Development of condition-based maintenance strategy for fault diagnosis for ship engine systems. (15th July 2022)

• Record Type: Journal Article
• Authors: Karatuğ, Çağlar; Arslanoğlu, Yasin
• Is Part Of: Ocean engineering. Volume 256(2022)
• Publication Date: 2022-07-15
• Subjects: Artificial neural network -- Marine vessel -- Performance monitoring -- Ship operational efficiency -- Fault diagnosis; Ocean engineering -- Periodicals; Ocean engineering; Periodicals; 620.4162
• DOI: 10.1016/j.oceaneng.2022.111515
• Languages: English
• ISSNs: 0029-8018

Abstract

Abstract: Shipping effectively covers a large part of cargo transportation in the world in an economical and reliable way. Thus, energy-efficient operation on ships is an essential subject to ensure both increasing of the efficiency level of the global transportation and economic savings. In this subject, an effective maintenance strategy followed in the ship's engine room is one of the powerful solutions. In this way, system reliability and operational safety increase while operational expenses decrease. A condition-based strategy is an up-to-date approach for maintenance. Within this method, decisions could be made about the system based on past information. In this study, some parameters of the large-sized container ship are collected for the development of the condition-based maintenance strategy. The dataset is analysed by the artificial neural network in order to the constitution of the engine performance model. Finally, the usability and effectiveness of the developed maintenance strategy are demonstrated with three scenarios. As a result of the exemplified scenarios, the improved maintenance strategy ensures that the fault diagnosis could be made effectively, depending on the instant condition of the examined engine and its past information. The proposed methodology could also adapt to any system or engine for any kind of ship. Highlights: A condition-based maintenance model for ship machinery has been proposed. A success of the ANN model has been evaluated by MSE and MAE. A decision support system that ensures fault diagnosis has been developed. 3 scenarios have been exemplified by the developed decision support system.