Tracking of High-Order Stray-Flux Harmonics Under Starting for the Detection of Winding Asymmetries in Wound-Rotor Induction Motors

Abstract

Wound rotor induction motors (WRIM) are widely used in a vast number of high output power industrial applications due to their capability of reaching high start torques while maintaining low inrush currents. Nonetheless, these machines are very prone to require early maintenance, and the possibility of presenting rotor winding asymmetry failures is high due to their more complex rotor circuit. Although some recent works have proposed techniques that overcome the drawbacks of conventional methods, an additional research effort for the development of alternative approaches able to enhance their performance and reliability is desirable. In this work, a new method for the diagnosis of rotor asymmetries in WRIM is presented. The proposed methodology is based on a feed-forward neural network (FFNN) feed by suitable fault severity indicators, which rely on the maximum energy density of higher order harmonics (amplified by the failure) at strategic regions of the time-frequency maps obtained from stray flux signals under startup transient. Experimental results for three different levels of rotor asymmetries in a 11 KW WRIM prove the reliability of the enhanced proposed system in comparison to conventional approaches that only rely on the main sideband faultharmonic amplitudes.

High-Resistance Connection Diagnosis of Doubly Fed Induction Generators

“…Currently, many achievements have been made in the detection of HRC faults in induction motors internationally [6][7][8][9]. Based on analyzing and processing the external magnetic field during motor startup, ref.…”

“…However, this method needs to be carried out during startup, so it can only achieve offline detection. The study in [7] calculates the maximum energy density of high-order fault harmonic signals under the startup transient as training samples and uses feedforward neural networks for rotor fault degree classification. This method is only suitable for judging the degree of a fault during startup and requires strong signal processing and computational capabilities.…”

Methods of Condition Monitoring and Fault Detection for Electrical Machines

“…The use of wavelet transform for stator current analysis during motor startup is presented in [98,99]. The utilization of nonstationary stray flux harmonics for training feed-forward neural networks for monitoring wound rotor induction motors is presented in [100]. The use of transient stray fluxes and the currents for the fault diagnosis of damper winding in synchronous motors is presented in [101], while a similar work for fault detection of circular pumps is reported in [102].…”

“…The use of wavelet transform for stator current analysis during motor startup is presented in[98,99]. The utilization of nonstationary stray flux harmonics for training feed-forward neural networks for monitoring wound rotor induction motors is presented in[100]. The use of transient stray fluxes and…”

FPGA Implementation of AI-Based Inverter IGBT Open Circuit Fault Diagnosis of Induction Motor Drives

“…The Support Vector Machine (SVM)-based algorithms have demonstrated that they provide improved results for the classification and fault diagnosis of a three-phase induction motor [ 23 ]. The Bearing Damage Index (BDI), which is based on the wavelet packet node energy coefficient analysis method, has been proposed not only to detect faults in bearings but also to detect the severity level of the fault [ 24 ]. The Bearing Damage Index (BDI) is based on the wavelet packet node energy coefficient analysis method.…”