6 April 2022 in IEEE Transactions on Instrumentation and Measurement
Nondestructive testing methods are gradually used to monitor the state of power devices, including acoustic emission (AE) testing. However, the application of AE in power devices is still in the research stage and relies on manual analysis. In this article, the stress wave signal of the device working under different electrical parameters is combined with deep learning (DL) for the first time to judge the working state of the device. Time-domain signals, frequency-domain amplitudes, and envelope of the stress wave and their corresponding label are used for the training of the artificial neural network (ANN), 1-D convolutional neural network (1DCNN), long short-term memory (LSTM), and recurrent neural network (RNN). The training effect of 1DCNN combined with time-domain series is the best, and the accuracy rate can reach up to 100%. Compared with other classic 1DCNN models, the proposed 1DCNN method does not require complex feature extraction and model calculations, which accurately identifies the working state of the device and also improves its speed.
5 July 2021 in IEEE Sensors Journal
The traditional condition monitoring (CM) methods for power electronic devices are normally using electrical, magnetic, and thermal sensors. Alternatively, this paper uses the acoustic emission (AE) sensor to measure the mechanical stress wave generated inside the power electronic devices such as MOSFETs. Specifically, this paper focuses on the influence of measured surface, electrical parameters, and filters on the stress wave signal and the reliability of repeatability tests. Under the single pulse test with 300V drain-source voltage ( ${V}_{\text {ds}}$ ), the same acoustic emission sensor is pasted on the MOSFET package and the cooling surface with a coupling agent. The factors affecting stress waves are studied by changing electrical parameters and filters. The proposed experiments draw the following conclusions. 1) The characteristic parameters of the stress wave measured on the package and cooling surface of MOSFET are different under the same electrical parameters. 2) The characteristic parameters of the stress wave are almost unchanged under the same test conditions, which shows that the stress wave measurement method is reliable. 3) The peak value of the stress wave, the frequency domain amplitude, and energy are affected by ${V}_{\text {ds}}$ and turn-on time ( ${t}_{\text {on}}$ ). Specifically, the gate voltage ${V}_{\text {gs}}$ has no obvious trend to the amplitude. The impact on package is basically the same as the cooling surface.