Developing Generalized Health Index of Electric Vehicle Drivetrain
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Motors and reducers are core components of an electric vehicle’s drivetrain. If either the motor or reducer fails, the vehicle cannot operate, and at high speeds, this poses a significant safety risk. Therefore, preventing failures in these components is critical for customer safety. However, most existing fault diagnosis models for electric vehicle drivetrains show limited performance under real driving conditions because load and speed vary continuously.
In this study, we propose a novel vibration signal generalization method that combines order tracking with physics-based amplitude adjustment techniques to improve diagnostic accuracy under variable operating conditions. Furthermore, we developed an AI model incorporating a health index that enhances generalization performance, enabling scalability across 5 different vehicle types
To achieve this, we designed a data processing technique that standardizes measurement data from various vehicle types by integrating domain knowledge, such as order analysis based on CAN bus speed information. The resulting health index successfully distinguishes deteriorated vehicles from normal ones regardless of vehicle type or driving conditions.
The findings of this study are expected to play a key role in applications under variable speed conditions.
How to Cite
##plugins.themes.bootstrap3.article.details##
electirc vehicle, drivetrain, Health index
Lee, K.-W., Sung, D.-U., Han, Y., Yoo, Y., & Lee, J. (2023). Diagnosis and prognosis of chassis systems in autonomous driving conditions. In WCX 2023. SAE Paper 2013-01-0741. Detroit, MI, USA.
Lee, K.-W., Ryu, Y. H., Sung, D.-U., Yoo, D., Oh, J., & Oh, H. (2025). Development of a fault diagnosis and degradation prediction algorithm for the drivetrain of electric vehicles. In FISITA World Mobility Conference (WMC), WMC25-F-FMT-002. Barcelona, Spain.
Lee, N., Azarian, M. H., Pecht, M., Kim, J., & Im, J. (2019). A comparative study of deep learning-based diagnostics for automotive safety components using a Raspberry Pi. In 2019 IEEE International Conference on Prognostics and Health Management (ICPHM). San Francisco, CA, USA.
Lim, H., Lee, J. W., Boyack, J., & Choi, J. B. (2025). EV-PINN: A physics-informed neural network for predicting electric vehicle dynamics. In Proceedings of the IEEE International Conference on Robotics and Automation.
Oh, J., Yoo, D., Kim, C., Oh, H., Ryu, Y., Lee, K.-W., & Sung, D.-U. (2025). A hybrid fault diagnostic approach using operational transfer path analysis and denoising deep learning with remote sensors: Application to electric vehicles. Expert Systems with Applications, 270, 126470.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.