Optimizing Waste Heat Recovery in Marine Power Plants
Keywords:
Waste Heat Recovery, Marine Power Plants, Artificial Neural Networks, energy efficiency, Marine Sustainability, Machine LearningAbstract
In today’s world, the demand for marine industries to improve energy efficiency and reduce environmental impact from marine power plants through waste heat recovery (WHR) is increasing daily. the energy efficiency of the marine engine is about 50% with a large amount of energy removed as waste heat, especially in exhaust gases. The present research paper proposes the optimization of the WHR by adopting the artificial neural network (ANN) model, exploring real-world data extracted from marine power plants on board to investigate the optimization of waste heat recovery. The ANN model, which was trained with operational parameters including exhaust gas temperature, engine load and ambient conditions, showed a very good predictive capability producing an R2 of 0.95, RMSE of 3.85kW, and MAE of 2.68kW. The ANN model proved to be more accurate and reliable than conventional thermodynamic methods considering fluctuating operational conditions. as indicated by the sensitivity analysis, exhaust gas temperature and engine load were found to produce the greatest impact on the potential of WHR. The results have a tremendous impact on the maritime sector, enabling ship operators and owners to improve efficiency and sustainability while reducing exhaust gas emissions.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Kombo Theophilus-johnson, Ogboada (Mr), John (Dr)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Scientific Journal of Maritime Research understands the need for authors to disseminate and maximize the impact of their research. When submitting an article for publishing in Scientific Journal of Maritime Research, it implies that the Corresponding Author transfers, with the consent of all Coauthors, the copyright ownership in the referenced submission, including all versions in any format now known or hereafter developed, to the Scientific Journal of Maritime Research.
Copyright protects your original work and research material and prevents others from using it without your permission. Others will be required to credit you and your work properly, thus increasing its impact. Should your submission be rejected or withdrawn prior to acceptance for publication by Scientific Journal of Maritime Research, this transfer will be null and void.
Authors, users or readers of an article need clear instructions on how they can use the article. Scientific Journal of Maritime Research uses the Creative Commons Attribution-NonCommercial-NoDerivatives (CC-BY-NC-ND) 4.0 International License, which governs the use, publishing and distribution of articles by authors, publishers and the wider general public.
The authors are allowed to post a digital file of the published article, or the link to the published article (Scientific Journal of Maritime Research web page) may be made publicly available on websites or repositories, such as the Author’s personal website, preprint servers, university networks or primary employer’s institutional websites, third party institutional or subject-based repositories, and conference websites that feature presentations by the Author(s) based on the published article, under the condition that the article is posted in its unaltered Scientific Journal of Maritime Research form, exclusively for non-commercial purposes.
