Portal de Periódicos da CAPES

Iterative estimation for a non-linear IIR filter with moving average noise by means of the data filtering technique

2015; Oxford University Press; Volume: 34; Issue: 3 Linguagem: Inglês

10.1093/imamci/dnv067

1471-6887

Yanjiao Wang, Feng Ding,

Structural Health Monitoring Techniques

This paper considers the parameter estimation issues of a non-linear infinite impulse response (IIR) filter with moving average noise. The main objective is to present novel iterative estimation methods of a non-linear IIR filter by using the data filtering technique. Firstly, the gradient-based iterative (GI) algorithm is given for a non-linear IIR filter with moving average noise as a comparison. Secondly, a data filtering-based GI algorithm is presented for improving the parameter estimation accuracy. Thirdly, a data filtering-based least squares iterative algorithm is derived for improving the computation efficiency and boosting up the convergence rate. Finally, the simulation results are given to illustrate the performances of the proposed algorithms.