Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain
Convolution; Convolutional neural networks; Deep learning; Fast Fourier transforms; Fault detection; Frequency domain analysis; Gaussian noise (electronic); Roller bearings; Signal processing; Signal to noise ratio; Time domain analysis; Bearing; Bearing fault diagnosis; Convolution neural network;...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
MDPI
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-26804 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-268042023-05-29T17:36:50Z Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain Hakim M. Omran A.A.B. Inayat-Hussain J.I. Ahmed A.N. Abdellatef H. Abdellatif A. Gheni H.M. 57853404500 55212152300 6602271377 57214837520 57358838000 57304215000 57210428348 Convolution; Convolutional neural networks; Deep learning; Fast Fourier transforms; Fault detection; Frequency domain analysis; Gaussian noise (electronic); Roller bearings; Signal processing; Signal to noise ratio; Time domain analysis; Bearing; Bearing fault diagnosis; Convolution neural network; Convolutional neural network; Deep learning; Environmental noise; Faults diagnosis; Frequency domains; One-dimensional; One-dimensional convolutional neural network; Failure analysis; algorithm; Fourier analysis; signal noise ratio; signal processing; Algorithms; Fourier Analysis; Neural Networks, Computer; Signal Processing, Computer-Assisted; Signal-To-Noise Ratio The massive environmental noise interference and insufficient effective sample degradation data of the intelligent fault diagnosis performance methods pose an extremely concerning issue. Realising the challenge of developing a facile and straightforward model that resolves these problems, this study proposed the One-Dimensional Convolutional Neural Network (1D-CNN) based on frequency-domain signal processing. The Fast Fourier Transform (FFT) analysis is initially utilised to transform the signals from the time domain to the frequency domain; the data was represented using a phasor notation, which separates magnitude and phase and then fed to the 1D-CNN. Subsequently, the model is trained with White Gaussian Noise (WGN) to improve its robustness and resilience to noise. Based on the findings, the proposed model successfully achieved 100% classification accuracy from clean signals and simultaneously achieved considerable robustness to noise and exceptional domain adaptation ability. The diagnosis accuracy retained up to 97.37%, which was higher than the accuracy of the CNN without training under noisy conditions at only 43.75%. Furthermore, the model achieved an accuracy of up to 98.1% under different working conditions, which was superior to other reported models. In addition, the proposed model outperformed the state-of-art methods as the Signal-to-Noise Ratio (SNR) was lowered to ?10 dB achieving 97.37% accuracy. In short, the proposed 1D-CNN model is a promising effective rolling bearing fault diagnosis. � 2022 by the authors. Final 2023-05-29T09:36:50Z 2023-05-29T09:36:50Z 2022 Article 10.3390/s22155793 2-s2.0-85136342570 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136342570&doi=10.3390%2fs22155793&partnerID=40&md5=0bf503403cf706a19871ec2cf7b72984 https://irepository.uniten.edu.my/handle/123456789/26804 22 15 5793 All Open Access, Gold, Green MDPI Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Convolution; Convolutional neural networks; Deep learning; Fast Fourier transforms; Fault detection; Frequency domain analysis; Gaussian noise (electronic); Roller bearings; Signal processing; Signal to noise ratio; Time domain analysis; Bearing; Bearing fault diagnosis; Convolution neural network; Convolutional neural network; Deep learning; Environmental noise; Faults diagnosis; Frequency domains; One-dimensional; One-dimensional convolutional neural network; Failure analysis; algorithm; Fourier analysis; signal noise ratio; signal processing; Algorithms; Fourier Analysis; Neural Networks, Computer; Signal Processing, Computer-Assisted; Signal-To-Noise Ratio |
| author2 |
57853404500 |
| author_facet |
57853404500 Hakim M. Omran A.A.B. Inayat-Hussain J.I. Ahmed A.N. Abdellatef H. Abdellatif A. Gheni H.M. |
| format |
Article |
| author |
Hakim M. Omran A.A.B. Inayat-Hussain J.I. Ahmed A.N. Abdellatef H. Abdellatif A. Gheni H.M. |
| spellingShingle |
Hakim M. Omran A.A.B. Inayat-Hussain J.I. Ahmed A.N. Abdellatef H. Abdellatif A. Gheni H.M. Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain |
| author_sort |
Hakim M. |
| title |
Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain |
| title_short |
Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain |
| title_full |
Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain |
| title_fullStr |
Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain |
| title_full_unstemmed |
Bearing Fault Diagnosis Using Lightweight and Robust One-Dimensional Convolution Neural Network in the Frequency Domain |
| title_sort |
bearing fault diagnosis using lightweight and robust one-dimensional convolution neural network in the frequency domain |
| publisher |
MDPI |
| publishDate |
2023 |
| _version_ |
1806425704002224128 |
| score |
13.211869 |