Failure Mode Classification of IGBT Modules Under Power Cycling Tests Based on Data-Driven Machine Learning Framework

Yang, Xin; Zhang, Yue; Wu, Xinlong; Liu, Guoyou

doi:10.1109/tpel.2023.3314738

Cited by 18 publications

(2 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Common package-level failures for devices mainly comprise bond-wire failures and solder fatigue [34], as shown in Figure 2. This type of failure primarily stems from thermo-mechanical stresses [35], relative humidity stresses [36], and high current density stresses [37] during device operation, with thermo-mechanical stresses being dominating.…”

Section: Main Failure Modes and Characterization Parametersmentioning

confidence: 99%

Failure Characterization of Discrete SiC MOSFETs under Forward Power Cycling Test

Huang,

Singh,

Liu

et al. 2024

Energies

View full text Add to dashboard Cite

Silicon carbide (SiC)-based metal–oxide–semiconductor field-effect transistors (MOSFETs) hold promising application prospects in future high-capacity high-power converters due to their excellent electrothermal characteristics. However, as nascent power electronic devices, their long-term operational reliability lacks sufficient field data. The power cycling test is an important experimental method to assess packaging-related reliability. In order to obtain data closest to actual working conditions, forward power cycling is utilized to carry out SiC MOSFET degradation experiments. Due to the wide bandgap characteristics of SiC MOSFETs, the short-term drift of the threshold voltage is much more serious than that of silicon (Si)-based devices. Therefore, an offline threshold voltage measurement circuit is implemented during power cycling tests to minimize errors arising from this short-term drift. Different characterizations are performed based on power cycling tests, focused on measuring the on-state resistance, thermal impedance, and threshold voltage of the devices. The findings reveal that the primary failure mode under forward power cycling tests, with a maximum junction temperature of 130 ∘C, is bond-wire degradation. Conversely, the solder layer and gate oxide exhibit minimal degradation tendencies under these conditions.

show abstract

Section: Main Failure Modes and Characterization Parametersmentioning

confidence: 99%

Failure Characterization of Discrete SiC MOSFETs under Forward Power Cycling Test

Huang,

Singh,

Liu

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…Wang et al analyzed the impact of overload current on IGBT bonding wire and module reliability due to shedding [ 23 ]. Yang et al introduced a data-driven Convolutional Neural Network (CNN)-based approach for classifying different failure modes of IGBT modules under varying PCT conditions [ 24 ]. Through finite element simulation, Fan et al revealed that bonding lines and solder layers are vulnerable points leading to corrosion in high humidity environments within IGBT module packaging [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Digital-Twin-Driven Intelligent Insulated-Gate Bipolar Transistor Production Lines

Zhang,

Liu,

Song

et al. 2024

Sensors

View full text Add to dashboard Cite

With the rapid development of novel energy vehicles, power generation, photovoltaics, and other industries, power electronic devices have gained considerable attention. Insulated-gate bipolar transistors (IGBTs) have been widely used in those fields. With the emergence of intelligent manufacturing concepts such as Germany’s “Industry 4.0” and China’s “Made in China 2025”, conventional manufacturing which needs to be upgraded with higher efficiency and yield is rapidly pivoting toward digitalization and intelligence. The digital twin methodology has been extensively used in various industries for constructing virtual models of physical entities, facilitating real-time data interconnection to reduce costs and improve efficiency. This study proposes a modular intelligent IGBT production line based on the digital twin. Real-time data are transmitted from a physical line to a digital line for storage and analysis. The digital line is visualized, and an intelligent management platform containing multiple functions is developed. Additionally, a process simulation database is established to obtain the optimal process parameters. Numerous quality issues that can arise during each process of IGBT packaging are addressed using a problem-solving approach based on the digital twin methodology. Consequently, this digital-twin-based IGBT intelligent production line effectively enhances yield rates and efficiency. IGBT modules with various packaging forms such as ACF, ACE, and ACD are manufactured.

show abstract

Machine learning-based direct estimation of remaining useful life (RUL) of IGBT using multi-precursor prognostics

Prathiba,

Saravanan,

David

et al. 2024

Electr Eng

View full text Add to dashboard Cite

Failure Mode Classification of IGBT Modules Under Power Cycling Tests Based on Data-Driven Machine Learning Framework

Cited by 18 publications

References 62 publications

Failure Characterization of Discrete SiC MOSFETs under Forward Power Cycling Test

Failure Characterization of Discrete SiC MOSFETs under Forward Power Cycling Test

Digital-Twin-Driven Intelligent Insulated-Gate Bipolar Transistor Production Lines

Machine learning-based direct estimation of remaining useful life (RUL) of IGBT using multi-precursor prognostics

Contact Info

Product

Resources

About