Controlling of non-minimum phase micro hydro power plant based on adaptive B-Spline neural network

Abstract

Hydro power plant is a power generation system that have non-minimum phase model showing initial inverse response characteristic. For span of broad electrical load regulation, conventional non adaptive control techniques, such as PI and PID control would degrade the performance of this power generation system. To ensure the stability of Hydro power plant for severe load variations, we need a kind of controller that has adaptive capability. On the other hand, the utilization of conventional adaptive techniques such as Self Tuning Regulator and Model Reference Adaptive Controller will be diverge to control plants showing non-minimum phase mode. In this paper, the implementation of adaptive intelligence control based on B-Spline neural network along with forward controller for controlling micro hydro power plant will be presented. Based on its characteristic, this adaptive control technique could be implemented directly without any prior training phase. From the simulation studies, the proposed scheme results fast transient response to load variations compared to traditional PI control and also very stable in responding to severe disturbance.