ADAPTIVE NOISE CANCELLATION FOR A CLASS OF NONLINEAR IIR FILTERS

A new filter structure known as the NARMAX model (Non-linear Auto Regressive Moving Average model with eXogenous inputs) is introduced as a basis for the design of a class of non-linear filters which can be used for noise cancellation. The new design is an extension of the classical IIR filter, and it is shown that the filter parameters can be estimated by using a suboptimal least squares algorithm originally developed for system identification. Conditions for the convergence of the algorithm are briefly discussed and simulation results are presented which show the effectiveness of the new structure. © 1990.