A digital twin approach for maritime carbon intensity evaluation accounting for operational and environmental uncertainty

Abstract

Maritime industry has set ambitious goals to drastically reduce its greenhouse gas emissions through stipulating and enforcing a number of energy assessment measures. Unfortunately, measures like the EEDI, EEXI, SEEMP and CII do not account for the operational and environmental uncertainty of operations at sea, even though they do provide a first means of evaluating the carbon footprint of ships. The increasing availability of high-frequency operational data offers the opportunity to quantify and account for this uncertainty in energy performance predictions. Current methods to evaluate and predict energy performance at a whole energy system level do not sufficiently account for operational and environmental uncertainty. In this work, we propose a digital twin that accurately predicts the fuel consumption and carbon footprint of the hybrid propulsion system of an Ocean-going Patrol Vessel (OPV) of the Royal Netherlands Navy under the aggregate effect of operational and environmental uncertainty. It combines first-principle steady-state models with machine learning algorithms to reach an accuracy of less than 5% MAPE on both mechanical and electrical propulsion, while bringing a 40% to 50% improvement over a model that does not utilise machine learning algorithms. Results over actual voyage intervals indicate a prediction accuracy of consumed fuel and carbon intensity within 2.5% accounting for a confidence interval of 95%. Finally, the direct comparison between mechanical and electrical propulsion showed no clear energy-saving benefits and a strong dependency of the results on each voyage's specific operational and environmental conditions.