A genetic algorithm-based grey-box model for ship fuel consumption prediction towards sustainable shipping

• Published in: Annals of operations research Vol. 349; no. 2; pp. 525 - 551
• Main Authors: Yang, Liqian, Chen, Gang, Rytter, Niels Gorm Malý, Zhao, Jinlou, Yang, Dong
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2025; Springer Nature B.V
• Subjects: Accuracy; Business and Management; Combinatorics; Crude oil; Energy consumption; Energy efficiency; Energy management; Fuel consumption; Genetic algorithms; Greenhouse effect; Greenhouse gases; Marine propulsion; Mathematical models; Methods; Model accuracy; Oil tankers; Operations research; Operations Research/Decision Theory; Optimization; Parameter estimation; Power efficiency; Prediction models; S.I.: OR for Sustainability in Supply Chain Management; Sailing; Shipping; Shipping industry; Ships; Supply chains; Sustainability; Theory of Computation; Weather; Ship energy efficiency; Fuel consumption prediction; Sustainable shipping; Grey-box model; Genetic algorithm; Sustainability
• ISSN: 0254-5330; 1572-9338
• DOI: 10.1007/s10479-019-03183-5

In order to enhance sustainability in maritime shipping, shipping companies spend good efforts in improving the operational energy efficiency of existing ships. Accurate fuel consumption prediction model is a prerequisite of such operational improvements. Existing grey-box models (GBMs) are found with significant performance potential for ship fuel consumption prediction, although having a limitation of separating weather directions. Aiming to overcome this limitation, we propose a novel genetic algorithm-based GBM (GA-based GBM), where ship fuel consumption is modelled in a procedure based on basic principles of ship propulsion and the unknown parameters in this model are estimated with a GA-based procedure. Real ship operation data from a crude oil tanker over a 7-year sailing period are used to demonstrate the accuracy and reliability of the proposed model. To highlight the contribution of this work, we compare the proposed model against the latest GBM. The results show that the fitting performance of the proposed model is remarkably better, especially for oblique weather directions. The proposed model can be employed as a basis of ship energy efficiency management programs to reduce fuel consumption and greenhouse gas (GHG) emissions of a ship. This is beneficial to achieve the goal of sustainable shipping.