Research Information System
INTERNATIONAL JOURNAL OF MARITIME ENGINEERING, vol.165, pp.89-102, 2023 (SCI-Expanded)
The speed of vessels has long been recognized to have the highest impact on fuel consumption. The aim of this study is to develop a speed optimisation model using a time-constrained genetic algorithm (GA). Subsequent to this, this paper also presents the application of machine learning regression methods in constructing a model to predict the fuel consumption of vessels. The local outlier factor algorithm is used to eliminate outliers in prediction features. In this study, speed is found to be the most significant feature for fuel consumption prediction. On the other hand, GA evaluation results showed that random modifications in the default speed profile could increase GA performance and thus fuel savings more than constant speed limits during voyages. Moreover, at most 6% fuel saving was found using randomly modified voyage speed profiles in GA. Contrary to general opinion, the top speed limits broke the global minimum fuel consumption point searching capability of GA. However, for best results, voyage speed, top speed limit, and expected time of arrival (ETA) delays need to be considered together in a separate optimisation algorithm.