AI-Based Combustion Monitoring for NOx and CO2 Reduction in IC Engine-Powered Vehicles
Year: 2025
Type: article
Abstract: The reduction of Nitrogen Oxides (NOx) and Carbon Dioxide (CO₂) emissions from internal combustion (IC) engines is critical for meeting modern environmental regulations and advancing sustainable mobility. This study presents a comprehensive exploration of Artificial Intelligence (AI)-based combustion monitoring as a transformative approach to emission reduction. By leveraging Machine Learning (ML) and Deep Learning (DL) models, real-time data from engine sensors can be analysed to predict combustion behaviour and dynamically control key parameters such as injection timing, air-fuel ratio, and Exhaust Gas Recirculation (EGR). AI-driven systems demonstrate superior adaptability to transient engine conditions, enabling optimised combustion with minimal emissions. Integrating AI technologies enhances diagnostic precision, improves engine efficiency, and supports predictive control strategies that outperform conventional methods. This work highlights the potential of AI not only to meet stringent emission norms but also to pave the way toward intelligent and eco-friendly automotive propulsion systems. Major Findings: AI-powered combustion monitoring allows for the real-time tuning of engine settings, including fuel injection timing, air/fuel ratio, and exhaust gas recirculation, resulting in lower NOx and CO₂ emissions. Machine learning and deep learning based algorithms can efficiently adapt to the changing engine conditions, resulting in better combustion efficiency and fuel economy. This smart connectivity not only benefits the emission reduction efficiency but is also in favour of environmentally sustainable transport because it allows predictive maintenance and cleaner, benign vehicle technologies.
Authors: Nishigandha Patel, Sonika Gill, Puja Gholap, Kirti Wanjale, Naresh B. Dhamane, S. B. Angadi, Shital Yashwant Waware, Anant Sidhappa Kurhade
Language: English
Subfield: Fluid Flow and Transfer Processes
Field: Chemical Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4414213716