Study on prediction of gas injection mass fluctuation for hydrogen-diesel co-direct injection system: A prediction algorithm driven by model and perception iterative

Xiyu Yang, Fangliang Yang, Nan Li, Liang Zhang, Jian Lei, Cheng Shi, Yun Bai and Quan Dong

Energy, 2024, vol. 308, issue C

Abstract: The high-pressure hydrogen direct injection technology with diesel pilot ignition based on concentric biaxial needle injector is an advanced technology for low carbonization transformation of heavy power machinery at present, but it is faced with the problem that the pilot injection has a significant fluctuation of the main gas injection mass. Therefore, this paper describes the fluctuation rule of gas injection mass in detail, reveals the fluctuation mechanism through the characteristics of pressure oscillation in the system, and proposes an innovative prediction algorithm. It is found that the diesel pressure oscillation induced by pilot injection is the direct factor causing the fluctuation of gas injection mass. The fluctuation has the opposite trend to the diesel pressure oscillation, and both show the trend of underdamped cosine function oscillation. On this basis, a prediction algorithm for the fluctuation characteristics is established, which includes four main sub-algorithms. Among them, a sub-algorithm for predicting the fluctuation period is constructed based on the electro-hydraulic modeling method, a sub-algorithm for calibration of the underdamped dissipation system is constructed by using the real-time fitting and historical data iteration method, and a sub-algorithm for designing phase difference based on the real-time perceived fuel sound velocity. Finally, two-dimensional fitting is used to calibrate the amplitude and build a bridge between pressure oscillation and gas injection mass fluctuation. The results show that the prediction algorithm has high accuracy in almost all the common injection conditions. The regression determination coefficient (R2) of the predicted value and the measured value is 0.9118, and the root mean square error (RMSE) is 2.013 mg. Through the construction of the gas injection mass fluctuation prediction algorithm model, to achieve the accurate prediction of the gas injection mass, can provide feedback data for the advanced control strategy and provide certain basis for accurate control of the gas injection mass.

Keywords: Hydrogen; Internal combustion engine; Dual-fuel injection; Gas injection mass fluctuation; Prediction algorithm (search for similar items in EconPapers)
Date: 2024
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/S0360544224027762
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:308:y:2024:i:c:s0360544224027762

DOI: 10.1016/j.energy.2024.133002

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 ().