An efficient method for bearing fault diagnosis
Statistical features and wavelet based fault detection are attempted to find computationally less complex, low-memory, and power for real-time implementation. The mean absolute value (MAV), simple sign integral (SSI), waveform length (WL), slope sign change, and zero crossing are extracted from the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Systems Science & Control Engineering |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/21642583.2024.2329264 |
| _version_ | 1797257251690381312 |
|---|---|
| author | G. Geetha P. Geethanjali |
| author_facet | G. Geetha P. Geethanjali |
| author_sort | G. Geetha |
| collection | DOAJ |
| description | Statistical features and wavelet based fault detection are attempted to find computationally less complex, low-memory, and power for real-time implementation. The mean absolute value (MAV), simple sign integral (SSI), waveform length (WL), slope sign change, and zero crossing are extracted from the vibration signal, phase current signal-1, and phase current signal-2. The extracted features are combined varyingly to obtain 31 combinations and classified using a decision tree, k-nearest neighbor {k-NN}, and support vector machine. The identified features {MAV, SSI, WL} performed better with vibration and combined current signals, with an average accuracy of 99.8% and 99.5% with the k-NN classifier, respectively. Wavelet has shown an accuracy of 98%, and the Alexnet method obtained an average accuracy of 97.5% using a combined current signal, which is less than the time domain features-based machine learning approach. In addition, simple time-domain features require memory of 9.6 MB times less than wavelets and 4.18MB times less than Alexnet. The time domain-based technique requires a computation time of 30.21 minutes less than Alexnet and 53.54 minutes less than wavelets. Experimentally, the effectiveness of identified minimal features is verified using an induction motor current signal and achieved 100% accuracy with {MAV, SSI, WL}. |
| first_indexed | 2024-04-24T22:34:40Z |
| format | Article |
| id | doaj.art-db0d03eee09f4db8b58c4b208e552ab8 |
| institution | Directory Open Access Journal |
| issn | 2164-2583 |
| language | English |
| last_indexed | 2024-04-24T22:34:40Z |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Systems Science & Control Engineering |
| spelling | doaj.art-db0d03eee09f4db8b58c4b208e552ab82024-03-19T12:00:25ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832024-12-0112110.1080/21642583.2024.2329264An efficient method for bearing fault diagnosisG. Geetha0P. Geethanjali1School of Electrical Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, IndiaSchool of Electrical Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, IndiaStatistical features and wavelet based fault detection are attempted to find computationally less complex, low-memory, and power for real-time implementation. The mean absolute value (MAV), simple sign integral (SSI), waveform length (WL), slope sign change, and zero crossing are extracted from the vibration signal, phase current signal-1, and phase current signal-2. The extracted features are combined varyingly to obtain 31 combinations and classified using a decision tree, k-nearest neighbor {k-NN}, and support vector machine. The identified features {MAV, SSI, WL} performed better with vibration and combined current signals, with an average accuracy of 99.8% and 99.5% with the k-NN classifier, respectively. Wavelet has shown an accuracy of 98%, and the Alexnet method obtained an average accuracy of 97.5% using a combined current signal, which is less than the time domain features-based machine learning approach. In addition, simple time-domain features require memory of 9.6 MB times less than wavelets and 4.18MB times less than Alexnet. The time domain-based technique requires a computation time of 30.21 minutes less than Alexnet and 53.54 minutes less than wavelets. Experimentally, the effectiveness of identified minimal features is verified using an induction motor current signal and achieved 100% accuracy with {MAV, SSI, WL}.https://www.tandfonline.com/doi/10.1080/21642583.2024.2329264Bearing faultclassifierscurrent signalfeature combinationstatistical featuresdeep learning |
| spellingShingle | G. Geetha P. Geethanjali An efficient method for bearing fault diagnosis Systems Science & Control Engineering Bearing fault classifiers current signal feature combination statistical features deep learning |
| title | An efficient method for bearing fault diagnosis |
| title_full | An efficient method for bearing fault diagnosis |
| title_fullStr | An efficient method for bearing fault diagnosis |
| title_full_unstemmed | An efficient method for bearing fault diagnosis |
| title_short | An efficient method for bearing fault diagnosis |
| title_sort | efficient method for bearing fault diagnosis |
| topic | Bearing fault classifiers current signal feature combination statistical features deep learning |
| url | https://www.tandfonline.com/doi/10.1080/21642583.2024.2329264 |
| work_keys_str_mv | AT ggeetha anefficientmethodforbearingfaultdiagnosis AT pgeethanjali anefficientmethodforbearingfaultdiagnosis AT ggeetha efficientmethodforbearingfaultdiagnosis AT pgeethanjali efficientmethodforbearingfaultdiagnosis |