Identification of time-varying system with wavelet based approach using multiple wavelet basis functions

摘要

Identification problem of time varying system can be solved by conventional recursive estimation approach and wavelet based recursive estimation approach. In Wavelet based recursive estimation approach each time varying parameter is approximated by using multi-wavelet basis functions. The identification problem is then converted into time invariant system identification problem which can be solved by regression selection and parameter estimation using block LMS algorithm. This approach gives improved tracking performance for rapidly varying systems as compared to conventional recursive estimation approach by using LMS algorithm.