EUVIMEDEUVIMED entdecken
Crossref

A Survey of Machine-Learning Methods for Internal-Combustion Engine Calibration and Real-Time Control

Siddharth Bhimpure, Prasanna Sutar, Debjyoti Bandyopadhyay, Dr. Shailesh Sonawane, Dr. Sukrut S. Thipse

ARAI Journal of Mobility Technology · 16.07.2025 · 6 (3) · 2265-2285

DOI: 10.37285/ajmt.6.3.8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ARAI Journal of Mobility Technology, online erschienen am 16.07.2025. Verfasst von Siddharth Bhimpure und 4 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The calibration of internal combustion (IC) engines is considered a multi-objective optimization challenge that involves nonlinear, complex interactions among the performance metrics and control parameters. The conventional approaches such as lookup tables (LUTs) and Design of Experiments (DoE) are time consuming and often result in sub-optimal solutions particularly after the introduction of alternative fuels and strict global emission standards such as Euro 6, EPA, CPCB. The recent evolution in Machine Learning (ML) techniques assure transformative potential by enabling adaptive control strategies, surrogate modelling and virtual sensing. This paper provides a thorough literature review of the application of Machine Learning (ML) in engine calibration, encompassing ensemble techniques, artificial neural networks, support vector regression, and reinforcement learning. Comparative analysis with traditional methods reveals a significant reduction in calibration time and enhanced prediction accuracy. Furthermore, the review highlights the research gaps in real-time optimization, hybrid physics-ML models and adherence to regulations across various markets. The findings display the importance of ML as a foundation for next-generation engine development, presenting efficient, robust and globally compatible calibration solutions. Keywords: Machine Learning, Multi-Objective Optimization, Engine Calibration, Surrogate Modelling, Adaptive Engine Control

Zitieren

APA

Bhimpure, S., Sutar, P., Bandyopadhyay, D., Sonawane, D. S., & Thipse, D. S. S. (2025). A Survey of Machine-Learning Methods for Internal-Combustion Engine Calibration and Real-Time Control. ARAI Journal of Mobility Technology, 6(3), 2265-2285. https://doi.org/10.37285/ajmt.6.3.8

Vancouver

Bhimpure S, Sutar P, Bandyopadhyay D, Sonawane DS, Thipse DSS. A Survey of Machine-Learning Methods for Internal-Combustion Engine Calibration and Real-Time Control. ARAI Journal of Mobility Technology. 2025;6(3):2265-2285. doi:10.37285/ajmt.6.3.8

BibTeX
@article{Bhimpure2025,
  author = {Bhimpure, Siddharth and Sutar, Prasanna and Bandyopadhyay, Debjyoti and Sonawane, Dr. Shailesh and Thipse, Dr. Sukrut S.},
  title = {A Survey of Machine-Learning Methods for Internal-Combustion Engine Calibration and Real-Time Control},
  journal = {ARAI Journal of Mobility Technology},
  year = {2025},
  volume = {6},
  number = {3},
  pages = {2265--2285},
  doi = {10.37285/ajmt.6.3.8}
}
Kostenlos starten →