A Statistical Approach to Ship Fuel Consumption Monitoring

Abstract

The reduction of the environmental impact imposed by Kyoto Protocol and the growth of competitiveness imposed by the shipping market have urged shipping companies to pay increasing attention to ship energy efficiency improvement and CO2 emission reduction. According to the Ship Energy Efficiency Management Plan (SEEMP) recommended by the International Maritime Organization (IMO), the main scope of this article is in fact to overcome the deterministic limits of the monitoring systems installed in modern ships and support technical management in decision making based on large navigation databases. The proposed statistical approach is founded on a multiple linear regression and allows for both pointwise and interval predictions of the fuel consumption. At the end of each voyage, the model can be used to alert management for a possible change in ship performance in all those situations where the actual fuel consumption lies outside the prediction interval. Moreover, the model can also be utilized to quantify the contribution to the fuel consumption due to the hull and propeller fouling, which is particularly profitable for shipping companies and operators to claim for carbon credits after a specific improvement operation.