Applying machine learning techniques to predict laminar burning velocity for ammonia/hydrogen/air mixtures

Ustun, Cihat Emre, Herfatmanesh, Mohammad Reza, Valera-Medina, Agustin ORCID: https://orcid.org/0000-0003-1580-7133 and Paykani, Amin 2023. Applying machine learning techniques to predict laminar burning velocity for ammonia/hydrogen/air mixtures. Energy and AI 13 , 100270. 10.1016/j.egyai.2023.100270

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

Ammonia utilisation in internal combustion engines has attracted wide interest due to the current trend toward decarbonisation, as ammonia is a zero-carbon fuel with different combustion properties to hydrocarbons. The laminar burning velocity (LBV) is a fundamental property of fuels with a significant effect on the combustion processes and accurate calculations and measurements of the LBV over a wide range of fuel blends, pressures and flow conditions is a time-consuming, complicated procedure. The main goal of the current study is to predict the LBV of NH3/H2/air mixtures using a hybrid machine learning (ML) approach based on a training dataset consisting of both the experimental LBV values and additional data obtained from numerical simulations with a detailed kinetic model. Initial ML model training data is collected from existing experimental LBV in the literature for NH3/H2/air mixtures. Then, synthetic data is generated using one-dimensional (1D) simulations to reduce data inhomogeneinty and increase accuracy of the ML model. In total, 24 different ML algorithms are tested to find the best model both for the experimental and the hybrid dataset. The results suggest that both Gaussian Process Regression (GPR) and Neural Networks (NNs) can be utilised to predict LBV of NH3/H2/air mixtures with reasonable accuracy. The hybrid ML model achieved a coefficient of determination of R = 0.998. Finally, hybrid ML model hyperparameters are optimised to achieve a coefficient of determination of R = 0.999. It was also found that ML can speed up LBV computation from 9500 to 27000 times compared to 1D simulations with a reduced mechanism.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Elsevier
ISSN:	2666-5468
Funders:	EPSRC
Date of First Compliant Deposit:	16 May 2023
Date of Acceptance:	6 May 2023
Last Modified:	21 Jul 2023 05:53
URI:	https://orca.cardiff.ac.uk/id/eprint/159437

Actions (repository staff only)

Edit Item