MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis
This study proposes MSFF-Net, a lightweight deep learning framework for bearing fault diagnosis based on frequency-domain multi-sensor fusion. The vibration and acoustic signals are initially converted into the frequency domain using the fast Fourier transform (FFT), enabling the extraction of tempo...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/14/4348 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839615230063149056 |
|---|---|
| author | Miao Dai Hangyeol Jo Moonsuk Kim Sang-Woo Ban |
| author_facet | Miao Dai Hangyeol Jo Moonsuk Kim Sang-Woo Ban |
| author_sort | Miao Dai |
| collection | DOAJ |
| description | This study proposes MSFF-Net, a lightweight deep learning framework for bearing fault diagnosis based on frequency-domain multi-sensor fusion. The vibration and acoustic signals are initially converted into the frequency domain using the fast Fourier transform (FFT), enabling the extraction of temporally invariant spectral features. These features are processed by a compact one-dimensional convolutional neural network, where modality-specific representations are fused at the feature level to capture complementary fault-related information. The proposed method demonstrates robust and superior performance under both full and scarce data conditions, as verified through experiments on a publicly available dataset. Experimental results on a publicly available dataset indicate that the proposed model attains an average accuracy of 99.73%, outperforming state-of-the-art (SOTA) methods in both accuracy and stability. With only about 70.3% of the parameters of the SOTA model, it offers faster inference and reduced computational cost. Ablation studies confirm that multi-sensor fusion improves all classification metrics over single-sensor setups. Under few-shot conditions with 20 samples per class, the model retains 94.69% accuracy, highlighting its strong generalization in data-limited scenarios. The results validate the effectiveness, computational efficiency, and practical applicability of the model for deployment in data-constrained industrial environments. |
| format | Article |
| id | doaj-art-a683458f218d49b2b08e77fc0cbe8b51 |
| institution | Matheson Library |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-a683458f218d49b2b08e77fc0cbe8b512025-07-25T13:36:05ZengMDPI AGSensors1424-82202025-07-012514434810.3390/s25144348MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault DiagnosisMiao Dai0Hangyeol Jo1Moonsuk Kim2Sang-Woo Ban3Department 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 KoreaDepartment of Information & Communication Engineering, Graduate School, Dongguk University, Gyeongju 38066, Republic of KoreaThis study proposes MSFF-Net, a lightweight deep learning framework for bearing fault diagnosis based on frequency-domain multi-sensor fusion. The vibration and acoustic signals are initially converted into the frequency domain using the fast Fourier transform (FFT), enabling the extraction of temporally invariant spectral features. These features are processed by a compact one-dimensional convolutional neural network, where modality-specific representations are fused at the feature level to capture complementary fault-related information. The proposed method demonstrates robust and superior performance under both full and scarce data conditions, as verified through experiments on a publicly available dataset. Experimental results on a publicly available dataset indicate that the proposed model attains an average accuracy of 99.73%, outperforming state-of-the-art (SOTA) methods in both accuracy and stability. With only about 70.3% of the parameters of the SOTA model, it offers faster inference and reduced computational cost. Ablation studies confirm that multi-sensor fusion improves all classification metrics over single-sensor setups. Under few-shot conditions with 20 samples per class, the model retains 94.69% accuracy, highlighting its strong generalization in data-limited scenarios. The results validate the effectiveness, computational efficiency, and practical applicability of the model for deployment in data-constrained industrial environments.https://www.mdpi.com/1424-8220/25/14/4348bearing fault diagnosisone-dimensional convolutional neural networkacoustic dataVibration dataMulti-sensor data fusion |
| spellingShingle | Miao Dai Hangyeol Jo Moonsuk Kim Sang-Woo Ban MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis Sensors bearing fault diagnosis one-dimensional convolutional neural network acoustic data Vibration data Multi-sensor data fusion |
| title | MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis |
| title_full | MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis |
| title_fullStr | MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis |
| title_full_unstemmed | MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis |
| title_short | MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis |
| title_sort | msff net multi sensor frequency domain feature fusion network with lightweight 1d cnn for bearing fault diagnosis |
| topic | bearing fault diagnosis one-dimensional convolutional neural network acoustic data Vibration data Multi-sensor data fusion |
| url | https://www.mdpi.com/1424-8220/25/14/4348 |
| work_keys_str_mv | AT miaodai msffnetmultisensorfrequencydomainfeaturefusionnetworkwithlightweight1dcnnforbearingfaultdiagnosis AT hangyeoljo msffnetmultisensorfrequencydomainfeaturefusionnetworkwithlightweight1dcnnforbearingfaultdiagnosis AT moonsukkim msffnetmultisensorfrequencydomainfeaturefusionnetworkwithlightweight1dcnnforbearingfaultdiagnosis AT sangwooban msffnetmultisensorfrequencydomainfeaturefusionnetworkwithlightweight1dcnnforbearingfaultdiagnosis |