دانشگاه مازندران

 آمار

تعداد نشریات32
تعداد شماره‌ها570
تعداد مقالات5,523
تعداد مشاهده مقاله8,423,778
تعداد دریافت فایل اصل مقاله6,196,792
Behnamtalab, Ehsan, Behnamtalab, Mohsen. (1405). A Hybrid CFD–Machine Learning Framework for Modeling Discharge Hysteresis in Twin Circular Culverts. پژوهشنامه مدیریت اجرایی, 3(1), 117-130. doi: 10.22080/ceas.2026.31318.1079
Ehsan Behnamtalab; Mohsen Behnamtalab. "A Hybrid CFD–Machine Learning Framework for Modeling Discharge Hysteresis in Twin Circular Culverts". پژوهشنامه مدیریت اجرایی, 3, 1, 1405, 117-130. doi: 10.22080/ceas.2026.31318.1079
Behnamtalab, Ehsan, Behnamtalab, Mohsen. (1405). 'A Hybrid CFD–Machine Learning Framework for Modeling Discharge Hysteresis in Twin Circular Culverts', پژوهشنامه مدیریت اجرایی, 3(1), pp. 117-130. doi: 10.22080/ceas.2026.31318.1079
Behnamtalab, Ehsan, Behnamtalab, Mohsen. A Hybrid CFD–Machine Learning Framework for Modeling Discharge Hysteresis in Twin Circular Culverts. پژوهشنامه مدیریت اجرایی, 1405; 3(1): 117-130. doi: 10.22080/ceas.2026.31318.1079

A Hybrid CFD–Machine Learning Framework for Modeling Discharge Hysteresis in Twin Circular Culverts

Civil Engineering and Applied Solutions
دوره 3، شماره 1، فروردین 2027، صفحه 117-130    اصل مقاله (949.53 K)
نوع مقاله: Original Article
شناسه دیجیتال (DOI): 10.22080/ceas.2026.31318.1079
نویسندگان
Ehsan Behnamtalab* 1؛ Mohsen Behnamtalab2
1Department of Engineering, Civil Engineering Group, Hakim Sabzevari University, Sabzevar, Iran
2Civil Engineering Department, Sharif University of Technology, Tehran, Iran
تاریخ دریافت: 29 بهمن 1404،  تاریخ بازنگری: 06 فروردین 1405،  تاریخ پذیرش: 13 خرداد 1405 
چکیده
This study investigates the hydraulic behavior of twin circular culverts under unsteady flow, considering rising and receding inlet flows and varying upstream water levels. Three-dimensional numerical simulations were conducted using RANS equations with the RNG k–ε turbulence model and validated against laboratory data, showing excellent agreement. Results indicate that through-flow discharge remains nearly constant across rising and receding phases, while overtopping flow exhibits significant differences (~22%). Outflow during recession is approximately 1.5 times higher than during the rising stage. Complementary data-driven modeling using eight machine learning algorithms, including Gradient Boosting, AdaBoost, Random Forest, and Neural Networks, demonstrated high accuracy in predicting nonlinear discharge–head relationships, with R² up to 0.992 for numerical and 0.985 for experimental data. Models performed better during receding phases due to more stable flow conditions. The integration of CFD simulations and machine learning provides detailed flow insights and rapid, accurate discharge estimation, offering a reliable framework for culvert design, flow assessment, and hydraulic optimization under complex unsteady conditions.
کلیدواژه‌ها
Twin culvert؛ Head-Discharge؛ Numerical simulation؛ Machine learning؛ RANS
مراجع
  1. Norman, J. M., Houghtalen, R.J. and Johnston, W.J Hydraulic design of highway culverts. Second ed. Washington, DC (US): FHWA; 2001.
  2. Chang, H.-K., Tan, Y.-C., Lai, J.-S., Pan, T.-Y., Liu, T.-M., Tung, C.-P. Improvement of a drainage system for flood management with assessment of the potential effects of climate change. Hydrological Sciences Journal, 2013; 58: 1581–1597. doi:10.1080/02626667.2013.836276.
  3. Mamo, T. G. Evaluation of the Potential Impact of Rainfall Intensity Variation due to Climate Change on Existing Drainage Infrastructure. Journal of Irrigation and Drainage Engineering, 2015; 141: 05015002. doi:10.1061/(ASCE)IR.1943-4774.0000887.
  4. Pereira, M., Fernandes, L., Macário, E., Gaspar, S., Pinto, J. Climate Change Impacts in the Design of Drainage Systems: Case Study of Portugal. Journal of Irrigation and Drainage Engineering, 2015; 141: 05014009. doi:10.1061/(ASCE)IR.1943-4774.0000788.
  5. Todeschini, S. Trends in long daily rainfall series of Lombardia (northern Italy) affecting urban stormwater control. International Journal of Climatology, 2012; 32: 900–919. doi:10.1002/joc.2313.
  6. Wang, S., Feng, Z., Guo, C., Wei, J., Zhao, R. Research on the method of identifying vertical earth pressure of hinged prefabricated culvert box culvert on the top slab. Scientific Reports, 2024; 14: 18844. doi:10.1038/s41598-024-69893-4.
  7. Gao, C., Elzarka, H. The use of decision tree based predictive models for improving the culvert inspection process. Advanced Engineering Informatics, 2021; 47: 101203. doi:10.1016/j.aei.2020.101203.
  8. Othman, K., Kavianpour, M., Amini, A., Aminpour, Y. A state-of-the-art review of physical modeling of scouring at the culvert outlet. ISH Journal of Hydraulic Engineering, 2024; 30: 1–8. doi:10.1080/09715010.2024.2340626.
  9. Ahmed, K. O., Kavianpour, M. R., Amini, A., Aminpour, Y. Physical modeling of the effect of shape, blockage, and flow variability on scour in culvert outlets. PLoS One, 2024; 19: e0306252. doi:10.1371/journal.pone.0306252.
  10. Dasika, B. New Approach to Design of Culverts. Journal of Irrigation and Drainage Engineering, 1995; 121: 261–264. doi:10.1061/(ASCE)0733-9437(1995)121:3(261).
  11. Montes, J. S., Dasika, B. Discussion and Closure: New Approach to Design of Culverts. Journal of Irrigation and Drainage Engineering, 1997; 123: 71–72. doi:10.1061/(ASCE)0733-9437(1997)123:1(71).
  12. Hager, W. H., Giudice, G. D. Generalized Culvert Design Diagram. Journal of Irrigation and Drainage Engineering, 1998; 124: 271–274. doi:10.1061/(ASCE)0733-9437(1998)124:5(271).
  13. Johnson, P., Brown, E. Stream Assessment for Multicell Culvert Use. Journal of Hydraulic Engineering-asce - J HYDRAUL ENG-ASCE, 2000; 126: 381–386. doi:10.1061/(ASCE)0733-9429(2000)126:5(381).
  14. Ansar, M., Alexis, A., Damisse, E. Flow computations at Kissimmee River gated structures: A comparative study. South Florida (FL): Hydrology and Hydraulics Dept; 2002. Report No.:
  15. Lee, K. S., Jin, R. S. Development of program for box culverts design. In: Proceedings of the 35th Conference; 2003; South Korea. p. 2686–2689.
  16. Ku, H. J., Jun, K. S. Development of culvert design model. In: Proceedings of Korea Water Resources Association Conference; 2008; South Korea. p. 645–649.
  17. Richmond, M. C., Deng, Z., Guensch, G. R., Tritico, H., Pearson, W. H. Mean flow and turbulence characteristics of a full-scale spiral corrugated culvert with implications for fish passage. Ecological Engineering, 2007; 30: 333–340. doi:10.1016/j.ecoleng.2007.04.011.
  18. Chanson, H. Hydraulics of open channel flow. Second ed. London (UK): Elsevier; 2004. doi:10.1016/B978-0-7506-5978-9.X5000-4.
  19. Chow, V. T. Open-Channel Hydraulic. First ed. Columbus (OH): McGraw-Hill Education; 1959.
  20. Yoo, D.-H., Lee, S. Direct determination of the width or the height for a box culvert applying dimensionless equations. KSCE Journal of Civil Engineering, 2012; 16: 1302–1307. doi:10.1007/s12205-012-1695-1.
  21. Kang, M. S., Koo, J. H., Chun, J. A., Her, Y. G., Park, S. W., Yoo, K. Design of drainage culverts considering critical storm duration. Biosystems Engineering, 2009; 104: 425–434. doi:10.1016/j.biosystemseng.2009.07.004.
  22. May, L. W. Hydraulic Design Handbook. First ed. Columbus (OH): McGraw-Hill Education; 1999.
  23. Schall, J. D., Thompson, P. L., Zerges, S. M., Kilgore, R. T., Morris, J. L. Hydraulic Design of Highway Culverts. Third ed. Washington, DC (US): FHWA; 2012.
  24. French, J. L. First Progress Report on Hydraulics of Short Pipes: Hydraulic Characteristics of Commonly Used Pipe Entrances. Washington, DC (US): U.S. Dept. of Commerce, National Bureau of Standards; 1955. Report No.: NBS Report no. 4444.
  25. French, J. L. Second Progress Report on Hydraulics of Culverts: Pressure and Resistance Characteristics of a Model Pipe Culvert. Washington, DC (US): U.S. Dept. of Commerce, National Bureau of Standards; 1956. Report No.: NBS Report no. 4911.
  26. French, J. L. Third Progress Report on Hydraulics of Culverts: Effect of Approach Channel Characteristics on Model Pipe Culvert Operation. Washington, DC (US): U.S. Dept. of Commerce, National Bureau of Standards; 1957. Report No.:
  27. French, J. L. Fourth Progress Report on Hydraulics of Culverts: Hydraulics of improved Inlet Structures for Pipe Culverts. Washington, DC (US): U.S. Dept. of Commerce, National Bureau of Standards; 1961. Report No.: NBS Report no. 7178.
  28. French, J. L. Sixth progress report on hydraulics of culverts: Tapered box culvert inlets. Washington, DC (US): U.S. Dept. of Commerce, National Bureau of Standards; 1966. Report No.: NBS Report no. 9355.
  29. French, J. L., Bossy, H. G. Seventh progress report on hydraulics of culverts: Tapered box culvert inlets with fall concentration in the inlet structure. Washington, DC (US): U.S. Dept. of Commerce, National Bureau of Standards; 1967. Report No.: NBS Report no. 9528.
  30. Lyn, D., Dey, S., Saksena, S., Merwade, V. Culvert versus Bridge Hydraulics for Larger-Span or Short Culverts. Journal of Hydraulic Engineering, 2024; 150: 04024002. doi:10.1061/JHEND8.HYENG-13650.
  31. Bodhaine, G. L. Measurement of peak discharge at culverts by indirect methods. Washington, DC (US): US Government Printing Office; 1968. Report No.: 03-A3.
  32. Aly, A. M. Machine Learning Reshaping Computational Fluid Dynamics: A Paradigm Shift in Accuracy and Speed. Fluids, 2025; 10: 275. doi:10.3390/fluids10100275.
  33. Mao, R., Lan, Y., Liang, L., Yu, T., Mu, M., Leng, W., Long, Z. Rapid CFD Prediction Based on Machine Learning Surrogate Model in Built Environment: A Review. Fluids, 2025; 10: 193. doi:10.3390/fluids10080193.
  34. Nie, Y., Yu, K. H., Wang, Y., Liu, P. Applications of machine learning and deep learning in hydrology from a bibliometric perspective: a comprehensive review. Discover Artificial Intelligence, 2025; 5: 242. doi:10.1007/s44163-025-00471-x.
  35. Jafari, S. M., Zahiri, A. R., Bozorg Hadad, O., Mohammad Rezapour Tabari, M. A hybrid of six soft models based on ANFIS for pipe failure rate forecasting and uncertainty analysis: a case study of Gorgan city water distribution network. Soft Computing, 2021; 25: 7459–7478. doi:10.1007/s00500-021-05706-4.
  36. Tabari, M. M. R., Sanayei, H. R. Z. Prediction of the intermediate block displacement of the dam crest using artificial neural network and support vector regression models. Soft Computing, 2019; 23: 9629–9645. doi:10.1007/s00500-018-3528-8.
  37. Qin, Y., Su, C., Chu, D., Zhang, J., Song, J. A Review of Application of Machine Learning in Storm Surge Problems. Journal of Marine Science and Engineering, 2023; 11: 1729. doi:10.3390/jmse11091729.
  38. Habib, M. A., Abolfathi, S., O’Sullivan, J. J., Salauddin, M. Efficient data-driven machine learning models for scour depth predictions at sloping sea defences. Frontiers in Built Environment, 2024; Volume 10 - 2024: doi:10.3389/fbuil.2024.1343398.
  39. Shah, S. A., Jehanzaib, M., Yoo, J., Hong, S., Kim, T.-W. Investigation of the Effects of Climate Variability, Anthropogenic Activities, and Climate Change on Streamflow Using Multi-Model Ensembles. Water, 2022; 14: 512. doi:10.3390/w14040512.
  40. Masoumi, F., Jorabloo, M., Shobeyri, G. Optimizing Reservoir Operations with Reinforcement Learning: A Data-Driven Framework. Civil Engineering and Applied Solutions, 2025; 1: 56–67. doi:10.22080/ceas.2025.29738.1032.
  41. Rodrigues, D. T., Santos e Silva, C. M., dos Reis, J. S., Palharini, R. S. A., Cabral Júnior, J. B., da Silva, H. J. F., Mutti, P. R., Bezerra, B. G., Gonçalves, W. A. Evaluation of the Integrated Multi-SatellitE Retrievals for the Global Precipitation Measurement (IMERG) Product in the São Francisco Basin (Brazil). Water, 2021; 13: 2714. doi:10.3390/w13192714.
  42. Židek, K., Piteľ, J., Balog, M., Hošovský, A., Hladký, V., Lazorík, P., Iakovets, A., Demčák, J. CNN Training Using 3D Virtual Models for Assisted Assembly with Mixed Reality and Collaborative Robots. Applied Sciences, 2021; 11: 4269. doi:10.3390/app11094269.
  43. Anderson, J. D., & Wendt, J. Computational fluid dynamics. ed. New York (NY): McGraw-hill; 1995.
  44. Hirt, C. W., Nichols, B. D. Volume of fluid (VOF) method for the dynamics of free boundaries. Journal of Computational Physics, 1981; 39: 201–225. doi:10.1016/0021-9991(81)90145-5.
  45. White, F. M., Majdalani, J. Viscous fluid flow. Fourth ed. New York (NY): McGraw-Hill; 2006.
  46. Santa Fe. Incorporated: FLOW-3D User’s Manual Version 9.3. New Mexico (NM): 2008.
  47. Hirt, C. W., Sicilian, J. M. A porosity technique for the definition of obstacles in rectangular cell meshes. In: International Conference on Numerical Ship Hydrodynamics, 4th; 1985; Washington, DC (US). p. 19.
  48. Hirt, C. W. T. CFD-101: The Basics of Computational Fluid Dynamics Modeling, FLOW-3D Manual, Flow Science Press, Flow Science, Inc. 2011. https://www.flow3d.com/resources/cfd-101/.
  49. Meselhe, E., Hebert, K. Laboratory Measurements of Flow through Culverts. Journal of Hydraulic Engineering-asce - J HYDRAUL ENG-ASCE, 2007; 133: 973–976. doi:10.1061/(ASCE)0733-9429(2007)133:8(973).
آمار
تعداد مشاهده مقاله: 35
تعداد دریافت فایل اصل مقاله: 17


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب