Practical Design of Stepped Spillways Using Machine Learning Methods and Fuzzy Inference System

Abstract

Energy-dissipating pools or flip bucket structures reduce the energy of downstream flow in conventional spillways. Recently, stepped spillways have been widely used to dissipate the flow of energy downstream. Flows on the stepped spillways are complex and advanced techniques such as Fuzzy Logic (FL), Adaptive Neuro-Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN), Genetic Programming (GP), Deep Learning, and Tree-Based models are required to calculate energy dissipation ratios. Fuzzy Logic has the advantage of considering physical processes when examining problems using rule bases. In this study, energy dissipation over stepped spillways is calculated using machine learning methods and the Fuzzy Inference System in Python programming language. Experimental data by different researchers are used to model stepped spillways. Two new parameters, such as an approach channel and step-top geometric ratios, are used in addition to the literature to obtain energy dissipation ratios on stepped spillways. Artificial Neural Network Regressor (ANN) from machine learning methods gives minimum percentages and absolute errors (-0.117% and 1.398) and maximum R^2 values (0.976) for the testing dataset. Although the accuracy of the ANN method changes with hidden layer sizes and ratios between training and testing data, the Fuzzy Logic (FL) is independent to training data. The FL method represents good results with low Mean Percentages Error (MPE) and Mean Absolute Errors (MAE) (-1.688% and 2.000) and an R^2 value (0.951), and the produced Python function using the fuzzy inference system can be applied easily to different flow conditions and stepped spillways.

Keywords

• Stepped spillways
• energy dissipation
• skfuzzy
• fuzzy logic
• artificial neural network regressor
• machine learning methods.

Makine Öğrenme Yöntemleri ve Bulanık Çıkarım Sistemi Kullanılarak Basamaklı Dolusavakların Pratik Tasarımı

Abstract

Enerji sönümleyici havuzlar veya sıçratma eşiği yapıları, klasik dolusavakların mansabındaki akım enerjisini sönümlemektedir. Son yıllarda, akım enerjisini sönümlemek amacıyla basamaklı dolusavaklar yaygın olarak kullanılmaktadır. Basamaklı dolusavaklardaki akım karmaşık olup enerji sönümleme oranlarını hesaplamak için ileri tekniklere sahip Bulanık Mantık (BM), Yapay Sinir Ağları Uyarlamalı - Bulanık Çıkarım Sistemi (YSA- BÇS), Yapay Sinir Ağları (YSA), Genetik Programlama (GP), Derin Öğrenme ve Ağaç Tabanlı modeller kullanılmaktadır. BM, kural tabanları kullanarak problemleri incelerken fiziksel süreçleri göz önünde bulundurabilme avantajına sahiptir. Bu çalışmada, Python programlama dilinde makine öğrenmesi yöntemleri ve Bulanık Çıkarım Sistemi kullanılarak basamaklı dolusavakların enerji sönümleme oranları hesaplanmıştır. Basamaklı dolusavakları modellemek için farklı araştırmacıların deneysel verileri kullanılmıştır. Basamaklı dolusavaklarda enerji sönümleme oranlarını tahmin edebilmek için literatürde kullanılan parametrelere ek olarak yaklaşım kanalı ve basamak üstü geometrik oranları gibi iki yeni parametre kullanılmıştır. Makine öğrenmesi yöntemlerinden YSA ile test veri seti için minimum yüzde ve mutlak hata (-% 0.117 ve 1.398) ve maksimum R^2 değerleri (0.976) elde edilmiştir. YSA yönteminin doğruluğu gizli katman boyutları ve eğitim-test veri oranlarıyla değişse de Bulanık Mantık (BM) yönteminin sonuçları eğitim verilerinden bağımsızdır. BM yönteminde düşük ortalama yüzdelik ve mutlak hatalar (% -1.688 ve 2.000) ve 0.951 R^2 değeri ile iyi sonuçlar elde edilmiştir ve BM yöntemi kullanılarak üretilen Python fonksiyonu farklı akış koşullarına ve basamaklı dolusavaklara kolayca uygulanabilme imkânına sahiptir.

Keywords

• Basamaklı dolusavak
• Enerji sönümleme
• skfuzzy
• Bulanık mantık
• yapay sinir ağı regresörü
• makine öğrenmesi yöntemleri.

References

1. Chanson, H. (2000). Forum article. Hydraulics of Stepped Spillways: Current Status. Jl Hyd Engrg, ASCE,126.
2. Chanson H. (2004). Drag reduction in skimming flow on stepped spillways by aeration. J Hydraul Res, 42:316–22. https://doi.org/10.1080/00221686.2004.9728397.
3. Berkün, M. (2007) Su Yapıları. Birsen Yayınevi [in Turkish].
4. Boes, RM., Chanson, H., Matos, J., Ohtsu, I., Yasuda, Y., Takahasi, M. (2000). Characteristics of Skimming Flow over Stepped Spillways. J Hydraul Eng, 126:860–73. https://doi.org/10.1061/(asce)0733-9429(2000)126:11(860).
5. Boes, RM., Hager, WH. (2003). Hydraulic Design of Stepped Spillways. J Hydraul Eng, 129:671–9. https://doi.org/10.1061/(asce)0733-9429(2003)129:9(671).
6. Chanson, H. (1993). Stepped spillway flows and air entrainment. Can J Civ Eng, 20:422–35. https://doi.org/10.1139/l93-057.
7. Chanson, H. (1998). Review of studies on stepped channel flows. Work Flow Charact around Hydraul Struct River Environ, 25.
8. Bai, ZL., Peng, Y., Zhang, JM. (2017). Three-Dimensional Turbulence Simulation of Flow in a V-Shaped Stepped Spillway. J Hydraul Eng, 143:06017011. https://doi.org/10.1061/(asce)hy.1943-7900.0001328.

9. Felder, S., Chanson, H. (2014). Effects of Step Pool Porosity upon Flow Aeration and Energy Dissipation on Pooled Stepped Spillways. J Hydraul Eng, 140:04014002. https://doi.org/10.1061/(asce)hy.1943-7900.0000858.
10. Zare, HK., Doering, JC. (2012). Effect of rounding edges of stepped spillways on the flow characteristics. Can J Civ Eng, 39:140–53. https://doi.org/10.1139/L11-121.
11. Zhang, G, Chanson, H. (2018). Effects of Step and Cavity Shapes on Aeration and Energy Dissipation Performances of Stepped Chutes. J Hydraul Eng, 144:04018060. https://doi.org/10.1061/(asce)hy.1943-7900.0001505.
12. Zhou, Y., Wu, J., Ma, F., Hu, J. (2020). Uniform flow and energy dissipation of hydraulic-jump-stepped spillways. Water Sci Technol Water Supply, 20:1546–53. https://doi.org/10.2166/ws.2020.056.
13. Felder, S., Fromm, C., Chanson, H. (2012) The Universıty of Queensland Report Ch86/12 Air Entrainment And Energy Dissipation On A 8.9° Slope Stepped Spillway with Flat and Pooled Steps School of Civil Engineering.
14. Felder, S., Guenther, P., Chanson, H. (2012). The University of Queensland Report CH87/12 Air-water flow properties and energy dissipation on stepped spillways: a physical study of several pooled stepped configurations. School of Civil Engineering.
15. Mero, S., Mitchell, S. (2017). Investigation of energy dissipation and flow regime over various forms of stepped spillways. Water Environ J, 31:127–37. https://doi.org/10.1111/wej.12224.
16. Peyras, L., Royet, P., Degoutte, G. (1992). Flow and Energy Dissipation over Stepped Gabion Weirs. J Hydraul Eng, 118:707–17. https://doi.org/10.1061/(asce)0733-9429(1992)118:5(707).
17. Rice, CE., Kadavy, KC. (1996). Model Study of a Roller Compacted Concrete Stepped Spillway. J Hydraul Eng, 122:292–7. https://doi.org/10.1061/(asce)0733-9429(1996)122:6(292).
18. Torabi, H., Parsaie, A., Yonesi, H., Mozafari, E. (2018). Energy Dissipation on Rough Stepped Spillways. Iran J Sci Technol - Trans Civ Eng, 42:325–30. https://doi.org/10.1007/s40996-018-0092-5.
19. Wu, J., Qian, S., Wang, Y., Zhou, Y. (2020). Residual Energy on Ski-Jump-Step and Stepped Spillways with Various Step Configurations. J Hydraul Eng, 146:06020002. https://doi.org/10.1061/(asce)hy.1943-7900.0001710.
20. Zare, HK., Doering, JC. (2012). Inception Point of Air Entrainment and Training Wall Characteristics of Baffles and Sills on Stepped Spillways. J Hydraul Eng, 138:1119–24. https://doi.org/10.1061/(asce)hy.1943-7900.0000630.
21. Ashoor, A., Riazi, A. (2019). Stepped Spillways and Energy Dissipation: A Non-Uniform Step Length Approach. Appl Sci, 9:5071. https://doi.org/10.3390/app9235071.
22. De Carvalho, RF., Amador, AT. (2009). Physical and numerical investigation of the skimming flow over a stepped spillway. Adv Water Resour Hydraul Eng - Proc 16th IAHR-APD Congr 3rd Symp IAHR-ISHS, 1767–72. https://doi.org/10.1007/978-3-540-89465-0_304/COVER.
23. Tabbara, M., Chatila, J., Awwad, R. (2005). Computational simulation of flow over stepped spillways. Comput Struct, 83:2215–24. https://doi.org/10.1016/j.compstruc.2005.04.005.
24. Yalcin, EE., Ikinciogullari, E., Kaya, N. (2023). Comparison of Turbulence Methods for a Stepped Spillway Using Computational Fluid Dynamics. Iran J Sci Technol - Trans Civ Eng, 47:3895–911. https://doi.org/10.1007/S40996-023-01127-5/FIGURES/14.
25. Ghaderi, A., Abbasi, S., Abraham, J., Azamathulla, HM. (2020). Efficiency of Trapezoidal Labyrinth Shaped stepped spillways. Flow Meas Instrum, 72:101711. https://doi.org/10.1016/j.flowmeasinst.2020.101711.
26. Ghaderi, A., Abbasi, S., Di Francesco, S. (2021). Numerical Study on the Hydraulic Properties of Flow over Different Pooled Stepped Spillways. Water, 13:710. https://doi.org/10.3390/w13050710.
27. Ikinciogullari, E. (2023). Stepped spillway design for energy dissipation. Water Supply, 23:749–63. https://doi.org/10.2166/WS.2023.016.
28. Ikinciogullari, E. (2023). A novel design for stepped spillway using staggered labyrinth trapezoidal steps. Flow Meas Instrum, 93:102439. https://doi.org/10.1016/J.FLOWMEASINST.2023.102439.
29. Ikinciogullari, E. (2023). Energy dissipation performance of the trapezoidal stepped spillway. J Eng Res,11(2A). https://doi.org/10.36909/JER.13649.
30. Ikinciogullari, E. (2024). Energy dissipation performance of labyrinth and harmonic stepped spillways. J Hydroinformatics 2024. https://doi.org/10.2166/HYDRO.2024.221.
31. [31] Mohammad, M., Tabari, R., Tavakoli, S. (2016). Effects of Stepped Spillway Geometry on Flow Pattern and Energy Dissipation. Arab J Sci Eng, 41:1215–24. https://doi.org/10.1007/s13369-015-1874-8.
32. Reeve, DE., Zuhaira, AA., Karunarathna, H. (2019). Computational investigation of hydraulic performance variation with geometry in gabion stepped spillways. Water Sci Eng, 12:62–72. https://doi.org/10.1016/j.wse.2019.04.002.
33. Korkut, O., Demirel, S., Taşar, B., Kaya, YZ. (2023). Adana İli Referans Evapotranspirasyon Miktarının Bulanık Smrgt, Anfis ve Çoklu Doğrusal Regresyon Kullanılarak Tahmini. Osmaniye Korkut Ata Üniversitesi Fen Bilim Enstitüsü Derg, 6:106–20. https://doi.org/10.47495/OKUFBED.1079066.
34. Üneş, F., Taşar, B., Demirci, M., Zelenakova, M., Kaya, YZ., Varçin, H. (2021). Daily Suspended Sediment Prediction Using Seasonal Time Series and Artificial Intelligence Techniques. Rocz Ochr Sr, 23:117–37. https://doi.org/10.54740/ROS.2021.008.
35. Salmasi, F., Özger, M. (2014). Neuro-Fuzzy Approach for Estimating Energy Dissipation in Skimming Flow over Stepped Spillways. Arab J Sci Eng, 39:6099–108. https://doi.org/10.1007/S13369-014-1240-2/METRICS.
36. Roushangar, K., Akhgar, S., Salmasi, F., Shiri, J. (2016). Neural networks- and neuro-fuzzy-based determination of influential parameters on energy dissipation over stepped spillways under nappe flow regime. https://doi.org/10.1080/09715010.2016.1235472.
37. Mojtahedi, A., Soori, N., Mohammadian, M. (2020). Energy dissipation evaluation for stepped spillway using a fuzzy inference system. SN Appl Sci, 2:1–13. https://doi.org/10.1007/S42452-020-03258-0/
38. Irzooki, RH., Rasheed Mohammed, J., Ameen, AS. (2016). Computational Fluid Dynamics Modeling of Flow over Stepped Spillway. Tikrit J Eng Sci Available Online Tikrit J Eng Sci, 23:1–11.
39. Geurts, P., Ernst, D., Wehenkel, L. (2006). Extremely randomized trees. Mach Learn. https://doi.org/10.1007/s10994-006-6226-1.
40. Chen, T., Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. https://doi.org/10.1145/2939672.2939785.
41. Kaya, H., Guler, E., Kırmacı, V. (2023). Prediction of temperature separation of a nitrogen-driven vortex tube with linear, kNN, SVM, and RF regression models. Neural Comput Appl. https://doi.org/10.1007/s00521-022-08030-6.
42. Bakır, R., Orak, C., Yüksel, A. (2024). Optimizing hydrogen evolution prediction: A unified approach using random forests, lightGBM, and Bagging Regressor ensemble model. Int J Hydrogen Energy, 67:101–10. https://doi.org/https://doi.org/10.1016/j.ijhydene.2024.04.173.
43. Golgiyaz, S., Cellek, MS., Daskin, M., Talu, MF., Onat, C. (2023). Flame stability measurement through image moments and texture analysis. Meas Sci Technol. https://doi.org/10.1088/1361-6501/acb001.
44. Zadeh L. A. (1967). Fuzzy sets. Inf Control, 8:38–53.
45. Singh, S., Singh, S., Banga, VK. (2020). Design of fuzzy logic system framework using evolutionary techniques. Soft Comput, 24:4455–68. https://doi.org/10.1007/s00500-019-04207-9.
46. Mamdani, EH., Assilian, S. (1975). An experiment in linguistic synthesis with a fuzzy logic controller. Int J Man Mach Stud. https://doi.org/10.1016/S0020-7373(75)80002-2.
47. Șen Z. (2009). Fuzzy logic and hydrological modeling.
48. Li, S., Zhang, J., Xu, W. (2018). Numerical investigation of air–water flow properties over steep flat and pooled stepped spillways. J Hydraul Res, 56:1–14. https://doi.org/10.1080/00221686.2017.1286393.
49. Alashan, S. (2020) Innovative Trend Analysis Methodology in Logarithmic Axis. Konjes 2020;8:573–85. https://doi.org/doi:10.36306/konjes.668212.