Adaptive neural network applications in ship motion control

Abstract

For the purpose of improving the performance of ship motion control, this paper proposes an intelligent reference modeling adaptive controller for ship steering. The controller is based on artificial intelligence. We used fuzzy logic and neural networks to design the feedback controller, used multilayer perceptron neural network to design the reference model and the identification network. Based on the fuzzy control and neural network, an intelligent adaptive control algorithm was presented in the paper. In order to enhance adaptive characteristics of the controller, the parameters of membership functions and connection weights were revised online by neural network learning algorithm. The simulating result indicates that the performance of the ship controller is valuable and easy to implement. © 2012 Springer-Verlag GmbH.