Answers are grounded in this paper and cite their sources.
The maritime sector faces significant challenges in digitalization due to fragmented operational data structures under real shipboard conditions. Existing studies often rely on simulated or isolated analytical applications, highlighting the absence of an end-to-end maritime data model. This study addresses this gap by proposing and validating a sustainable maritime data model that manages real operational data from collection to utilization within a unified framework. The proposed model integrates lossless compression, secure ship–shore transmission, systematic data cleaning, validation, contextual labeling, and structured storage, explicitly considering maritime operational constraints. The model is validated using 155 days of real operational data obtained from a turbocharged low-speed two-stroke main engine installed on a bulk carrier. Spearman rank correlation analysis conducted under stable operating conditions reveals physically interpretable relationships among key engine parameters. In particular, a strong positive correlation (ρ = 0.67) is identified between turbocharger rotational speed and scavenging air pressure, while the relationship between turbocharger rotational speed and scavenging air temperature before the cooler is also high (ρ ≈ 0.65), confirming the expected thermodynamic coupling within the turbocharging and air-handling system. The results demonstrate that the proposed data model effectively transforms heterogeneous and manually recorded shipboard data into a validated and structured dataset suitable for long-term analysis. The study contributes to maritime digitalization by providing a practical and scalable data management architecture validated on real ship data, supporting reliable data-driven decision-making processes.
No takes yet. Share an insight, caveat, or question.
Ceylan et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: