a stable neuro-identifier for nonlinear systems with applications to flexible -link manipulators

this paper present approach for stable identification of multivariable nonlinear system dynamics using artificial neural networks a state -space representation is considered for the neural dentifier both parallel and series -parallel models are presented the method can be considered both as an online identifier that canbe used as a basis for designing neural network controllers as well as an off-line learning scheme for monitoring the system states unlike many other methods the proposed approach does not assume any knowledge of the nonlinearities of the system. the proposed learning rule is a novel approach based on themodifiecation of the backpropagation algorithm.

Keywords:

identificatioin , neural networks , nonlinear systems