SEARCH WITHIN CONTENT
Citation Information : International Journal on Smart Sensing and Intelligent Systems. Volume 6, Issue 1, Pages 171-190, DOI: https://doi.org/10.21307/ijssis-2017-534
License : (CC BY-NC-ND 4.0)
Received Date : 30-August-2012 / Accepted: 11-January-2013 / Published Online: 20-February-2013
This paper presents data fusion algorithm of fault diagnosis considering sensor measurement uncertainty. Random-fuzzy variables (RFV) are used to model testing patterns (TPs) and fault template patterns (FTPs) respectively according to on-line sensor monitoring data and typical historical sensor data reflecting every fault mode. A similarity measure is given to calculate matching degree between a TP and each FTP in fault database such that Basic Probability Assignment (BPA) can be obtained by normalizing matching degree. Several BPAs provided by many sensor sources are fused by Dempster’s rule of combination. A diagnosis decision-making can be done according to the fusion results. Finally,the diagnosis examples of machine rotor system with vibration sensors show that the proposed method can enhance accuracy and reliability of data fusion-based diagnosis system.
 X. Fan, M. Zuo. “Fault diagnosis of machines based on DS evidence theory. Part 2: Application of the improved DS evidence theory in gearbox fault diagnosis”, Pattern Recognition Letters, Vol. 27, No. 5, 2006, pp. 377-385.
 X. B. Xu, H. S. Feng, Z. Wang, C. L. Wen. “An information fusion method of fault diagnosis based on interval basic probability assignment”, The Chinese Journal of Electronics, Vol. 20, No. 2, 2011, pp. 255-260.
 IEC-ISO, Guide to the Expression of Uncertainty in Measurement, 1992.
 X. B. Xu, C. L. Wen, Y. C. Wang. “Information fusion algorithm of fault diagnosis based on random set metrics of fuzzy fault features”, Journal of Electronics & Information Technology, Vol. 31, No. 7, 2009, pp. 1635-1640.
 A. Ferrero and S. Salicone. “The random-fuzzy variables: a new approach to the expression of uncertainty in measurement”, IEEE Transactions on Instrumentations and Measurement, Vol. 53, No. 5, 2004, pp. 1370-1377.
 G. Shafer. A Mathematical Theory of Evidence, New Jersey: Princeton University Press, Princeton, 1976.
 S. Salicone. Measurement Uncertainty: an Approach via the Mathematical Theory of Evidence, Springer series in reliability engineering, Springer-Verlag, New York, 2007.
 A. Ferrero and S. Salicone. “Modeling and processing measurement uncertainty within the theory of evidence: Mathematics of random–fuzzy variables”, IEEE Transactions on Instrumentations and Measurement, Vol. 56, No. 3, 2007, pp. 704–716.
 A. Ferrero and S. Salicone. “A method based on random-fuzzy variables for online estimation of the measurement uncertainty of DSP-based instruments”, IEEE Transactions on Instrumentations and Measurement, Vol. 53, No. 5, 2004, pp. 1362-1369.
 A. Ferrero, S. Salicone. “The construction of random-fuzzy variable from the available relevant metrological information”, IEEE Transactions on Instrumentations and Measurement, Vol. 58, No. 2, 2009, pp. 365-374.
 L. Ma. Equipment fault diagnosis technique and its application, Chinese academy of carrier rocket technology, China: Beijing Jinghang Corporation, Technical Report, 1998, pp.34-58.