A SHIP DIGITAL TWIN FOR SAFE AND SUSTAINABLE SHIP OPERATIONS

Mingyang Zhang ^a, Spyros Hirdaris ^b, Nikolaos Tsoulakos ^c

^a Department of Mechanical Engineering, Marine Technology Group, Aalto University, Espoo, Finland
^b American Bureau of Shipping, Global Ship Systems Centre, Athens, Greece
^c Laskaridis Shipping Co. Ltd

Presented at the Build IT 2023 Workshop, CNR, Italy – October 2023

ABSTRACT

This paper presents a novel digital twin that can predict ship motions and fuel consumption in real operational
conditions. The analysis is based on two optimal Deep Learning Models (DLM) namely (a) a transformer neural
network used for the analysis of ship motions and (b) a Long Short-Term Memory (LSTM) network for the
prediction of ship fuel consumption. Comparisons of results against sea trial data suggest that subject to further
testing and validation DLM could be used as part of a digital twin framework for safe and sustainable ship operations.