Data-driven Reliability Prediction Review of Power MOSFETs
This study provides a comprehensive review and analysis of reliability prediction methods for power metal oxide semiconductor field effect transistors(MOSFETs)both domestically and globally,elucidating the evolution from classical statistical methods to advanced machine learning techniques.Statistical methodologies,such as gaussian process regression,autoregressive integrated moving average(ARIMA)models,and other classical statistical methods,were investigated,with an emphasis on continuous model optimization and extension.Regarding machine learning approaches,the investigation focused on techniques such as support vector machines(SVM),artificial neural networks(ANN),and continuously evolving deep learning models.Finally,development trends were analyzed,and potential future research directions discussed.
power MOSFETreliability predictionmachine learningdata-driven
万方数据
维普
