Research on Fuzzy Fault Diagnosis of the Equipments

Abstract:

The paper introduces a method of fault diagnosis using fuzzy set theory. In the paper, the principle that a fault symptom either exists or doesnt exist is abandoned. A crisp number between 0 and 1 is used to denote the degree of fault symptom, by which the fault symptom vector is constructed. For every kind of fault symptom, a fuzzy pair-wise comparison matrix is constructed. The elements of the pair-wise comparison matrix are triangular fuzzy numbers which denote the qualitative comparisons between the membership values of the given fault symptom with the reference to a pair of possible faults respectively. The least logarithm squares method is applied to determine the membership of the fault symptom with respect to each fault, and then the fuzzy diagnosis matrix is constructed. A simple weighted addition is used to calculate the fault vector based on the fuzzy diagnosis matrix and the fault symptom vector. Center of area is used to determine the best non-fuzzy performance value of the fuzzy number, according to which the fuzzy numbers can be ranked. The ordering of all the possible faults based on the fault symptoms is determined. At the end of the paper, an example is used to demonstrate the procedure of fuzzy fault diagnosis.

• Periodical: Applied Mechanics and Materials (Volumes 411-414)
• Pages: 1484-1487
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.411-414.1484
• Online since: September 2013
• Authors: Ji Yang Qi, Li Na Ren, Shan Ping Ning, Yu Fu
• Keywords: Fault Diagnosis, Fault Vector, Fuzzy Diagnosis Matrix

References

[1] J. P. Wu, Y. X. Wu and Z.L. Long, Design and realization of fault diagnosis expert system based on fuzzy mathematics, Package Engineering. 24(2003)49-52.

[2] C. Arindam，D. Kajal, Fuzzy Support Vector Machine for bankruptcy prediction, Applied Soft Computing Journal. 11(2011)2472-2486.

DOI: 10.1016/j.asoc.2010.10.003

[3] H. L. Pan, W.R. Jiang, and H.H. He, The fault diagnosis model of FMS workflow based on adaptive weighted fuzzy Petri net, Advanced Designs and Researches for Manufacturing. 605-607(2013)837-843.

DOI: 10.4028/www.scientific.net/amr.605-607.837

[4] A. Chaudhuri, K. De, Fuzzy Support Vector Machine for bankruptcy prediction, Applied Soft Computing Journal. 11(2011)2472-2486.

DOI: 10.1016/j.asoc.2010.10.003

[5] C. H. Chai, J. X. Liu and S. T. He, The application of fuzzy mathematics in airplane malfunction diagnosis. Fuzzy Systems and Mathematics, 17(2003)107-110.

[6] J. Cao and G. G. Zhou, Web-based partner selection and evaluation in agile virtual enterprise. China Mechanical Engineering. 15(2004)2010-(2014).

[7] Y L. Zhang: Locomotive and Rolling Stock Technology, The technologies of fuzzy fault diagnosis and its application in hydraulic systems, " Locomotive and Rolling Stock Technology. 6(1999)31-33.