Advances in Deep Learning-Based Vehicle Fault Diagnosis

DOI

10.2991/978-94-6463-821-9_57How to use a DOI?

Keywords

Deep Learning; Vehicle Fault Diagnosis; Subsystem Analysis; Predictive Maintenance

Abstract

With the rapid development of automotive systems toward electrification and intelligence, fault diagnosis faces unprecedented complexity. Traditional rule-based methods struggle to address dynamic and multimodal faults in modern vehicles. Deep learning (DL) technology has revolutionized fault diagnosis by leveraging its ability to autonomously extract high-dimensional features and adapt to cross-domain scenarios. Existing research on DL-based automotive fault diagnosis predominantly focuses on isolated subsystems, lacking systematic analysis of their application conditions and characteristics in holistic systems, particularly in new energy systems. This review focuses on collaborative diagnostic technology systems for vehicle subsystems. First, it briefly introduces DL algorithms for automotive fault diagnosis. Second, it investigates a diagnostic framework covering multiple subsystems, including the powertrain, chassis safety system, sensor system, and electric system of new energy vehicles, using a “fault-data-model” tripartite analytical framework to elucidate research progress in each subsystem. Finally, it explores emerging directions, such as the integration of knowledge graphs, digital twin technologies, and lightweight model deployment, providing a technical roadmap for next-generation intelligent maintenance systems. This work summarizes the performance and application effects of various DL algorithms for different automotive subsystems, aiming to foster interdisciplinary collaboration and accelerate the transition from algorithmic innovation to engineering practice.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Congsha Li
PY  - 2025
DA  - 2025/08/31
TI  - Advances in Deep Learning-Based Vehicle Fault Diagnosis
BT  - Proceedings of the 2025 2nd International Conference on Mechanics, Electronics Engineering and Automation (ICMEEA 2025)
PB  - Atlantis Press
SP  - 573
EP  - 593
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-821-9_57
DO  - 10.2991/978-94-6463-821-9_57
ID  - Li2025
ER  -