Prediction of double-regulated hydraulic turbine on-cam energy characteristics by artificial neural networks approach

• Published in: FME transactions Vol. 44; no. 2; pp. 125 - 132
• Main Authors: Božić, Ivan, Jovanović, Radiša
• Format: Journal Article
• Language: English
• Published: University of Belgrade - Faculty of Mechanical Engineering, Belgrade 2016
• Subjects: hydraulic turbine; neural network; on-cam characteristics
• ISSN: 1451-2092; 2406-128X
• DOI: 10.5937/fmet1602125B

The determination of the energy characteristics of a double-regulated hydro turbine is based on numerous measuring points during extensive and expensive experimental model tests in the laboratory and on site prototype tests at the hydropower plant. By the spatial interpolation of representative measured points that belong to the so-called on-cam curves for different speed factors, the hill performance diagram is obtained. The focus of the paper is the contemporary method of artificial neural network models use for the prediction of turbine characteristics, especially in not measured operation modes. A part of the existing set of experimental data for the Kaplan turbine energy parameters is used to train three developed neural network models. The reliability of applied method is considered by analysing, testing and validating the predicted turbine energy parameters in comparison with the remaining data.