Application of MMAS and Rough Sets in Compound-Fault Diagnosis of Bearing

Abstract:

The diagnosis of compound-fault is always a difficult point, and there is not an effective method in equipment diagnosis field. Rough set theory is a relatively new soft computing tool to deal with vagueness and uncertainty. Condition attribute reduce algorithm is the key point of rough set research. However, it has been proved that finding the best reduction is the NP-hard problem. For the purpose of getting the reduction of systems effectively, an improved algorithm is put forward. The worst Fisher criterion was adopted as heuristic information to improve the searching efficiency and Max-Min Ant System was selected. Simplify the fault diagnosis decision table, then clear and concise decision rules can be obtained by rough sets theory. This method raises the accuracy and efficiency of fault diagnosis of bearing greatly.

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 6319-6324
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.6319
• Online since: January 2012
• Authors: Hai Ying Kang, Ren Fa Shen, Yan Jie Qi, Wen Yan, Hai Qi Zheng
• Keywords: Compound-Fault, Condition Attribute Reduction, MMAS, Rough Set Theory (RST)

References

[1] Zuo Hong, Gu Jiaming, Yu Jinlu, Fault Diagnosis of rolling bearings based on Supporting Vector Machine, Bearing, vol. 8, 2008, pp.36-39.

[2] ZHou Tianpei, Bearing fault diagnosis method based on rough set-neural network system, Bearing, vol. 2, 2008, pp.39-42.

[3] ZHang Hanlei, Zhou Jiemin, Li Gang, Mixed fault diagnosis based on wavelet analysis in induction motors, Proceedings of the CSEE, vol. 26 (8), 2006, pp.159-162.

[4] Xu ZHangsui, Fang Liqing, Mi Dong, Compound-fault recognition based on information importance analysis of fault, JOURNAL OF COMBUSTION SCIENCE AND TECHNOLOGY, vol. 7(2), 2001, pp.141-143.

[5] ZHang Wenxui, Qiu Guofang, Uncertain decision based on rough set, Beijing: Qinghua University Publishing Company, (2005).

[6] Lixiang Shen, Francis EH Tay, Liangsheng Qu, Yudi Shen, Fault diagnosis using rough sets theory, Computers in Industry, vo1. (43) 2000, pp.61-72.

DOI: 10.1016/s0166-3615(00)00050-6

[7] Skowron A, Rauszer C, The discernibility matrices and functions in information systems, Intelligent Decision: Handbook of Applications and Advances of the Rough Sets Theory, 1992, pp.331-362.

DOI: 10.1007/978-94-015-7975-9_21

[8] Parpinelli R S, Lopes H S, Freitas, Data mining with an ant colony optimization algorithm, IEEE Transactions on Evolutionary Computation, vol. 6(4), 2002, pp.321-332.

DOI: 10.1109/tevc.2002.802452

[9] T. Stützle, H. Hoos, Improvements on the Ant System: Introducing MAX-MIN Ant System, In Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms, Springer Verlag, Wien, 1997, pp.245-249.

DOI: 10.1007/978-3-7091-6492-1_54

[10] Sergios Theodoridis, Konstantinos Koutroumbas, Pattern Recognition, Beijing: Electronic Industries Press, the third version, pp.307-313.