Prediction of Discharge Coefficient of Crump Weir Using Artificial Neural Network (ANN)

Sani Yakubu Khalifa, Babatunde Korode Adeogun, Abubakar Ismail, Morufu Ajibola Ajibike, Muhammad Mujahid Muhammad

Abstract


The flow characteristics changes with varying geometry of the hydraulic weir and how the weir is inclined to the direction of flow in a channel. In this way, several studies have investigated the performance weirs experimental with paying much attention to the accurate prediction of discharge coefficient. Thus, the main objective of this study is to employ artificial intelligence (AI) techniques to predict the discharge coefficient (Cd) of crump weir models. Hence, the precision and use of seven data-driven models including Bayesian neural network (BNN), multiple linear regression (MLR), multi-layer perceptron neural network (MLPNN), genetic algorithm (GA), support vector machine (SVM), Radial Basis Function (RBF) and curve fitting neural network (CFNN) were examined for estimating of the Cd. To achieve this, experiments were conducted on eighteen crump weir models of different apex angles 80o, 90o 100o, 110o 120o, and 130°. The upstream angles of the weir models were set in decreasing order of 85o, 70o, 55o, 40o, 25o, and 10o. While the downstream angles were increased to 15o, 20o, 25o, 30o, 35o, and 40o respectively. 360 laboratory test results were used, 70% for training, 15% for testing, and 15% for validation. And statistical parameters of coefficient of determination (R2), root-mean-square error (RMSE), and mean absolute error (MAE), were employed as the criteria for the comparison of the model's performance. Results showed good agreements between the observed and estimated values using the AI-based models. However, among these models, the CFNN managed to estimate the Cd of the weir with the highest precision and accuracy than the rest of the models (RMSE=0.1635x10-4, R2=0.9981,). Also, it was found that the most efficient crump was weir model 17 for having the least Cd of 1.14914 and least percentage error of 12.97412, which has been optimized using GA with a Cd value of 1.14815.


Full Text:

PDF

References


Alauddin, M., Hossain, M., Uddin, M., and Haque, M. (2017). “A Review on Hydraulic and Morphological Characteristics in River Channels Due to Spurs”, World Academy of Science, Engineering and Technology International Journal of Geological and Environmental Engineering, Vol. 11, No. 4, 397–404.

Al-Naely, H., Al-Khafaji, Z., & Khassaf, S. (2018). Effect of Opening Holes on the Hydraulic Performance for Crump Weir. International Journal of Engineering, 31(12), 2022-2027.

Al-Sudani, Z. A., Salih, S. Q., & Yaseen, Z. M. (2019). Development of multivariate adaptive regression spline integrated with differential evolution model for streamflow simulation. Journal of Hydrology, 573, 1-12.

Arora K. R. (2005). Fluid mechanics and hydraulic machines. Standard publishers Distributors, 1705-B Nai Sarak, Post Box No.: 1066, Delhi-110006.

Azimi H, Bonakdari H, Ebtehaj I (2019) Design of radial basis function- based support vector regression in predicting the discharge coefficient of a side weir in a trapezoidal channel. Appl Water Sci 9(4):78

Barr, J., (1910). Experiments upon the flow of water over triangular notches. Engineering (London)

Bengtson Harlan (2010). Open channel flow measurement. Bright hub. Retrieved March 6, 2011, from http://www.brighthub.com/engineering/civil/articles/65701.aspx

Bos, M.G. (1989). Discharge measurement structures. International Institute for Land Reclamation and Improvement (ILRI), publication 20, Wageningen, The Netherlands.

Chanson, H. (2004). The hydraulics of open channel flow: an introduction. Butterworth-Heinemann, Oxford, UK, 2nd edition. Retrieved March 6, 2011, from http://www.wikipedia.com

Daneshfaraz R, Minaei O, Abraham J, Dadashi S, Ghaderi A (2019) 3-D Numerical simulation of water flow over a broad-crested weir with openings. ISH J Hydraul Eng. https ://doi.org/10.1080/09715 010.2019.15810 98

Dolcetti, G., & García Nava, H. (2019). Wavelet spectral analysis of the free surface of turbulent flows. Journal of Hydraulic Research, 57(2), 211-226.

Ghorbani, M. A., & DEHGHANI, R. (2017). Comparison of Bayesian neural networks and artificial neural network to estimate suspended sediments in the rivers (case study: Simineh rood).

Greve, F. V. (1932). Flow of water through circular, parabolic and triangular vertical notch weirs. Purdue Univ. Eng. Bull., 16, No. 2, Res. Series 40

Haghiabi, A. H., Parsaie, A., & Ememgholizadeh, S. (2018). Prediction of discharge coefficient of triangular labyrinth weirs using Adaptive Neuro Fuzzy Inference System. Alexandria Engineering Journal, 57(3), 1773-1782.

Heidari, E., Sobati, M. A., & Movahedirad, S. (2016). Accurate prediction of nanofluid viscosity using a multilayer perceptron artificial neural network (MLP-ANN). Chemometrics and intelligent laboratory systems, 155, 73-85.

Herschy R. W. (1978), Hydrometry principles and practices. Department of the Environment Water Data Unit; Reading, A Wiley – Interscience Publication, John Wiley and Sons

Hertzler, R. A. (1938). Determination of a formular for the 1200 V-notch weir. Civil Engineering, 756.

Jan Chyan-Deng, Chia-Jung Chang, and Feng-Hao Kuo (2009), Experiments on Discharge Equations of Compound Broad-Crested Weirs. Journal of Irrigation and Drainage Engineering © Asce / July/August 2009 / 511

Jan Chyan-Deng, Chia-Jung Chang, and Ming-His Lee (2006), Discussion of Design and calibration of compound sharp-crested weir by J. Martinez et al. Journal of Hydraulic Engineering, 132(8), 868–871.

Karami, H., Karimi, S., Bonakdari, H., & Shamshirband, S. (2018). Predicting discharge coefficient of triangular labyrinth weir using extreme learning machine, artificial neural network and genetic programming. Neural Computing and Applications, 29(11), 983-989.

King, H. W. (1916). Flow of water over right-angled V-notch weir. Univ. Mich. Technic. 29, No. 3, 189

Khalifa, S. Y., & Umar, A. (2018). Evaluation of Unsteady Open Channel Flow Characteristics over Crump Weir. ATBU Journal of Science, Technology and Education, 6(4), 306-315.

Lenz, A. T., (1943). Viscosity and surface tension effects in V-notch weir coefficients. Trans. A.S.C.E., 108

Martinez J., Reca J., Morillas M. T., and López J. G.; (2005), Discussion of Design and Calibration of a Compound Sharp-Crested Weir. Journal of Hydraulic Engineering © ASCE Vol. 131, No.2, pp. 112-116.

Mehr, A. D., Nourani, V., Kahya, E., Hrnjica, B., Sattar, A. M., & Yaseen, Z. M. (2018). Genetic programming in water resources engineering: A state-of-the-art review. Journal of Hydrology, 566, 643-667.

Moazamnia M, Hassanzadeh Y, Nadiri AA, Khatibi R, Sadeghfam S (2019) Formulating a strategy to combine artificial intelligence models using Bayesian model averaging to study a distressed aquifer with sparse data availability. J Hydrol 571:765–781

Muhammad, M. M., Yusof, K. W., Mustafa, M. R. U., Zakaria, N. A., & Ab Ghani, A. (2018). Prediction models for flow resistance in flexible vegetated channels. International journal of river basin management, 16(4), 427-437.

Nadiri A. A, Sedghi Z, Khatibi R, Sadeghfam S (2018) Mapping specific vulnerability of multiple confined and unconfined aquifers by using artificial intelligence to learn from multiple DRASTIC frameworks. J Environ Manage 227:415–428

Piratheepan M., Winston N.E.F., and Pathirana K.P.P. (2006), Discharge measurements in open channels using compound sharp-crested weirs. Journal of the Institution of Engineers, Sri Lanka Vol. xxxx, No. 03, pp.31-38.

Richard H. French (1985), “Open-Channel Hydraulics.” Mc Graw Hill, New York.

Rickard C.,Day R.,Purseglove J., 2003," River Weirs – Good Practice Guide", Environment. Agency, Rio House, Waterside Drive, Aztec West, Almondsbury, Bristol, BS32 4UD.

Roushangar K, Alami MT, Majedi Shiri J, Asl M (2017) Determining discharge coefficient of the labyrinth and arced labyrinth weirs using support vector machine. Hydrol Res 49(3):924–938

Sadeghfam S, Daneshfaraz R, Khatibi R, Minaei O (2019) Experimental studies on scour of supercritical flow jets in upstream of screens and modelling scouring dimensions using artificial intelligence to combine multiple models (AIMM). J Hydroinform. https ://doi.org/10.2166/hydro .2019.076

Sanikhani, H., Kisi, O., Maroufpoor, E., & Yaseen, Z. M. (2019). Temperature-based modeling of reference evapotranspiration using several artificial intelligence models: application of different modeling scenarios. Theoretical and applied climatology, 135(1-2), 449-462.

Sattar, A. A., Elhakeem, M., Rezaie-Balf, M., Gharabaghi, B., & Bonakdari, H. (2019). Artificial intelligence models for prediction of the aeration efficiency of the stepped weir. Flow Measurement and Instrumentation, 65, 78-89.

Shen, J. (1960). Discharge characteristics of triangular-notch thin-plate weirs. U.S. Dept. of Interior, Geological Survey, draft for I.S.O.

Simon A. L. (1976). Practical hydraulics. John Wiley and Sons, Inc. New York. London. Sydney. Toronto.

Yousif, A. A., Sulaiman, S. O., Diop, L., Ehteram, M., Shahid, S., Al-Ansari, N., & Yaseen, Z. M. (2019). Open channel sluice gate scouring parameters prediction: different scenarios of dimensional and non-dimensional input parameters. Water, 11(2), 353.

Zahabi H, Torabi M, Alamatian E, Bahiraei M, Goodarzi M (2018) Effects of geometry and hydraulic characteristics of shallow reservoirs on sediment entrapment. Water 10(12):1725 Zhou Q, Zhou H,

Zhou Q, Yang F, Luo L, Li T (2015) Structural damage detection based on posteriorprobability support vector machine and Dempster-Shafer evidence theory. Appl Soft Comput 36:368–374

Zounemat-Kermani, M., & Mahdavi-Meymand, A. (2019). Hybrid meta-heuristics artificial intelligence models in simulating discharge passing the piano key weirs. Journal of Hydrology, 569, 12-21.


Refbacks

  • There are currently no refbacks.