Year: 2026
Type: article
Abstract: The increasing complexity and stringent real-time reliability requirements of modern ship power plants (SPPs) render conventional digital twins insufficient when relying solely on either physics-based or data-driven models. Furthermore, the lack of unified IT/OT integration and semantic consistency limits their practical deployment in operational maritime environments. The aim of this study was to develop and validate a hybrid digital twin (HDT) framework that ensures adaptive modelling, semantic interoperability, and secure real-time integration within the ship’s cyber-physical infrastructure. To achieve this, a cognitively adaptive HDT architecture was proposed. It merged physics-based thermodynamic models with data-driven CNN-LSTM components via a dynamic authority-shift mechanism governed by real-time uncertainty. The framework incorporated a cognitive simulation model (CSM) based on OWL 2.0 ontologies and SWRL rules for the semantic validation of physical constraints directly within the operational loop. Additionally, a semantic-functional dual exchange (SFDX) protocol was introduced to unify physical telemetry and ontological descriptors. This integration of cognitive validation and dynamic model balancing ensured robust operation under sensor degradation and cyber-physical disturbances. Experimental validation was performed using a Hardware-in-the-Loop testbed simulating real SPP conditions. The results demonstrated stable operation exceeding 10⁴ messages per second, with end-to-end latency below 0.25 seconds and data loss under 0.3%. The hybrid model reduced mean remaining useful life prediction error by 20-25% compared to standalone approaches, maintaining physical-semantic consistency below a 3% deviation threshold. Architectural evaluation confirmed the effectiveness of a distributed onboard-edge-cloud paradigm, executing real-time control locally while delegating computationally intensive retraining to higher tiers. The proposed framework established a scalable foundation for trustworthy and cognitively integrated SPP digital twins (DTs)
Institution: Odesа Polytechnic National University
Language: English
Subfield: Industrial and Manufacturing Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7201868565