Estimation of peak outflow in dam failure using neural network approach under uncertainty analysis
- 115 Downloads
This paper presents two Artificial Neural Network (ANN) based models for the prediction of peak outflow from breached embankment dams using two effective parameters including height and volume of water behind the dam at the time of failure. Estimation of optimal weights and biases in the training phase of the ANN is analysed by two different algorithms including Levenberg—Marquardt (LM) as a standard technique used to solve nonlinear least squares problems and Imperialist Competitive Algorithm (ICA) as a new evolutionary algorithm in the evolutionary computation field. Comparison of the obtained results with those of the conventional approach based on regression analysis shows a better performance of the ANN model trained with ICA. Investigation on the uncertainty band of the models indicated that LM predictions have the least uncertainty band whilst ICA’s have the lowest mean prediction error. More analysis on the models’ uncertainty is conducted by a Monte Carlo simulation in which 1000 randomly generated sets of input data are sampled from the database of historical dam failures. The result of 1000 ANN models which have been analysed with three statistical measures including p-factor, d-factor, and DDR confirms that LM predictions have more limited uncertainty band.
Keywordsdam failure neural network Levenberg—Marquardt Imperialist Competitive Algorithm uncertainty analysis
Unable to display preview. Download preview PDF.
- 2.Atashpaz-Gargari, E. and Lucas, C., Imperialist competitive algorithm: An algorithm for optimization inspired by imperialistic competition, IEEE Congress on Evolutionary Computation, 2007, pp. 4661–4667.Google Scholar
- 4.Babaeyan Amini, A., Nourani, V., and Hakimzadeh, H., Application of artificial intelligence tools to estimate peak outflow from earth dam breach, Int. J. Earth Sci. Eng., 2011, vol. 4, no. 6, pp. 243–246.Google Scholar
- 8.Fread, D.L., Some Limitations of Dam-Break Flood Routing Models, Preprint, American Society of Civil Engineers, Fall Convention, St. Louis, Mo, 1981.Google Scholar
- 14.Hosseini Nasab, E., Khezri, M., Khodamoradi, S.M., and Atashpaz Gargari, E., An application of Imperialist Competitive Algorithm to Simulation of Energy Demand Based on Economic Indicators: Evidence from Iran, Europ. J. Sci. Res., 2010, vol. 43, no. 4, pp. 495–506.Google Scholar
- 16.Levenberg, K., A method for the solution of certain non-linear problems in least squares, Quart. Appl. Math., 1944, vol. 2, no. 2, pp. 164–168.Google Scholar
- 26.Taher-Shamsi, A., Shetty, A.V., and Ponce, V.M., Embankment Dam Breaching: Geometry and Peak Outflow Charactristic, Dam Eng., 2003, vol. 14, no. 2, pp. 73–87.Google Scholar
- 27.Tahershamsi, A. and Sheikholeslami, R., Optimization to identify Muskingum Model parameters using imperialist competitive algorithm, Int. J. Optim. Civil Eng., 2011, vol. 1, no. 3, pp. 473–482.Google Scholar
- 29.Wahl, T.L., Prediction of Embankment Dam Breach Parameters, A Literature Review and Needs Assessment, Bureau of Reclamation, U.S. Department of the Interior, Denver, 60, Rep. no. DSO–98–004, 1998.Google Scholar
- 31.Willemsen, P.G., Bailer, C.A.L., and Kaempf, T.A., ICAP-Variability-Alerts Joint Working Group Meeting, Paris, October 8, 2004.Google Scholar