OBD-II Big Data–Driven ML and AI-Based Virtual Sensing for Fuel Economy, Component Health, and Carbon Intelligence

Year : 2026 | Volume : 13 | Issue : 01 | Page : 39 50
    By

    Arumugam Palanichamy,

  • Karthikeyan Subramanian,

  • Rajavel Rangasamy,

  • Suresh Alex Selvaraj,

  1. Research Scholar, Department of Marine Engineering, AMET University, Chennai, Pin-603112, Tamilnadu, India
  2. Assistant General Manager, Department of Fuel Cell Development, Ashok Leyland Technical Centre, Chennai, Pin-600103, Tamilnadu, India
  3. Principal, Head of Engineering Department, Sri Balaji Chockalingam Engineering College, Irumbedu, Arni, Pin-632301, Tamilnadu, India
  4. Professor, Department of Marine Engineering, AMET University, Chennai, Pin-603112, Tamilnadu, India

Abstract

The rapid growth of connected vehicles has led to the large-scale availability of high-frequency On-Board Diagnostics II (OBD-II) data; however, much of this data remains underutilised, as existing studies and commercial systems typically address fuel economy, maintenance, or emissions in isolation or rely on additional physical sensors. Such fragmented and sensor-dependent approaches limit scalability and increase system cost, particularly in high-volume and resource-constrained vehicle markets. To address this gap, this study proposes an OBD-II big data–driven machine learning and artificial intelligence based virtual sensing approach that enables simultaneous estimation of fuel economy, component health, and carbon intelligence using only standard onboard signals. Continuous real-world OBD-II data collected during naturalistic vehicle operation are analysed using physics-guided feature extraction combined with unsupervised learning and interpretable AI techniques to derive sensor-less virtual metrics, including fuel economy (kmpl), gross vehicle weight or payload trends, clutch and brake wear indicators, battery state of health, remaining driving range, and carbon dioxide emissions. By exploiting intrinsic relationships between engine torque demand, vehicle dynamics, operating conditions, and fuel consumption behaviour, the proposed approach demonstrates that multiple energy, health, and sustainability indicators can be inferred reliably without additional hardware. Overall, this work supports fuel-efficient operation, proactive maintenance, and accurate carbon monitoring, contributing to reduced fuel consumption, lower greenhouse gas emissions, and improved total cost of ownership, while offering a scalable pathway toward software-defined vehicle intelligence using existing vehicle data infrastructure.

Keywords: Virtual Sensing, OBD-II Big Data, Machine Learning and Artificial Intelligence, Fuel Economy Analysis, Vehicle Component Health Monitoring, Carbon Emission Intelligence

[This article belongs to Journal of Automobile Engineering and Applications ]

How to cite this article:
Arumugam Palanichamy, Karthikeyan Subramanian, Rajavel Rangasamy, Suresh Alex Selvaraj. OBD-II Big Data–Driven ML and AI-Based Virtual Sensing for Fuel Economy, Component Health, and Carbon Intelligence. Journal of Automobile Engineering and Applications. 2026; 13(01):39-50.
How to cite this URL:
Arumugam Palanichamy, Karthikeyan Subramanian, Rajavel Rangasamy, Suresh Alex Selvaraj. OBD-II Big Data–Driven ML and AI-Based Virtual Sensing for Fuel Economy, Component Health, and Carbon Intelligence. Journal of Automobile Engineering and Applications. 2026; 13(01):39-50. Available from: https://journals.stmjournals.com/joaea/article=2026/view=236343


References

[1] Bishop, C. M., Pattern Recognition and Machine Learning, Springer, New York, USA, 2006.

[2] Hastie, T., Tibshirani, R., and Friedman, J., The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, New York, USA, 2009.

[3] Géron, A., Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, O’Reilly Media, Sebastopol, CA, USA, 2019.

[4] Breiman, L., “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

[5] Lundberg, S. M., and Lee, S.-I., “A unified approach to interpreting model predictions,” Advances in Neural Information Processing Systems (NeurIPS), vol. 30, pp. 4765–4774, 2017.

[6] Franco, A., López, R., and Gallego, J., “OBD-based monitoring of vehicle energy use under real driving conditions,” IEEE Access, vol. 7, pp. 103211–103223, 2019.

[7] Wang, J., Liu, H., and Chen, Y., “Machine learning models for vehicle fuel consumption prediction using OBD data,” Energy Conversion and Management, vol. 222, pp. 113199, 2020.

[8] Ma, S., Zhao, X., and Liu, Y., “Real-world driving cycle construction using large-scale OBD data,” Transportation Research Part D: Transport and Environment, vol. 87, pp. 102498, 2020.

[9] Wu, Y., Song, J., and Yu, H., “Big data driven analysis of vehicle energy consumption,” Applied Energy, vol. 275, pp. 115410, 2020.

[10] SAE International, “Use of OBD data for vehicle performance and fuel economy analysis,” SAE Technical Paper 2018-01-0399, 2018.

[11] Kadlec, P., Gabrys, B., and Strandt, S., “Data-driven soft sensors in the process industry,” Computers & Chemical Engineering, vol. 33, no. 4, pp. 795–814, 2009.

[12] Fortuna, L., Graziani, S., and Xibilia, M. G., Soft Sensors for Monitoring and Control of Industrial Processes, Springer, London, UK, 2007.

[13] Ge, Z., Song, Z., Ding, S. X., and Huang, B., “Data mining and analytics in the process industry: The role of machine learning,” Journal of Process Control, vol. 67, pp. 123–138, 2017.

[14] Wang, L., Wang, Y., and Zhang, L., “Virtual sensing for automotive applications: Concepts and challenges,” IEEE Transactions on Vehicular Technology, vol. 68, no. 11, pp. 10488–10500, 2019.

[15] Jardine, A. K. S., Lin, D., and Banjevic, D., “A review on machinery diagnostics and prognostics implementing condition-based maintenance,” Mechanical Systems and Signal Processing, vol. 20, no. 7, pp. 1483–1510, 2006.

[16] Lei, Y., Li, N., Guo, L., Li, N., Yan, T., and Lin, J., “Machinery health prognostics: A systematic review,” Mechanical Systems and Signal Processing, vol. 104, pp. 799–834, 2018.

[17] Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., and Gao, R. X., “Deep learning and its applications to machine health monitoring,” Mechanical Systems and Signal Processing, vol. 115, pp. 213–237, 2019.

[18] Hannan, A., Arebey, M., and Begum, R., “Machine learning based predictive analytics for automotive applications,” IEEE Access, vol. 8, pp. 18187–18204, 2020.

[19] Rakha, H., Ahn, K., and Trani, A., “Development of VT-Micro model for estimating hot stabilized fuel consumption,” Transportation Research Part D: Transport and Environment, vol. 9, no. 1, pp. 49–74, 2004.

[20] Sun, M., Chen, X., and Zhang, Y., “Real-world vehicle fuel consumption modeling based on big data analytics,” Energy, vol. 193, pp. 116738, 2020.

[21] Chen, Y., Liu, S., and Li, L., “Fuel consumption estimation based on real-world driving data using machine learning,” Applied Energy, vol. 238, pp. 1268–1280, 2019.

[22] Fontaras, G., and Samaras, Z., “On-road fuel consumption and CO₂ emissions of light-duty vehicles,” Energy Policy, vol. 36, no. 10, pp. 3579–3588, 2008.

[23] Barth, M., and Boriboonsomsin, K., “Real-world carbon dioxide impacts of traffic congestion,” Transportation Research Record, vol. 2058, pp. 163–171, 2008.

[24] Hasan, M. K., and Feng, S., “A review of data-driven energy consumption models for vehicles,” Renewable and Sustainable Energy Reviews, vol. 144, pp. 110984, 2021.

[25] Zhao, S., Li, M., and Wang, H., “Artificial intelligence for sustainable transportation systems,” Journal of Cleaner Production, vol. 234, pp. 114–125, 2019.

[26] Tao, F., Zhang, H., Liu, A., and Nee, A. Y. C., “Digital twins and cyber–physical systems toward smart manufacturing,” Engineering, vol. 5, no. 4, pp. 653–661, 2019.

[27] Boschert, S., and Rosen, R., “Digital twin—The simulation aspect,” in Mechatronic Futures, Springer, Cham, Switzerland, pp. 59–74, 2016.

[28] Zhang, J., Wang, Y., and Li, L., “Big data analytics in intelligent transportation systems,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 9, pp. 3436–3448, 2019.

[29] Li, Y., Zhang, X., and Wang, Z., “Deep learning and machine learning for vehicle energy consumption prediction,” Applied Energy, vol. 257, pp. 113987, 2020.

[30] Meseguer, J. E., Puig, V., and Quevedo, J., “Driving styles and fuel consumption characterization using data-driven methods,” IEEE Intelligent Transportation Systems Magazine, vol. 10, no. 1, pp. 50–62, 2018.

[31] Qi, Y., Luo, L., and Wang, S., “Driving behavior analysis based on vehicle trajectory big data,” Transportation Research Part C: Emerging Technologies, vol. 95, pp. 234–247, 2018.

[32] Hu, X., Yuan, H., Zou, C., Li, Z., and Zhang, L., “Battery state-of-health estimation using machine learning,” IEEE Transactions on Transportation Electrification, vol. 4, no. 4, pp. 111–120, 2018.

[33] He, W., Williard, N., Chen, C., and Pecht, M., “State of health estimation of lithium-ion batteries,” Journal of Power Sources, vol. 196, no. 23, pp. 10314–10321, 2011.

[34] Jain, A., Aslam, M., and Mehmood, N., “Machine learning applications in the automotive industry: A comprehensive review,” IEEE Access, vol. 9, pp. 10112–10130, 2021.

[35] Chen, M., Xu, S., and Zhao, Y., “AI-based energy modeling for intelligent vehicles,” Energy AI, vol. 6, pp. 100095, 2021.Top of Form

Regular Issue Subscription Original Research
Volume 13
Issue 01
Received 19/01/2026
Accepted 25/01/2026
Published 11/02/2026
Publication Time 23 Days
2

Login


My IP

PlumX Metrics