周昂,帕孜来·马合木提,李高原,等.基于SMA-Elman的IGBT寿命预测研究[J]. 微电子学与计算机,2023,40(3):117-124. doi: 10.19304/J.ISSN1000-7180.2022.0371
引用本文: 周昂,帕孜来·马合木提,李高原,等.基于SMA-Elman的IGBT寿命预测研究[J]. 微电子学与计算机,2023,40(3):117-124. doi: 10.19304/J.ISSN1000-7180.2022.0371
ZHOU A,PAZILAI M H M T,LI G Y,et al. Research on IGBT life prediction based on SMA-Elman[J]. Microelectronics & Computer,2023,40(3):117-124. doi: 10.19304/J.ISSN1000-7180.2022.0371
Citation: ZHOU A,PAZILAI M H M T,LI G Y,et al. Research on IGBT life prediction based on SMA-Elman[J]. Microelectronics & Computer,2023,40(3):117-124. doi: 10.19304/J.ISSN1000-7180.2022.0371

基于SMA-Elman的IGBT寿命预测研究

Research on IGBT life prediction based on SMA-Elman

  • 摘要: 绝缘栅双极晶体管(insulated gate bipolar transistor,IGBT)作为功率变换器的重要组成部分,其剩余使用寿命的预测极为重要. 针对IGBT的剩余使用寿命问题,提出了利用黏菌优化算法(slime mould algorithm,SMA)优化Elman神经网络实现权值和阈值的自适应选择,并将其用于IGBT的寿命预测. 首先,对NASA研究中心老化试验数据集中的栅射极关断电压尖峰峰值进行平滑处理.其次,对处理后的数据进行时域特征提取.再次,用核主成分分析(kernel principle component analysis,KPCA)进行优选降维。最后,利用SMA-Elman神经网络模型实现IGBT的寿命预测. 结果表明,提出的SMA-Elman神经网络模型相比Elman、BP神经网络及SVR模型具有更优的性能,均方误差为0.021%,均方根误差为0.014,拟合度为0.998,可以更好地实现IGBT剩余使用寿命的预测.

     

    Abstract: The insulated gate bipolar transistor (IGBT) is an important part of power converter, and the prediction of its remaining service life is very important. In response to the remaining service life of IGBT, the method of optimizing the adaptive options of the Elman neural network implementation of the Elman neural network is optimized by using the slime mould algorithm (SMA), and it is used for the life prediction of IGBT. Firstly, the peak of the gate emitter turn-off voltage in the aging test data set of NASA research center is smoothed. Secondly, the time domain feature is extracted from the processed data. Thirdly, the kernel principle component analysis (KPCA) is used for optimization dimensionality reduction. Finally, the SMA-Elman neural network model is used to predict the lifetime of IGBT. The results show that the proposed SMA-Elman neural network has better performance than Elman and BP neural network and SVR, the mean square error is 0.021%, the root mean square error is 0.014, the fitting degree is 0.998, and it can better predict the remaining service life of IGBT.

     

/

返回文章
返回