A sampled-data nonlinear filter

The paper describes a method of constructing a general form of nonlinear filter in a digital computer. The filter is easily realised and optimised, and the technique provides for the gathering of the necessary statistical data. The memory part of the filter is based on a sampled-data Laguerre filter chain, which is particularly convenient in the expansion of nonlinear operators. The filter memory can be readily adjusted and auxiliary processing can be included for this purpose. An important relationship between product averages of linear filter outputs is described which is used to give economies in computation. The paper ends with the description of some results obtained in the solution of a nonlinear identification problem.