Assessing fuel economy and NOx emissions of a hydrogen engine bus using neural network algorithms for urban mass transit systems

Seongsu Kim and Junghwan Kim

Energy, 2023, vol. 275, issue C

Abstract: The transition from compressed natural gas (CNG) to hydrogen has begun in mass transportation applications in Seoul, South Korea. This study investigates the feasibility of using a hydrogen combustion engine for city buses in Seoul. A hydrogen-fueled, six-cylinder, 11,046-cm3 spark-ignition engine equipped with a mixer-type fuel supply system is proposed. An experiment using a single-cylinder engine is performed to obtain operating and performance maps. These maps are then used in the vehicle simulation model. Combustion characteristics are investigated using three-dimensional numerical simulation validated by the experimental results. A regression analysis is conducted using neural network algorithms to determine the dominant operating parameters on nitric oxides (NOx) emissions, and 373 bus routes in Seoul are analyzed using real-time driving data and recent annual statistics. The vehicle driving simulation using actual Seoul bus driving data reveals an average fleet fuel economy of 121.7 g/km, confirming that hydrogen-engine buses can be more efficient than the CNG buses currently in use. A 70-MPa tank can store 34.78 kg of hydrogen, which yields a maximum travel distance of 388 km longer than the longest route (bus #9411 at 77 km). The result indicates that even a 20-Mpa fuel tank, enabling a bus to travel 144 km, is sufficient for Seoul city buses.

Keywords: Hydrogen; Mixer-type fuel supply; Engine development; Urban mass transport system; Driving simulation; 1D simulation (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223009118
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:275:y:2023:i:c:s0360544223009118

DOI: 10.1016/j.energy.2023.127517

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 ().