Fault detection for HDS by means of neural networks: application to two tanks hydraulic system
Résumé
Identification of Hybrid Dynamic System (HDS) is a challenging problem since it involves the estimation of different sets of parameters without knowing in advance which sections of the measured data correspond to the different modes of the system. This paper addresses such identification problem, by focusing the attention on the identification of a global model that predicts the continuous outputs of the HDS. In particular, we propose a methodology that permits to consider the identification of HDS in terms of the architectures and the learning algorithms developed for Feed-Forward neural networks.