A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear Pairs
Gears are fundamental components used to transmit power and motion in modern industry. Their health condition monitoring is crucial to ensure reliable operations, prevent unscheduled shutdowns, and minimize human casualties. From this standpoint, the present study proposed a one-dimensional convolut...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/4/413 |
| _version_ | 1827744673623441408 |
|---|---|
| author | Onur Can Kalay Esin Karpat Ahmet Emir Dirik Fatih Karpat |
| author_facet | Onur Can Kalay Esin Karpat Ahmet Emir Dirik Fatih Karpat |
| author_sort | Onur Can Kalay |
| collection | DOAJ |
| description | Gears are fundamental components used to transmit power and motion in modern industry. Their health condition monitoring is crucial to ensure reliable operations, prevent unscheduled shutdowns, and minimize human casualties. From this standpoint, the present study proposed a one-dimensional convolutional neural network (1-D CNN) model to diagnose tooth root cracks for standard and asymmetric involute spur gears. A 6-degrees-of-freedom dynamic model of a one-stage spur gear transmission was established to achieve this end and simulate vibration responses of healthy and cracked (25%–50%–75%–100%) standard (20°/20°) and asymmetric (20°/25° and 20°/30°) spur gear pairs. Three levels of signal-to-noise ratios were added to the vibration data to complicate the early fault diagnosis task. The primary consideration of the present study is to investigate the asymmetric gears’ dynamic characteristics and whether tooth asymmetry would yield an advantage in detecting tooth cracks easier to add to the improvements it affords in terms of impact resistance, bending strength, and fatigue life. The findings indicated that the developed 1-D CNN model’s classification accuracy could be improved by up to 12.8% by using an asymmetric (20°/30°) tooth profile instead of a standard (20°/20°) design. |
| first_indexed | 2024-03-11T04:49:31Z |
| format | Article |
| id | doaj.art-dec04a6517e947f595b25f16f68f55f9 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-11T04:49:31Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-dec04a6517e947f595b25f16f68f55f92023-11-17T20:08:16ZengMDPI AGMachines2075-17022023-03-0111441310.3390/machines11040413A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear PairsOnur Can Kalay0Esin Karpat1Ahmet Emir Dirik2Fatih Karpat3Department of Mechanical Engineering, Bursa Uludag University, Bursa 16059, TurkeyDepartment of Electrical and Electronics Engineering, Bursa Uludag University, Bursa 16059, TurkeyDepartment of Computer Engineering, Bursa Uludag University, Bursa 16059, TurkeyDepartment of Mechanical Engineering, Bursa Uludag University, Bursa 16059, TurkeyGears are fundamental components used to transmit power and motion in modern industry. Their health condition monitoring is crucial to ensure reliable operations, prevent unscheduled shutdowns, and minimize human casualties. From this standpoint, the present study proposed a one-dimensional convolutional neural network (1-D CNN) model to diagnose tooth root cracks for standard and asymmetric involute spur gears. A 6-degrees-of-freedom dynamic model of a one-stage spur gear transmission was established to achieve this end and simulate vibration responses of healthy and cracked (25%–50%–75%–100%) standard (20°/20°) and asymmetric (20°/25° and 20°/30°) spur gear pairs. Three levels of signal-to-noise ratios were added to the vibration data to complicate the early fault diagnosis task. The primary consideration of the present study is to investigate the asymmetric gears’ dynamic characteristics and whether tooth asymmetry would yield an advantage in detecting tooth cracks easier to add to the improvements it affords in terms of impact resistance, bending strength, and fatigue life. The findings indicated that the developed 1-D CNN model’s classification accuracy could be improved by up to 12.8% by using an asymmetric (20°/30°) tooth profile instead of a standard (20°/20°) design.https://www.mdpi.com/2075-1702/11/4/413deep learningfault diagnosisvibration signalgear designasymmetric gear |
| spellingShingle | Onur Can Kalay Esin Karpat Ahmet Emir Dirik Fatih Karpat A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear Pairs Machines deep learning fault diagnosis vibration signal gear design asymmetric gear |
| title | A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear Pairs |
| title_full | A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear Pairs |
| title_fullStr | A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear Pairs |
| title_full_unstemmed | A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear Pairs |
| title_short | A One-Dimensional Convolutional Neural Network-Based Method for Diagnosis of Tooth Root Cracks in Asymmetric Spur Gear Pairs |
| title_sort | one dimensional convolutional neural network based method for diagnosis of tooth root cracks in asymmetric spur gear pairs |
| topic | deep learning fault diagnosis vibration signal gear design asymmetric gear |
| url | https://www.mdpi.com/2075-1702/11/4/413 |
| work_keys_str_mv | AT onurcankalay aonedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs AT esinkarpat aonedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs AT ahmetemirdirik aonedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs AT fatihkarpat aonedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs AT onurcankalay onedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs AT esinkarpat onedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs AT ahmetemirdirik onedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs AT fatihkarpat onedimensionalconvolutionalneuralnetworkbasedmethodfordiagnosisoftoothrootcracksinasymmetricspurgearpairs |