Back Propagation Feed Forward Neural Networks (BPFFNN) technology was employed to predict the ship manoeuvring motion during the operation. Consequently, it will be required to estimate the manoeuvring performance of ships at different displacements, speeds and rudder angles.
A navigation simulator was used to generate the required data for training and testing the Artificial Neural Networks (ANN). The inputs to the ANN are the main variables, which affect the ship turning manoeuvre, while the outputs are the limits of it. These outputs depend on the inputs of the ANN and their construction (number of hidden layers, number of neurons, weights and biases).
Thirty four data sets were provided to the system, seventy five percent of these were used in the training process and the rest was kept as blind manoeuvres to test the system performance. The investigations were carried out for three different types of ship container, bulk carrier and tanker.
The results obtained show a good agreement with the data sets of the training and the blind manoeuvres.
Applying Artificial Intelligence (A.I) to Predict the Limits of Ship Turning Manoeuvres
Jahrbuch der Schiffbautechnischen Gesellschaft ; Kapitel : 20 ; 99 ; 132-139
01.01.2007
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Numerical study of ship rolling in turning manoeuvres
British Library Conference Proceedings | 2006
|SIMULATOR OF SHIP MANOEUVRES DURING ANCHORING OPERATION
British Library Conference Proceedings | 1999
|British Library Conference Proceedings | 2009
|On Knowledge-Driven Ship Manoeuvres/ Simulation and Fullscale
British Library Conference Proceedings | 1992
|