Title :
Stochastic analysis of adaptive gradient identification of Wiener-Hammerstein systems for Gaussian inputs
Author :
Bershad, N.J. ; Bouchired, S. ; Castanie, F.
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA
fDate :
2/1/2000 12:00:00 AM
Abstract :
This correspondence investigates the statistical behavior of two adaptive gradient search algorithms for identifying an unknown Wiener-Hammerstein system (WHS) with Gaussian inputs. The first scheme attempts to identify the WHS with an LMS adaptive filter. The LMS algorithm identifies a scaled version of the convolution of the input and output linear filters of the WHS. The second scheme attempts to identify the unknown WHS with a gradient adaptive WHS when the shape of the nonlinearity is known a priori. The mean behavior of the gradient recursions are analyzed when the WHS nonlinearity is modeled by an error function. The mean recursions yield very good agreement with Monte Carlo simulations for slow learning
Keywords :
Gaussian processes; Monte Carlo methods; adaptive filters; gradient methods; identification; least mean squares methods; search problems; Gaussian inputs; LMS adaptive filter; Monte Carlo simulations; Wiener-Hammerstein systems; adaptive gradient identification; adaptive gradient search algorithms; convolution; error function; gradient recursions; input linear filters; nonlinearity; output linear filters; scaled version; statistical behavior; stochastic analysis; Adaptive filters; Convolution; Gaussian noise; Least squares approximation; Nonlinear filters; Nonlinear systems; Parameter estimation; Recursive estimation; Shape; Stochastic systems;
Journal_Title :
Signal Processing, IEEE Transactions on
