Symbolic Computations in Volterra System Identification

This paper is concerned with symbolic computations in Volterra system identification using higher order cumulants. An efficient method that implements the Leonov-Shiryaev theorem is introduced. The proposed method relies on the exploitation of recursive relations between cumulants. The method is applied on the problem of blind identification of Volterra-Hammerstein systems excited by stationary higher order white noise. It solves previously intractable instances