Title :
Research and Application of Data Mining in Fault Diagnosis for Big Machines
Author :
Chen, Zhigang ; Zhang, Laibin ; Wang, Zhaohui ; Liang, Wei ; Li, Qinggang
Author_Institution :
China Univ. of Pet., Beijing
Abstract :
The fault characteristics of big equipments are complex and difficult to distinguish, this paper presents a new method elaborating on selecting more interrelated vibration parameters as original characteristic vectors, and how to mine features from fault database and then analyze running conditions of rotating parts of big machines by applying fuzzy clustering. The theories of establishing models, specific algorithms and steps have been given in it. Applied example showed that the method was correct and the result of the fault diagnosis had also been proved to be reliable and accurate.
Keywords :
data mining; database management systems; electric machine analysis computing; electric machines; fault diagnosis; fuzzy set theory; pattern clustering; big equipments; big machines; data mining; fault database; fault diagnosis; fuzzy clustering; vibration parameters; Artificial neural networks; Automation; Data analysis; Data engineering; Data mining; Educational institutions; Fault diagnosis; Mechatronics; Pattern recognition; Petroleum; Data mining; Fault diagnosis; Feature obtaining; Fuzzy clustering;
Conference_Titel :
Mechatronics and Automation, 2007. ICMA 2007. International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-0828-3
Electronic_ISBN :
978-1-4244-0828-3
DOI :
10.1109/ICMA.2007.4304167
