一种新型的SiC金属氧化物半导体场效应管的寿命预测OA
A Novel SiC MOSFET Lifetime Prediction
为应对碳化硅金属氧化物半导体场效应管(SiC MOSFET)在高频、高温和大功率密度应用中面临的可靠性挑战,提出了一种新型的融合卷积神经网络、高效通道注意力机制与双向长短期记忆网络的SiC MOSFET寿命预测方法.该方法以漏源极导通电压为核心退化特征,结合异常值剔除、归一化和指数平滑等预处理策略,并通过滑动窗口对退化时间序列进行重构,实现小样本条件下的有效建模.实验对比结果表明,所提方法在预测精度、稳定性和鲁棒性方面均具有明显优势.
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 in-tegrated a CNN,an ECA mechanism,and a BiLSTM.This method used the drain-source on-state volt-age drop as the core degradation feature,incorporated preprocessing strategies such as outlier removal,nor-malization,and exponential smoothing,and reconstructed the degradation time series through a sliding win-dow to achieve effective modeling under small sample conditions.Comparative experimental results demon-strate that the proposed method offers significant advantages in prediction accuracy,stability,and robustness.
胡娅维;方响;尹传安;林子俊;林小卫
浙江广力工程机械有限公司,丽水,323700||安徽大学电气工程与自动化学院,合肥,230601安徽大学电气工程与自动化学院,合肥,230601江淮汽车技术中心,合肥,231299浙江广力工程机械有限公司,丽水,323700浙江广力工程机械有限公司,丽水,323700
机械制造
碳化硅金属氧化物半导体场效应管寿命预测卷积神经网络双向长短期记忆网络高效通道注意力功率循环
SiC metal-oxide-semiconductor field-effect transistors(MOSFET)lifetime predictionconvolutional neural network(CNN)bidirectional long short-term memory(BiLSTM)efficient channel attention(ECA)power cycling
《中国机械工程》 2026 (4)
959-966,998,9
国家自然科学基金(52377035)安徽省先进电力电子与电能变换工程研究中心开放课题(APE202504)
评论