Rolling Element Bearing Faults Detection and Classification Technique Using Vibration Signals
Early and accurate detection of bearing faults is essential for the safe and reliable working of industrial machinery units. The main problem of the traditional fault diagnosis method is manually extracting the features which require the experimenter’s experience and expert knowledge. Therefore, the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Engineering Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4591/27/1/53 |
| _version_ | 1797611975888338944 |
|---|---|
| author | Mohammad Mohiuddin Md. Saiful Islam |
| author_facet | Mohammad Mohiuddin Md. Saiful Islam |
| author_sort | Mohammad Mohiuddin |
| collection | DOAJ |
| description | Early and accurate detection of bearing faults is essential for the safe and reliable working of industrial machinery units. The main problem of the traditional fault diagnosis method is manually extracting the features which require the experimenter’s experience and expert knowledge. Therefore, the shallow diagnostic model’s classification rate does not produce good results. To address this issue, this research proposes a technique to detect and classify bearing faults based on an effective convolutional neural network (CNN) model, which is capable of performing complex vibration signals and removing the impact of expert expertise on the feature extraction process. A time-moving segmentation window is used to segment the vibration raw signal and the segmented signals are decomposed up to two levels using DWT. After that, decomposed signals are converted into grayscale images to train and test the proposed CNN model. To verify the performance of the model, CWRU bearing dataset and MFPT dataset are used. The proposed CNN model achieves the highest accuracy in terms of performance both under different load conditions as well as under noisy situations with varying SNR values. The experimental findings show that the proposed system is effective and extremely dependable in detecting bearing faults. |
| first_indexed | 2024-03-11T06:35:52Z |
| format | Article |
| id | doaj.art-67f6060b117d4c6b818e0e5f2dc12bd6 |
| institution | Directory Open Access Journal |
| issn | 2673-4591 |
| language | English |
| last_indexed | 2024-03-11T06:35:52Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Engineering Proceedings |
| spelling | doaj.art-67f6060b117d4c6b818e0e5f2dc12bd62023-11-17T10:55:01ZengMDPI AGEngineering Proceedings2673-45912022-11-012715310.3390/ecsa-9-13339Rolling Element Bearing Faults Detection and Classification Technique Using Vibration SignalsMohammad Mohiuddin0Md. Saiful Islam1Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology (CUET), Chittagong 4349, BangladeshDepartment of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology (CUET), Chittagong 4349, BangladeshEarly and accurate detection of bearing faults is essential for the safe and reliable working of industrial machinery units. The main problem of the traditional fault diagnosis method is manually extracting the features which require the experimenter’s experience and expert knowledge. Therefore, the shallow diagnostic model’s classification rate does not produce good results. To address this issue, this research proposes a technique to detect and classify bearing faults based on an effective convolutional neural network (CNN) model, which is capable of performing complex vibration signals and removing the impact of expert expertise on the feature extraction process. A time-moving segmentation window is used to segment the vibration raw signal and the segmented signals are decomposed up to two levels using DWT. After that, decomposed signals are converted into grayscale images to train and test the proposed CNN model. To verify the performance of the model, CWRU bearing dataset and MFPT dataset are used. The proposed CNN model achieves the highest accuracy in terms of performance both under different load conditions as well as under noisy situations with varying SNR values. The experimental findings show that the proposed system is effective and extremely dependable in detecting bearing faults.https://www.mdpi.com/2673-4591/27/1/53bearing faultDWTvibration signalsgray imageconvolutional neural network |
| spellingShingle | Mohammad Mohiuddin Md. Saiful Islam Rolling Element Bearing Faults Detection and Classification Technique Using Vibration Signals Engineering Proceedings bearing fault DWT vibration signals gray image convolutional neural network |
| title | Rolling Element Bearing Faults Detection and Classification Technique Using Vibration Signals |
| title_full | Rolling Element Bearing Faults Detection and Classification Technique Using Vibration Signals |
| title_fullStr | Rolling Element Bearing Faults Detection and Classification Technique Using Vibration Signals |
| title_full_unstemmed | Rolling Element Bearing Faults Detection and Classification Technique Using Vibration Signals |
| title_short | Rolling Element Bearing Faults Detection and Classification Technique Using Vibration Signals |
| title_sort | rolling element bearing faults detection and classification technique using vibration signals |
| topic | bearing fault DWT vibration signals gray image convolutional neural network |
| url | https://www.mdpi.com/2673-4591/27/1/53 |
| work_keys_str_mv | AT mohammadmohiuddin rollingelementbearingfaultsdetectionandclassificationtechniqueusingvibrationsignals AT mdsaifulislam rollingelementbearingfaultsdetectionandclassificationtechniqueusingvibrationsignals |