Bearing Fault Diagnosis Using a Vector-Based Convolutional Fuzzy Neural Network
Abstract
:1. Introduction
- The vector-CFNN model with fewer parameters was proposed to classify bearing failure by using spindle vibration signals.
- The fusion layer was introduced to improve the model’s classification accuracy by fusing the spatial and depth information of feature maps.
- Compared with other methods, vector-CFNN increases accuracy by up to 25% and requires only approximately 1000 learnable parameters.
2. Conventional CNN
2.1. Convolutional Layer
2.2. Pooling Layer
2.3. Flattening and Fully Connected Layer
3. Vector-CFNN
3.1. CFNN
3.2. Fuzzification Layer
3.3. Rule Layer
3.4. Defuzzification Layer
3.5. Vector-Based Convolution
3.6. Fusion Layer
4. Experimental Results
4.1. Data Acquisition
4.2. Data Pre-Processing
4.3. Evaluation of Fault Diagnosis
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Garzón, C.V.; Moncayo, G.B.; Alcantara, D.H.; Morales-Menendez, R. Fault Detection in Spindles Using Wavelets—State of the Art. IFAC Pap. 2018, 1, 450–455. [Google Scholar] [CrossRef]
- Zhai, Q.; Ye, Z.S. RUL Prediction of Deteriorating Products Using an Adaptive Wiener Process Model. IEEE Trans. Ind. Inform. 2017, 13, 2911–2921. [Google Scholar] [CrossRef]
- Yuwono, M.; Qin, Y.; Zhou, J.; Guo, Y.; Celler, B.G.; Su, S.W. 2 Automatic Bearing Fault Diagnosis Using Particle Swarm Cluster-ing and Hidden Markov Model. Eng. Appl. Artif. Intell. 2016, 47, 88–100. [Google Scholar] [CrossRef]
- Lall, P.; Deshpande, S.; Nguyen, L. ANN Based RUL Assessment for Copper-Aluminum Wirebonds Subjected to Harsh Environments. In Proceedings of the 2016 IEEE International Conference on Prognostics and Health Management (ICPHM), Ottawa, ON, Canada, 20–22 June 2016; pp. 1–10. [Google Scholar]
- Li, X. Remaining Useful Life Prediction of Bearings Using Fuzzy Multimodal Extreme Learning Regression. In Proceedings of the 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), Shanghai, China, 16–18 August 2017; pp. 499–503. [Google Scholar]
- Ertunç, H.M.; Ocak, H.; Aliustaoglu, C. ANN- and ANFTIS-Based Multi-Staged Decision Algorithm for the Detection and Diagnosis of Bearing Faults. Neural Comput. Appl. 2013, 22, 435–446. [Google Scholar] [CrossRef]
- Madhusudana, C.K.; Gangadhar, N.; Kumar, H.K.; Narendranath, S. Use of Discrete Wavelet Features and Support Vector Ma-chine for Fault Diagnosis of Face Milling Tool. SDHM Struct. Durab. Health Monit. 2018, 12, 111–127. [Google Scholar]
- Jingbo, G.; Yifan, H. Research on Fault Diagnosis Based on Singular Value Decomposition and Fuzzy Neural Network. Shock. Vib. 2018, 2018, 8218657. [Google Scholar]
- Zhang, W.; Li, X.; Ding, Q. Deep residual learning-based fault diagnosis method for rotating machinery. ISA Trans. 2019, 95, 295–305. [Google Scholar] [CrossRef]
- Huang, T.; Zhang, Q.; Tang, X.; Zhao, S.; Lu, X. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems. Artif. Intell. Rev. 2022, 55, 1289–1315. [Google Scholar] [CrossRef]
- Zhang, T.; Liu, S.; Wei, Y.; Zhang, H. A novel feature adaptive extraction method based on deep learning for bearing fault diagnosis. Measurement 2021, 185, 110030. [Google Scholar] [CrossRef]
- Niu, J.; Liu, C.; Zhang, L.; Liao, Y. Remaining Useful Life Prediction of Machining Tools by 1D-CNN LSTM Network. In Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China, 6–9 December 2019; pp. 1056–1063. [Google Scholar]
- Wang, H.; Xu, J.; Yan, R.; Sun, C.; Chen, X. Intelligent Bearing Fault Diagnosis Using Multi-Head Attention-Based CNN. Procedia Manuf. 2020, 49, 112–118. [Google Scholar] [CrossRef]
- Wang, H.; Xu, J.W.; Yan, R.Q.; Gao, R.X. A New Intelligent Bearing Fault Diagnosis Method Using SDP Representation and SE-CNN. IEEE Trans. Instrum. Meas. 2020, 69, 2377–2389. [Google Scholar] [CrossRef]
- Fu, C.; Lv, Q.; Lin, H.C. Development of Deep Convolutional Neural Network with Adaptive Batch Normalization Algorithm for Bearing Fault Diagnosis. Shock. Vib. 2020, 2020, 8837958. [Google Scholar] [CrossRef]
- Yuying, Z.; Yi, L.; Jing, Z. Research on Numerical Control Machine Fault Diagnosis Based on Distribution Adaptive One-Dimensional Convolutional Neural Network. In Proceedings of the Journal of Physics: Conference Series, Hangzhou, China, 14–16 May 2021. [Google Scholar]
- Han, S.; Oh, S.; Jeong, J. Bearing Fault Diagnosis Based on Multiscale Convolutional Neural Network Using Data Augmentation. J. Sens. 2021, 2021, 6699637. [Google Scholar] [CrossRef]
- Lecun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-Based Learning Applied to Document Recognition. Proc. IEEE 1998, 86, 2278–2324. [Google Scholar] [CrossRef] [Green Version]
- Lin, C.-J.; Jhang, J.-Y. Bearing Fault Diagnosis Using a Grad-CAM-Based Convolutional Neuro-Fuzzy Network. Mathematics 2021, 9, 1502. [Google Scholar] [CrossRef]
- Lin, C.-J.; Lin, C.-H.; Wang, S.-H. Integrated Image Sensor and Light Convolutional Neural Network for Image Classification. Math. Probl. Eng. 2021, 2021, 5573031. [Google Scholar] [CrossRef]
- Galety, M.G.; Mukthar, F.H.A.; Maaroof, R.J.; Rofoo, F. Deep Neural Network Concepts for Classification Using Convolutional Neural Network: A Systematic Review and Evaluation. Technium 2021, 3, 58–70. [Google Scholar] [CrossRef]
- Lin, C.-J.; Jhang, J.-Y.; Young, K.-Y. Parameter Selection and Optimization of an Intelligent Ultrasonic-Assisted Grinding System for SiC Ceramics. IEEE Access 2020, 8, 195721–195732. [Google Scholar] [CrossRef]
- Ellery, A. Artificial intelligence through symbolic connectionism—A biomimetic rapprochement. In Biomimetic Technologies: Actuators, Robotics & Integrated Systems; Ngo, D., Ed.; Woodhead Publishing: Cambridge, UK, 2015. [Google Scholar]
- Ou, J.; Li, Y. Vector-Kernel Convolutional Neural Networks. Neurocomputing 2019, 330, 253–258. [Google Scholar] [CrossRef]
- Lin, M.; Chen, Q.; Yan, S. Network in Network. arXiv 2013, arXiv:1312.4400. [Google Scholar] [CrossRef]
- Ma, Z.; Chang, D.; Xie, J.; Ding, Y.; Wen, S.; Li, X.; Si, Z.; Guo, J. Fine-Grained Vehicle Classification with Channel Max Pooling Modified CNNs. IEEE Trans. Veh. Technol. 2019, 68, 3224–3233. [Google Scholar] [CrossRef]
- Bearing Data Center: Seeded Fault Test Data. Available online: https://engineering.case.edu/bearingdatacenter/welcome (accessed on 2 March 2023).
Category | Numbers of Fragments |
---|---|
Normal bearing | 1657 |
Fault in inner race | 1893 |
Fault in ball | 1894 |
Fault in outer race | 3324 |
Total | 8768 |
Layer | Kernel Size | |
---|---|---|
Feature extraction | Convolution1 | (9, 1), channel = 6 |
Convolution2 | (1, 9), channel = 6 | |
Max_pooling1 | (2, 2) | |
Convolution3 | (9, 1), channel = 6 | |
Convolution4 | (1, 9), channel = 6 | |
Max_pooling2 | (2, 2) | |
Classification | Fusion Method | |
Fuzzy Layer | ||
Output Layer |
Model | Fusion Method | Lowest Accuracy | Highest Accuracy | Average Accuracy | Parameter |
---|---|---|---|---|---|
ANN | - | 71.77% | 77.32% | 75.78% | 533,008 |
FNN | - | 82.38% | 93.98% | 88.76% | 132,368 |
CNN | - | 91.62% | 93.77% | 92.43% | 22,854 |
CFNN | - | 98.68% | 98.8% | 98.80% | 3890 |
GAP | 95.92% | 99.86% | 97.68% | 3578 | |
GMP | 95.61% | 99.75% | 98.06% | 3578 | |
CAP | 91.82% | 99.32% | 96.17% | 3674 | |
CMP | 95.57% | 99.58% | 98.11% | 3674 | |
Network Mapping | 99.25% | 99.67% | 99.49% | 6106 | |
Vector-CFNN | - | 97.76% | 99.61% | 98.89% | 1910 |
GAP | 99.81% | 99.91% | 99.84% | 1214 | |
GMP | 98.73% | 99.39% | 99.11% | 1214 | |
CAP | 99.52% | 99.79% | 99.68% | 1502 | |
CMP | 99.63% | 99.78% | 99.71% | 1502 | |
Network Mapping | 99.61 | 99.82 | 99.69% | 5278 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lin, C.-J.; Lin, C.-H.; Lin, F. Bearing Fault Diagnosis Using a Vector-Based Convolutional Fuzzy Neural Network. Appl. Sci. 2023, 13, 3337. https://doi.org/10.3390/app13053337
Lin C-J, Lin C-H, Lin F. Bearing Fault Diagnosis Using a Vector-Based Convolutional Fuzzy Neural Network. Applied Sciences. 2023; 13(5):3337. https://doi.org/10.3390/app13053337
Chicago/Turabian StyleLin, Cheng-Jian, Chun-Hui Lin, and Frank Lin. 2023. "Bearing Fault Diagnosis Using a Vector-Based Convolutional Fuzzy Neural Network" Applied Sciences 13, no. 5: 3337. https://doi.org/10.3390/app13053337
APA StyleLin, C.-J., Lin, C.-H., & Lin, F. (2023). Bearing Fault Diagnosis Using a Vector-Based Convolutional Fuzzy Neural Network. Applied Sciences, 13(5), 3337. https://doi.org/10.3390/app13053337