Speed Optimisation Module of a Hydraulic Francis turbine based on Artificial Neural Networks. Application to the Dynamic Analysis and Control of an Adjustable Speed Hydro Plant

The advantages of adjustable speed hydroelectric generation have been highlighted by several authors. The optimum speed for actual working conditions must be continuously adjusted by means of an appropriate control system. This process gives rise to dynamic changes in operation variables. In this paper an artificial neural network is used to generate the reference speed that optimises the turbine efficiency. The main results of measurements on a test loop with an axial-flow turbine are reported.