Recent advancements in data-driven methodologies for the fault diagnosis and prognosis of marine systems : a systematic review

Velasco-Gallego, Christian and Navas De Maya, Beatriz and Matutano Molina, Clara and Lazakis, Iraklis and Cubo Mateo, Nieves (2023) Recent advancements in data-driven methodologies for the fault diagnosis and prognosis of marine systems : a systematic review. Ocean Engineering, 284. 115277. ISSN 0029-8018 (https://doi.org/10.1016/j.oceaneng.2023.115277)

[thumbnail of Velasco-Gallego-etal-OE-2023-Recent-advancements-in-data-driven-methodologies-for-the-fault-diagnosis]
Preview
Text. Filename: Velasco_Gallego_etal_OE_2023_Recent_advancements_in_data_driven_methodologies_for_the_fault_diagnosis.pdf
Accepted Author Manuscript
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo

Download (1MB)| Preview

Abstract

In recent years, there has been an interest increase in smart maintenance within the shipping sector due to the benefits and opportunities associated with its implementation. Consequently, an increase in maintenance analytics studies for marine systems has been perceived. Due to the lack of reviews that encompass the body of knowledge of data-driven methodologies for the data pre-processing, fault diagnosis and prognosis of marine systems, this study aims to introduce the findings of a systematic literature review conducted on data-driven methodologies for three critical domains: 1) data pre-processing, 2) fault diagnosis, and 3) fault prognosis of marine systems. To determine the current state-of-the-art, a total of 88 primary studies published from 2016 to 2022 have been analysed and five research questions have been proposed. Examples of key findings are the advancements in the analysis of deep learning approaches, the quality of the data pre-processing methods, and the availability of fault data. Results of the systematic review indicate that advancements in Prognostics and Health Management (PHM), advancements in AI, and advancements in the creation of open-fault datasets are the main future work recommendations to be addressed in the upcoming years.

ORCID iDs

Velasco-Gallego, Christian, Navas De Maya, Beatriz, Matutano Molina, Clara, Lazakis, Iraklis ORCID logoORCID: https://orcid.org/0000-0002-6130-9410 and Cubo Mateo, Nieves;