Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset
Bearing defects are a common problem in rotating machines and equipment that can lead to unexpected downtime, costly repairs, and even safety hazards. Diagnosing bearing defects is crucial for preventative maintenance, and deep learning models have shown promising results in this field. On the other...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/6/3157 |
| _version_ | 1797609076695236608 |
|---|---|
| author | Yubin Yoo Hangyeol Jo Sang-Woo Ban |
| author_facet | Yubin Yoo Hangyeol Jo Sang-Woo Ban |
| author_sort | Yubin Yoo |
| collection | DOAJ |
| description | Bearing defects are a common problem in rotating machines and equipment that can lead to unexpected downtime, costly repairs, and even safety hazards. Diagnosing bearing defects is crucial for preventative maintenance, and deep learning models have shown promising results in this field. On the other hand, the high complexity of these models can lead to high computational and data processing costs, making their practical implementation challenging. Recent studies have focused on optimizing these models by reducing their size and complexity, but these methods often compromise classification performance. This paper proposes a new approach that reduces the dimensionality of input data and optimizes the model structure simultaneously. A much lower input data dimension than that of existing deep learning models was achieved by downsampling the vibration sensor signals used for bearing defect diagnosis and constructing spectrograms. This paper introduces a lite convolutional neural network (CNN) model with fixed feature map dimensions that achieve high classification accuracy with low-dimensional input data. The vibration sensor signals used for bearing defect diagnosis were first downsampled to reduce the dimensionality of the input data. Next, spectrograms were constructed using the signals of the minimum interval. Experiments were conducted using the vibration sensor signals from the Case Western Reserve University (CWRU) dataset. The experimental results show that the proposed method could be highly efficient in terms of computation while maintaining outstanding classification performance. The results show that the proposed method outperformed a state-of-the-art model for bearing defect diagnosis under different conditions. This approach is not limited to the field of bearing failure diagnosis, but could be applied potentially to other fields that require the analysis of high-dimensional time series data. |
| first_indexed | 2024-03-11T05:56:26Z |
| format | Article |
| id | doaj.art-a008864b777742418b46ad48ac89ff0c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:56:26Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a008864b777742418b46ad48ac89ff0c2023-11-17T13:46:47ZengMDPI AGSensors1424-82202023-03-01236315710.3390/s23063157Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU DatasetYubin Yoo0Hangyeol Jo1Sang-Woo Ban2Department of Information & Communication Engineering, Graduate School, Dongguk University, Gyeongju 38066, Republic of KoreaDepartment of Information & Communication Engineering, Graduate School, Dongguk University, Gyeongju 38066, Republic of KoreaDepartment of Information & Communication Engineering, Graduate School, Dongguk University, Gyeongju 38066, Republic of KoreaBearing defects are a common problem in rotating machines and equipment that can lead to unexpected downtime, costly repairs, and even safety hazards. Diagnosing bearing defects is crucial for preventative maintenance, and deep learning models have shown promising results in this field. On the other hand, the high complexity of these models can lead to high computational and data processing costs, making their practical implementation challenging. Recent studies have focused on optimizing these models by reducing their size and complexity, but these methods often compromise classification performance. This paper proposes a new approach that reduces the dimensionality of input data and optimizes the model structure simultaneously. A much lower input data dimension than that of existing deep learning models was achieved by downsampling the vibration sensor signals used for bearing defect diagnosis and constructing spectrograms. This paper introduces a lite convolutional neural network (CNN) model with fixed feature map dimensions that achieve high classification accuracy with low-dimensional input data. The vibration sensor signals used for bearing defect diagnosis were first downsampled to reduce the dimensionality of the input data. Next, spectrograms were constructed using the signals of the minimum interval. Experiments were conducted using the vibration sensor signals from the Case Western Reserve University (CWRU) dataset. The experimental results show that the proposed method could be highly efficient in terms of computation while maintaining outstanding classification performance. The results show that the proposed method outperformed a state-of-the-art model for bearing defect diagnosis under different conditions. This approach is not limited to the field of bearing failure diagnosis, but could be applied potentially to other fields that require the analysis of high-dimensional time series data.https://www.mdpi.com/1424-8220/23/6/3157bearing fault diagnosisconvolutional neural networksspectrogramshort-time Fourier transformCWRU dataset |
| spellingShingle | Yubin Yoo Hangyeol Jo Sang-Woo Ban Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset Sensors bearing fault diagnosis convolutional neural networks spectrogram short-time Fourier transform CWRU dataset |
| title | Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset |
| title_full | Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset |
| title_fullStr | Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset |
| title_full_unstemmed | Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset |
| title_short | Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset |
| title_sort | lite and efficient deep learning model for bearing fault diagnosis using the cwru dataset |
| topic | bearing fault diagnosis convolutional neural networks spectrogram short-time Fourier transform CWRU dataset |
| url | https://www.mdpi.com/1424-8220/23/6/3157 |
| work_keys_str_mv | AT yubinyoo liteandefficientdeeplearningmodelforbearingfaultdiagnosisusingthecwrudataset AT hangyeoljo liteandefficientdeeplearningmodelforbearingfaultdiagnosisusingthecwrudataset AT sangwooban liteandefficientdeeplearningmodelforbearingfaultdiagnosisusingthecwrudataset |