A New Method for Pore Pressure Prediction on Malfunctioning Cells Using Artificial Neural Networks

Embankment rockfill dams are the most common dam construction types used in the world today. One third of all embankment dam failures are caused by dam slope instability. The dam is stable when the slopes are stable. Slope safety of the dam is assessed through pore and total pressure data analysis r...

Full description

Saved in:
Bibliographic Details
Published in:Water resources management 2021-02, Vol.35 (3), p.979-992
Main Authors: Markovic, Milica, Brankovic, Jelena Markovic, Stosovic, Miona Andrejevic, Zivkovic, Srdjan, Brankovic, Bojan
Format: Article
Language:English
Subjects:
Artificial neural networks
Atmospheric Sciences
Cells
Civil Engineering
Dam construction
Dam failure
Dam safety
Dam stability
Dams
Data analysis
Earth and Environmental Science
Earth Sciences
Embankment dams
Embankment stability
Embankments
Environment
Geotechnical Engineering & Applied Earth Sciences
Hydrogeology
Hydrology/Water Resources
Neural networks
Pore pressure
Predictions
Pressure
Pressure measurement
Rockfill dams
Service life
Slope stability
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Embankment rockfill dams are the most common dam construction types used in the world today. One third of all embankment dam failures are caused by dam slope instability. The dam is stable when the slopes are stable. Slope safety of the dam is assessed through pore and total pressure data analysis registered on pressure measurement cells installed in the dam. During the service life of a dam, one or more cells may malfunction after years of operation. Cell replacement implies economically unjustified high costs and is usually technically impossible and high risk. In this paper, the problem of a malfunctioning cell with a small available dataset is analysed. A new method for pore pressure prediction on malfunctioning cells has been developed using several successive artificial neural networks (ANNs) to obtain high accuracy of the predicted values. The results show that these predicted values are more precise than values we could have obtained using only one artificial neural network for prediction.
ISSN:0920-4741
1573-1650
DOI:10.1007/s11269-021-02763-0