Detecting motor bearing faults: Monitoring an induction motor's current and detecting bearing failure

Abstract

Three-phase induction motors are widely used in the industry for heating, cooling, refrigeration, pumping, conveyors, and similar applications. However, there are instances that these motors fail due to bearing faults, insulation faults, and rotor faults. When failure occurs, the bearings need to be replaced. Although the replacement of defective bearings is the cheapest fix, it is the most diffult one to detect. Fortunately, a circuit monitor for these motors is now available. Incipient bearing failures are detectable by the presence of characteristic machine vibration frequencies associated with the various modes of bearing failure. The circuit monitor can detect these frequencies using wavelet packet decomposition and a radial basis neural network. By monitoring an induction motor's current, this device defines a bearing failure. © 2008 Elsevier B.V., All rights reserved.