The switching characteristics of GaN HEMT devices exhibit a very complex dynamic nonlinear behavior and multi-physics coupling characteristics, and traditional switching current models based on physical mechanisms have significant limitations. This article adopts a hybrid architecture of convolutional neural network and long short-term memory network (CNN-LSTM). In the 1D-CNN layer, the one-dimensional convolutional neural network can automatically learn and extract local transient features of time series data by sliding convolution operations on time series data through its convolution kernel, making these local transient features present a specific form in the local time window. In the double-layer LSTM layer, the neural network model captures the transient characteristics of switch current through the gating mechanism and state transfer. The hybrid architecture of the constructed model has significant advantages in accuracy, with metrics such as root mean square error (RMSE) and mean absolute error (MAE) significantly reduced, compared to traditional switch current models, solving the problem of insufficient accuracy in traditional models. The neural network model has good fitting performance at both room and high temperatures, with an average coefficient close to 1. The new neural network hybrid architecture has short running time and low computational resource consumption, meeting the needs of practical applications.
The contact interfaces of a press-pack insulated-gate bipolar transistor (PP-IGBT) module under fluctuating thermal stress will undergo minor friction and mutual sliding during service, which results in damage to the contact surface and a decline in the thermal performance of the contact interface. Therefore, the temperature inside the module will continue to increase, leading to eventual failure. In this work, a life prediction method based on thermal resistance degradation within a PP-IGBT module is established. The junction temperature can be determined via power loss and a resistance-capacitance (RC) thermal network model, and a life prediction model of the PP-IGBT module is developed based on thermal resistance degradation. The method considers the service quality under power cycling conditions and the influence of the self-accelerating effect of damage accumulation at the contact interface of the PP-IGBT module on fatigue life. The experimental results verify that the proposed PP-IGBT module life prediction method can effectively predict service life under power cycling conditions.
This work employs a deep learning method to develop a high-precision model for predicting the breakdown voltage (Vbr) and forward I-V characteristics of silicon carbide Schottky barrier diodes (SiC SBDs). The model significantly reduces the testing costs associated with destructive experiments, such as breakdown voltage testing. Although the model requires a certain amount of time to establish itself, it supports linear variations in related variables once developed. A predicted model for Vbr with an accuracy of up to 99% was successfully developed using 600 sets of input data after 200 epochs of training. After training for 1000 epochs, the deep learning-based model could predict not only point values like Vbr but also curves, such as forward I-V characteristics, with a mean squared error (MSE) of less than 10−3. Our research shows the applicability and high efficiency of introducing deep learning into device characteristic prediction.