Determining the capability of artificial intelligence in estimating energy dissipation of skimming flow regime at stepped spillways

Document Type : Research Article


1 assistante proffessor, Agriculture Department, Payame Noor University, Iran

2 Ph.D Student- Hydraulic structures- Dep. of Civil Engineering- University of Sistan and Balouchestan- Zahedan

3 Assitant Professor, Dept. Of Water Sciences Engineering, Faculty of Agriculture, Jahrom University, Fars, Iran


Energy dissipation in stepped spillways is one of the primary goals of such structures. In this study, the accuracy of the Artificial Neural Network (ANN), Adaptive Fuzzy Neural Inference System based on the trained Firefly Algorithm utilized for optimization (ANFIS-FA) and the Gene Expression Programming method (GEP), in estimating the energy loss of skimming flow regime over stepped spillways was studied. Also, by performing sensitivity analysis, the importance of input parameters in predicting energy loss for each of the three mentioned methods was investigated. For this purpose, 154 series of experimental data were considered. The input parameters for each method include hydraulic jump, Froude number, Drop number, number of steps, Pseudo bottom slope and the ratio of the critical depth to the height of each step. The results show that all three methods had a higher ability to predict energy loss compared to classical methods based on conventional regression methods. The accuracy of the ANFIS-FA method is slightly higher than the GEP method. The accuracy of the ANN is slightly lower than mentioned methods. However, the highest accuracy is related to the multilayer perceptron ANN with 3 hidden layers with 12, 8 and 7 nodes in each layer, respectively. In all three methods, the most effective parameter was found to be the drop number and the least effective parameter was the bottom slope.


Main Subjects

[1] H. Chanson, L. Toombes, Experimental investigations of air entrainment in transition and skimming flows down a stepped chute, Canadian Journal of Civil Engineering, 29(1) (2002) 145-156
[2] N. Rajaratnam, Skimming flow in stepped spillways, Journal of Hydraulic Engineering, 116(4) (1990) 587-591
[3] H. Chanson, Hydraulics of stepped chutes and spillways, CRC Press, 2002.
[4] A.L.A. Simões, H.E. Schulz, R. De Melo Porto, Stepped and smooth spillways: resistance effects on stilling basin lengths, Journal of Hydraulic Research, 48(3) (2010) 329-337.
[5] G.C. Christodoulou, Energy dissipation on stepped spillways, Journal of Hydraulic Engineering, 119(5) (1993) 644-650.
[6] H. Chanson, Comparison of energy dissipation between nappe and skimming flow regimes on stepped chutes, Journal of Hydraulic Research, 32(2) (1994) 213-218.
[7] R.M. Boes, W.H. Hager, Hydraulic design of stepped spillways, Journal of Hydraulic Engineering, 129(9) (2003) 671-679.
[8] Y. Yasuda, Energy dissipation of skimming flows on stepped-channel chutes, in:  Fluvial, Environmental and Coastal Developments in Hydraulic Engineering, CRC Press,(2004) 77-90.
[9] F. Salmasi, M. Özger, Neuro-fuzzy approach for estimating energy dissipation in skimming flow over stepped spillways, Arabian Journal for Science and Engineering, 39(8) (2014) 6099-6108.
[10] K. Roushangar, S. Akhgar, F. Salmasi, J. Shiri, Neural networks-and neuro-fuzzy-based determination of influential parameters on energy dissipation over stepped spillways under nappe flow regime, ISH Journal of Hydraulic Engineering, 23(1) (2017) 57-62.
[11] A. Parsaie, A.H. Haghiabi, Evaluation of energy dissipation on stepped spillway using evolutionary computing, Applied Water Science, 9(6) (2019) 144.1-7.
[12] J.R. Quinlan, Learning with continuous classes, in:  5th Australian joint conference on artificial intelligence, World Scientific, (1992) 343-348.
[13] Y. Wang, I.H. Witten, Induction of model trees for predicting continuous classes,  (1996).
[14] L. Jiang, M. Diao, H. Xue, H. Sun, Energy dissipation prediction for stepped spillway based on genetic algorithm–support vector regression, Journal of Irrigation and Drainage Engineering, 144(4) (2018) 04018003.1-9.
[15] A. Parsaie, A.H. Haghiabi, The hydraulic investigation of circular crested stepped spillway, Flow Measurement and Instrumentation, 70 (2019) 101624.1-5.
[16] M.R. Meybodi, H. Beygy, Neural Network Engineering Using Learning Automata: Determination  of Desired Size for Three Layers Feed Forward Neural Networks, Journal of Faculty of Engineering (University of Tehran), 34(4 (70)) (2001) 1-26. (in Persian).
[17] M.E. Tipping, The relevance vector machine, in:  Advances in neural information processing systems, (2000) 652-658.
[18] X.-S. Yang, Firefly algorithms for multimodal optimization, in:  International symposium on stochastic algorithms, Springer, (2009) 169-178.
[19] X.-S. Yang, X. He, Firefly algorithm: recent advances and applications, arXiv preprint arXiv:1308.3898,  (2013) 1-14.
[20] M. Saniee-Abadeh, Z. Jabal-Amelian, Evolutionary algorithms and biological calculations, Niaze-Danesh Publication, 2013.
[21] Q. Fu, Z. Liu, N. Tong, M. Wang, Y. Zhao, A novel firefly algorithm based on improved learning mechanism, in:  International conference on logistics engineering, management and computer science (LEMCS 2015), Atlantis Press, (2015) 1-9.
[22] I. Fister, I. Fister Jr, X.-S. Yang, J. Brest, A comprehensive review of firefly algorithms, Swarm and Evolutionary Computation, 13 (2013) 34-46.
[23] J.-S. Jang, ANFIS: adaptive-network-based fuzzy inference system, IEEE transactions on systems, man, and cybernetics, 23(3) (1993) 665-685.
[24] A. Abraham, Adaptation of fuzzy inference system using neural learning, in:  Fuzzy systems engineering, Springer,(2005) 53-83.
[25] C. Ferreira, Gene expression programming: mathematical modeling by an artificial intelligence, Springer, 2006.