Gradient-based Iterative Parameter Estimation for a Finite Impulse Response System with Saturation Nonlinearity

This paper studies the identification problems of a nonlinear finite impulse response system with saturation nonlinearity. Introducing a symbolic function, an over-parameterization gradient-based iterative algorithm is presented for estimating the parameters of the nonlinear system with saturation nonlinearity. In order to enhance the computational efficiency, a gradient-based iterative algorithm and a hierarchical gradient-based iterative algorithm are presented for the nonlinear systems. The computational loads of these algorithms are analyzed and compared.