RESEARCH PAPER
Parametric Fault Diagnosis Approach for the Power Switching Device of Three-Phase Inverter Utilizing HTISFF-VSPWN
More details
Hide details
1
School of Electrical Engineering, Beijing jiaotong university, China
2
Science and Technology on Reliability Physics and Application of Electronic Component Laboratory, China Electronic Product Reliability and Environmental Testing Research Institute
Guangzhou, China, China
These authors had equal contribution to this work
Submission date: 2024-08-31
Final revision date: 2024-10-17
Acceptance date: 2025-08-25
Online publication date: 2025-09-07
Publication date: 2025-09-07
Corresponding author
Linghui Meng
Science and Technology on Reliability Physics and Application of Electronic Component Laboratory, China Electronic Product Reliability and Environmental Testing Research Institute
Guangzhou, China, China
HIGHLIGHTS
- Hilbert transform is used for feature extraction and data dimensionality reduction.
- Multi-scale feature extraction is realized by constructing variable step size volume block.
- Highlight important features through reverse attention mechanism.
- Multiple source features are fused as the final feature tensor.
KEYWORDS
TOPICS
ABSTRACT
The three-phase inverter plays a pivotal role in various fields such as modern industry, rail transit, and aerospace. However, early parametric fault diagnosis of inverter switching devices faces challenges due to redundant feature data and the subtle differences in fault features across different degradation levels. To overcome these issues, we propose a novel method called HTISFF-VSPWN for parametric fault diagnosis. Our approach involves extracting key characteristics from the three-phase voltage and current data of the inverter using the Hilbert transform. Following this, we train the model after dimension reduction. Experimental results conducted on SIC MOSFETs parametric fault data reveal that HTISFF-VSPWN outperforms other methods. Compared to 1DCNN, 1DCNN-LSTM, DRSN, IWOA-1DCNN-LSTM and MTF-SPCNN, our method achieves a diagnostic accuracy improvement of 3.69%, 2.81%, 1.6%, 0.67% and 0.92% respectively. The diagnostic time was reduced by 64s, 106s, 120s, 182s and 99s compared with the comparison method.