The Safety Detection for Double Tapered Roller Bearing Based on Deep Learning
The double tapered roller bearing is widely used in mechanical equipment, due to its complex structure, traditional safety detection is difficult to recognize early weak fault. In order to solve this problem, a deep learning method for safety detection of roller bearing is put forward. In experiment, vibration signals of bearing are firstly separated into a series of intrinsic mode functions by empirical mode decomposition, then we extracted the transient energy to construct eigenvectors. In pattern recognition, deep learning method is used to generate safety detector by unsupervised study. There are three states rolling bearings in experiments, as normal, inner fault and outer fault. The results show that the proposed method is more stable and accurately to identify bearing faults, and the classification accuracy is 98%.
KeywordsDeep learning Roller bearing Empirical mode decomposition Safety detection
This paper was supported by the National Natural Science Foundation of China (Grant No. 11702091), and the Natural Science Foundation of Hunan Province of China (Grant No. 2018JJ3140).
- 3.Liu, Z., Pan, D., Zuo, M., et al.: A review on fault diagnosis for rail vehicles. J. Mech. Eng. 52(14), 124–141 (2016)Google Scholar
- 4.Liao, Y., Liu, Y., Yang, S., et al.: Numerical simulation and experimental study of a railway vehicle roller bearing with outer ring fault. J. Vib. Meas. Diagn. 34(3), 539–594 (2014)Google Scholar
- 7.He, G., Xin, Z., Zuo, C., et al.: Fault diagnosis method for rolling bearing of metro vehicle based on EMD and SVM. Railw. Comput. Appl. 24(8), 1–5 (2015)Google Scholar
- 8.Liu, J., Zhao, Z., Zhang, G., et al.: Research on fault diagnosis method for Bogie bearings of metro vehicle. J. China Railw. Soc. 37(1), 30–36 (2015)Google Scholar
- 12.Jiao, L., Yang, S., Liu, F., et al.: Seventy years beyond neural networks: retrospect and prospect. Chin. J. Comput. 39(8), 1697–1716 (2016)Google Scholar
- 22.Li, W., Shan, W., Zeng, X.: Bearing fault identification based on deep belief network. J. Vib. Eng. 29(2), 340–347 (2016)Google Scholar