A course control system of unmanned surface vehicle (USV) using back-propagation neural network (BPNN) and artificial bee colony (ABC) algorithm

Abstract

Course control is the basis of Unmanned Surface Vehicle (USV) control system, largely determines the performance of USV. Because of some uncontrollable factors such as wind, wave and other random disturbances, the course control of an Unmanned Surface Vehicle (USV) is always difficult. In recent years, there have been some studies of adaptive course control system for USV, but they are not precise enough for engineering practice. In this paper, we propose a novel adaptive course control method based on Back-propagation Neural Network (BPNN) and Artificial Bee Colony (ABC) algorithm. We use classic PID algorithm as the main course control algorithm, and back-propagation neural network (BPNN) is also utilized to achieve more effective self-adaptive PID control. At the same time, in order to improve the convergence speed and precision of BPNN, we bring in Artificial Bee Colony (ABC) algorithm to minimize the error of system and adjust the weight of BPNN. The system has been proven in simulation that it can accurately output the rudder angle according to the input course angle and can perform better than that without ABC algorithm optimization. The error of parameters obtained by this method is within the acceptable range, which can provide reference for engineering practice.