
the Project
Project Aim
The main objective of ReLife is to develop and demonstrate a Digital Twin platform that:

· covers the entire life cycle of a ship,
· enhances its sustainable and climate-neutral operation,
· enables timely and valid decision-support,
· supports the transition to circular economy practices,
· reduces CO₂ emissions and environmental loads in each life phase,
· optimises the design, construction, operation and recycling of the ship.
ReLife is fully aligned with the priority area “Environment & Circular Economy” of the Programme “Competitiveness” 2021–2027 (ESPA 2021–2027) and is co-financed by the European Union.
ReLife follows the ship throughout every stage of its life cycle, enabling informed and sustainable decision-making.

Ship design and construction based on life-cycle data and environmental impact assessment, laying the foundations for sustainable and efficient operation.

The vessel at the beginning of its operational life, achieving optimal performance, minimal environmental footprint, and comprehensive data capture that serves as a baseline for future monitoring.

Continuous vessel operation under real operational conditions, with ongoing assessment of energy efficiency and environmental performance.

Accumulated wear and performance degradation resulting from long-term operation, with early deviation detection and decision support for maintenance and life-extension actions.

End-of-life management of the vessel, focusing on safe decommissioning, material recycling, and alignment with the principles of the green circular economy.
Objectives
The development of ReLife is based on specific strategic objectives that reflect the project's commitment to innovation, sustainability, and digital transformation in shipping:
– Development of an integrated environmental footprint management platform
Coverage of all ship life cycle phases, adaptability to different ship types.
– Implementation of a hybrid data fusion environment (cloud–fog–mist)
Integration of heterogeneous data from sensors, ship systems, and shore-based facilities.
– Energy efficiency monitoring & predictive maintenance with AI
Use of physical models, deep learning, and FMU units to predict failures and performance deviations.
– Shore-based digital twin for design, construction, and end of life phases
LifeCycle Assessment (LCA), Zero-defect construction, remaining useful lifetime prediction.
– Scalable platform able to retrain & validate ML models
Continuous improvement through dynamic datasets and responsible AI mechanisms.
– Decision Support System (DSS)
KPIs, , energy optimization, risk detection, and optimal operation models.
– Pilot tests on real ships and user training

Ελληνικά (GR)
English (United Kingdom) 

