ABSTRACT
The traditional bearing fault type recognition algorithm has the advantages of high recognition accuracy and good recognition performance when dealing with pure bearing fault data, but its recognition performance drops sharply in the actual noise environment. In order to effectively improve the reliability and accuracy of bearing fault type recognition, combined with the huge advantages of deep learning algorithm in the recognition field, one bearing fault type recognition technology based on ResNet and FPN. This Combined Neural Network is proposed to be applied in the actual working condition. This paper utilizes the Case Western Reserve University CWRU dataset. First, MATLAB is used to simulate the original bearing data through the channel. And the dataset under various signal-to-noise ratios are constructed accordingly. Then, the combined neural network constructed in this paper is trained and tested with the constructed data samples. After original dataset and constructed dataset been decomposed and reorganized by traditional empirical mode decomposition (EMD), multi-dimensional feature extraction and fault type recognition are completed through convolutional neural network (CNN). Finally, the proposed combined neural network algorithm is compared with the traditional bearing fault type recognition algorithm. The experimental results show that the recognition performance of RFNet is far superior to the traditional recognition algorithm under the actual working conditions.
- SCHOMMER S, NGUYEN V H, MAAS S, 2017. Model updating for structural health monitoring using static and dynamic measurements. Procedia Engineering, 199: 2146-2153.Google ScholarCross Ref
- Zhang K, Zuo W, Chen Y, 2017. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing APublication of the IEEE Signal Processing Society, 26(7): 3142-3155.Google ScholarDigital Library
- Li Y, Lu Z, Li J, 2018. Improving Deep Learning Feature with Facial Texture Feature for Face Recognition. Wireless Personal Communications, 103(2): 1195-1206.Google ScholarDigital Library
- Wang S H, Lv Y D, Sui Y, 2018. Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling. Journal of Medical Systems, 42(1): 2.Google ScholarDigital Library
- Zhu X, Meng Q, Ding B, 2018. Weighted pooling for image recognition of deepconvolutional neural networks. Cluster Computing.Google Scholar
- Wang X, Lu S, Zhang S. 2020. Rotating angle estimation for hybrid stepper motors with application to bearing fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 69(8): 5556-5568.Google ScholarCross Ref
- Yan R, Gao R X, Chen X. 2014. Wavelets for fault diagnosis of rotary machines: A review with applications. Signal processing, 96: 1-15.Google Scholar
- ALTobi M A S, Bevan G, Wallace P, 2019. Fault diagnosis of a centrifugal pump using MLPGABP and SVM with CWT. Engineering Science and Technology, an International Journal, 22(3): 854-861.Google Scholar
- Lu Q, Shen X, Wang X, 2021. Fault Diagnosis of Rolling Bearing Based on Improved VMD and KNN. Mathematical Problems in Engineering, 2021:1-11.Google ScholarCross Ref
- 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(2): 179-189.Google ScholarDigital Library
- Jiang H, Li X, Shao H, 2018. Intelligent fault diagnosis of rolling bearings using an improved deep recurrent neural network. Measurement Science and Technology, 29(6): 065107.Google ScholarCross Ref
- Han T, Zhang L, Yin Z, 2021. Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine. Measurement, 177(1):109022.Google ScholarCross Ref
- Mao W, Feng W, Liu Y, 2021. A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis. Mechanical Systems and Signal Processing, 150(12):107233.Google ScholarCross Ref
- Gao D, Zhu Y, Ren Z, 2021. A novel weak fault diagnosis method for rolling bearings based on LSTM considering quasi-periodicity. Knowledge-Based Systems, 231: 107413.Google ScholarDigital Library
- Wang T, Qiao M, Zhang M, 2020. Data-driven prognostic method based on self-supervised learning approaches for fault detection. Journal of Intelligent Manufacturing, 31(7): 1611-1619.Google ScholarDigital Library
- Yang D, Karimi H R, Sun K. 2021. Residual wide-kernel deep convolutional auto-encoder for intelligent rotating machinery fault diagnosis with limited samples. Neural Networks, 141:133-144.Google ScholarDigital Library
Index Terms
- Research on Bearing Fault Type Recognition Technology Based on RFNet Combined Neural Network
Recommendations
Research on Facial Expression Recognition Technology Based on Convolutional-Neural-Network Structure
Human facial expressions change so subtly that recognition accuracy of most traditional approaches largely depend on feature extraction. In this article, the authors employ a deep convolutional neural network CNN to devise a facial expression ...
Research on Face Recognition Based on the Fusion of Convolution and Wavelet Neural Network
ICVR 2018: Proceedings of the 4th International Conference on Virtual RealityIntelligent artificial neural network (ANN) is an important method of reasoning and deduction of face recognition, which greatly improves the correctness and efficiency of intelligent decision making. The existed neural network algorithm for face ...
Fault Bearing Identification Based on Wavelet Packet Transform Technique and Artificial Neural Network
ICSEM '10: Proceedings of the 2010 International Conference on System Science, Engineering Design and Manufacturing Informatization - Volume 02Bearing race faults have been detected by using wavelet packet transform (WPT) technique, combined with a feature selection of energy spectrum. Vibration signals from ball bearings having defects on inner race and outer race have been considered for ...
Comments