A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks
Achieving a reliable fault diagnosis for gears under variable operating conditions is a pressing need of industries to ensure productivity by averting unwanted breakdowns. In the present work, a hybrid approach is proposed by integrating Hu invariant moments and an artificial neural network for expl...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2020-09-01
|
| Series: | Metrology and Measurement Systems |
| Subjects: | |
| Online Access: | http://journals.pan.pl/dlibra/publication/134587/edition/117622/content |
| _version_ | 1818154229258256384 |
|---|---|
| author | F. Michael Thomas Rex A. Andrews A. Krishnakumari P. Hariharasakthisudhan |
| author_facet | F. Michael Thomas Rex A. Andrews A. Krishnakumari P. Hariharasakthisudhan |
| author_sort | F. Michael Thomas Rex |
| collection | DOAJ |
| description | Achieving a reliable fault diagnosis for gears under variable operating conditions is a pressing need of industries to ensure productivity by averting unwanted breakdowns. In the present work, a hybrid approach is proposed by integrating Hu invariant moments and an artificial neural network for explicit extraction and classification of gear faults using time-frequency transforms. The Zhao-Atlas-Marks transform is used to convert the raw vibrations signals from the gears into time-frequency distributions. The proposed method is applied to a single-stage spur gearbox with faults created using electric discharge machining in laboratory conditions. The results show the effectiveness of the proposed methodology in classifying the faults in gears with high accuracy. |
| first_indexed | 2024-12-11T14:23:11Z |
| format | Article |
| id | doaj.art-e03c850f1d4546f6854ad7ca1026d870 |
| institution | Directory Open Access Journal |
| issn | 2300-1941 |
| language | English |
| last_indexed | 2024-12-11T14:23:11Z |
| publishDate | 2020-09-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Metrology and Measurement Systems |
| spelling | doaj.art-e03c850f1d4546f6854ad7ca1026d8702022-12-22T01:02:49ZengPolish Academy of SciencesMetrology and Measurement Systems2300-19412020-09-0127345146410.24425/mms.2020.134587A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networksF. Michael Thomas Rex0A. Andrews1A. Krishnakumari2P. Hariharasakthisudhan3National Engineering College, Department of Mechanical Engineering, Kovilpatti – 628 503, Tamil Nadu, IndiaNational Engineering College, Department of Mechanical Engineering, Kovilpatti – 628 503, Tamil Nadu, IndiaHindustan Institute of Technology and Science, Department of Mechanical Engineering, Chennai – 603103, Tamil Nadu, IndiaNational Engineering College, Department of Mechanical Engineering, Kovilpatti – 628 503, Tamil Nadu, IndiaAchieving a reliable fault diagnosis for gears under variable operating conditions is a pressing need of industries to ensure productivity by averting unwanted breakdowns. In the present work, a hybrid approach is proposed by integrating Hu invariant moments and an artificial neural network for explicit extraction and classification of gear faults using time-frequency transforms. The Zhao-Atlas-Marks transform is used to convert the raw vibrations signals from the gears into time-frequency distributions. The proposed method is applied to a single-stage spur gearbox with faults created using electric discharge machining in laboratory conditions. The results show the effectiveness of the proposed methodology in classifying the faults in gears with high accuracy.http://journals.pan.pl/dlibra/publication/134587/edition/117622/contentgear faultahao-atlas-markstime-frequency domain featureshu invariant momentsann |
| spellingShingle | F. Michael Thomas Rex A. Andrews A. Krishnakumari P. Hariharasakthisudhan A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks Metrology and Measurement Systems gear fault ahao-atlas-marks time-frequency domain features hu invariant moments ann |
| title | A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks |
| title_full | A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks |
| title_fullStr | A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks |
| title_full_unstemmed | A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks |
| title_short | A hybrid approach for fault diagnosis of spur gears using Hu invariant moments and artificial neural networks |
| title_sort | hybrid approach for fault diagnosis of spur gears using hu invariant moments and artificial neural networks |
| topic | gear fault ahao-atlas-marks time-frequency domain features hu invariant moments ann |
| url | http://journals.pan.pl/dlibra/publication/134587/edition/117622/content |
| work_keys_str_mv | AT fmichaelthomasrex ahybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks AT aandrews ahybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks AT akrishnakumari ahybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks AT phariharasakthisudhan ahybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks AT fmichaelthomasrex hybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks AT aandrews hybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks AT akrishnakumari hybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks AT phariharasakthisudhan hybridapproachforfaultdiagnosisofspurgearsusinghuinvariantmomentsandartificialneuralnetworks |