Adaptive filtering algorithms are investigated when system models are subject to model structure errors and regressor signal perturbations. System models for practical applications are often approximations of high-ord...Adaptive filtering algorithms are investigated when system models are subject to model structure errors and regressor signal perturbations. System models for practical applications are often approximations of high-order or nonlinear systems, introducing model structure uncertainties. Measurement and actuation errors cause signal perturbations, which in turn lead to uncertainties in regressors of adaptive filtering algorithms. Employing ordinary differential equation （ODE） methodologies, we show that convergence properties and estimation bias can be characterized by certain differential inclusions. Conditions to ensure algorithm convergence and bounds on estimation bias are derived. These findings yield better understanding of the robustness of adaptive algorithms against structural and signal uncertainties.展开更多
基金The research of B. G. Fitzpatrck was partly supported by the Joint Technology Office and the Air Force Office of Scientific Research through the Multidisciplinary Research Initiative (No. F49620-02-1-0319)the Air Force Office of Scientific Research (No. FA9550-09-1-0524)+2 种基金The research of G. Yin was partly supported by the Air Force Office of Scientific Research (No. FA9550-10-1-0210)partly by the Natural Science Foundation of China (No. 70871055)The research of L. Wang was partly by supported by the Air Force Office of Scientific Research (No. FA9550-10-1-0210)
文摘Adaptive filtering algorithms are investigated when system models are subject to model structure errors and regressor signal perturbations. System models for practical applications are often approximations of high-order or nonlinear systems, introducing model structure uncertainties. Measurement and actuation errors cause signal perturbations, which in turn lead to uncertainties in regressors of adaptive filtering algorithms. Employing ordinary differential equation （ODE） methodologies, we show that convergence properties and estimation bias can be characterized by certain differential inclusions. Conditions to ensure algorithm convergence and bounds on estimation bias are derived. These findings yield better understanding of the robustness of adaptive algorithms against structural and signal uncertainties.
