Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction

作     者：Nguyen, Van Nhanh Chung, Nghia Balaji, G. N. Rudzki, Krzysztof Hoang, Anh Tuan 

作者机构：HUTECH Univ Inst Engn Ho Chi Minh City Vietnam Ho Chi Minh City Univ Transport Inst Maritime Ho Chi Minh City Vietnam Vellore Inst Technol Sch Comp Sci & Engn Vellore India Gdyn Maritime Univ Fac Marine Engn Gdynia Poland Dong Nai Technol Univ Fac Engn Bien Hoa City Vietnam Korea Univ Grad Sch Energy & Environm 145 Anam ro Seoul 02841 South Korea 

出 版 物：《ALEXANDRIA ENGINEERING JOURNAL》 (Alexandria Engineering Journal)

年 卷 期：2025年第118卷

页      面：664-680页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 

主　　题：Ship fuel consumption Maritime industry Internet of things Explainable machine learning SHAP values Model prediction 

摘      要：The International Maritime Organization has proposed several operational policies and measures to lower ships specific fuel consumption (SFC) and associated emissions toward the sustainability of maritime activities, showing the need for creating exact predictive models based on actual operational conditions. Modern combined and integrated techniques between highly precise sensors, the Internet of Things (IoT), and advanced machine learning (ML) can help in accurate real-time data collection and robust prediction model building. In this work, an IoT-driven approach combined with explainable ML models was developed to predict the SFC of ships based on data collected from high-quality sensors. Indeed, five different MLs were employed including linear regression, decision tree, random forest, XGBoost, and Gradient Boosting Regression. Resultantly, XGBoost emerged as the best model for predicting SFC with the highest R2 (Train: 0.997, Test: 0.95), lowest MSE (Train: 1.052, Test: 16.791), and minimal MAPE (Train: 0.08 %, Test: 0.23 %). Moreover, the interpretability analysis identified Main engine shaft power as the most significant predictor with a mean SHAP value of around 3.5. More importantly, these findings highlighted the importance of engine power, torque, and speed in driving model predictions for ship SFC, thus helping in a comprehensive understanding of the black-box model.