A neural network PID controller with dynamic structure adjustment for DC-DC switching converters

In this paper, a neural network PID controller with dynamic structure adjustment is proposed for DC-DC switching converters. To improve the efficiency of the controller and reduce its power consumption, the neural network for the proposed controller can change its structure adaptively in transient state according to the variation of voltage error, while it is disabled in steady state. Firstly, the whole voltage error range is divided into four parts to distinguish the location of voltage error. Then, the adaptive structure change mechanism is designed for neural network. Furthermore, a buck DC–DC switching converter using the proposed controller is designed and implemented on the field programmable gate array (FPGA) and printed circuit board (PCB). The experimental results demonstrated that it has similar transient performance in a DC-DC switching converter to that the conventional neural network PID controller, where neural network has the fixed structure. Meanwhile, the proposed controller has less power consumption and higher efficiency in transient state than a conventional neural network PID controller.