TR2022-130
Topological Data Analysis for Electric Motor Eccentricity Fault Detection
-
- "Topological Data Analysis for Electric Motor Eccentricity Fault Detection", Annual Conference of the IEEE Industrial Electronics Society (IECON), DOI: 10.1109/IECON49645.2022.9968912, October 2022, pp. 1-6.BibTeX TR2022-130 PDF
- @inproceedings{Wang2022oct2,
- author = {Wang, Bingnan and Lin, Chungwei and Inoue, Hiroshi and Kanemaru, Makoto},
- title = {Topological Data Analysis for Electric Motor Eccentricity Fault Detection},
- booktitle = {Annual Conference of the IEEE Industrial Electronics Society (IECON)},
- year = 2022,
- pages = {1--6},
- month = oct,
- doi = {10.1109/IECON49645.2022.9968912},
- url = {https://www.merl.com/publications/TR2022-130}
- }
,
- "Topological Data Analysis for Electric Motor Eccentricity Fault Detection", Annual Conference of the IEEE Industrial Electronics Society (IECON), DOI: 10.1109/IECON49645.2022.9968912, October 2022, pp. 1-6.
-
MERL Contacts:
-
Research Areas:
Data Analytics, Electric Systems, Machine Learning, Multi-Physical Modeling
Abstract:
In this paper, we develop topological data analysis (TDA) method for motor current signature analysis (MCSA), and apply it to induction motor eccentricity fault detection. We introduce TDA and present the procedure of extracting topological features from time-domain data that will be represented using persistence diagrams and vectorized Betti sequences. The procedure is applied to induction machine phase current signal analysis, and shown to be highly effective in differentiating signals from different eccentricity levels. With TDA, we are able to use a simple regression model that can predict the fault levels with reasonable accuracy, even for the data of eccentricity levels that are not seen in the training data. The proposed method is model-free, and only requires a small segment of time-domain data to make prediction. These advantages make it attractive for a wide range of fault detection applications.
Related News & Events
-
NEWS Bingnan Wang gave seminar talk at WEMPEC in University of Wisconsin-Madison Date: October 28, 2022
MERL Contacts: Dehong Liu; Bingnan Wang; Jinyun Zhang
Research Areas: Applied Physics, Data Analytics, Multi-Physical ModelingBrief- MERL researcher Bingnan Wang gave seminar talk at Wisconsin Electric Machines and Power Electronics Consortium (WEMPEC), which is recognized globally for its sustained contributions to electric machines and power electronics technology. He gave an overview of MERL research, especially on electric machines, and introduced our recent work on quantitative eccentricity fault diagnosis technologies for electric motors, including physical-model approach using improved winding function theory, and data-driven approach using topological data analysis to effectively differentiate signals from different fault conditions.
The seminar was given on Teams. MERL researchers Jin Zhang, Dehong Liu, Yusuke Sakamoto and Bingnan Wang held meetings with WEMPEC faculty members before the seminar to discuss various research topics, and met virtually with students after the talk.
- MERL researcher Bingnan Wang gave seminar talk at Wisconsin Electric Machines and Power Electronics Consortium (WEMPEC), which is recognized globally for its sustained contributions to electric machines and power electronics technology. He gave an overview of MERL research, especially on electric machines, and introduced our recent work on quantitative eccentricity fault diagnosis technologies for electric motors, including physical-model approach using improved winding function theory, and data-driven approach using topological data analysis to effectively differentiate signals from different fault conditions.
Related Publication
- @article{Wang2024jun,
- author = {Wang, Bingnan and Lin, Chungwei and Inoue, Hiroshi and Kanemaru, Makoto}},
- title = {Induction Motor Eccentricity Fault Detection and Quantification using Topological Data Analysis},
- journal = {IEEE Access},
- year = 2024,
- month = jun,
- url = {https://www.merl.com/publications/TR2024-063}
- }