A neural network controller for switching power converters

Since switching power converters behave in a highly nonlinear manner, conventional controllers are incapable of obtaining good dynamical performance. The use of a neural network as an adaptive feedforward controller as well as another neural network as an emulator for switching DC-DC converters is addressed. The simulation results show that this neural network control system can provide good dynamical responses even under high-frequency pulsed supply voltage and high-frequency pulsed reference signal.<>