To address the reliability challenges faced by SiC MOSFETs in high-frequency, high-temperature, and high-power density applications, a novel lifetime prediction method was proposed that integrated a CNN, an ECA mechanism, and a BiLSTM. This method used the drain-source on-state voltage drop as the core degradation feature, incorporated preprocessing strategies such as outlier removal, normalization, and exponential smoothing, and reconstructed the degradation time series through a sliding window to achieve effective modeling under small sample conditions. Comparative experimental results demonstrate that the proposed method offers significant advantages in prediction accuracy, stability, and robustness.
SiC MOSFET是一种基于碳化硅材料的单极性功率半导体器件,采用绝缘栅结构设计。在长期工作过程中,工作温度的波动以及热循环应力可能导致器件芯片或封装出现失效。根据失效发生部位的不同,SiC MOSFET的失效模式分为芯片失效和封装失效两类[12]。其中,与器件磨损老化相关的失效模式是寿命预测研究的重点对象。一些能够反映SiC MOSFET器件可靠性退化的关键电学参数常被选作退化特征量,包括阈值电压、结温、漏源极导通电阻、漏源极导通电压、米勒平台电压等。为判定器件是否达到失效状态,通常需要设定相应的失效判据,即各参数相对于初始值允许的最大变化幅度。失效判据通常以参数相对漂移量达到某一阈值来量化定义,其通用表达式为
HUWenjin. A New Structure Design of IGBT with Low Miller Capacitance[D]. Chengdu: University of Electronic Science and Technology of China, 2022.
[3]
ZOLPERJ C. Emerging Silicon Carbide Power Electronics Components[C]∥Twentieth Annual IEEE Applied Power Electronics Conference and Exposition (APEC). 2005: 11-17.
[4]
ZHANGZ, FUG, WANB, et al. A High-efficiency IGBT Health Status Assessment Method Based on Data Driven[J]. IEEE Transactions on Electron Devices, 2021, 68(1): 168-174.
GUOWen. Research on Prediction Method of Remaining Useful Life and Thermal Fatigue Model of Power MOSFET[D]. Nanchang: East China Jiaotong University, 2020.
MAOMingbo, MENGZhaoliang, GAOYong, et al. Research and Implementation of Life Prediction Method for SiC MOSFET Module Based on PSO-BP Neural Network[J]. Journal of Power Supply, 2025, 23(1): 229-235.
ZENGDayi, YANGJihong, ZOUYisheng, et al. Bearing Life Prediction Method Based on Parallel Multi-channel Convolutional Long Short-Term Memory Network[J]. China Mechanical Engineering, 2020, 31(20): 2454-2462.
SONGLijun, LIUSonglin, XINYu, et al. Residual Life Prediction for Bearings Based on Bearing Degradation State Assessment and IGAT-BiGRU Network[J]. China Mechanical Engineering, 2025, 36(7): 1562-1572.
[17]
WANGQ, WUB, ZHUP, et al. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks[C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2020: 11531-11539.
[18]
XIANGX, LIX, ZHANGY, et al. A Short-term Forecasting Method for Photovoltaic Power Generation Based on the TCN-ECA Net-GRU Hybrid Model[J]. Scientific Reports, 2024, 14: 6744.
SHENYutong. Study on Off-state Stress Degradation Mechanism and Life Modeling of Wide Bandgap Semiconductor Power Devices[D]. Xian: Xidian University, 2023.
[21]
YUNM, YANGD, HES, et al. Failure Quantitative Assessment Approach to MOSFET Power Device by Detecting Parasitic Parameters[J]. Frontiers in Physics, 2022, 10: 1050678.
[22]
ZAHRAS T, IMDADS K, KHANS, et al. Power Transformer Health Index and Life Span Assessment: a Comprehensive Review of Conventional and Machine Learning Based Approaches[J]. Engineering Applications of Artificial Intelligence, 2025, 139: 109474.