Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·
 

Artificial intelligence and finite element modelling for monitoring flood defence structures

Publication files not online:

Author: Pyayt, A.L. · Mokhov, I.I. · Kozionov, A. · Kusherbaeva, V. · Melnikova, N.B. · Krzhizhanovskaya, V.V. · Meijer, R.J.
Type:article
Date:2011
Source:2011 3rd IEEE Workshop on Environmental, Energy, and Structural Monitoring Systems, EESMS 2011, 28 September 2011, Milan, Italy, 34-40
Identifier: 442935
doi: doi:10.1109/EESMS.2011.6067047
Keywords: Informatics · Anomaly detection · Machine learning methods · UrbanFlood project · Virtual Dike · Dikes · Levees · Safety and Security · Defence, Safety and Security · Communication & Information · BIS - Business Information Services · TS - Technical Sciences

Abstract

We present a hybrid approach to monitoring the stability of flood defence structures equipped with sensors. This approach combines the finite element modelling with the artificial intelligence for real-time signal processing and anomaly detection. This combined method has been developed for the UrbanFlood early warning system and successfully tested on a large-scale sea dike during a simulated strong storm with very high water level. The artificial intelligence module detects the onset of dike instability after being trained on the data from the Virtual Dike finite element simulation. © 2011 IEEE.