Evaluation of emission of the hydrogen-enriched diesel engine through machine learning

Erlin Tian, Guoning Lv and Zuhe Li

Energy, 2024, vol. 307, issue C

Abstract: Improving the engine operation by implementing intelligent algorithms is crucial for meeting stricter emissions regulations and enhancing engine performance. Therefore, in this study, hydrogen enrichment effects on emissions from a diesel engine were examined. The diesel engine's intake port was used to add hydrogen. Different quantities of hydrogen (2.5–13 lpm) were used to study the effects of hydrogen on the diesel engine at various engine loads (0–100 %) and speeds. The results of the study indicate that machine learning methods are highly effective modeling techniques with a high level of accuracy. Moreover, XGBoost outperformed other methods regarding its prediction performance, specifically for CO2 (R2 = 0.997) compared to random forest prediction (R2 = 0.964). These techniques strongly agreed with experimental findings, ranging from 97 % to 99 %. Other machine learning algorithms were also used to predict CO and NOx, but their R2 values were slightly lower than those of machine learning models, further highlighting the excellent predictive capabilities of XGBoost modeling.

Keywords: Emission; Machine learning; Diesel engine; Hydrogen; Accuracy analysis (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224020772
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:307:y:2024:i:c:s0360544224020772

DOI: 10.1016/j.energy.2024.132303

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().