India-based maritime technology company BlueWater has launched an LNG voyage optimisation system, aimed at limiting boil-off rates by optimising tank pressure and maximising utilisation of generated natural boil-off gas (NBOG).
The system uses a hybrid approach based on machine learning and thermodynamic principles to optimally plan and monitor LNG voyages with efficient boil-off-gas management, speed scheduling and weather routing, the company says.
Thermodynamic models are used to predict the liquid-gas equilibrium conditions for the given LNG composition, liquid temperature, and stowage. Machine learning models are then used to predict the boil-off-rate based on the deviation from the theoretical liquid-gas equilibrium.
This hybrid approach accounts for the heat ingress coming into the tanks, sloshing caused by rough seas and chemical properties of the LNG grade to predict the boil-off-rate.
The optimum operating pressure for limiting the boil-off rate is also calculated, taking into account the liquid temperature, weather, and the composition of LNG as it changes throughout the voyage.
The NBOG model starts from initial LNG composition and predicts ageing impacts as the voyage progresses. The algorithm then takes the temperature and pressure requirements at the discharge port into account to plan a schedule that minimises the total LNG consumption while adhering to the discharge requirements.