Open AccessFault detection and isolation based on fuzzy‐integral fusion approach
Author(s) -
Jafari Hamideh,
Poshtan Javad
Publication year - 2019
Publication title -
iet science, measurement and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.418
H-Index - 49
eISSN - 1751-8830
pISSN - 1751-8822
DOI - 10.1049/iet-smt.2018.5005
Subject(s) - induction motor , fuzzy logic , fault detection and isolation , reliability (semiconductor) , fault (geology) , pattern recognition (psychology) , computer science , feature (linguistics) , fusion , control theory (sociology) , artificial intelligence , engineering , voltage , power (physics) , physics , linguistics , philosophy , actuator , control (management) , quantum mechanics , seismology , geology , electrical engineering
In this study, the bearing, as well as the electric faults of an induction motor, are diagnosed using the fuzzy‐integral data‐fusion method in feature level with high reliability. Time domain of various features is computed using the induction motor three‐phase current and voltage measurements. Appropriate features are extracted by means of the proposed method and then classified by the fuzzy C ‐means algorithm. The fuzzy membership functions show the relation between a feature set and a fault to establish the mappings between the features and the given faults. Finally, different features are fused using the fuzzy‐integral method to produce diagnostic results. The technique is validated experimentally on an induction motor coupled with a centrifugal pump. The capability of the proposed technique is also evaluated in the presence of disturbances and simultaneous occurrence of different faults. The results indicate an increase in the reliability in fault detection and isolation.