PID neural network decoupling control for doubly fed hydro-generator system

Proportional, integral and differential are defined as a neuron respectively, combined with neural network in this paper. PID neural network (PIDNN) is built and the structure of PIDNN is also simple. Using the PID neural network, the strong coupled time-varying system can be decoupled and controlled easily. The doubly fed hydro-generator system is a novel type of hydraulic generation system. Considering the performances of uncertain and nonlinear as well as parameters coupling and time-variation for three parts of water flux, hydro-turbine and generator, the PIDNN control strategy is introduced. By comparison with the conventional PID control, the results of simulation show that hydro-generator system is good robustness against system parameters uncertainly and load disturbance.