Evaluation of the Performance of Classical and Artificial Intelligence Approaches in Prediction of Critical Submergence of Horizontal Intakes in Open Channel Flows

Authors

1 Assoc. Prof., Dept. of Water Eng., Faculty of Civil Eng., University of Tabriz, Iran

2 Master of Water and Hydraulic Structure Engineering, Faculty of Civil Eng., University of Tabriz, Iran

Abstract

 Horizontal intakes are of the most common structures for water withdrawal from open channels such as rivers, lakes and dam reservoirs. One of the hydraulic phenomena that mainly occurs during the water withdrawal process of the channels is the formation of vortex and air bubbles that can cause many problems for hydro-mechanical facilities of intakes. Insufficient height of water above the intake pipes (submergence depth) is the major cause of the vortex formation on horizontal intakes. Due to the importance of this phenomenon, many models have been developed to estimate the critical submergence depth. However, due to the uncertainties of the vortex formation near the intake, the obtained results often do not show a desired accuracy. In this study, using three experimental data series, the performance of artificial intelligence techniques (adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM), gene expression programming (GEP)) and classical models were investigated for predicting the critical submergence depth of horizontal intakes with different bottom clearances in open channel flows. The results indicated that in estimating the critical submergence depth, the artificial intelligence techniques are more accurate than the classical models and a good agreement could be seen between the observed and predicted values. The best result for the test series was obtained for C=di/2 state (di and C were intake diameter and bottom clearance, respectively) using SVM method with the values of R=0.988, DC=0.976 and RMSE=0.191. According to the results of sensitivity analysis, it was observed that the relative velocity and Weber number in intake pipe were the most and the least significant parameters in the estimation of critical submergence depth, respectively.

Keywords


Ahmad Z, Rao KV and Mittal MK, 2008. Critical Submergence for Horizontal Intakes in Open Channel Flows. Department of Civil Engineering, Indian Institute of Technology Roorkee, India.
Amphlett MB, 1978. Air entraining vortices at a vertically inverted intake. Hydraulic Research Station, Report No. OD 17, Wallingford, England.
Govindaraju RS, 2000. Artificial neural networks in hydrology. I: preliminary concepts. Journal of Hydrologic Engineering 5(2): 115-123.
Baykara A, 2013. Effect of hydraulic parameters on the formation of vortices at intake structures. Master Thesis, Middle East Technical University (METU), Ankara, Turkey.
Ferreria C, 2001. Gene expression programming: a new adaptive algorithm for solving problems. Complex System 13(2): 87–129.
Ferreira C, 2004. Gene expression programming and the evolution of computer programs. Pp. 82-103. In: Custro LN, Von Zuben FJ, (eds.), Recent Developments in Biologically Inspired Computing, Chapter V, GEP and the Evolution of Computer Programs, Idea Group Publishing, New York, USA.
Gordon JL, 1970. Vortices at intakes. Water Power 22(4): 137-138.
Gulliver JS, Rindels AJ and Lindblom KC, 1986. Designing intakes to avoid free-surface Vortices. International Journal of Water Power & Dam Construction 38(9): 24-28.
Gunn SR, 1998. Support vector machines for classification and regression. ISIS Technical Report 14, Department of Engineering, Science and Mathematics, University of Southampton, UK.
Gurbuzdal FA, 2009. Scale effects on the formation of vortices at intake structures. Doctoral dissertation, Middle East Technical University (METU), Ankara, Turkey.
Hashemi Marghzar S, Montazerin N and Rahimzadeh H, 2003. Flow field, turbulence and critical condition at a horizontal intake Journal of Power and Energy 217(1): 53-62.
Jang JR, 1993. ANFIS: adaptive network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics 23: 665-685.
Khan MS and Coulibaly P, 2006. Application of support vector machine in lake water level Prediction. Journal of Hydraulic Engineering 11(3): 199–205.
Kisi O, Karahan ME and Sen Z, 2006. River suspended sediment modeling using fuzzy logic approach. Hydrological Processes 20(20): 4351–4362.
Kisi O, Shiri J and Tombul M, 2013. Modeling rain fall-runoff process using soft computing techniques. Computers & Geosciences 51: 108-117.
Li H, Chen H, Ma Z and Zhou Y, 2008. Experimental and numerical investigation of free surface vortex. Journal of Hydrodynamics 4: 485-491.
Lohani AK, Goel NK and Bhatia KS, 2007. Deriving stage-discharge-sediment concentration relationships using fuzzy logic. Hydrological Sciences Journal 52(4):793–807.
Prosser MJ, 1977. The Hydraulic Design of Pump Sumps and Intakes. British Hydromechanics Research Association/Construction Industry Research & Information Association, London.
Reddy YR and Pickford JA, 1973. Vortices at intakes in conventional sumps. Water power 3:108-9.
Roushangar K and Alizadeh F, 2015. Suitability of different modelling strategies in predicting of solid load discharge of an alluvial river. Pp 1-10. 36th world congress of IAHR, 3 July, The Netherlands.
Roushangar K, Akhgar S, Salmasi F and Shiri J, 2014. Modeling energy dissipation over stepped spillways using machine learning approaches. Journal of Hydrology 508: 254-265.
Sarkardeh H, Zarrati AR and Roshan R, 2010. Effect of intake head wall and trash rack on vortices. Journal of Hydraulic Research 48(1): 108-112.
Shiri J and Kisi O, 2011.Comparison of genetic programming with neuro-fuzzy systems for predicting short-term water table depth fluctuations. Computers Geosciences 37(10): 1692–1701.
Swaroop R, 1973. Vortex formation at intakes. M.S. Dissertation, Civil Engineering Department, University of Roorkee (now IIT Roorkee), Roorkee, India.
Tayfur G, Ozdemir S and Singh VP, 2003. Fuzzy logic algorithm for runoff-induced sediment transport from bare soil surfaces. Advanced Water Resource 26: 1249–1256.
Vapnik V, 1995. The Nature of Statistical Learning Theory. Data Mining and Knowledge Discovery, Springer Verlag, New York, 47p.
Yildrim N, Kocabas F and Gulcan SC, 2000. Flow-boundary effects on critical submergence of intake pipe. Journal of Hydraulic Engineering 126(4): 288-297.