Artificial neural networks for the interpretation of piezometric levels at the rock-concrete interface of arch dams. (1st January 2019)

• Record Type: Journal Article
• Authors: de Granrut, M.; Simon, A.; Dias, D.
• Is Part Of: Engineering structures. Volume 178(2019)
• Page Start: 616
• Page End: 634
• Publication Date: 2019-01-01
• Subjects: Arch dam -- Rock/concrete interface -- Neural network -- Data analysis; Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2018.10.033
• Languages: English
• ISSNs: 0141-0296

Abstract

Highlights: A neural network is used to analyse monitored uplift pressures on an arch dam. A sensitivity analysis is used as main criteria during the tuning of the network. This sensitivity analysis permits a thorough physical interpretation of the model. The non additive effects of the external loads on the piezometric levels are shown. The temporal evolution of the rock-concrete interface is highlighted. Abstract: The aperture of the rock-concrete interface of arch dams can be characterised by analysing local piezometric levels. This highly non linear phenomenon involves thresholds effects. Consequently, it is poorly described by additive models such as HST (Hydrostatic, Season, Time), which is the classical multi linear regression model used in dam monitoring to assess the safety of structures. The presented study applies a more flexible statistical method, the Artificial Neural Network (ANN), so as to interpret uplift pressures in a French arch dam, via piezometric measurements. A thorough sensitivity analysis (SA) is performed in order to diagnose the evolution of the aperture of the interface. The originality of this work lies in the proposed methodology used to perform this SA avoiding extrapolation as much as possible, and on the tuning of the network which is implemented with a parametric study that integrates physically interpretable elements, as a supplement to the classical quantitative metrics. ANN turns out to be highly efficient and interpretable when used to study non linear phenomena. Finally, the gain that ANN brings to operational monitoring is discussed.