Abstract This paper introduces a design procedure for detemunation of weight matrices of an MLP-based controller to locally stabilize a class of multi-input nonlineaz systems consisting of a lineaz system together with a nonlineaz saturated actuator with or without hysteresis. No assumption is made on the stability of the open-loop system. Two different design problems aze considered: 1) designing a neural network which maximizes the guazanteed domain of stability of the overall system when the actuator bounds aze given, and 2) designing a neural network which guazantees the stability of the overall system in apre-specified region in state-space with a minimum actuator bound. The proposed controller has excellent advantage over the classical ones, regazding its guaranteed domain of stability. The design procedure replaces eazlier recursive neural network learning algorithms with a simple optimization problem.
[1]
Tingshu Hu,et al.
Stabilization of LTI systems with planar anti-stable dynamics using saturated linear feedback
,
1998,
Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).
[2]
Zongli Lin,et al.
Semi-global exponential stabilization of linear discrete-time systems subject to input saturation via linear feedbacks
,
1995
.
[3]
M. Vidyasagar,et al.
Nonlinear systems analysis (2nd ed.)
,
1993
.
[4]
Frank L. Lewis,et al.
Multilayer neural-net robot controller with guaranteed tracking performance
,
1996,
IEEE Trans. Neural Networks.