Application of Deep Neural Networks for Performance and Emission Prediction in Ammonia-Fueled Spark Ignition Engines 


Vol. 31,  No. 4, pp. 339-345, Dec.  2025
10.7464/ksct.2025.31.4.339


PDF
  Abstract

The decarbonization of internal combustion engines (ICE) necessitates advanced predictive tools for ammonia, a zero-carbon fuel with complex combustion dynamics. This study develops a deep neural network (DNN) framework to predict performance parameters and emissions in ammonia-fueled spark ignition engines. Experimental data from a V-twin engine and AVL-BOOST simulations were integrated to train a multi-layer DNN architecture. Data partitioning followed a 70%-15%-15% split for training, validation, and testing. The model achieved exceptional accuracy, with training/validation losses converging range from 10–4 to 10–3, MAE below 0.5%, and R2 > 0.99 across all datasets. The DNN captured critical non-linear phenomena: BMEP’s dependence on ignition timing, showing peak performance at optimal phasing, and NOx reduction under advanced ignition due to lowered peak temperatures.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

Q. N. Y, P. Ho-Van, O. Lim, "Application of Deep Neural Networks for Performance and Emission Prediction in Ammonia-Fueled Spark Ignition Engines," Clean Technology, vol. 31, no. 4, pp. 339-345, 2025. DOI: 10.7464/ksct.2025.31.4.339.

[ACM Style]

Quach Nhu Y, Phuc Ho-Van, and Ocktaeck Lim. 2025. Application of Deep Neural Networks for Performance and Emission Prediction in Ammonia-Fueled Spark Ignition Engines. Clean Technology, 31, 4, (2025), 339-345. DOI: 10.7464/ksct.2025.31.4.339.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

pISSN : 1598 - 9712
eISSN : 2288 - 0690

한국연구재단 등재학술지