BP neural network for non-invasive IGBT junction temperature online detection. (February 2023)

• Record Type: Journal Article
• Authors: Liu, Li; Peng, Qianlei; Jiang, Huaping; Ran, Li; Wang, Yang; Du, Changhong; Chen, Jian; Zhou, Hongbo; Chen, Yang; Peng, Zhiyuan
• Is Part Of: Microelectronics and reliability. Volume 141(2023)
• Publication Date: 2023-02
• Subjects: IGBT Insulated Gate Bipolar Transistor -- Tj IGBT Junction Temperature -- NTC Negative Thermal Coefficient thermistor -- TNTC temperature of NTC thermistor -- SVPWM Space Vector PWM Modulation -- Ic the load current -- fsw the IGBT switching frequency -- Vdc the DC link voltage -- Eon the switching on energy -- Eoff the switching off energy -- TSEP temperature sensitive electrical parameter -- CTE Coefficient of Thermal Expansion -- DCB Direct Copper Bonding -- FWD Free Wheeling Diode -- BP Back Propagation neural network -- TDNN Time Delay Neural Network -- RUL Remaining Useful Life -- HBT Hetero junction Bipolar Transistor -- KBNN Knowledge Neural Network -- SVR Support Vector Regression -- RF Random Forest; IGBT -- Junction temperature -- Degradation -- Neural networks -- Electric vehicles; Electronic apparatus and appliances -- Reliability -- Periodicals; Miniature electronic equipment -- Periodicals; Appareils électroniques -- Fiabilité -- Périodiques; Équipement électronique miniaturisé -- Périodiques; Electronic apparatus and appliances -- Reliability; Miniature electronic equipment; Periodicals; 621.3815
• DOI: 10.1016/j.microrel.2022.114882
• Languages: English
• ISSNs: 0026-2714

Abstract

Abstract: A number of studies have focused on Insulated Gate Bipolar Transistor (IGBT) junction temperature prediction methods. Some methods introduce extra circuits or sensors for an invasive prediction. However, the most of current methods hardly consider the situation that the junction temperature prediction may be affected by the IGBT degradation after long term operation. In this paper, the neural network using DC link voltage, switching frequency, load current and Negative Thermal Coefficient thermistor (NTC) temperature as inputs is proposed for junction temperature online prediction. The neural network training is completed through the IGBT module tests. The accelerated aging tests are then performed to validate the neural network results over lifetime. The static and transient working conditions are respectively validated at different aging degrees. Finally, a neural network with good accuracy could be achieved by a series of experiments considering IGBT device degradation.