Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction
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 operati...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S111001682500095X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576527663890432 |
|---|---|
| author | Van Nhanh Nguyen Nghia Chung G.N. Balaji Krzysztof Rudzki Anh Tuan Hoang |
| author_facet | Van Nhanh Nguyen Nghia Chung G.N. Balaji Krzysztof Rudzki Anh Tuan Hoang |
| author_sort | Van Nhanh Nguyen |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-1736ea2d2fe44da88926c49f1b12fc6e |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-1736ea2d2fe44da88926c49f1b12fc6e2025-01-31T05:10:11ZengElsevierAlexandria Engineering Journal1110-01682025-04-01118664680Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption predictionVan Nhanh Nguyen0Nghia Chung1G.N. Balaji2Krzysztof Rudzki3Anh Tuan Hoang4Institute of Engineering, HUTECH University, Ho Chi Minh City, Viet NamInstitute of Maritime, Ho Chi Minh City University of Transport, Ho Chi Minh City, Viet NamSchool of Computer Science and Engineering, Vellore Institute of Technology, Vellore, IndiaFaculty of Marine Engineering, Gdynia Maritime University, Gdynia, PolandFaculty of Engineering, Dong Nai Technology University, Bien Hoa City, Viet Nam; Graduate School of Energy and Environment, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, South Korea; Corresponding author at: Faculty of Engineering, Dong Nai Technology University, Bien Hoa City, Viet Nam.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.http://www.sciencedirect.com/science/article/pii/S111001682500095XShip fuel consumptionMaritime industryInternet of thingsExplainable machine learningSHAP valuesModel prediction |
| spellingShingle | Van Nhanh Nguyen Nghia Chung G.N. Balaji Krzysztof Rudzki Anh Tuan Hoang Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction Alexandria Engineering Journal Ship fuel consumption Maritime industry Internet of things Explainable machine learning SHAP values Model prediction |
| title | Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction |
| title_full | Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction |
| title_fullStr | Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction |
| title_full_unstemmed | Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction |
| title_short | Internet of things-driven approach integrated with explainable machine learning models for ship fuel consumption prediction |
| title_sort | internet of things driven approach integrated with explainable machine learning models for ship fuel consumption prediction |
| topic | Ship fuel consumption Maritime industry Internet of things Explainable machine learning SHAP values Model prediction |
| url | http://www.sciencedirect.com/science/article/pii/S111001682500095X |
| work_keys_str_mv | AT vannhanhnguyen internetofthingsdrivenapproachintegratedwithexplainablemachinelearningmodelsforshipfuelconsumptionprediction AT nghiachung internetofthingsdrivenapproachintegratedwithexplainablemachinelearningmodelsforshipfuelconsumptionprediction AT gnbalaji internetofthingsdrivenapproachintegratedwithexplainablemachinelearningmodelsforshipfuelconsumptionprediction AT krzysztofrudzki internetofthingsdrivenapproachintegratedwithexplainablemachinelearningmodelsforshipfuelconsumptionprediction AT anhtuanhoang internetofthingsdrivenapproachintegratedwithexplainablemachinelearningmodelsforshipfuelconsumptionprediction |