Real-Time Diagnosis Based on Signal Convolution-Pooling Processing and Shared Filter Learning for Transistor Open-Circuit Faults in a T-Type Inverter
- Resource Type
- Periodical
- Authors
- Wang, B.; Chen, G.; Song, J.; Peng, C.; Krein, P.T.; Ma, H.
- Source
- IEEE Transactions on Power Electronics IEEE Trans. Power Electron. Power Electronics, IEEE Transactions on. 39(5):6281-6297 May, 2024
- Subject
- Power, Energy and Industry Applications
Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
General Topics for Engineers
Nuclear Engineering
Signal Processing and Analysis
Transportation
Circuit faults
Inverters
Feature extraction
Fault diagnosis
Convolution
Neural networks
Integrated circuit modeling
Convolution-pooling model
filter parameter sharing
open-circuit (OC) faults
real-time fault diagnosis
T-type inverters
- Language
- ISSN
- 0885-8993
1941-0107
This article proposes a data-driven method based on signal convolution pooling for real-time fault diagnosis in T-type inverters. The model is composed of an auxiliary neural network and a multilayer convolution feature classifier (MCFC). The auxiliary neural network can learn and provide filter parameters for an MCFC by learning from a small training dataset. Through shared filter learning and a global average pooling layer, a feedforward MCFC can greatly reduce testing time. This makes the approach suitable for real-time fault diagnosis. A feature processing function is used to retain fault features observed in the measured three-phase current signals while avoiding the effects of load changes. A multisignal sequence reconstruction strategy is proposed to transform multiple time-series diagnostic signals into an input feature map for the MCFC. This strategy extends the domain of the MCFC information by increasing the input channel count of the auxiliary neural network. The combined approach increases fault diagnosis accuracy compared to prior work. The performance of the proposed diagnosis method is validated with experiments.