Nonlinear Time-Varying System Identification Using the NARMAX Model and Multiresolutions Wavelet Expansions
Hua‐Liang Wei, M. Balikhin, Steve A. Billings · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · 2003
Identification techniques for nonlinear time-varying systems are investigated based on the NARMAX model and multiresolution wavelet expansions. It is shown that a NARMAX model with time-varying coefficients can be reduced to a time-invariant linear-in-the-parameters analysis problem by then adapted to estimate the parameters. An application data relating to magnetic storms is used to illustrate the realistic application of the new identification technique.