Development of Electric Vehicle Battery SOH Prediction Model using Vehicle Inspection Data

Jungsoo Park; Youngmin Jang; Sein Oh; Hyunwoo Jo; Wonduck Park; Hosang Lee; Do-Gyeong Kim

doi:10.22680/kasa2025.17.4.092

All Issue

2025 Vol.17, Issue 4 Preview Page

Development of Electric Vehicle Battery SOH Prediction Model using Vehicle Inspection Data 자동차검사 데이터를 활용한 전기자동차 배터리 상태지수 예측 모델 개발

31 December 2025. pp. 92-97

PDF XML

Abstract

This study develops an SOH prediction model for electric vehicle batteries using periodic technical inspection data collected under driving conditions. As the EV market expands rapidly, accurate SOH estimation is essential for battery safety management, maintenance optimization, and circular economy policy design. The model employs Ridge regression with L2 regularization to address multicollinearity among key predictors as vehicle age, cumulative mileage, total operating time, and total discharge. Cross-validation results showed MAE=2.24%p and RMSE=2.74%p, outperforming a random forest baseline. Variable importance analysis revealed that age and mileage were the strongest predictors, with calendar aging and cycle aging contributing comparably to SOH degradation. A framework is proposed to estimate time-to-threshold for SOH criteria using daily usage patterns. This supports targeted inspection scheduling, residual value assessment for used EVs, and policy development for battery reuse and recycling. By leveraging large-scale field inspection data, the research bridges the gap between laboratory-based SOH modeling and practical diagnostic applications for EV safety management.

Keywords

Periodic technical inspection(자동차검사)

Electric vehicle(전기자동차)

Battery management systems(배터리 관리 시스템)

State of health(배터리 건강 상태)

Predictive model(예측 모델)

References

World Economic Forum, 2025, “Homepage,” https://www.weforum.org.

Ministry of Land, Infrastructure and Transport Statistic System, 2025, “Statistics Portal,” https://stat.molit.go.kr.

Bilfinger, P., et al., 2025, “Why We Need a Standardized State of Health Definition for Electric Vehicle Battery Packs - A Proposal for Energy- and Capacity-Based Metrics,” arXiv.org.

10.1038/s44406-025-00010-8

Hsu, Y. C., Wang, P., and W. F. Wu, 2023, “State of Health Prediction and Reliability Analysis of Li-ion Battery,” IEOM Society International, pp. 1376~1377.

10.46254/AN13.20230409

Santolaya, M. E., Pous, A. M., Casals, L. C., Corchero, C., and Eichman, J., 2024, “Quantifying the Impact of Battery Degradation in Electric Vehicle Driving through Key Performance Indicators,” Batteries, Vol. 10, No. 4, pp. 8199~8212.

10.3390/batteries10030103

Park, J. S., Kim, D. G., Kim, Y. D., and Han, C. P., 2022, “A Study on the Benefits Estimation Derived from Vehicle Inspection Scheme,” Transactions of KSAE, Vol. 30, No. 11, pp. 909~916.

10.7467/KSAE.2022.30.11.909

Doose, S., Hahn, A., Fischer, S., Müller, J., Haselrieder, W., and Kwade, A. 2023, “Comparison of the consequences of state of charge and state of health on the thermal runaway behavior of lithium ion batteries,” Journal of Energy Storage, Vol. 62, pp. 106837~106837.

10.1016/j.est.2023.106837

Joshi, T., Leon, C., Snyder, M., Sankuratri, A., and Raza, M., 2024, “Analyzing Internal Resistance in Lithium Nickel Cobalt Oxide Vehicle Batteries for Enhanced SOC and SOH Prediction,” pp. 1113~1118.

10.1109/SoutheastCon52093.2024.10500138

Madani, S. S., Ziebert, C., Vahdatkhah, P., and Sadrnezhaad, S. K., 2024, Recent Progress of Deep Learning Methods for Health Monitoring of Lithium-Ion Batteries, Vol. 10, Iss: 6, pp. 204~204.

10.3390/batteries10060204

Alamin, K. S. S., Chen, Y., Macii, E., Poncino, M., and Vinco, S., 2025, “Advancing Electric Vehicle Battery Management: A Data-Driven Digital Twin Approach for Real-Time Monitoring and Performance Enhancement,” IEEE Transactions on Vehicular Technology, pp. 1~15.

10.1109/TVT.2025.3565907

Park, S. J., Kang, B. J., Kim, W., Kang, M., Lim, C., and Hong, Y., 2024, “Electric Vehicle Battery Lifespan Diagnosis Technology Based on Resistance Trends Under Real-World Operating Conditions,” Vol. MA2024-02, Issue 3, pp. 390~390.

10.1149/MA2024-023390mtgabs

Zhang, Z., Wang, S., Lin, N., Wang, Z., and Liu, P., 2023, “State of Health Estimation of Lithium-Ion Batteries in Electric Vehicles Based on Regional Capacity,” Vol. 15, Issue 3, pp. 2052~2052.

10.3390/su15032052

Xiao Y, Shi X, Li X, Duan Y, Li X, Zhang J, et al., 2024, “Machine Learning Applied to Lithium‐Ion Battery State Estimation for Electric Vehicles: Method Theoretical, Technological Status, and Future Development. Energy storage,” Energy storage.

10.1002/est2.70080

Information

Publisher :Korean Auto-vehicle Safety Association
Publisher(Ko) :한국자동차모빌리티안전학회
Journal Title :Journal of Auto-vehicle Safety Association
Journal Title(Ko) :자동차안전학회지
Volume : 17
No :4
Pages :92-97
Received Date : 2025-11-10
Accepted Date : 2025-11-17
DOI :https://doi.org/10.22680/kasa2025.17.4.092

Journal of Auto-vehicle Safety Association ISSN:2005-9396(Print) 자동차안전학회지

All Issue