Improving condtion-based maintenance of a naval propulsion plants using ensemble learning

Abstract

Because of the terrible technological and scientific progress in recent decades in the field of war defense of states and war politics, frigates have become an integral part of the navies of most countries in the world. Availability and reliability of naval propulsion plants of these Frigates are key elements to cope with because, maintenance costs represent a large slice of total operational expenses, which directly or indirectly affects the performance of ships while fulfillingtheir missions. Depending on the adopted strategy, the impact of maintenance on overall expenses can remarkably vary.In this work we take into consideration an improving condition-based maintenance of a Frigate equipped with a CODLAG naval propulsion plant where we use a machine learning approach to show the effectiveness of the proposed Ensemble Learning methods and to be benchmark them in a realistic maritime application.