Determining Impending Slip of Slop and Optimized Embankment Operation Volume of Earth Dams Using a Combination of Neural Networks and Genetic Algorithms (GA)

Document Type : Research Article

Authors

1 Tafresh University, Tafresh, Iran

2 Geotechnical Engineering Research Center, International Institute of Earthquake Engineering and Seismology

3 Afarinesh institution of higher education, Borujerd, Iran

Abstract

In this study, impending slip of slope and optimized embankment operation volume of earth dams have been determined using optimization benefiting from a combination of neural networks and genetic algorithms (GA). Further, coefficient of slope stability of earth dam have been determined using neural network and has been compared with outputs of finite element software PLAXIS. In order to training the neural network from derivative data, 150 models of earth dams have been used in finite element software PLAXIS.
Slope stability analysis has been done in order to determining the safety factor at desired sliding surface and the most probable fracture process and the least related safety factor. The determination of the most probable fracture process at the impending slip (determining the least safety factor) is the genetic algorithm application. Moreover, another application of genetic algorithm in this research is optimizing the embankment operation volume of earth dam in the manner that minimum of safety factor derived. In this research analysis has been done in order to simpler use of proposed dimensions for engineers using various properties of soil in embankment of earth dam for different heights. Results have been shown as figures and tables which optimal dimensions and volume of the dam without using the software can be derived from them.

Keywords

Main Subjects


[1] Hernandez S, Fontan A. Practical applications of desigS.Hernandez, A.Fontan. Practical applications of design optimization. Southampton (UK): WIT Press; (2002).
[2] R .Fletcher.Practical methods of optimization. Chichester: Wiley; (2001).
[3] A .Saribas, F.Erbatur.Optimization and sensitivity of retaining structures. ASCE Journal of Geotechnical Engineering, 122(8)(1996) 649-656.
[4] T.Jones. Artificial intelligence application programming. Hingham (MA): Charles River Media; (2003).
[5] F.Glover, M.Laguna. Tabu search. Boston: Kluwer Academic Publishers; (1997).
[6] V.Yepes, J.Medina. Economic heuristic optimization for heterogeneous fleet VRPHESTW. ASCE Journal of Transportation Engineering, 132(4) (2006) 303–311.
[7] J.Holland. Adaptation in natural and artificial systems. Ann Arbor:University of Michigan Press; (1975).
[8] D.Goldberg. Genetic algorithms in search, optimization and machine learning. Addison- Wesley; (1989).
[9] W.Jenkins. Plane frame optimum design environment based on genetic algorithm. ASCE Journal of Structural Engineering, 118(11) (1992) 3103-3112.
[10] F .Gonzalez, V.Yepes, J.Alcala, M .Carrera, C .Perea. Simulated annealing optimization of walls, portal and box reinforced concrete road structures. In: Proceedings of the ninth international conference on computer aided optimum design in engineering. 80(2)(2005) 175–186.
[11] C.Perea,I.Paya,V.Yepes,F.Gonzalez.Heuristic optimization of reinforced concrete road bridges and frames. In: Proceedings second FIB congress. 39(8)(2006) 676-688.
[12] C.Perea,V.Yepes,J.Alcala,A.Hospitaler,F.Gonzalez-Vidosa. Heuristic optimization of reinforced concrete road bridge frames. In: Proceedings of the eighth conference on computational structures technology. (2006).
[13] I.Paya,V.Yepes,J.Clemente,F.Gonzalez-Vidosa.Heuristic optimization of reinforced concrete building frames. Revista Internacional de Methods Num´ericos para C´alculo y Dise˜noen Ingenieria. 22(3) (2006) 241–59 (in Spanish).
[14] I.Raeisizadeh. Application of Neural Networks and Genetic Algorithms in Determination of Stability Factor and Optimization of Soil Dam Diversion Volume, Master's Thesis,Arak Azad University.(2009)(in Persian).