Fuzzy control for nonlinear systems modeled via neural-network
Zhen‐Yuan Chen, Cheng‐Wu Chen, Wei-Ling Chiang, Jiing-Don Huang · 2003
It is known that backpropagation networks are always used for modeling. This study is concerned with the stability problem of a neural network (NN) system which consists of a few subsystems represented by NN models. In this paper, the dynamics of each NN model is converted into a linear inclusion representation. Subsequently, based on the representations, the stability conditions in terms of Lyapunov's direct method are derived to guarantee the stability of nonlinear systems. Finally, a numerical example with simulations is given to illustrate the results.