Journals / DSİ Teknik Bülteni / 2021 / Sayı: 138

THE PREDICTION OF END DEPTH RATIO WITH SUPPORT VECTOR REGRESSION: A FLOW MEASUREMENT TOOL FOR THE IRRIGATION CHANNELS

VEKTÖR DESTEK REGRESYON İLE DÜŞÜ DERİNLİK ORANI TAHMİNİ: SULAMA KANALLARI İÇİN BİR DEBİ ÖLÇÜM ARACI

Pages
1–10
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The purpose of the study is to demonstrate and discuss the success of the linear equations which were based on limited laboratory data with artificial intelligence models.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The necessity of metering discharge is important due to estimate correct supply of water according to plant and soil type and consequently estimate rational pricing.
📊
Key Findings & Data:A virtual experimental set up was utilized to generate 10 000 synthetic data.
💡
Conclusion & Impact:The purpose of the study is to demonstrate and discuss the success of the linear equations which were based on limited laboratory data with artificial intelligence models.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

The necessity of metering discharge is important due to estimate correct supply of water according to plant and soil type and consequently estimate rational pricing. The most common way is to use weirs, such us rectangular or triangular. However, those weirs should be cleaned regularly due to accumulation of sediment in front of the weirs. On the other hand, the channels can be constructed with a drop due to topography. There are some empirical approaches in the literature to estimate discharge by utilizing the relationship between drop depth and discharge. In the present study, it is provided to construct a virtual experimental set up via three-dimensional surface created by artificial intelligence model by learning from the end depth ratio (EDR) and discharge on rectangular open channels with varying surface roughness and bed slopes, collected by different researchers. A virtual experimental set up was utilized to generate 10 000 synthetic data. Those generated data were compared with two linear equations available in the literature. The purpose of the study is to demonstrate and discuss the success of the linear equations which were based on limited laboratory data with artificial intelligence models.

Özet

Toprağın yapısına ve bitki türüne göre yeterli miktarda sulama suyunun iletilmesine ve buna karşılık daha ölçülü bir yaklaşımla ücretlendirme yapılmasını sağlamak için akan suyun debisinin ölçülmesine duyulan ihtiyaç önemlidir. Dikdörtgen ve üçgen şeklindeki savaklar bu amaç için kullanılan en yaygın yöntemlerdendir. Ancak savakların önünde zaman içinde katı madde birikmesi olacağından düzenli olarak temizlenmeleri gerekmektedir. Bununla birlikte, arazinin topoğrafyası gereği iletim kanallarında zorunlu düşü yapılması gerekebilmektedir. Düşü derinliği ile debi arasındaki ilişki kullanılarak debi tahmini için halihazırda literatürde bazı ampirik yaklaşımlar mevcuttur. Bu çalışmada yapay zekâ modeli ile farklı araştırmacılar tarafından dikdörtgen açık kanallarda çeşitli pürüzlülük ve kanal taban eğimlerine karşılık ölçülen düşü derinlik oranları (DDO) ve debi verilerinden öğrenerek oluşturulan üç boyutlu yüzey ile sanal deney düzeneği kurulması sağlanmıştır. Oluşturulan sanal deney düzeneği 10 bin adet sentetikDDO değeri türetilmesinde kullanılmıştır. Türetilen sentetik veriler, literatürde verilen iki lineer denklem sonuçları ile kıyaslanmıştır. Çalışmanın amacı kısıtlı deney verileri ile türetilen lineer denklemlerin başarılarını, yapay zekâ modellemesi ile tahmin edilerek türetilen sentetik veriler üzerinde gösterip, tartışabilmektir.

🔖

Cite This Article

TİĞREK, Ş., ŞARLAK, N., ÜSTÜN, D. (2021). THE PREDICTION OF END DEPTH RATIO WITH SUPPORT VECTOR REGRESSION: A FLOW MEASUREMENT TOOL FOR THE IRRIGATION CHANNELS. DSİ Teknik Bülteni, Sayı: 138, 1–10. https://ajindex.com/articles/348321

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (2)

  1. Abrari, E., Ergil, M., Beirami, M.K., “Solving trapezoidal free overfall by inserting a brink pressure effect into sharp-crested weir theory”, J. Irrig. Drain. Eng., 144 (7), 04018013, 2018 [2] Abrari E., Ergil M., Beirami M.K., “Flow measurement using free over-fall in generalized trapezoidal channels based on one velocity point method”, Flow Meas. Instrum., 69, 101615, 2019 [3] Afrin T., Kaye N.B., Khan A.A., Testik F.Y., “Numerical investigation of free overfall from a circular pipe flowing full upstream”, J. Hydraul Eng., 143 (6), 04017004, 2017 [4] Anderson M.V., “Non-uniform flow in front of a free overfall”, Acta Polytechnic Scandinavia, 42, 1-24, 1967 [5] Bertsekas D.P., Nonlinear Programming. Athena Scientific, Belmont, MA, 1995 [6] Bhallamudi M.S., “End depth in trapezoidal and exponential channels”, Journal of Hydraulic Research, 32(2), 219-232, 1994 [7] Cristianini N., Shawe-Taylor J., An Introduction to Support Vector Machines: and other Kernel-Based Learning Methods, Cambridge University Press,
  2. New York, USA, 2000 [8] Dai S., Ma Y., Jin S., “Application of fawer theory to end depth in trapezoidal sloping channel”, J. Irrig. Drain. Eng., 145 (12), 2019 [9] Davis A.C., Ellett B.G.S., Jacob R.P., “Flow measurements in sloping channels with rectangular free overfall”, J. Hydraul Eng., 124 (7), 760-763, 1998 [10] Delleur J.W., Dooge J.C., Gent K.W., “Influence of the slope and roughness on the free overfall”, Journal of Hydraulic Division, 82(4), 30-35, 1956 [11] Dumais S., Platt J., Heckerman D., Sahami M., Inductive Learning Algorithms and Representations for Text Categorization, 7th International Conference on Information and Knowledge Management, BethesdaMaryland, 1998 [12] Ferro V., “Theoretical end-depth-discharge relationship for free overfall”, J. Irrig. Drain. Eng.,125 (1), 40-44, 1999 [13] Fırat C.E., Effect of roughness on flow measurements in sloping rectangular free overfall, Master Thesis, Middle East Technical University, Natural and Applied Sciences, Ankara, 2004 [14] Gunn S. R., Support vector machines for classification and regression, Technical Report, Faculty of Engineering, Science and Mathematics, School of Electronics and Computer Science, University of Southampton, Southampton, UK., 1998 [15] Guo Y., Zhang L., Shen Y., Zhang J., “Modeling study of free overfall in a rectangular channel with strip roughness”, J. Hydraul Eng., 134 (5), 664-667, 2008 [16] Kirinčić V., Čeperić E., Vlahinić S., Lerga J., “Support vector mach