BP neural network based PID control for ship steering

A new kind of algorithm of controller for ship is proposed. BP neural network based PID control is one of artificial neural networks which can emulate ship´s manual steering as autopilot for ship steering. This paper introduces the principle, characteristics and learning algorithm of the BP neural network. Getting BP neural network based PID control for ship steering by combining BP neural network and traditional PID. Making use of MATLAB, simulate this new kind of controller for ship in consideration of disturbances of wind, wave and current and without them respectively. The simulation shows that the BP neural network based PID control for ship steering can improve the robustness of the system and has better adapt ability to the ship model etc.