In this report, we consider the part of our work which concerns the approximation of nonlinear dynamic systems using neural networks. Based on a new paradigm of neurons with local memory (NNLM), we discuss the representation of control systems by neural networks. Using this formulation, the basic issues of controllability and observability for the dynamic system are addressed. A separation principle of learning and control is presented for NNLM, showing that the weights of the network do not affect its dynamics. Theoretical issues concerning local linearization via a coordinate transformation and nonlinear feedback are discussed. For illustration of the approach simulation results for no nonlinear control of an aircraft encountering wind shear on take-off is presented.
Bibliographical noteFunding Information:
*The work of the authors affiliated with the Center for Optimization and Semantic Control was supported in part by AFOSR under Grants No. 890158, F49 620-93-01-0012, and F49 620-96-l-0151. Earlier versions of this work have been reported in references [l-9].
- Dynamic neural networks
- Nonlinear control