Abstract
Modern system identification theory basically deals with the problem of the efficient extraction of system dynamic properties based on available data measurements. Once one has a parameterized mathematical model, the actual parameter value determination and the estimation of the system variables appear as the two most important issues to be faced. Furthermore, if the two previous estimations have to be performed simultaneously, the model does not exactly describe the system and the measurements are realized in noisy environments; then we have a combined estimation problem that incorporates some very interesting and nontrivial difficulties, especially for NLS: singularities and effects of uncertainties. The problem of simultaneous state and parameter estimation for multi-input multi-output nonlinear systems (MIMO NLS) under mixed uncertainties (unmodelled dynamics as well as observation noises) is tackled.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have