A combination of computational fluid dynamics, artificial neural network, and support vectors machines models to predict flow variables in curved channel

Document Type : Article

Authors

Department of Civil Engineering, Razi University, Kermanshah, Iran

Abstract

This study show the combination of computational fluid dynamics (CFD) and soft computing techniques to make viewpoint for two-phase flow modelling and accuracy evaluation of soft computing methods in the three-dimensional flow variables prediction in curved channels. Therefore, artificial neural network (ANN) and support vectors machines (SVM) models with CFD is designed to estimate velocity and flow depth variable in 60° sharp bend. Experimental results in 6 different flow discharges of 5, 7.8, 13.6, 19.1, 25.3 and 30.8 l/s to train and test, ANN and SVM models is used. The results of numerical models with experimental values are compared and the models accuracy is confirmed. The results evaluation show that all three models ANN, SVM and CFD perform well in flow velocity prediction, with correlation coefficient (R) of 0.952, o.806, and 0.680, and flow depth (R) of 0.999, 0.696, and 0.614 respectively. ANN model to predict both velocity and flow depth variables with mean absolute relative error (MARE) of 0.055 and 0.004 is the best model. Then SVM and CFD models with MARE of 0.069 and 0.089 in velocity prediction and in flow depth prediction CFD and SVM models with MARE of 0.007 and 0.011 are the best models, respectively.

Keywords

Main Subjects


  1. Baghlani, A. Simulation of ow and mass dispersion in meandering channels", Scientia Iranica, Transactions A: Civil Engineering, 19, pp. 1463-1472 (2012). 2. Shukry, A. Flow around bends in an open ume", Transactions, ASCE, 115, pp. 751-788 (1950). 3. Rozovskii, I.L. Flow of water in bends of open channels", Israel Program for Science Translation, Jerusalem, pp. 1-233 (1961). 4. DeVriend, H.J. and Geoldof, H.J. Main ow velocity in short river bends", Journal of Hydraulics Engineering, 109(7), pp. 991-1011 (1983). 5. Bergs, M.A. Flow processes in a curved alluvial channel", Ph.D. Thesis, The University of Iowa (1990). 6. Ye, J. and McCorquodale, J.A. Simulation of curved open channel ows by 3D hydrodynamic model", Journal of Hydraulic Engineering- ASCE, 124(7), pp. 687-698 (1998). A. Gholami et al./Scientia Iranica, Transactions A: Civil Engineering 26 (2019) 726{741 739 7. Blanckaert, K. and Graf, W.H. Mean ow and turbulence in open channel bend", Journal of Hydraulic Engineering, 127(10), pp. 835-847 (2001). 8. Barbhuiya, A.K. and Talukdar, S. Scour and three dimensional turbulent ow _elds measured by ADV at a 90_ horizontal forced bend in a rectangular channel", Flow Measurement and Instrumentation, 21, pp. 312- 321 (2010). 9. Ramamurthy, A., Han, S., and Biron, P. Threedimensional simulation parameters for 90_ open channel bend ows", Journal of Computing in Civil Engineering. ASCA, 27(3), pp. 282-291 (2013). 10. Gholami, A., Akhtari, A.A., Minatour, Y., Bonakdari, H., and Javadi, A.A. Experimental and numerical study on velocity _elds and water surface pro_le in a strongly-curved 90_ open channel bend", Engineering Applications of Computational Fluid Mechanics, 8(3), pp. 447-461 (2014). 11. Leschziner, M.A. and Rodi, W. Calculation of strongly curved open channel ow", Journal of the Hydraulics Division, 105(10), pp. 1297-1314 (1979). 12. Naji, M.A., Ghodsian, M., Vaghe_, M., and Panahpur, N. Experimental and numerical simulation of ow in a 90_ bend", Flow Measurement and Instrumentation, 21(3), pp. 292-298 (2010). 13. DeMarchis, M. and Napoli, E. 3D numerical simulation of curved open channel ows", Proceedings of 6th International Conference on Water Resources, Hydraulics & Hydrology, pp. 86-91, Chalkida, Evia Island, Greece, May 11-13 (2006). 14. Bodnar, T., Prihoda, J. Numerical simulation of turbulent free-surface ow in curved channel", Flow, Turbulence and Combustion, 76, pp. 429-442 (2006). 15. Gholami, A., Bonakdari, H., and Akhtari, A.A. Assessment of water depth change patterns in 120 sharp bend using numerical model", Water Science and Engineering, 4(9), pp. 336-344 (2016). 16. Bonakdari, H., Larrarte, F., and Joannis, C. E_ect of a bend on the velocity _eld in a circular sewer with free surface ow", Proceeding of 6th International Conference on Sustainable Techniques and Strategies in Urban Water Management, pp. 1401-1408, Lyon, France, June 24-28 (2007). 17. Zeng, J., Constantinescu, G., Blanckaert, K., and Weber, L. Flow and bathymetry in sharp openchannel bends: Experiments and predictions", Water Resources Research, 44(9), w09401, pp. 1-22 (2008). 18. Gholami, A., Bonakdari, H., and Akhtari, A.A. Developing _nite volume method (FVM) in numerical simulation of ow pattern in 60_ open channel bend", Journal of Applied Research in Water and Wastewater, 3(1), pp. 193-200 (2016). 19. Kisi, O. and Cigizoglu, H.K. Comparison of di_erent ANN techniques in river ow prediction", Civil Engineering Environment System, 14, pp. 211-231 (2007). 20. Najafzadeh, M. and Azamathulla, H.M. Neuro-fuzzy GMDH to predict the scour pile groups due to waves", Journal of Computing in Civil Engineering, 29(5), 04014068 (2013). 21. Najafzadeh, M., Barani, G.A., and Hessami Kermani, M.R. Estimation of pipeline scour due to waves by GMDH", Journal of Pipeline Systems Engineering and Practice, 5(3), 06014002 (2014). 22. Najafzadeh, M. and Zahiri, A. Neuro-fuzzy GMDHbased evolutionary algorithms to predict ow discharge in straight compound channels", Journal of Hydrologic Engineering, 20(12), 04015035 (2015). 23. Najafzadeh, M., Barani, G.A., and Hessami-Kermani, M.R. Evaluation of GMDH networks for prediction of local scour depth at bridge abutments in coarse sediments with thinly armored beds", Ocean Engineering, 104, pp. 387-396 (2015). 24. Najafzadeh, M., Etemad-Shahidi, A., and Lim, S.Y. Scour prediction in long contractions using ANFIS and SVM", Ocean Engineering, 111, pp. 128-135 (2016). 25. Najafzadeh, M., Balf, M.R., and Rashedi, E. Prediction of maximum scour depth around piers with debris accumulation using EPR, MT, and GEP models", Journal of Hydroinformatics, 18(5), pp. 867-884 (2016). 26. Najafzadeh, M. and Sattar, A.M. Neuro-fuzzy GMDH approach to predict longitudinal dispersion in water networks", Water Resources Management, 29(7), pp. 2205-2219 (2015). 27. Gholami, A., Bonakdari, H., Ebtehaj, I., and Akhtari, A.A. Design of an adaptive neuro-fuzzy computing technique for predicting ow variables in a 90_ sharp bend", Journal of Hydroinformatics, 19(4), jh2017200 (2017). 28. Gholami, A., Bonakdari, H., Zaji, A.H., Fenjan, S.A., and Akhtari, A.A. New radial basis function network method based on decision trees to predict ow variables in a curved channel", Neural Computing and Applications, 30(9), pp. 2771-2785 (2018). 29. Gholami, A., Bonakdari, H., Zaji, A.H., Ajeel Fenjan, S., and Akhtari, A.A. Design of modi_ed structure multi-layer perceptron networks based on decision trees for the prediction of ow parameters in 90 openchannel bends", Engineering Applications of Computational Fluid Mechanics, 10(1), pp. 193-208 (2016). 30. Gholami, A., Bonakdari, H., Ebtehaj, I., Shaghaghi, S., and Khoshbin, F. Developing an expert group method of data handling system for predicting the geometry of a stable channel with a gravel bed", Earth Surface Processes and Landforms, 42(10), pp. 1460- 1471 (2017). DOI: 10.1002/esp.4104 740 A. Gholami et al./Scientia Iranica, Transactions A: Civil Engineering 26 (2019) 726{741 31. Shaghaghi, S., Bonakdari, H., Gholami, A., Ebtehaj, I., and Zeinolabedini, M. Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design", Applied Mathematics and Computation, 313, pp. 271- 286 (2017). 32. Kaveh, A. and Nasrollahi, A. Charged system search and particle swarm optimization hybridized for optimal design of engineering structures", Scientia Iranica, Transactions A: Civil Engineering, 21, pp. 295-305 (2014). 33. Ebtehaj, I., Bonakdari, H., Zaji, A.H., Azimi H., and Shari_, A. Gene expression programming to predict the discharge coe_cient in rectangular side weirs", Applied Soft Computing, 35, pp. 618-628 (2015). 34. Karimi, S., Bonakdari, H., and Gholami, A. Determination discharge capacity of triangular labyrinth side weir using multi-layer neural network (ANN-MLP)", Current World Environment, 10(Special issue 1), pp. 111-119 (2015). 35. Zarif Sanayei, H.R., Talebbeydokhti, N., and Moradkhani, H. 3D estimation of metal elements in sediments of the Caspian Sea with moving least square and radial basis function interpolation methods", Scientia Iranica, Transactions A: Civil Engineering, 22, pp. 1661-1673 (2015). 36. Bonakdari, H., Baghalian, S., Nazari, F., and Fazli, M. Numerical analysis and prediction of the velocity _eld in curved open channel using arti_cial neural network and genetic algorithm", Engineering Applications of Computational Fluid Mechanics, 5(3), pp. 384-396 (2011). 37. Sahu, M., Jana, S., Agarwal, S., and Khatua, K.K. Point form velocity prediction in meandering open channel using arti_cial neural network", 2nd International Conference on Environmental Science and Technology, 6, pp. 209-212, Singapore: IACSIT Press (2011). 38. Gholami, A., Bonakdari, H., Zaji, A.H., and Akhtari, A.A. Simulation of open channel bend characteristics using computational uid dynamics and arti_cial neural networks", Engineering Applications of Computational Fluid Mechanics, 9(1), pp. 355-361 (2015). 39. Fenjan, S.A., Bonakdari, H., Gholami, A., and Akhtari, A.A. Flow variables prediction using experimental, computational uid dynamic and arti_cial neural network models in a sharp bend", International Journal of Engineering-Transactions A: Basics, 29(1), pp. 14-21 (2016). 40. Gholami, A., Bonakdari, H., Zaji, A.H., Akhtari, A.A., and Khodashenas, S.R. Predicting the velocity _eld in a 90_ open channel bend using a gene expression programming model", Flow Measurement and Instrumentation, 46, pp. 189-192 (2015). 41. Gholami, A., Bonakdari, H., Zaji, A.H., Michelson, D.G., and Akhtari, A.A. Improving the performance of multi-layer perceptron and radial basis function models with a decision tree model to predict ow variables in a sharp 90_ bend", Applied Soft Computing, 48, pp. 563-583 (2016). 42. Akhtari, A.A., Abrishami, J., and Shari_, M.B. Experimental investigations water surface characteristics in strongly-curved open channels", Journal of Applied Sciences, 9(20), pp. 3699-3706 (2009). 43. Arm_eld Limited, Co., Instruction Manual of Miniature Propeller Velocity Meter Type H33 (1995). 44. Fluent Manual, Manual and User Guide of Fluent Software, Fluent Inc (2005). 45. Rezaeian Zadeh, M., Amin, S., Khalili, D., and Singh, V.P. Daily outow prediction by multilayer perception with logistic sigmoid and tangent sigmoid activation functions", Journal of Water Resources Management, 24(11), pp. 2673-2688 (2010). 46. Ebtehaj, I. and Bonakdari, H. Evaluation of sediment transport in sewer using arti_cial neural network", Engineering Applications of Computational Fluid Mechanics, 7(3), pp. 382-392 (2013). 47. Levenberg, K. A method for the solution of certain non-linear problems in least-squares", The Quarterly of Applied Mathematics, 2, pp. 164-168 (1944). 48. Zaji, A.H. and Bonakdari, H. Application of arti_cial neural network and genetic programming models for estimating the longitudinal velocity _eld in open channel junctions", Flow Measurement and Instrumentation, 41, pp. 81-89 (2015). 49. Vapnik, V., The Nature of Statistical Learning Theory, Springer Verlag, New York, USA (1995) 50. Vapnik, V.N. and Vapnik, V., Statistical Learning Theory, 1, Wiley, New York (1998). 51. Adarsh, S. Prediction of longitudinal dispersion coe _cient in natural channels using soft computing techniques", Scientia Iranica. Transaction A, Civil Engineering, 17(5), pp. 363-371 (2010). 52. Wang, R., Zhan, Y., and Zhou, H. Application of transform in fault diagnosis of power electronics circuits", Scientia Iranica, 19(3), pp. 721-726 (2012). 53. Ebtehaj, I., Bonakdari, H., Shamshirband, S., and Mohammadi, K. A combined support vector machinewavelet transform model for prediction of sediment transport in sewer", Flow Measurement and Instrumentation, 47, pp. 19-27 (2016). 54. Ebtehaj, I. and Bonakdari, H. A support vector regression-_rey algorithm-based model for limiting velocity prediction in sewer pipes", Water Science & Technology, 73(9), pp. 2244-2250 (2016). A. Gholami et al./Scientia Iranica, Transactions A: Civil Engineering 26 (2019) 726{741 741 55. Bowden, G.J., Maier, H.R., and Dandy, G.C. Optimal division of data for neural network models in water resources applications", Water Resources Research, 38(2), pp. 1-11 (2002).