As one of the core components of electric vehicles,IGBTs'health monitoring and remaining life prediction play a vital role in proactive maintenance.The Bi-LSTM model based on Bayesian optimiza-tion and attention mechanism is proposed to predict the remaining useful life of IGBT in this paper.The proposed method can effectively improve the accuracy of IGBT remaining service life prediction.VCE-on through IGBT accelerated aging test is collected in this study,verifying its feasibility as a failure character-istic parameter.This data is used as an experimental data set to validate the proposed method through sim-ulation.The experimental analysis results show that the proposed hybrid prediction model has lower deg-radation prediction error than the classical LSTM and other prediction models,demonstrating significant theoretical and practical value.
关键词
电动汽车IGBT/剩余寿命预测/贝叶斯优化算法/注意力机制/双向长短时记忆网络
Key words
electric vehicles of IGBT/remaining life prediction/Bayesian optimization algorithm/atten-tion mechanism/bidirectional long short-term memory
维普
万方数据