Data-Driven Fault Detection and Feature Selection from CAN-Bus Diagnostics in Commercial Vehicle

Beyza Nur Büyükdemir; Suat Köroğlu; Bahar Ataş; Nurcan Gökırmak; Enis Karaarslan

doi:10.61969/jai.1862835

Data-Driven Fault Detection and Feature Selection from CAN-Bus Diagnostics in Commercial Vehicle

Abstract

Mitigating unplanned breakdowns in commercial vehicle fleets is critical for operational efficiency, yet challenging due to the complexity of diagnostic data. This study presents a predictive maintenance framework designed for control systems, utilizing fault codes transmitted via the J1939 CAN Bus protocol. We analyzed Diagnostic Message 1 (DM1) structures, specifically Suspect Parameter Numbers (SPNs) and Failure Mode Identifiers (FMIs), to extract interpretable features for real-time applications. The research utilizes a dataset of operational telemetry and diagnostic logs from 120 internal combustion buses over two years. We developed a structured feature engineering pipeline that incorporates temporal alignment, correlation analysis, and XGBoost-based feature weighting to track mechanical fault progression, with a specific focus on engine oil pressure events. To improve model interpretability, we integrated SHAP analysis. Our results identify cumulative runtime and braking system indicators as strong predictors for early fault detection. By converting discrete diagnostic codes into continuous indicators, the proposed framework enables direct integration of predictive intelligence within fleet management and supervisory systems.

Keywords

References

Aeddula, O., Frank, M., Ruvald, R., Johansson Askling, C., Wall, J., & Larsson, T. (2024). AI-driven predictive maintenance for autonomous vehicles for product-service system development. Procedia CIRP, 128, 84–89. https://doi.org/10.1016/j.procir.2024.05.016
Bekar, E. T., Nyqvist, P., & Skoogh, A. (2020). An intelligent approach for data pre-processing and analysis in predictive maintenance with an industrial case study. Advances in Mechanical Engineering, 12(5), 1687814020919207. https://doi.org/10.1177/1687814020919207
Büyükdemir, B. N., Köroğlu, S., Ataş, B., Gökirmak, N., & Karaarslan, E. (2025). Smart fleet management in urban public transportation: Machine learning based predictive maintenance with real-time CAN-Bus data. In Proceedings of the 2025 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1–6). 10.1109/ASYU67174.2025.11208302
Cavus, M., Dissanayake, D., & Bell, M. (2025). Next Generation of Electric Vehicles: AI-Driven Approaches for Predictive Maintenance and Battery Management. Energies, 18(5), 1041. https://doi.org/10.3390/en18051041
Ercevik, A. I., & Ozbayoglu, A. M. (2025). Artificial intelligence based predictive maintenance for electric buses (arXiv:2510.23879) [Preprint]. ArXiv. https://arxiv.org/abs/2510.23879
Alves Garcia, B. R. (2024). Combining Random Forest and SHAP for interpretability and insights in predictive maintenance (Master’s thesis, National College of Ireland, Dublin). https://norma.ncirl.ie/id/eprint/8670
Hakami, A. (2024). Strategies for overcoming data scarcity, imbalance, and feature selection challenges in machine learning models for predictive maintenance. Scientific Reports, 14, 9645. https://doi.org/10.1038/s41598-024-59958-9
Hancock, J. T., Khoshgoftaar, T. M., & Liang, Q. (2025). A problem-agnostic approach to feature selection and analysis using SHAP. Journal of Big Data, 12, 12. https://doi.org/10.1186/s40537-024-01041-1

Ibrahim, H., Ali, A. M., & Attia, T. (2025). Optimizing electric bus performance via predictive maintenance: A combined experimental and modeling approach. Frontiers in Future Transportation, 5, 1506866. https://doi.org/10.3389/ffutr.2024.1506866
Kaur, A., & Sarmadi, M. (2024). Comparative analysis of machine learning techniques for imbalanced genetic data. Annals of Data Science, 12(5), 1553–1575. https://doi.org/10.1007/s40745-024-00575-8
Lins, R. G., de Freitas, T. N., & Gaspar, R. (2025). Methodology for commercial vehicle mechanical systems maintenance: Data-driven and deep learning based prediction. IEEE Access, 13, 33799–33812. https://doi.org/10.1109/ACCESS.2025.3543600
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in Neural Information Processing Systems (Vol. 30). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
Mahale, Y., Kolhar, S., & More, A. S. (2025). A comprehensive review on artificial intelligence driven predictive maintenance in vehicles: Technologies, challenges, and future research directions. Discover Applied Science, 7, 243. https://doi.org/10.1007/s42452-025-06681-3
Nagy, J., & Lakatos, I. (2024). Predictive maintenance and predictive repair of road vehicles—Opportunities, limitations and practical applications. Engineering Proceedings, 79(1), 27. https://doi.org/10.3390/engproc2024079027
Rana, S. (2025). AI-driven fault detection and predictive maintenance in electrical power systems: A systematic review of data-driven approaches, digital twins, and self-healing grids. American Journal of Advanced Technology and Engineering Solutions, 1(1), 258–289. https://doi.org/10.63125/4p25x993
Rasheed, R., Qazi, F., Agha, D. S., Ahmed, A., Asif, A., & Shams, H. (2024). Machine learning approaches for in-vehicle failure prognosis in automobiles: A review. VFAST Transactions on Software Engineering, 12(1), 169–182. https://doi.org/10.21015/vtse.v12i1.1713
Syed, S. (2024). Enhancing school bus engine performance: Predictive maintenance and analytics for sustainable fleet operations. Library of Progress-Library Science, Information Technology & Computer, 44(3), 17765–17775.
Tormos, B., Pla, B., Sánchez-Márquez, R., & Carballo, J. L. (2025). Explainable AI using on-board diagnostics data for urban buses maintenance management: A study case. Information, 16(2), 74. https://doi.org/10.3390/info16020074
Zhang, C. (2024). Intelligent fault prediction and diagnosis of intelligent networked vehicle based on filter pruning with snapshot stacked ensemble deep neural network. In Proceedings of the 2024 4th International Conference on Mobile Networks and Wireless Communications (ICMNWC) (pp. 1–5). IEEE. 10.1109/ICMNWC63764.2024.10872049

Details

Primary Language

English

Subjects

Planning and Decision Making

Journal Section

Research Article

Authors

Beyza Nur Büyükdemir
1000-9000-4304-6432
Türkiye

Suat Köroğlu
0009-0000-3677-3740
Türkiye

Bahar Ataş
0000-0001-6457-6226
Türkiye

Nurcan Gökırmak
0009-0001-9776-3041
Türkiye

Enis Karaarslan ^*
0000-0002-3595-8783
Türkiye

Publication Date

February 28, 2026

Submission Date

January 13, 2026

Acceptance Date

February 24, 2026

Published in Issue

Year 2026 Number: 10

DOI

https://doi.org/10.61969/jai.1862835

IZ

https://izlik.org/JA67FK62DH

Cite

RIS / Bibtex

APA

Büyükdemir, B. N., Köroğlu, S., Ataş, B., Gökırmak, N., & Karaarslan, E. (2026). Data-Driven Fault Detection and Feature Selection from CAN-Bus Diagnostics in Commercial Vehicle. Journal of AI, 10, 24-36. https://doi.org/10.61969/jai.1862835