Artificial Intelligence in Combustion Science: A Comprehensive Review of Machine Learning and Genetic Algorithms

Strategic Insights -

Artificial intelligence (AI) has revolutionized the field of combustion science, transforming the way researchers approach combustion efficiency, emissions, and energy production. A recent review article published in Applied Sciences presents a detailed analysis of the recent advancements in combustion science and engineering, focusing on the application of machine learning (ML) and genetic algorithms (GAs) from 2015 to 2024. The study highlights the growing role of ML and GAs in enhancing combustion efficiency, reducing emissions, and optimizing energy production, providing insights into the current state of the art and future trends in this critical field.

Key Takeaways:

  • A systematic search in the Scopus database identified 165 peer-reviewed articles relevant to AI applications in combustion science, covering a range of combustion scenarios and fuel types.
  • The most frequently applied methods in predictive modeling include artificial neural networks (ANNs), support vector machines (SVMs), and random forests (RFs), achieving high accuracy in predicting NO emissions and flame speed.
  • Genetic algorithms (GAs) demonstrated effectiveness in fuel blend optimization and geometry design, achieving emission reductions of up to 30% in experimental setups.
  • The study highlights persistent challenges such as data availability, model generalization, and reproducibility, and proposes future directions toward more interpretable and standardized applications of ML/GA in combustion science.
  • The research was conducted by a team of scientists from Kielce University of Technology, led by Jacek Lukasz Wilk-Jakubowski, and published in the journal Applied Sciences.

Statistics:

  • 165 peer-reviewed articles were analyzed in the review, covering a range of combustion scenarios and fuel types.
  • The most frequently applied methods in predictive modeling include ANNs (45%), SVMs (20%), and RFs (15%).
  • GAs demonstrated effectiveness in fuel blend optimization with emission reductions of up to 30% in experimental setups.
  • A total of 12 countries contributed to the research, with significant contributions from Canada, China, France, Germany, India, Iran, Japan, Malaysia, Pakistan, Saudi Arabia, the United Kingdom, and the United States.

Sources:

  • NewsRx. New Research on Machine Learning from Kielce University of Technology Summarized (Data-Driven Computational Methods in Fuel Combustion: A Review of Applications). Life Science Weekly. July 29, 2025; p 2204.
  • Data-Driven Computational Methods in Fuel Combustion: A Review of Applications. Applied Sciences, 2025,15(13):7204. (Applied Sciences - http://www.mdpi.com/journal/applsci)