The dynamic performance of photovoltaic supplied dc motor fed from DC-DC converter and controlled by neural networks

Abstract

This paper presents an adaptive neural network controller (ANNC) that is used to control the speed of a separately excited DC motor driving a centrifugal pump load and fed from photovoltaic (PV) generator through DC-DC buck-boost converter. The controller is also used to track the maximum power point (MPP) of the PV generator by controlling the converter duty ratio. Such kinds of controllers must have two objective functions to perform these two tasks, but in this research the objective function related to the MPP is converted to a constrained for the second objective function by making some approximation in the system equations. An adaptive neural network identifier (ANNI), which emulates the dynamic behavior of the motor system, plays an important role in computing the system Jacobian and hence updating the weights and biases of the ANNC. The weights and biases of both networks are updated on line using a BP algorithm with adaptive learning rate. The computation of the adaptive learning rate is based on the value of the speed error through an empirical formula to get faster response with less oscillation and minimum overshoot. The transient response of the motor speed, current and voltage for a step change in the reference speed and the insolation are presented.