Fault detection and isolation of inland navigation channel: application to the Cuinchy-Fontinettes reach

摘要

Inland navigation networks are mainly used for\udtransport with economic and environmental benefits. In a\udclimate change context which leads to the scarcity of the water\udresource, the control of navigation levels and the supervision\udof these networks become crucial. Thus, this paper is focused\udon the sensors Fault Detection and Isolation of inland navigation\udreaches. A modeling method based on the identification\udtechnique is proposed. Then, based on residuals, the dynamic\udclassification algorithm AUDyC leads to the detection and\uddiagnosis of sensors faults. Setting errors and slow drifts are\udconsidered. The proposed methods are applied on the Cuinchy-\udFontinettes reach benchmark.