A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification
In this article, a novel data-driven method is proposed for open-circuit fault diagnosis of insulated gate bipolar transistor used in three-phase pulsewidth modulation converter. Based on the sampled three-phase current signals, fast Fourier transform and ReliefF algorithm are used to select most co...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/155302 |
| _version_ | 1811688729299910656 |
|---|---|
| author | Xia, Yang Xu, Yan Gou, Bin |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Xia, Yang Xu, Yan Gou, Bin |
| author_sort | Xia, Yang |
| collection | NTU |
| description | In this article, a novel data-driven method is proposed for open-circuit fault diagnosis of insulated gate bipolar transistor used in three-phase pulsewidth modulation converter. Based on the sampled three-phase current signals, fast Fourier transform and ReliefF algorithm are used to select most correlated features. Then, based on two randomized learning technologies named extreme learning machine and random vector functional link network, a hybrid ensemble learning scheme is proposed for extracting mapping relationship between fault modes and the selected features. Furthermore, in order to achieve an accurate and fast diagnostic performance, a sliding-window classification framework is designed. Finally, parameters in the diagnostic model are optimized by a multiobjective optimization programming model to achieve optimal balance between diagnosis accuracy and speed. At offline testing stage, the overall average diagnostic accuracy can be as high as 99% with the diagnostic time of around one-cycle sampling time. Furthermore, real-time experiments verify its effectiveness and reliability under different operation conditions. |
| first_indexed | 2024-10-01T05:36:50Z |
| format | Journal Article |
| id | ntu-10356/155302 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:36:50Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1553022022-03-17T07:24:28Z A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification Xia, Yang Xu, Yan Gou, Bin School of Electrical and Electronic Engineering Rolls-Royce@NTU Corporate Lab Engineering::Electrical and electronic engineering Hybrid Ensemble Learning Multiobjective Optimization Programming In this article, a novel data-driven method is proposed for open-circuit fault diagnosis of insulated gate bipolar transistor used in three-phase pulsewidth modulation converter. Based on the sampled three-phase current signals, fast Fourier transform and ReliefF algorithm are used to select most correlated features. Then, based on two randomized learning technologies named extreme learning machine and random vector functional link network, a hybrid ensemble learning scheme is proposed for extracting mapping relationship between fault modes and the selected features. Furthermore, in order to achieve an accurate and fast diagnostic performance, a sliding-window classification framework is designed. Finally, parameters in the diagnostic model are optimized by a multiobjective optimization programming model to achieve optimal balance between diagnosis accuracy and speed. At offline testing stage, the overall average diagnostic accuracy can be as high as 99% with the diagnostic time of around one-cycle sampling time. Furthermore, real-time experiments verify its effectiveness and reliability under different operation conditions. Ministry of Education (MOE) Nanyang Technological University National Research Foundation (NRF) This work was supported in part by the Ministry of Education (MOE), Republic of Singapore, under Grant AcRF TIER 1 2019-T1- 001-069 (RG75/19), and in part by the National Research Foundation (NRF) of Singapore under Project NRF2018-SR2001-018. The work of Y. Xu was supported by the Nanyang Assistant Professorship from Nanyang Technological University, Singapore. Paper no. TII-19-3957. 2022-03-17T07:24:28Z 2022-03-17T07:24:28Z 2019 Journal Article Xia, Y., Xu, Y. & Gou, B. (2019). A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification. IEEE Transactions On Industrial Informatics, 16(8), 5223-5233. https://dx.doi.org/10.1109/TII.2019.2949344 1551-3203 https://hdl.handle.net/10356/155302 10.1109/TII.2019.2949344 2-s2.0-85084332304 8 16 5223 5233 en 2019-T1- 001-069 (RG75/19) NRF2018-SR2001-018 TII-19-3957 IEEE Transactions on Industrial Informatics © 2019 IEEE. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Hybrid Ensemble Learning Multiobjective Optimization Programming Xia, Yang Xu, Yan Gou, Bin A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification |
| title | A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification |
| title_full | A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification |
| title_fullStr | A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification |
| title_full_unstemmed | A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification |
| title_short | A data-driven method for IGBT open-circuit fault diagnosis based on hybrid ensemble learning and sliding-window classification |
| title_sort | data driven method for igbt open circuit fault diagnosis based on hybrid ensemble learning and sliding window classification |
| topic | Engineering::Electrical and electronic engineering Hybrid Ensemble Learning Multiobjective Optimization Programming |
| url | https://hdl.handle.net/10356/155302 |
| work_keys_str_mv | AT xiayang adatadrivenmethodforigbtopencircuitfaultdiagnosisbasedonhybridensemblelearningandslidingwindowclassification AT xuyan adatadrivenmethodforigbtopencircuitfaultdiagnosisbasedonhybridensemblelearningandslidingwindowclassification AT goubin adatadrivenmethodforigbtopencircuitfaultdiagnosisbasedonhybridensemblelearningandslidingwindowclassification AT xiayang datadrivenmethodforigbtopencircuitfaultdiagnosisbasedonhybridensemblelearningandslidingwindowclassification AT xuyan datadrivenmethodforigbtopencircuitfaultdiagnosisbasedonhybridensemblelearningandslidingwindowclassification AT goubin datadrivenmethodforigbtopencircuitfaultdiagnosisbasedonhybridensemblelearningandslidingwindowclassification |