Unsupervised anomaly detection for multilevel converters based on wavelet transform and variational autoencoders
- Resource Type
- Conference
- Authors
- Ye, Shu; Zhang, Feng
- Source
- 2022 IEEE Energy Conversion Congress and Exposition (ECCE) Energy Conversion Congress and Exposition (ECCE), 2022 IEEE. :1-6 Oct, 2022
- Subject
- Aerospace
Components, Circuits, Devices and Systems
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Transportation
Training
Multilevel converters
Noise reduction
Voltage
Feature extraction
Wavelet packets
Robustness
fault diagnosis
anomaly detection
multilevel converters
variational autoencoder
- Language
- ISSN
- 2329-3748
This paper proposes an anomaly detection scheme for multilevel converters based on a wavelet packet transform and variational autoencoder (WPT-VAE). The wavelet packet transform is used for dimensionality reduction and feature extraction of raw signals. The extracted features are normalized and then sent to the VAE to perform further feature extraction and waveform regeneration. Based on a five-level nested neutral-point-piloted (NNPP) converter, the effectiveness of the proposed method is verified by experiments. The normal dataset is used for model training, while a mixed dataset composed of normal and abnormal data is used for testing. The results show that the proposed WPT-VAE exhibits superior performances in anomaly detection compared with a widely used classification algorithm. Abnormal data can be quickly and accurately distinguished from normal data for early intervention to prevent serious faults, which has good practical value.