Robust adaptive filtering using evolutionary algorithm-based parameter estimation

We develop effective algorithms for simultaneous robust adaptive filtering/control and unknown parameter estimation. The need for adaptive control of poorly known systems is recognized in a diverse range of applications. Due to the nonlinear dependency of the problem on the unknown parameters, an exact solution to this problem is not known to date. The approach discussed here uses a robust adaptive filtering/control algorithm to fulfill the control objectives while a structured global search algorithm based on an evolutionary algorithm identifies the unknown (possibly changing) parameters. Casting the nonlinear parameter estimation problem as an optimization problem, this approach overcomes the unnecessary approximations that are commonly adopted in the existing solutions. At the same time the robustness of the adaptive control algorithm is not compromised since the adaptation criterion used in this algorithm accounts for the uncertainty in parameter estimation as well as the exogenous perturbation signals that are often used to assist parameter estimation.