Abstract
In this paper, a novel fault diagnosis method for variable frequency drive (VFD)-fed induction motors is proposed using Wavelet Packet Decomposition (WPD) and greedy-gradient max-cut (GGMC) learning algorithm. The proposed method is developed using experimental stator current data in the lab for two 0.25 HP induction motors fed by a VFD, subjected to healthy and faulty cases under various operating frequencies and motor loadings. The features are extracted from stator current signals using WPD by evaluating energy eigenvalues and feature coefficients at decomposition levels. The proposed method is validated by comparing with other graph-based semi-supervised learning (GSSL) algorithms, local and global consistency (LGC) and Gaussian field and harmonic function (GFHF). To enable fault diagnosis for untested motor operating conditions, mathematical equations to calculate features for untested cases are developed through surface fitting using features extracted from tested cases.
Highlights
Induction motors are most widely used in various industrial sectors, either connected direct online or fed by variable frequency drives (VFDs)
Harmonics may cause higher stress in bearings and windings of the motor; harmonics cause poor signal to noise ratio when using stator currents for fault diagnosis; a fault diagnosis algorithm developed for a fixed motor operating frequency may become invalid due to varying drive output frequencies in VFD applications; control loops of VFDs may affect how electrical or mechanical variables of induction motors are coupled under faulty conditions [2]
For VFD-fed induction motor’s operation, the changing frequency at the VFD output might affect or even invalid an induction motor fault diagnosis approach that is functional at a fixed operating frequency. To overcome such concerns and fill in this research gap for VFD-fed induction motors, we propose a fault diagnosis method using Wavelet Packet Decomposition (WPD) and greedy-gradient max-cut (GGMC) learning in this paper
Summary
Induction motors are most widely used in various industrial sectors, either connected direct online or fed by variable frequency drives (VFDs). The main contribution of this paper includes: 1) propose an effective fault diagnosis method for VFD-fed induction motors using a GSSL learning algorithm, GGMC; 2) develop a novel feature extraction technique using WPD by evaluating energy eigenvalues and feature coefficients at decomposition levels using the stator current signal; 3) to enable fault diagnosis for untested frequency and motor loading conditions using the proposed method, develop mathematical equations for feature calculation for such untested motor operating conditions through surface fitting using features extracted from experimental data of tested conditions. EXPERIMENTS IN THE LAB In this paper, learning datasets are stator current signals measured in the lab for various healthy and faulty cases of an induction motor fed by a VFD. One hole was drilled for one BRB fault (Fig. 3(a)); two and three holes were drilled on adjacent rotor bars for two and three BRB faults (Figs. 3(b) and 3(c)), respectively, which is quite different from previous experiments done in the lab for two and three BRB faults for direct online induction motors with drilled holes 90◦ apart [16]–[18]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
