The Insulated Gate Bipolar Transistor (IGBT) is the component with the highest failure rate in power converters, and its reliability is a critical issue in power electronics. IGBT module failure is largely caused by solder layer fatigue or bond wires fall-off. This paper proposes a multi-chip IGBT module failure monitoring method based on the module transconductance, which can accurately monitor IGBT module chip failures and bond wire failures. The paper first introduces the failure mechanism and module structure of the multi-chip IGBT module; then, it proposes a reliability model based on the module transconductance and analyzes the relationship between chip failure, bond wire failure, and the transmission characteristic curve of the IGBT module. Finally, the module transconductance under chip failure and bond wire failure is measured and calculated through simulation, and the temperature is calibrated, which can eliminate the influence of temperature on health monitoring. The results show that the method has a high sensitivity to chip failures and bond wire failures, can realize the failure monitoring of multi-chip IGBT modules, and is of great significance for improving the reliability of power converters.

The idea of Ubiquitous Power Internet of Things (UPIoTs) accelerates the development of intelligent monitoring and diagnostic technologies. In this paper, a diagnostic method suitable for power equipment in an interference environment was proposed based on the deep Convolutional Neural Network (CNN): MobileNet-V2 and Digital Image Processing (DIP) methods to conduct fault identification process: including fault type classification and fault localization. A data visualization theory was put forward in this paper, which was applied in frequency response (FR) curves of transformer to obtain dataset. After the image augmentation process, the dataset was input into the deep CNN: MobileNet-V2 for training procedures. Then a spatial-probabilistic mapping relationship was established based on traditional Frequency Response Analysis (FRA) fault diagnostic method. Each image in the dataset was compared with the fingerprint values to get traditional diagnosing results. Next, the anti-interference abilities of the proposed CNN-DIP method were compared with that of the traditional one while the magnitude of the interference gradually increased. Finally, the fault tolerance of the proposed method was verified by further analyzing the deviations between the wrong diagnosing results with the corresponding actual labels. Experimental results showed that the proposed deep visual identification (CNN-DIP) method has a higher diagnosing accuracy, a stronger anti-interference ability and a better fault tolerance.