Estimation of Roughness Coefficient in Erodible Channels by ANNs and the ANFIS Methods

Document Type : Research Article

Authors

1 faculty of engineering,Department of Civil Engineering, Golestan University,

2 Civil Engineering Department, Faculty of Engineering, Golestan University

Abstract

 Estimating the roughness coefficient of erodible open channels plays an important role in their hydraulic design. This parameter also is important for the development of numerical models. For this reason, several empirical methods have been presented so far to estimate the roughness coefficient, while these methods are not sufficiently accurate. In this paper, the so-called Artificial Neural Networks (ANNs) and Adaptive Network-Based Fuzzy Inference System (ANFIS) methods as soft computing methods are used to estimate the roughness coefficient in erodible open channels. To achieve this, none-dimensional water depth with sediment particle averaged size ( hd50 ),, shear Reynolds numbers (R*) , Sheilds parameter (θ), and none-dimensional sediment falling velocity with shear velocity (wU f ) in channel obtained by Buckingham dimensional analysis are considered as input variables. Final results show ANFIS (R2 =0.8433) and ANNs (R2 =0.8515) model performance in comparison to empirical methods and regression-based methods like Multilinear regression and multi nonlinear regression methods to estimate the roughness coefficient. Evaluation of the input variables’ effectiveness on the coefficient via a sensitivity analysis versus the variation of error estimation by elimination of variables shows effectiveness of variables like shear Reynolds number and none-dimensional water depth usually ignored in empirical methods. The final results showed that due to complicity of sediment transport mechanism in erodible channels, models developed here can be a suitable alternative to estimate roughness coefficient.

Keywords

Main Subjects


[1]. Ferguson, R., (2010). Time to abandon the Manning equation? Earth Surf. Process. Landf. 35.
[2]. SUMER, B. MUTLU (2013). “LECT URE NOTES ON TURBULENCE.”, Technical University of Denmark.
 [3]. Powell, D. M. (2014). Flow resistance in gravelbed rivers: Progress in research. Earth-Science Reviews, 136, 301-338.
[4]. Simons, D. B., & Richardson, E. V. (1996). Resistance to flow in alluvial channels. US Government Printing Office.
[5]. Ackers, P. & White, W. R. (1973). «Sediment transport: new approach and analysis». Journal of the Hydraulics Division, 99 (hy11).
[6]. Hammond, F. D., Heathershaw, A. D., and Langhorne, D. N. (1984) .‘‘A comparison between Shields’ threshold criterion and the Henderson movement of loosely packed gravel in a tidal channel.’’ Sedimentology, 31, .26–15
[7]. Colosimo, C., Copertino, V. A., & Veltri, M. (1986). «Average velocity estimation in gravel-bed rivers». In Proc., 5th IAHR-APD Congress (pp. 1-15).
[8]. Wilson, K. C. (1989). Mobile-bed friction at high shear stress. Journal of Hydraulic Engineering, 115(6), .038-528
[9]. Yalin, M. S. “River Mechanics, 219 pp.” (1992).
 [10]. Sumer, B. M., Kozakiewicz, A., Fredsøe, J., & Deigaard, R. (1996). «Velocity and concentration profiles in sheet-flow layer of movable bed». Journal of Hydraulic Engineering, 122(10), 549-558.
[11]. KIM J.S, LEE .J., KIM W. , Yong J. K. (2010) Roughness coefficient and its uncertainty in gravelbed river, Water Science and Engineering
[12]. Yang, H. C., & Chang, F. J. (2005). «Modeling combined open channel flow by artificial neural networks». Hydrological Processes, 19 (18), 37473762.
[13]. Yuhong, Z., & Wenxin, H. (2009). «Application of artificial neural network to predict the friction factor of open channel flow». Communications in Nonlinear Science and Numerical Simulation, 14(5), 2373-2378.
[14]. Shayya, W. H., & Sablani, S. S. (1998). «An artificial neural network for non-iterative calculation of the friction factor in pipeline flow». Computers and electronics in agriculture, 21(3), 219-228.
[15]. Abdeen, M. A. M. (2004). «Artificial neutral network model for predicting the impact changing water structures’ locations on the hydraulic performance of branched open channel system». Mechanics and Mechanical Engineering,7(2), 179-192.
[16]. Zahiri, A., & Dehghani, A. A. (2009). «Flow discharge determination in straight compound channels using ANN». World Academy of Science, Engineering and Technology, 58, 12-15.
[17] Azamathulla H. Md., (2012), “ Gene-expression programming to predict friction factor for Southern Italian rivers, Journal of Neural Computing and Applications, 23 (8),  1421–142
[18]. Arpan P. & Kishanjit K. K., (2018) Gene expression programming to predict Manning’s n in meandering flows, Canadian Journal of Civil Engineering, Vol. 45, No. 4 : pp. 304-313
[19]. Bateni, S. M., Borghei, S. M., & Jeng, D. S. (2007). «Neural network and neuro-fuzzy assessments for scour depth around bridge piers». Engineering Applications of Artificial Intelligence, 20(3), 401-414.
[20].Begum, S. A., Fujail, A. M., & Barbhuiya, A. K. (2012). «Artificial neural network to predict equilibrium local scour depth around semicircular bridge abutments». 6th SASTech, Malaysia, Kuala Lumpur.
[21].Kazeminezhad, M. H., Etemad-Shahidi, A., & Bakhtiary, A. Y. (2010). «An alternative approach for investigation of the wave-induced scour around pipelines». Journal of Hydroinformatics, 12(1), 51-65.
[22].Ghazanfari-Hashemi, S., Etemad-Shahidi, A., Kazeminezhad, M. H., & Mansoori, A. R. (2011). «Prediction of pile group scour in waves using support vector machines and ANN». Journal of Hydroinformatics, 13(4), 609-620.
[23]. Zaji, A. H., & Bonakdari, H. (2015). Application of artificial neural network and genetic programming models for estimating the longitudinal velocity field in open channel junctions. Flow Measurement and Instrumentation, 41, 81-89.
[24]. Sheikh Khozani, Z., Hossein Bonakdari, H., Zaji. A.H. (2017).Estimating the shear stress distribution in circular channels based on the randomized neural networktechnique. Applied Soft Computing , 58, 441-448.
[25]. Sadegh Safari M., Aksoy, H., & Mohammadi, M. (2016). Artificial neural network and regression models for flow velocity at sediment incipient deposition. Journal of Hydrology, 541, 1420-1429.
[26]. Johnson, P. A. & Ayyub, B. M. (1996) «Modeling uncertainty in prediction of pier scour». Journal of Hydraulic.
[27]. Muzzammil, M. (2000). «ANFIS approach to the scour depth prediction at a bridge abutment». Journal of Hydroinformatics 12 (4):474-485.
[28]. Muzzammil, M., and J. Alam. (2011). «ANFISbased approach to scour depth prediction at abutments in armored beds». Journal of Hydroinformatics 13 (4):699-713.
[29]. Zanganeh, M., Yeganeh-Bakhtiary, A., & Bakhtyar, R. (2011). Combined particle swarm optimization and fuzzy inference system model for estimation of current-induced scour beneath marine pipelines. Journal of Hydroinformatics, 13(3), 558-573.
[30]. Bateni, S. M., & Jeng, D. S. (2007). Estimation of pile group scour using adaptive neuro-fuzzy approach. Ocean Engineering, 34(8), 1344-1354.
 [31]. Ozger, M. (2009)  «Comparison of fuzzy inference systems for stream flow prediction». Hydrological Sciences Journal 54(2), 261–273.
[32]. Azmathullah, H. Md., Ghani, A. A. & Zakaria, N. A. (2009) «.ANFIS-based approach to predicting scour location of spillway». Water management.
[33]. McCulloch, W. S., & Pitts, W. (1943). «A logical calculus of the ideas immanent in nervous activity». The bulletin of mathematical biophysics, 5(4), 115-133.
[34]. Rogers, L.L. & Dowla, F.U. (1994) «Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling». Water Resources Research. 30 (2), 457–481.
[35]. Hecht-Nielsen, R. (1978). «Kolmogorov’s mapping neural network existence theorem». In Proceedings of the international conference on Neural Networks (Vol. 3, pp. 11-13). New York: IEEE Press.
[36]. Jang JSR. (1993)».ANFIS Adaptive-Network-Based Fuzzy Inference systems». IEEE Trans System Man Cybern; 23(3): 665-685.
[37]. Chiu S.L (1994). «Fuzzy model identification based on cluster estimation. Intelligent Fuzzy Systems»; 2:234–244. Engineering 122(2), 66–72.