Intelligent Model For A Mini Hydropower Plant And Its Adaptive Control

This paper proposes a comparison between three control strategies for the power control of the mini hydropower plan. To develop and implement this controllers, the mathematical modelling of the electrical energy production is performed, by applying identification methods on based on the experiments performed during the operation of the power plant. To improve the operation process, the variation of the real power in time depending on the water flow on the turbine blades is learnt using means of artificial intelligence. The learning procedure is performed by training neural networks. The approached control structures consists of a cascade structure, with a PD controller in the internal loop and a fractional-order PID controller in its external loop. The achieved performances obtained by the process are improved furthermore by computing an adaptive system based on the strategy of converting the process between the continuous to discrete time and then back to the continuous time considering the variation in time of the sampling time. This conversion is implemented using trained neural networks, too.