Recursive identification for multi-channel Hammerstein systems

This paper considers the recursive identification for multi-channel Hammerstein systems with internal noises and observation noise, where the linear parts are ARX systems. With the help of the correlations of system inputs and output, the recursive algorithms are proposed for estimating unknown coefficients of the linear subsystem, while the system nonlin-earity is recursively estimated by using the kernel functions. Strong consistency of the estimates is proved under reasonable conditions, and a simulation example is provided.