A novel neuro-estimator and it's application to parameter estimation in a remotely piloted vehicle

The paper presents a novel neuro-computing approach to the problem of state estimation by means of a hybrid combination of a Hopfield neural network a nd a feedforward multilayer neural net capable to solve certain optimizatio n problems. This neuro-estimator is very appropriate for the real-time impl ementation of nonlinear state estimators, especially when the modeling of u ncertainty is considered in the problem. The proposed estimator is applied to estimate the aerodynamic parameters of a remotely piloted vehicle. Simul ation results show the effectiveness of the proposed method. (C) 2000 Elsev ier Science Ltd; All rights reserved.