Early warning, prediction, and optimization based on digital twins for maritime operations (NTNU lead)
Develop advanced tools for early warning, prediction, and optimization based on digital twins for maritime industry. The digital twin possesses four fundamental functionalities: data storage/sensitivity analysis, modelling/simulation, data-based prediction, and dynamic autonomy.
Task 4.2.1 — Approximation-based model approach for sensitivity analysis: SA on surrogate models, trade-off between local and global SA, application oriented analysis.
Task 4.2.2 — Data-driven adaptive observer for ship component predictive maintenance: Anomaly detection, machine learning, predictive models for ship components.
Task 4.2.3 — Customizable optimization tools for operational efficiency: Online performance model with real-time optimization, constraints handling, full scale testing.
Task 4.2.4 — Implementation of auto-control for full autonomy operations: Trajectory tracking, adaptive docking, anti-rolling, hierarchical control schemes.
PhD Topic 3: Sensitivity analysis of ship status for onboard supporting of maritime operations.
PhD Topic 4: Data-based maintenance for prediction of ship propulsion performance and reliability.
Postdoc Topic 2: Path optimization for surface vessels in close-range areas with complex spatial variability.
Case studies, reports, papers. Budget: 10,000 kNOK.
NTNU (lead), SINTEF, RRM, DNV GL, ÅKP