo-random signal design and "model-on-demand" estimation applied to nonlinear identification of a RTP wafer reactor , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[7] Peter Lindskog,et al. A System Identification Software Tool for General MISO ARX-Type of Model Structures , 1996 .

[8] A. Stenman. Just-in-Time Models with Applications to Dynamical Systems , 1997 .

[9] P. Lindskog. Methods, Algorithms and Tools for System Identification Based on Prior Knowledge , 1996 .

[10] J. T. C. Lee,et al. A comparison of HDP sources for polysilicon etching , 1996 .

[11] George Cybenko,et al. Just-in-Time Learning and Estimation , 1996 .

[12] H. A. Barker,et al. Design of Pseudo-Random Perturbation Signals for Frequency-Domain Identification of Non linear Systems , 1997 .