A novel identification scheme using wavelet networks is presented for nonli
near dynamical systems. Based on fixed wavelet networks, parameter adaptati
on laws are developed using a Lyapunov synthesis approach. This guarantees
rite stability of the overall identification scheme and the convergence of
both the parameters and the state errors, even in the presence of modelling
errors. Using the decomposition and reconstruction techniques of multireso
lution decompositions, variable wavelet networks are introduced to achieve
a desired estimation accuracy and a suitable sized network, and to adapt to
variations of the characteristics and operating points in nonlinear system
s. B-spline wavelets are used to form the wavelet networks and the identifi
cation scheme is illustrated using a simulated example.