IGBT aging monitoring and remaining lifetime prediction based on long short-term memory (LSTM) networks

• Published in: Microelectronics and reliability 2020-11, Vol.114, p.113902, Article 113902
• Main Authors: Li, Wanping, Wang, Bixuan, Liu, Jingcun, Zhang, Guogang, Wang, Jianhua
• Format: Article
• Language: English
• Subjects: Fault identification; IGBT; Lifetime prediction; LSTM; Machine learning; Power semiconductor reliability
• ISSN: 0026-2714; 1872-941X
• DOI: 10.1016/j.microrel.2020.113902

Reliable remaining useful lifetime (RUL) prediction of power semiconductors is challenging, despite knowledge of valid aging precursors. In this paper, an aging platform for IGBTs is built to collect the real-time Vce-on data and its thermal circuit is carefully designed to control the temperature range. A decent error and uncertainty of the measurement system have been identified. A novel machine learning technique that is effective to deal with the time-sequence data, i.e. recurrent neural networks (RNN) using long short-term memory (LSTM) units, is introduced to predict the RUL of IGBTs and compared with two conventional methods. The proposed method is found able to deliver a proper prediction at an early stage and update the results during the aging process. •Accelerated power cycling tests and online aging data under different temperature conditions•Application of the Long Short-Term Memory (LSTM) Network to power semiconductor lifetime prediction•Comparison of the LTSM and conventional prediction approaches