Qingnan Wang
ABSTRACT
Bearing faults, characterized by their low probability occurrence and limited sample availability, present challenges in accurate diagnosis. Traditional data-driven diagnostic methods exhibit reduced accuracy and generalization in small datasets. This paper presents a Siamese networks model based on metric learning, which is used for bearing faults classification. Vibration signals are preprocessed using continuous wavelet transform (CWT), and features are extracted through the MobileNetV3 backbone network. The model employs Euclidean distance measurement for training and classification, demonstrating high accuracy under limited sample data.
- EREN L, INCE T, KIRANYAZ S, 2019. A generic intelligent bearing fault diagnosis system using compact adaptive 1d CNN classifier. Journal of Signal Processing Systems, 91:179-189.Google Scholar
Digital Library
- LEI Y G, YANG B, JIANG X W, Nandi. 2020. Applications of machine learning to machine fault diagnosis:a review and roadmap. Mechanical Systems and Signal Processing,138.Google Scholar
- Liu R, Yang B, Zio E, 2018. Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing (S1096-1216), 108: 33-47.Google Scholar
- VOULODIMOS A, DOULAMIS N, DOULAMIS A, 2018. Deep learning for computer vision: A brief review. Computational Intelligence and Neuroscience, 2018: 7068349Google ScholarDigital Library
- TIAN C W, FEI L K, ZHENG W X, 2020. Deep learning on image denoising: an overview. Neural Networks, 131: 251-275.Google ScholarCross Ref
- YOUNG T, HAZARIKA D, PORIA S, 2018. Recent trends in deep learning based natural language processing. IEEE Computational Intelligence Magazine, 13(3): 55-75.Google ScholarCross Ref
- WEN L, LI X Y, GAO L, 2018. A new convolutional neural network-based data-driven fault diagnosis method. IEEE Transactions on Industrial Electronics, 65(7):5990-5998.Google ScholarCross Ref
- LI Y B, SI S B, LIU Z L, 2019. Review of local mean decomposition and its application in fault diagnosis of rotating machinery . Journal of Systems Engineering and Electronics, 30(4): 799-814.Google ScholarCross Ref
- HU T, TANG T, LIN R, 2020. A simple data augmentation algorithm and a self-adaptive convolutional architecture for few-shot fault diagnosis under different working conditions, Measurement, 156:107539.Google ScholarCross Ref
- CHICCO D. 2021. Siamese neural networks:an overview, Artificial Neural Networks, 2190:73-94Google ScholarCross Ref
- KOCH G, ZEMEL R, SALAKHUTDINOV R. 2015. Siamese neural networks for one-shot image recognition. Proceedings of the ICML Deep Learning Workshop.Google Scholar
- ZHANG Y, PARDO B, DUAN Z. 2018. Siamese style convolutional neural networks for sound search by vocal imitation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(2):429-441Google ScholarDigital Library
- AHRABIAN K, BABAALI B. 2019. Usage of auto encoders and Siamese networks for online handwritten signature verification. Neural Computing and Applications, 31(12):9321-9334.Google ScholarCross Ref
- Howard AG, Zhu ML, Chen B, 2017. MobileNet-Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861Google Scholar
- Sandler M, Howard A, Zhu ML, 2018. MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 4510–4520Google Scholar
- Howard A, Sandler M, Chen B, 2019. Searching for MobileNetV3. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul: IEEE,1314–1324.Google Scholar
Recommendations
Bearing fault diagnosis method based on improved Siamese neural network with small sample
AbstractFault diagnosis of rolling bearings is very important for monitoring the health of rotating machinery. However, in actual industrial production, owing to the constraints of conditions and costs, only a small number of bearing fault samples can be ...
Ensemble deep learning-based fault diagnosis of rotor bearing systems
Highlights- A novel ensemble learning approach based on CRN, DBN and DAE is proposed for fault diagnosis of rotor-bearing system.
AbstractFor rotating machinery, early and accurate diagnosis of rotor and bearing component fault is of great significance. The classic fault diagnosis model includes two key modules, feature extraction and fault classification. In order to ...
A survey on Deep Learning based bearing fault diagnosis
AbstractNowadays, Deep Learning is the most attractive research trend in the area of Machine Learning. With the ability of learning features from raw data by deep architectures with many layers of non-linear data processing units, Deep ...
Comments