Preliminary communication

ANFIS Based Model for Ship Speed Prediction

Marko Valčić orcid.org/0000-0001-5352-4594 ; Sveučilište u Rijeci, Pomorski fakultet u Rijeci, Studentska 2, 51000 Rijeka, Croatia.
Radovan Antonić ; Sveučilište u Splitu, Pomorski fakultet u Splitu, Zrinsko-Frankopanska 38, 21000 Split, Croatia.
Vinko Tomas ; Sveučilište u Rijeci, Pomorski fakultet u Rijeci, Studentska 2, 51000 Rijeka, Croatia.

Abstract

Timely and precise speed prediction for large merchant ships is exceptionally important in almost all aspects of maritime transport. This paper explores the possibility of using the Adaptive
Neuro-Fuzzy Inference System (ANFIS) for creating models for speed prediction of a bulk carrier depending on external hydrometeorological disturbances, namely wind speed, signifi cant wave height and the speed of the sea current. Using a navigational simulator, an appropriate data base concerning the effect of the wind, waves and currents on the ship speed with regard to different directions of the disturbances was formed. This base was used to create data sets for training, testing and verifying the validity of the ANFIS model. An analysis of the effect of selecting the appropriate input-output membership functions while creating the ANFIS model was also performed in order to solve the above mentioned problem. The results gained by the created model are surely promising, which opens a perspective on the implementation of the created model in certain segments of maritime affairs.

Keywords

ANFIS model; prediction; ship speed; simulation

Hrčak ID:

75675

URI

https://hrcak.srce.hr/75675

Publication date:

7.12.2011.

Visits: 3.341 *