Answers are grounded in this paper and cite their sources.
Data-driven maintenance (DDM) of marine propulsion systems is central to safer, more efficient shipping, yet adoption remains limited, and most research assumes suitable data already exist, an assumption rarely verified in practice. This study investigates not only what a working DDM environment requires, but also where an operator holding real fleet data should begin to build it. It combines an expert survey that scores sixteen enabling factors for importance and implementation difficulty and maps their dependencies, with a readiness assessment grading the maintenance data of an LPG carrier fleet and a naval platform fleet against the ISO/IEC 25012 quality characteristics. The survey results are analysed with weighted fuzzy aggregation and an Importance–Difficulty Matrix; the fleet data are assessed both per source and relationally across sources. The panel treats every enabler as both important and difficult, so the task is one of sequencing rather than selection. In both fleets, where automatic measurement is already sound, readiness is constrained less by the data captured than by the human-generated records and the links between sources. On this basis, a stepwise blueprint, demonstrated on both fleets, turns data-quality findings into enabler priorities and an implementation sequence for other operators to test.
No takes yet. Share an insight, caveat, or question.
Dodis et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: