Deep Learning Neural Networks for Heat-Flux Health Condition Monitoring Method of Multi-Device Power Electronics System

Semiconductor devices are usually used in parallel to increase the current rating, but uneven degradation is inevitable among the chips. Based on heat-flux heath condition monitoring (HHCM), one can diagnose the package degradation of individual chips using external measurements and a neural network (NN). In this paper several deep learning neural networks are analyzed in terms of training speed and accuracy. The paralleled devices are tested in steady state and transient conditions with variation of the operating point. Thermo-electrical measurement data are used for training and validating the NNs. The results show that a two-stage deep learning NN could increase the classification accuracy significantly and it is also possible to develop HHCM for field deployment in wind turbines.

[1]  Huai Wang,et al.  Comprehensive investigation on current imbalance among parallel chips inside MW-scale IGBT power modules , 2015, 2015 9th International Conference on Power Electronics and ECCE Asia (ICPE-ECCE Asia).

[2]  Mauro Ciappa,et al.  Selected failure mechanisms of modern power modules , 2002, Microelectron. Reliab..

[3]  Xin Zhou,et al.  Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data , 2016 .

[4]  Miao He,et al.  Deep Learning Based Approach for Bearing Fault Diagnosis , 2017, IEEE Transactions on Industry Applications.

[5]  Li Ran,et al.  Failure and Reliability Analysis of a SiC Power Module Based on Stress Comparison to a Si Device , 2017, IEEE Transactions on Device and Materials Reliability.

[6]  Leon M. Tolbert,et al.  Fault Diagnosis and Reconfiguration for Multilevel Inverter Drive Using AI-Based Techniques , 2007, IEEE Transactions on Industrial Electronics.

[7]  Marco Liserre,et al.  Overview of Multi-MW Wind Turbines and Wind Parks , 2011, IEEE Transactions on Industrial Electronics.

[8]  Pingfeng Wang,et al.  Failure diagnosis using deep belief learning based health state classification , 2013, Reliab. Eng. Syst. Saf..

[9]  Fan Yang,et al.  A Temperature Gradient-Based Potential Defects Identification Method for IGBT Module , 2017, IEEE Transactions on Power Electronics.

[10]  Bing Ji,et al.  Gate–Emitter Pre-threshold Voltage as a Health-Sensitive Parameter for IGBT Chip Failure Monitoring in High-Voltage Multichip IGBT Power Modules , 2019, IEEE Transactions on Power Electronics.

[11]  Frede Blaabjerg,et al.  Reliability Improvement of Power Converters by Means of Condition Monitoring of IGBT Modules , 2017, IEEE Transactions on Power Electronics.

[12]  L. Ran,et al.  Monitoring Solder Fatigue in a Power Module Using Case-Above-Ambient Temperature Rise , 2011, IEEE Transactions on Industry Applications.