Title
A comprehensive review on the prediction of ship energy consumption and pollution gas emissions
Author
Wang, K. (TU Delft Transport Engineering and Logistics; Dalian Maritime University)
Wang, Jianhang (Dalian Maritime University)
Huang, Lianzhong (Dalian Maritime University)
Yuan, Yupeng (University of Cambridge; MOST)
Wu, Guitao (Dalian Maritime University)
Xing, Hui (Dalian Maritime University)
Wang, Zhongyi (Dalian Maritime University)
Wang, Zhuang (Shanghai Jiao Tong University)
Jiang, X. (TU Delft Transport Engineering and Logistics) 
Date
2022
Abstract
Ship energy consumption and emission prediction are critical for ship energy efficiency management and pollution gas emission control, both of which are major concerns for the shipping industry and hence continue to attract global attention and research interest. This article examined the energy efficiency data sources, big data analysis for energy efficiency, and analyzed the ship energy consumption and emission prediction models. The ship energy consumption and pollution gas emission prediction models are comprehensively summarized based on the modeling method and principles. The theoretical analysis and artificial intelligence-based ship energy consumption model, as well as the top-down and bottom-up ship emission prediction models, are thoroughly examined in terms of influencing factors, model accuracy, data sources, and practical applications. On this basis, the challenges of ship energy consumption and emission prediction are discussed, and future research suggestions are proposed, providing a foundation for the development of ship energy consumption and emission prediction technologies. The analysis results show that the principles, parameters of concern, and data quality all have a significant impact on the performance of the prediction models. Consequently, the prediction model's accuracy can be improved by combining intelligent algorithms and machine learning. In the future, high precision, self-adapting, ship fuel consumption and emission prediction models based on artificial intelligence technology should be further studied, in order to improve their prediction performance, and thus providing solid foundations for the optimization management and control of the ship energy consumption and emissions.
Subject
Artificial intelligence
Big data analysis
Energy consumption model
Energy efficiency optimization
Low-carbon shipping
Ship emission prediction
To reference this document use:
http://resolver.tudelft.nl/uuid:599ce3a1-f057-45f9-891d-3b256362b55c
DOI
https://doi.org/10.1016/j.oceaneng.2022.112826
Embargo date
2023-05-01
ISSN
0029-8018
Source
Ocean Engineering, 266
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
review
Rights
© 2022 K. Wang, Jianhang Wang, Lianzhong Huang, Yupeng Yuan, Guitao Wu, Hui Xing, Zhongyi Wang, Zhuang Wang, X. Jiang