Title :
Neural network based adaptive tracking controller for a reactive ion etching system
Author :
Pei, Yubo ; May, Gary S.
Author_Institution :
Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
The theoretical development of a nonlinear adaptive tracking control architecture for reactive ion etching (RIE) systems is presented. This design is based on a dual time scale assumption of RIE dynamics. Two multi-layer feedforward neural networks are employed in this architecture. One is trained off-line to approximately invert the nonlinear dynamics of the etching plant, and the other, which is capable of online learning, is used to dynamically cancel the inversion error. Stability analysis is provided using the Lyapunov method, and a weight adjustment rule for the online learning neural network is derived that, can guarantee closed-loop stability
Keywords :
Lyapunov methods; adaptive control; feedforward neural nets; integrated circuit manufacture; learning systems; neurocontrollers; nonlinear control systems; online operation; process control; sputter etching; stability; tracking; Lyapunov method; VLSI fabrication; closed-loop stability; dual time scale; dynamic inversion error cancellation; etching dynamics; etching plant; multilayer feedforward neural networks; neural network-based adaptive tracking controller; nonlinear adaptive tracking control architecture; nonlinear dynamics inversion; off-line training; online learning; reactive ion etching system; stability analysis; weight adjustment rule; Adaptive control; Adaptive systems; Control systems; Etching; Feedforward neural networks; Multi-layer neural network; Neural networks; Nonlinear control systems; Programmable control; Stability analysis;
Conference_Titel :
American Control Conference, 2001. Proceedings of the 2001
Conference_Location :
Arlington, VA
Print_ISBN :
0-7803-6495-3
DOI :
10.1109/ACC.2001.946019
