A Heading Control Strategy Based On Neural Network PID Controller

Abstract

Aiming at the problem that the motion characteristics of ships sailing at sea or inland rivers are time-varying and nonlinear, and the heading is difficult to control in real time and accurately, this paper proposes a heading control strategy based on neural network PID controller. The neural network PID controller imitates the structure of neural network. A series of formula derivations can prove that the output of the controller has proportional, integral and differential effects on the error. The parameters of this neural network PID controller are adaptively adjusted in real time online according to the error and the rate of error change. Therefore, the ship control system can still output the optimal control strategy in real time under the complicated and changeable operating environment. Matlab / Simulink is used for simulation. The simulation results prove that the heading control strategy based on neural network PID controller has obvious superiority in real-time and precise control of heading.