Fault detection system for the Évora irrigation canal

Louro, Diogo; Mendes, Mário J. G. C.; Valério, Duarte; Costa, José Sá da

http://hdl.handle.net/10400.21/10779

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Fault_MJGCMendes.pdf		2.87 MB	Adobe PDF	Download

Send Feedback

Authors

Louro, Diogo

Mendes, Mário J. G. C.

Valério, Duarte

Costa, José Sá da

Abstract(s)

A model-based fault detection (FD) system was developed for a Simulink simulation of a four pool irrigation canal in ´Evora, Portugal. Incipient and abrupt faults in the gates, the water oﬀ-take valves and the water level sensors were considered. Neural Networks were used to model the canal and ﬁnd the residue. The training algorithm employed for the NNs was found to be an important factor determining the success of the FD system.

Keywords

Fault detection Fault-tolerant systems Control applications Neural networks Irrigation canals

URI

http://hdl.handle.net/10400.21/10779

Citation

LOURO, Diogo; [et al] – Fault detection system for the Évora irrigation canal. IFAC Proceedings Volumes. ISSN 1474-6670. Vol. 45, N.º 20 (2012), pp. 750-755