Feedforward neural network and ANFIS-based approaches to forecasting the off-cam energy characteristics of Kaplan turbine

Abstract

The determination of the energy characteristics of a Kaplan hydraulic turbine is based on numerous measuring points during extensive and expensive experimental model tests in laboratory and on-site prototype tests at the hydropower plant. The results of those experimental researches are valuable insofar as they are detailed and comprehensive. In order to reduce the number of modes, in which the double-regulated turbine has to be tested with the aim of obtaining the off-cam energy characteristics in unknown operating modes, the application of contemporary artificial neural networks models is presented in the paper. The rationalization of the turbine test conditions may not be at the expense of the quality of the obtained characteristics. Two types of neural networks, feedforward neural networks and adaptive network-based fuzzy inference system with different partitioning methods, were used. The reliability of applied method was considered by analyzing and validating the predicted turbine energy parameters with the results obtained in the highly sophisticated laboratory.