Parameter Estimation Techniques for Nonlinear Systems
1982; Elsevier BV; Volume: 15; Issue: 4 Linguagem: Inglês
10.1016/s1474-6670(17)63039-8
ISSN2589-3653
AutoresS.A. Billings, I. J. LEONTARITIS,
Tópico(s)Advanced Control Systems Optimization
ResumoThe identification of nonlinear systems using parameter estimation methods based on input-output models is considered. A nonlinear difference equation representation for a wide class of nonlinear systems is introduced by considering the observability of nonlinear systems and extending the classical autoregressive moving average model to include polynomic terms. The effects of internal noise are investigated and modified recursive extended least squares and maximum likelihood algorithms are derived and shown to produce unbiased estimates in the presence of multiplicative noise.
Referência(s)