Roller Element Bearing of Mine Ventilating Fan with Fault Diagnosis Based on Mechanics Properties and RBF Neural Network

Abstract:

Roller element bearing is an important part of mine ventilating fan. The management and maintenance of the equipment is very important. Therefore, it is necessary to employ fault diagnosis process to the roller element bearing. In this paper, mechanics properties of roller element bearing are analyzed. Then, Radial Basis Function (RBF) neural network is used for the fault diagnosis of the roller element bearing. The structure and inference of RBF network are discussed in detail. The roller element bearing fault diagnosis model is established based on RBF network. A case study is given. The proposed method is applied to the fault diagnosis of roller element bearing. The result shows that the proposed method can improve efficiency of the fault diagnosis.

• Periodical: Advanced Materials Research (Volume 625)
• Pages: 125-129
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.625.125
• Online since: December 2012
• Authors: Ying Hong Zhang, Cong Li, Hui Jing, Bing Bing Gao
• Keywords: Fault Diagnosis, Mechanical Property, Mine Ventilating Fan, RBF Neural Network, Roller Element Bearing

References

[1] Sitao Wu. Induction Machine Fault Detection Using SOM-Based RBF Neural Networks [J]. IEEE Transactions on Industrial Electronics, 2004, 51(1):183-194

DOI: 10.1109/tie.2003.821897

[2] Na Liu. Fault Diagnosis of Power Transformer Using a Combinatorial Neural Network [J]. Transactions of China Electro-technical Society, 2003,18(2):83-86

[3] Su Wensheng. Research on Rolling Element Bearing Vibration Signal Processing and Feature Extraction Method [D]. Doctor thesis of Dalian University of Technology. 2010 (in Chinese)

[4] N.A. Tandon, A.B. Choudhury. A Review of Vibration and Acoustic Measurement Methods for Detection of Defects in Rolling Element Bearing [J]. Tribology International, 1999,32(8):469-480

DOI: 10.1016/s0301-679x(99)00077-8

[5] Sun Fang, Wei Zijie. Rolling Bearing Fault Diagnosis Based on Wavelet Packet and RBF Neural Network [C]. Proceedings of the 26th Chinese Control Conference, 2007:451-455

DOI: 10.1109/chicc.2006.4346979

[6] Yong-chun Liang, Jian-ye Liu. Power Transformer Fault Diagnosis using SOM-based RBF Neural Networks [C]. Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, 2006:3140-3143

DOI: 10.1109/icmlc.2006.258406

[7] Byungkyu P. Clustering based RBF neural network model for short-term freeway traffic volume forecasting [C]. ASCE. Proc of the Int Conf on Appl of Advanced Tech in Transportation Eng. USA: ASCE, 1998: 280-287

[8] Lin W, Yang C, Lin J, et al. A fault classification method by RBF neural network with OLS learning procedure [J]. IEEE Trans on Power Delivery, 2001, 16(4): 473-477

DOI: 10.1109/61.956723