In this paper a parallel ANN(artificial neural networks) for the automatic berthing will be discussed. This controller has a separated hidden layer each control an engine and a rudder respectively. Using this controller simulations were carried out where the initial conditions such as ship's positions and heading angle are different from teaching data. Finally comparison of separated hidden layer and united hidden layer will be described.
In this paper, consistently trained Artificial Neural Network controller for automatic ship berthing is discussed. Minimum time course changing manoeuvre is utilised to ensure such consistency and a new concept named 'virtual window' is introduced. Such consistent teaching data are then used to train two separate multi-layered feed forward neural networks for command rudder and propeller revolution output. After proper training, several known and unknown conditions are tested to judge the effectiveness of the proposed controller using Monte Carlo simulations. After getting acceptable percentages of success, the trained networks are implemented for the free running experiment system to judge the network's real time response for Esso Osaka 3-m model ship. The network's behaviour during such experiments is also investigated for possible effect of initial conditions as well as wind disturbances. Moreover, since the final goal point of the proposed controller is set at some distance from the actual pier to ensure safety, therefore a study on automatic tug assistance is also discussed for the final alignment of the ship with actual pier. http://www.transnav.eu the International Journal on Marine Navigation and Safety of Sea Transportation Volume 9 Number 3
Ship berthing has always considered as a multiple input multiple output phenomenon. And such controlling action becomes even more sophisticated when the ship approaches to a pier especially in low speed. The current and presence of wind also make the task more complicated. But, if a human brain can be replicated by any artificial intelligence technique to perform the same necessary action that human brain does, then automatic operation during complete berthing process is believed to be possible by many researchers. For that purpose as an initial stage of this research, artificial neural network is chosen as one of AI techniques for automatic berthing and to increase its learnability, concentration is given on the consistency of the teaching data provided. To do that, nonlinear programming method is used where ship's actual behavior is predicted using famous manoeuvring mathematical group model. After successfully training, ANN controller is tested for various known and unknown condition including wind disturbances and found good results. Finally, to verify the simulated successful results, the current research is based on execution of free running experiment with the implementation of automatic ship berthing using the same trained ANN where adequate decisions for command rudder and propeller revolution taken are decided automatically depending on real time multiple input parameters.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.