Condition-based maintenance of naval propulsion systems: Data analysis with minimal feedback. (September 2018)

• Record Type: Journal Article
• Authors: Cipollini, Francesca; Oneto, Luca; Coraddu, Andrea; Murphy, Alan John; Anguita, Davide
• Is Part Of: Reliability engineering & system safety. Volume 177(2018)
• Page Start: 12
• Page End: 23
• Publication Date: 2018-09
• Subjects: Data analysis -- Naval propulsion systems -- Condition-based maintenance -- Supervised learning -- Unsupervised learning -- Novelty detection -- Minimal feedback.; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2018.04.015
• Languages: English
• ISSNs: 0951-8320

Abstract

Highlights: Data-Driven models to investigate CBM on a ship propulsion system. State-of-the-art supervised and unsupervised learning techniques adopted. Unsupervised learning algorithms for anomaly detection. CBM approach in an unsupervised fashion adopting minimal feedback. Abstract: The maintenance of the several components of a Ship Propulsion Systems is an onerous activity, which need to be efficiently programmed by a shipbuilding company in order to save time and money. The replacement policies of these components can be planned in a Condition-Based fashion, by predicting their decay state and thus proceed to substitution only when really needed. In this paper, authors propose several Data Analysis supervised and unsupervised techniques for the Condition-Based Maintenance of a vessel, characterised by a combined diesel-electric and gas propulsion plant. In particular, this analysis considers a scenario where the collection of vast amounts of labelled data containing the decay state of the components is unfeasible. In fact, the collection of labelled data requires a drydocking of the ship and the intervention of expert operators, which is usually an infrequent event. As a result, authors focus on methods which could allow only a minimal feedback from naval specialists, thus simplifying the dataset collection phase. Confidentiality constraints with the Navy require authors to use a real-data validated simulator and the dataset has been published for free use through the OpenML repository.