Data Filtering Based Maximum Likelihood Gradient Method for Multivariable Nonlinear Systems

Aiming at the problem of redundant parameters in the over-parameterized model, a maximum likelihood algorithm for a class of multi-input nonlinear systems is studied based on the data filtering technique. This paper develops a filtering based maximum likelihood generalized extended gradient algorithm for multivariable nonlinear systems with autoregressive moving average noises and a maximum likelihood generalized extended gradient algorithm for comparison. Finally, the simulation results indicate that the derived algorithms are more effective for identifying multivariable nonlinear systems.