Fault detection using neural networks

This paper presents a neural network approach for the problem of sensor failure detection and identification for a flight control system without any sensor redundancy. The problem is solved with the introduction of online learning neural network estimators. The online learning of such a neural network is performed by using the extended backpropagation algorithm, a new method which offers several improvements with respect to the standard backpropagation algorithm.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>