Modélisation de L’affouillement de Pont par Réseaux de Neurones Artificiels basé sur l’ACP.
Abstract
Abstract: The present study aims at modeling the scour depth around circular bridge piers in Algeria (semi-arid zones) by Artificial Neural Networks (neuroemulation). In the pretreatment phase, the reduction of the dimensionality of the inputs to the neuronal model is performed by the classical linear method: Principal Component Analysis (PCA). The results obtained for this type of data showed that PCA provides very powerful models.
Résumé : La présente étude a pour objet la modélisation de la profondeur d’affouillement autour des piles de pont circulaires en Algérie (Zones semi-arides) par Réseaux de Neurone Artificiels (neuro- émulation). A la phase de prétraitement, la réduction de la dimensionnalité des entrées au modèle neuronal est effectuée par la méthode classique linéaire : l’analyse en composantes principales (ACP). Les résultats obtenus pour ce type de données ont montré que l’ACP fourni des modèles très performants.
Full Text:
PDFReferences
Abrahart, RJ.; Mount, NJ.; Shamseldin, AY. Neuroemulation: definition and key benefits for water resources research. Hydrological Sciences Journal 57(3) (2012) 407-23.
Choi, SU. ; Cheong, SH. Prediction of local scour around bridge piers using artificial neural networks. The Journal of the American Water Resources Association 42 (2) (2006) 487–94.
Deng, L.; Cai, C.S. Bridge Scour: Prediction, Modeling, Monitoring and ountermeasures-Review. Pract Periodical Struct Design Constr 15(2) (2010) 125-134.
Dibike, Y. B. ; Solomatine, D. et al. On the encapsulation of numerical-hydraulic models in artificial neural network. Journal of Hydraulic Research 37(2) (1999) 147-161.
Elnikhely, E. A. Minimizing Scour around Bridge Pile Using Holes. Ain Shams Engineering Journal 8(4) (2017) 499-506.
Fritsch, S.; Guenther, F. Neuralnet: Training of Neural Networks. R package version 1.33 (2016).
Jeng, D. S.; Bateni, S.M.; Lockett, E. Neural Network Assessment for Scour Depth around Bridge Piers. The University of Sydney (2005).
Johnson,.P.A. ; Dock,.D.A. Probabilistic Bridge Scour Estimates. J HydraulEng ASCE 124(7) (1998) 750-754.
Johnson Peggy, A. ; Gleason Gary, L.; et al. Rapid Assessment of Channel Stability in Vicinity of Road Crossing. Journal of Hydraulic Engineering 125(6) (1999).
Hicks, F. E.; Peacock, K. Suitability of Hec-Ras for Flood Forecasting. Canadian Water Resources Journal / Revue canadienne des ressourceshydriques 30(2) (2005)159-174.
Kambekar, A.R.; Deo, M.C. Estimation of Group Pile Scour Using Neural Networks. Journal of Applied Ocean Research. (2003).
Kumar, D.; Hira, Y.; Sushil, H. Estimation of Scour Depth around Bridge Piers by Using Hec-Ras (2011).
Liong, S. Y.; Chan, W.T. Runoff volume estimates with neural networks. third international conference on the application of artificial intelligence to civil and structural engineering. Edinburgh, UK (1993) 67-70.
Moussa, A. M. A. Evaluation of local scour around bridge piers for various geometrical shapes using mathematical models. Ain Shams Engineering Journal (2017).
Nasr-Allah, T.; Hemdan, Y.; Abdallah, M. M.; Mohamed, G.; ShawkyAwad, A. Experimental and Numerical Simulation of Scour at Bridge Abutment Provided with Different Arrangements of Collars. Alexandria Engineering Journal 55(2) (2016) 1455-1463.
Olsen, N. R. B.; Kjellesvig, H.M. Three-dimensional numerical flow modeling for estimation of maximum local scour depth. Journal of Hydraulic Research 36(4) (1998) 579-590.
Peters, R.; Schmitz, G.; et al. Flood routing modelling with Artificial Neural Networks. Advances in Geosciences 9 (2006).
Richardson, E. V.; Davis, S.R .Evaluating scour at bridges. Hydraulic Engineering Circular Federal Highway Administration, Washington, D.C. 18 (2001).
Fritsch, S.; Guenther, F .Neuralnet: Training of Neural Networks. R package version 1.33 (2006).
Peters, R.; Schmitz,G.; et al. Flood routing modelling with Artificial Neural Networks. Advances in Geosciences 9(2006)131-136.
Refbacks
- There are currently no refbacks.