Study on control-oriented emission predictions of ammonia-diesel dual-fuel engine with combustion identification

Ziqiang Chen, Peng Ju, Man Gong, Xiaodong Shi, Ciwei Qin and Lei Shi

Energy, 2025, vol. 333, issue C

Abstract: Model predictive control (MPC) represents an advanced technique for enhancing the optimal control of ammonia-diesel dual-fuel engines. This study focuses on developing control-oriented prediction models for combustion state and emissions based on injection parameters, providing a foundation for MPC. By integrating the multi-segment Wiebe model with heat release rate (HRR) classification, high-precision reconstruction of combustion states under varying injection conditions is achieved. Through correlation analysis between combustion characteristic parameters and emissions, a neural network-based prediction model is constructed and coupled with the combustion model to enable real-time prediction of unburned ammonia (uNH3), and nitrogen oxides (NOx) emissions. The results demonstrate that the developed combustion model accurately reconstructs the HRR of ammonia-diesel combustion, with maximum prediction errors for the crank angle at 10 % and 50 % of total heat release below 1.4 °CA, a maximum prediction error for combustion duration of 2.2 °CA, and a maximum error in the peak pressure rise rate of approximately 6 %. Following feature selection, the prediction accuracies for uNH3 and NOx are 0.919 and 0.933, respectively, with a model computation time of 7.35 ms, achieving real-time and precise prediction of engine's emission based on operating condition parameters and ammonia-diesel injection parameters.

Keywords: Ammonia-diesel engine; Control-oriented model; Combustion state reconstruction; Emission prediction (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225030324
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:333:y:2025:i:c:s0360544225030324

DOI: 10.1016/j.energy.2025.137390

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 ().