A High Accuracy Lifetime Estimation Method for SiC MOSFETs Based on CNN-LSTM Networks
IEEE Transactions on Device and Materials Reliability · 2026-06 · 26 (2) · 531-540
DOI: 10.1109/tdmr.2026.3673635 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Device and Materials Reliability, 2026-06. Verfasst von Xiaofeng Ding und 5 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Accurate lifetime prediction of power devices is critical for preventing unexpected converter failures and extending service life. However, existing methods often suffer from limited prediction accuracy, reliance on extensive experiments, and difficulties in practical implementation. This paper proposes a data-driven lifetime estimation method for silicon carbide (SiC) MOSFETs based on the prediction of a single aging precursor, i.e., the on-state drain-source voltage drop ( $V_{\mathrm {ds\_on}}$ ). The proposed method integrates the local feature extraction capability of convolutional neural networks (CNNs) with the temporal modeling strength of long short-term memory (LSTM) networks, enabling effective capture of complex degradation trends and improved prediction accuracy. Moreover, it facilitates practical implementation, as $V_{\mathrm {ds\_on}}$ is easy to measure online during normal operation. A DC power cycling test setup with online $V_{\mathrm {ds\_on}}$ sampling is designed to accelerate device aging and collect degradation datasets. Multiple devices can be aged simultaneously under different operating conditions using the proposed setup, improving test efficiency. Experimental results under various aging conditions demonstrate that the proposed method achieves the highest prediction accuracy of 99.3%, outperforming the LSTM-based and exponential model-based approaches, which achieve average accuracies of 96.4% and 41.1%, respectively. These advancements are beneficial for enhancing system reliability and reducing operational costs in practical applications.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Ding, X., Wang, B., Yang, Y., Zhao, M., Yang, K., & Peng, L. (2026). A High Accuracy Lifetime Estimation Method for SiC MOSFETs Based on CNN-LSTM Networks. IEEE Transactions on Device and Materials Reliability, 26(2), 531-540. https://doi.org/10.1109/tdmr.2026.3673635
Vancouver
Ding X, Wang B, Yang Y, Zhao M, Yang K, Peng L. A High Accuracy Lifetime Estimation Method for SiC MOSFETs Based on CNN-LSTM Networks. IEEE Transactions on Device and Materials Reliability. 2026;26(2):531-540. doi:10.1109/tdmr.2026.3673635
BibTeX
@article{Ding2026,
author = {Ding, Xiaofeng and Wang, Binbin and Yang, Yanyong and Zhao, Mingbo and Yang, Kun and Peng, Lyuzhang},
title = {A High Accuracy Lifetime Estimation Method for SiC MOSFETs Based on CNN-LSTM Networks},
journal = {IEEE Transactions on Device and Materials Reliability},
year = {2026},
volume = {26},
number = {2},
pages = {531--540},
doi = {10.1109/tdmr.2026.3673635}
}
EUVIMED