Metrika

  • citati u SCIndeksu: [1]
  • citati u CrossRef-u:[9]
  • citati u Google Scholaru:[]
  • posete u poslednjih 30 dana:5
  • preuzimanja u poslednjih 30 dana:4

Sadržaj

članak: 1 od 1  
2016, vol. 44, br. 2, str. 125-132
Predikcija energetskih kombinatorskih karakteristika dvojno regulisane hidraulične turbine pomoću veštačkih neuronskih mreža
Univerzitet u Beogradu, Mašinski fakultet, Srbija

e-adresaibozic@mas.bg.ac.rs
Sažetak
Određivanje energetskih kombinatorskih karakteristika dvojno regulisane hidraulične turbine se zasniva na rezultatima opsežnih i skupih eksperimentalnih ispitivanja na modelu u laboratoriji i terenskih merenja na prototipu u hidroelektranama. Eksploatacioni dijagram se dobija na osnovu prostornih interpolacija reprezentativnih mernih tačaka koje pripadaju kombinatorskim krivama formiranih za različite brzinske faktore. U radu je dat akcenat na primeni savremene metode veštačkih neuronskih mreža u određivanju kombintorskih karakteristika turbine posebno u radnim režimima koji nisu mereni. Deo postojećih podataka o energetskim parametrima Kaplan turbine koji su dobijeni eksperimentalnim putem iskorišćeni su za obučavanje tri razvijena modela veštačkih neuronskih mreža. Analizom, testiranjem i validacijom dobijenih energetskih parametara turbine međusobnim upoređivanjem sa ostalim eksperimentalnim podacima razmatrana je pouzdanost primenjene metode.
Reference
*** (2011) Official model test report - HPP Djerdap 1, test № 535. Lausanne, Switzerland: École Polytechnique Fédérale de Lausanne, Laboratory for Hydraulic Machines, (March-May 2008), Revised and completed version of Final Report
*** (1991) IEC 60041 - field acceptance tests to determine the hydraulic performance of hydraulic turbines, storage pumps and pump-turbines, international standard. Geneva: International Electrotechnical Commission
*** (2010) IEC 62006 - hydraulic machines: Acceptance tests of small hydroelectric installations, international standard. Geneva: International Electrotechnical Commission
*** (1999) IEC 60193 - hydraulic turbines, storage pumps and pump-turbines: Model acceptance tests, international standard. Geneva: International Electro technical Commission
Arnone, A., Marconcini, M., Rubechini, F., Schneider, A. (2009) Kaplan turbine performance prediction using CFD: An artificial neural network approach. u: Conference HYDRO, October 26-28., Lyon, France, Proceedings, Paper 263
Benišek, M. (1998) Hydraulic turbines. Belgrade: Faculty of Mechanical Engineering, (in Serbian)
Benišek, M., Božić, I., Čantrak, Đ., Ilić, D. (2011) Hydraulic tests of the bulb turbine unit at the hydropower plant 'Djerdap 2'. u: III International Symposium Contemporary Problems of Fluid Mechanics, 12-13.10.2011, Belgrade, pp. 187-194
Benišek, M., Petrović, D., Božić, I., Ćirić, Z., Damjanović, S., Zeljić, M. (2008) Propeller and combinatory characteristics determination of Kaplan turbine in HPS Zvornik with the aim of increasing its efficiency. u: Power Plant Symposium 2008, 28-31.10.2008, Vrnjacka Banja
Božić, I., Benišek, M. (2014) Experimental and numerical analysis of the Kaplan turbine characteristics. u: Full Papers Proceeding of International Conference 'Power Plants', 28-31.10.2014, Zlatibor, pp. 387-396
Božić, I. (2012) Theoretical and Experimental Investigation of the Energy Losses Distribution in the Hydraulic Axial Turbines. Belgrade: University of Belgrade, Faculty of Mechanical Engineering, PhD thesis
Cheng, W., Ye, Y., Cai, L. (2003) Modeling of hydro-turbine hill chart by neural network. Journal of Huazhong University of Science and Technology, Vol. 6
Gajić, A., Ignjatović, B., Predić, Z., Ivljanin, B. (2005) Test of cam characteristic of the Kaplan turbine by on-site measurement. FME Transactions, vol. 33, br. 3, str. 145-149
Haykin, S. (1998) Neural Networks: A comprehensive foundation. Prentice Hall
Hornik, K., Stinchcombe, M.M., White, H. (1989) Multilayer feedforward networks are universal approximators. Neural Networks, vol. 2, str. 359-366
Jia, R., Bai, L., Luo, X., Liu, F. (2004) Expert system on fault diagnosis based on neural network for hydropower units. Journal of Hydroelectric Engineering, Vol. 6, pp. 120-123
Jovanović, R., Sretenović, A., Živković, B. (2014) Application of artificial neural networks for prediction of heating energy consumption in University buildings. u: 18th International Research/Expert Conference Trends in the Development of Machinery and Associated Technology, 10-12 September, Budapest, Hungary, Proceedings
Kalogirou, S.A. (2001) Artificial neural networks in renewable energy systems applications: A review. Renewable and Sustainable Energy Reviews, 5(4): 373-401
Karatasou, S., Santamouris, M., Geros, V. (2006) Modeling and predicting building's energy use with artificial neural networks: Methods and results. Energy and Buildings, 38(8): 949-958
Mitas, L., Mitasova, H. (1988) General variational approach to the interpolation problem. Computers & Mathematics with Applications, 16(12): 983
Mitas, L., Mitasova, H. (1999) Spatial interpolation. u: Longley P., Goodchild M.F., Maguire D.J., Rhind D.W. [ur.] Geographical information systems: Principles, techniques, management and applications, Wiley, pp. 481-492
Pham, D.T., Liu, X. (1995) Neural networks for identification, predication and control. London: Springer-Verlag
Volkov, Yu.S., Miroshnichenko, V.L., Salienko, A.E. (2014) Mathematical modeling of hill diagram for Kaplan turbine. Scientific journal Machine Learning and Data Analysis, Vol. 1(10), pp. 1439-1450, in Russian
Xiao, Z., Wang, S., Zeng, H., Yuan, X. (2006) Identifying of Hydraulic Turbine Generating Unit Model Based on Neural Network. u: Sixth International Conference on Intelligent Systems Design and Applications, pp. 113-117
 

O članku

jezik rada: engleski
vrsta rada: neklasifikovan
DOI: 10.5937/fmet1602125B
objavljen u SCIndeksu: 25.06.2016.
Creative Commons License 4.0

Povezani članci

Nema povezanih članaka