کاربرد مدل‌های هوش مبتنی بر محاسبات نرم در بررسی میزان ضریب تخلیه دریچه کشویی در حالت جریان آزاد و آستانه متقارن به کمک مدل‌های KNN، ANN، GEP و SVM

نوع مقاله : پژوهشی

نویسندگان

1 گروه مهندسی عمران، دانشکده مهندسی عمران، دانشگاه تبریز، تبریز، ایران

2 گروه مهندسی عمران، دانشکده فنی و مهندسی، دانشگاه مراغه، مراغه، ایران

چکیده

در پژوهش حاضر میزان ضریب‌دبی دریچه کشویی با استفاده از روش‌های داده کاوی مبتنی بر مدل‌های ماشین‌بردار پشتیبان (SVM)، برنامه‌ریزی بیان ژن (GEP)، روش شبکه عصبی مصنوعی (ANN) و الگوریتم K نزدیک‌ترین همسایه (KNN) برای نخستین رابطه تئوری ارائه شده برای دریچه‌های کشویی در حالت آستانه غیرهم‌عرض، مورد ارزیابی قرار گرفت، تا عملکرد آن با استفاده از روش‌های محاسبات نرم سنجیده شود. برای مدل SVM، کرنل تابع پایه شعاعی (RBF) نتایج بهتری در مقایسه با کرنل‌های چند جمله‌ای (Polynomial)، خطی (Linear) و سیگموئید (Sigmoid) دارد. شاخص‌های آماری R، KGE، RMSE و MRE% برای مدل SVM-RBF در مرحله آزمون به‌ترتیب 96/0، 90/0، 018/0 و 92/1 است. در مدل KNN فاصله اندازه‌گیری Manhattan دقت بالاتری در پیش‌بینی ضریب‌دبی نسبت به معیارهای Euclidean، Euclidean Squared و Chebychev داشت. روش ANN در مقایسه با مدل‌های SVM، GEP و KNN دقت بیشتری دارد به‌طوری‌که برای این مدل 15/1=MRE% و 0098/0=RMSE است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Application of intelligence models based on soft computing in investigating the discharge coefficient of the sluice gate under free-flow condition and symmetrical sill with the help of KNN, ANN, GEP and SVM models

نویسندگان [English]

  • H.R. Abbaszadeh 1
  • Y. Hassanzadeh 1
  • R. Daneshfaraz 2
  • R. Norouzi 2
1 Ph.D. Student, Dept. of Civil Engineering, Faculty of Civil Engineering, University of Tabriz, Tabriz, Iran.
2 Professor, Dept. of Civil Engineering, Faculty of Engineering, University of Maragheh, Maragheh, Iran.
چکیده [English]

The use of sills with the gates leads to a reduction in the height of the gate. The sills affect the flow and change quantities, especially the discharge coefficient. In the present research, the discharge coefficient of the sluice gate is examined for the first presented theoretical relationship in a non-suppressed sill state to measure its performance using soft computing methods. For the models, 70% of the data were used for the training and the rest for the testing phases. The results of statistical indicators showed that in all SVM, KNN, GEP, and ANN models, the model with all input parameters was recognized as the superior model. In the SVM model, the results of various kernels showed that the Radial Basis Function kernel has better results in predicting the discharge coefficient compared to the Polynomial, Linear, and Sigmoid kernels. The results of the correlation coefficient (R), Root Mean Square Error (RMSE), mean percentage Relative Error (MRE%), and Kling Gupta Efficiency (KGE) in the test stage for the SVM model were 0.96, 0.018, 0.90, and 1.92%, respectively. The neighbor coefficient (K) results showed that in the K equal 2, the RMSE and MRE had a lower value and were close to the experimental results. In addition, in the KNN model, among distance criteria measures (Manhattan, Euclidean, Euclidean Squared, and Chebychev), the Manhattan criteria have a higher accuracy in predicting the discharge coefficient than the others. In the testing phase, this model's results were 0.97, 0.016, 0.96, and 1.70%. In addition, the results for the GEP model were 0.98, 0.019, 0.85, and 2.28%, respectively. In the present research, the ANN method is more accurate compared to SVM, GEP, and KNN models, so, for the ANN model, the KGE was in the very good range.

کلیدواژه‌ها [English]

  • Discharge measurement
  • Discharge coefficient
  • Control structure
  • Intelligent models
  • Statistical indicators
1. Negm, A.M., Alhamid, A.A. and El-Saiad, A.A., 1998. Submerged flow below sluice gate with a sill. Proceedings of International Conference on Hydro-Science and Engineering Hydro-Science and Engineering ICHE98, Advan ces in Hydro-Science and Engineering, Cottbus/Berlin, G. 2. Daneshfaraz, R. Norouzi, R. Abbaszadeh, H. and Azamathulla, H.M., 2022. Theoretical and experimental analysis of applicability of sill with different widths on the gate discharge coefficients. Water Supply, 22 (10), pp.7767–7781. DOI: https://doi.org/10.2166/ws.2022.354 3. Alhamid, A.A., 1999. Coefficient of discharge for free flow sluice gates. Journal of King Saud University - Engineering Sciences, 11 (1), pp.33-47. DOI: https://doi.org/10.1016/S1018-3639(18)30989-9 4. Salmasi, F. and Norouzi Sarkarabad, R., 2018. Investigation of different geometric shapes of sills on discharge coefficient of vertical sluice gate. Amirkabir Journal of Civil Engineering, 52 (1), 2-2 Doi: 10.22060/ceej.2018.14232.5596. DOI: https://doi.org/10.22060/ceej.2018.14232.5596 5. Karami, S. Heidari, M.M. and Adib Rad, M.H., 2020. Investigation of free flow under the sluice gate with the sill using flow-3D model. Iran J Sci Technol Trans Civ Eng, 44, pp.317–324. DOI: https://doi.org/10.1007/s40996-019-00310-x 6. Salmasi, F. and Abraham, J., 2020. Prediction of discharge coefficients for sluice gates equipped with different geometric sills under the gate using multiple non-linear regression (MNLR). Journal of Hydrology, 597, 125728. DOI: https://doi.org/10.1016/j.jhydrol.2020.125728 7. Ghorbani, M.A. Salmasi, F. Saggi, M.K. Bhatia, A.S. Kahya, E. and Norouzi, R., 2020. Deep learning under H2O framework: A novel approach for quantitative analysis of discharge coefficient in sluice gates. Journal of Hydroinformatics, 22 (6), pp.1603-1619. DOI: https://doi.org/10.2166/hydro.2020.003 8. Daneshfaraz, R. Norouzi, R. Abbaszadeh, H. Kuriqi, A. and Di Francesco, S., Influence of sill on the hydraulic regime in sluice gates: An experimental and numerical analysis. Fluids, 7 (7), 244. DOI: https://doi.org/10.3390/fluids7070244 9. Lauria, A. Calomino, F. Alfonsi, G. and D’Ippolito, A., 2020. Discharge Coefficients for Sluice Gates Set in Weirs at Different Upstream Wall Inclinations. Water, 12 (1), 245. DOI: https://doi.org/10.3390/w12010245 10. Raju, R., 1984. Scale Effects in Analysis of Discharge Characteristics of Weir and Sluice Gates; Kobus: Esslingen am Neckar, Germany. 11. Vapnik. VN., 1995. The Nature of Statistical Learning Theory, Springer-Verlag, New York. 12. Jahed Armaghani, D. Asteris, P.G. Askarian, B. Hasanipanah, M. Tarinejad, R. and Huynh, V.V., 2020. Examining hybrid and single SVM models with different kernels to predict rock brittleness. Sustainability, 12 (6), 2229. DOI: https://doi.org/10.3390/su12062229 13. Su, M.Y., 2011. Real-Time anomaly detection systems for denial-of-service attacks by weighted K-nearest neighbor classifiers. Expert Systems with Applications, 38, pp.3492–3498. DOI: https://doi.org/10.1016/j.eswa.2010.08.137 14. Al-Bulushi, N.I. King, P.R. Blunt, M.J. and Kraaijveld, M., 2010. Artificial neural networks workflow and its application in the petroleum industry. Neural Comput. Appl, 21, pp.409–421. DOI: https://doi.org/10.1007/s00521-010-0501-6 15. Mohammed, A.Y. and Sharifi, A., 2020. Gene Expression Programming (GEP) to predict coefficient of discharge for oblique side weir. Appl Water Sci, 10, 145. DOI: https://doi.org/10.1007/s13201-020-01211-5 16. Gupta, H.V. Kling, H. Yilmaz, K.K. and Martinez, G.F., 2009. Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling. J. Hydrol, 377 (1-2), pp.80–91. DOI: https://doi.org/10.1016/j.jhydrol.2009.08.003