Abstract




 
   

IJE TRANSACTIONS A: Basics Vol. 29, No. 1 (January 2016) 14-22    Article in Press

downloaded Downloaded: 294   viewed Viewed: 2703

  FLOW VARIABLES PREDICTION USING EXPERIMENTAL, COMPUTATIONAL FLUID DYNAMIC AND ARTIFICIAL NEURAL NETWORK MODELS IN A SHARP BEND
 
S. Ajeel Fenjan, H. Bonakdari, A. Gholami and A. A. Akhtari
 
( Received: March 13, 2015 – Accepted: January 28, 2016 )
 
 

Abstract    Bend existence induces changes in the flow pattern, velocity profiles and water surface. In the present study, based on experimental data, first three-dimensional computational fluid dynamic (CFD) model is simulated by using Fluent two-phase (water + air) as the free surface and the volume of fluid method, to predict the two significant variables (velocity and channel bed pressure) in 90º sharp bend. The CFD results are compared with experimental data, and CFD model is verified with average RMSE, 0.02 and 0.13 and MAE, 0.018 and 0.1 respectively for the velocity and the pressure. Then, two multi-layer perceptron artificial neural network (MLP-ANN) model is trained by observed datas. The results show that the value of R2, 0.984 and 0.99 respectively to predict the velocity of flow and pressure by ANN models are acceptable accuracy. ANN model acts more accurately with average erro value of MAE, 0.048 than the CFD model with average MAE, 0.06 to predict the velocity and pressure. The velocity and pressure pattern of flow is predictable through both numerical models, CFD and ANN models in every part of the channel.

 

Keywords    CFD model, ANN model, 90ş sharp bend, flow velocity, flow pressure

 

چکیده    وجود قوس موجب تغییر در الگوی جریان، پروفیل سرعت و سطح آب می­گردد. در تحقیق حاضر، با استناد به نتایج آزمایشگاهی موجود در ابتدا با استفاده از مدل سه­بعدی دینامیک سیالات محاسباتی فلوئنت به­صورت دو فازی (آب + هوا) و سطح آزاد و با استفاده از روش حجم سیال دو متغییر قابل توجه سرعت و فشار وارد بر کف کانال در قوس تند 90 درجه شبیه­سازی شده است. نتایج مدل دینامیک سیالات محاسباتی (CFD) با مقادیر آزمایشگاهی مقایسه و با متوسط RMSE، 02/0 و 13/0 و MAE، 018/0 و 1/0 به­ترتیب برای سرعت و فشار جریان صحت­سنجی شده است. در ادامه دو مدل شبکه عصبی مصنوعی پرسپترون چند لایه (ANN-MLP) با استفاده از داده­های مشاهداتی موجود آموزش داده می­شود. بررسی نتایج نشان می­دهد که مقدار R2، 984/0 و 99/0 برای پیش­بینی به­ترتیب سرعت و فشار جریان نشان از دقت قابل قبول دو مدل شبکه عصبی دارند. مدل شبکه عصبی با مقدار متوسط MAE، 048/0 نسبت به مدل دینامیک سیالالت با متوسط MAE، 06/0 در پیش­بینی سرعت و فشار دقت بیشتری دارد. همچنین الگوی سرعت و فشار جریان به کمک هر دو مدل عددی، دینامیک سیالات و شبکه عصبی در هر نقطه از میدان حل قابل پیش­بینی می­باشد.

References   

 

1.     Blanckaert, K. and Graf, W.H., "Mean flow and turbulence in open-channel bend", Journal of Hydraulic Engineering,  Vol. 127, No. 10, (2001), 835-847.

2.     Lu, W., Zhang, W., Cui, C. and Leung, A., "A numerical analysis of free-surface flow in curved open channel with velocity–pressure-free-surface correction", Computational Mechanics,  Vol. 33, No. 3, (2004), 215-224.

3.     Bodnár, T. and Příhoda, J., "Numerical simulation of turbulent free-surface flow in curved channel", Flow, turbulence and combustion,  Vol. 76, No. 4, (2006), 429-442.

4.     Zhang, M.-l. and Shen, Y.-m., "Three-dimensional simulation of meandering river based on 3-D rng κ-ɛ turbulence model", Journal of Hydrodynamics, Ser. B,  Vol. 20, No. 4, (2008), 448-455.

5.     Naji, A.M., Ghodsian, M., Vaghefi, M. and Panahpur, N., “Experimental and numerical simulation of flow in a 90° bend”, Flow Measurement and Instrumentation, Vol. 21, No. 3, (2010), 292-298

6.     Gholami, A., Akbar Akhtari, A., Minatour, Y., Bonakdari, H. and Javadi, A.A., "Experimental and numerical study on velocity fields and water surface profile in a strongly-curved 90° open channel bend", Engineering Applications of Computational Fluid Mechanics,  Vol. 8, No. 3, (2014), 447-461.

7.     Bonakdari, H. and Zinatizadeh, A.A., "Influence of position and type of doppler flow meters on flow-rate measurement in sewers using computational fluid dynamic", Flow Measurement and Instrumentation,  Vol. 22, No. 3, (2011), 225-234.

8.     Mignot, E., Bonakdari, H., Knothe, P., Lipeme Kouyi, G., Bessette, A., Rivire, N. and Bertrand-Krajewski, J., "Experiments and 3d simulations of flow structures in junctions and their influence on location of flowmeters", Water Science and Technology,  Vol. 66, No. 6, (2012), 1325.

9.     Ramamurthy, A., Han, S. and Biron, P., "Three-dimensional simulation parameters for 90 open channel bend flows", Journal of Computing in Civil Engineering,  Vol. 27, No. 3, (2013) 282-291.

10.   Bonakdari, H., Ebtehaj, I. and Azimi, H., "Numerical analysis of sediment transport in sewer pipe", International Journal of Engineering-Transactions B: Applications,  Vol. 28, No. 11, (2015), 1564-1570.

11.   Sharifipour, M., Bonakdari, H. and Zaji, A., "Impact of the confluence angle on flow field and flowmeter accuracy in open channel junctions", International Journal of Engineering-Transactions B: Applications,  Vol. 28, No. 8, (2015), 1145-1153.

12.   Hadian, M.R., Zarrati, A. and Eftekhari, M., "Development of an implicit numerical model for calculation of sub-and super-critical flows", International Journal of Engineering Transactions B: Applications,,  Vol. 18, No. 1, (2005), 85-95.

13.   Bilhan, O., Emiroglu, M.E. and Kisi, O., "Application of two different neural network techniques to lateral outflow over rectangular side weirs located on a straight channel", Advances in Engineering Software,  Vol. 41, No. 6, (2010), 831-837.

14.   Emiroglu, M.E., Bilhan, O. and Kisi, O., "Neural networks for estimation of discharge capacity of triangular labyrinth side-weir located on a straight channel", Expert Systems with Applications,  Vol. 38, No. 1, (2011), 867-874.

15.   Goel, A. and Pal, M., "Stage-discharge modeling using support vector machines", International Journal of Engineering Transactions A: Basics,  Vol. 25, No. 1, (2012), 1-9.

16.   Mirzaei, E., Minatour, Y., Bonakdari, H. and Javadi, A., "Application of interval-valued fuzzy analytic hierarchy process approach in selection cargo terminals, a case study", International Journal of Engineering-Transactions C: Aspects,  Vol. 28, No. 3, (2014), 387-296.

17.   Bahramifara, A., Shirkhanib, R. and Mohammadic, M., "An anfis-based approach for predicting the manning roughness coefficient in alluvial channels at the bank-full stage", International Journal of Engineering-Transactions B: Applications,,  Vol. 26, No. 2, (2013), 177-186.

18.   Haji, M.S., Mirbagheri, S., Javid, A., Khezri, M. and Najafpour, G., "A wavelet support vector machine combination model for daily suspended sediment forecasting", International Journal of Engineering-Transactions C: Aspects,  Vol. 27, No. 6, (2013), 855-864.

19.   Zaji, A.H. and Bonakdari, H., "Application of artificial neural network and genetic programming models for estimating the longitudinal velocity field in open channel junctions", Flow Measurement and Instrumentation,  Vol. 41, No., (2015), 81-89.

20.   Gholami, A., Bonakdari, H., Zaji, A.H., Akhtari, A.A. and Khodashenas, S.R., "Predicting the velocity field in a 90° open channel bend using a gene expression programming model", Flow Measurement and Instrumentation,  Vol. 46, (2015), 189-192.

21.   Yuhong, Z. and Wenxin, H., "Application of artificial neural network to predict the friction factor of open channel flow", Communications in Nonlinear Science and Numerical Simulation,  Vol. 14, No. 5, (2009), 2373-2378.

22.   Sahu, M., Jana, S., Agarwal, S., Khatua, K. and Mohapatra, S., "Point form velocity prediction in meandering open channel using artificial neural network", in Proceedings of International Conference on Environmental Science and Technology  (2011).

23.   Bonakdari, H., Baghalian, S., Nazari, F. and Fazli, M., "Numerical analysis and prediction of the velocity field in curved open channel using artificial neural network and genetic algorithm", Engineering Applications of Computational Fluid Mechanics,  Vol. 5, No. 3, (2011), 384-396.

24.   Baghalian, S., Bonakdari, H., Nazari, F. and Fazli, M., "Closed-form solution for flow field in curved channels in comparison with experimental and numerical analyses and artificial neural network", Engineering Applications of Computational Fluid Mechanics,  Vol. 6, No. 4, (2012), 514-526.

25.   Gholami, A., Bonakdari, H., Zaji, A.H. and Akhtari, A.A., "Simulation of open channel bend characteristics using computational fluid dynamics and artificial neural networks", Engineering Applications of Computational Fluid Mechanics,  Vol. 9, No. 1, (2015), 355-369.

26.   Akhtari, A., Abrishami, J. and Sharifi, M., "Experimental investigations water surface characteristics in strongly-curved open channels", Journal of Applied Sciences,  Vol. 9, No. 20, (2009), 3699-3706.

27.   Kim, S., Shiri, J. and Kisi, O., "Pan evaporation modeling using neural computing approach for different climatic zones", Water Resources Management,  Vol. 26, No. 11, (2012), 3231-3249.

28.   Zadeh, M.R., Amin, S., Khalili, D. and Singh, V.P., "Daily outflow prediction by multi layer perceptron with logistic sigmoid and tangent sigmoid activation functions", Water Resources Management,  Vol. 24, No. 11, (2010), 2673-2688.

29.   Ebtehaj, I. and Bonakdari, H., "Evaluation of sediment transport in sewer using artificial neural network", Engineering Applications of Computational Fluid Mechanics,  Vol. 7, No. 3, (2013), 382-392.

30.   Dawson, C.W. and Wilby, R., "An artificial neural network approach to rainfall-runoff modelling", Hydrological Sciences Journal,  Vol. 43, No. 1, (1998), 47-66.

31.   Kisi, O. and Kerem Cigizoglu, H., "Comparison of different ann techniques in river flow prediction", Civil Engineering and Environmental Systems,  Vol. 24, No. 3, (2007), 211-231.

32.   Levenberg, K., "A method for the solution of certain non–linear problems in least squares", The Quarterly of Applied Mathematics, Vol. 2, (1944), 164-168

 





International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir