Electric Motor Fault Detection and Diagnosis by Kernel Density Estimation and Kullback–Leibler Divergence Based on Stator Current Measurements

Abstract

This paper deals with the problem of fault detection and diagnosis of induction motor based on motor current signature analysis. Principal component analysis is used to reduce the three-phase current space to a 2-D space. Kernel density estimation (KDE) is adopted to evaluate the probability density functions of each healthy and faulty motor, which can be used as features in order to identify each fault. Kullback-Leibler divergence is used as an index to identify the dissimilarity between two probability distributions, and it allows automatic fault identification. The aim is also to improve computational performance in order to apply online a monitoring system. KDE is improved by fast Gaussian transform and a points reduction procedure. Since these techniques achieve a remarkable computational cost reduction with respect to the standard KDE, the algorithm can be used online. Experiments are carried out using two alternate current motors: an asynchronous induction machine and a single-phase motor. The faults considered to test the developed algorithm are cracked rotor, out-of-tolerance geometry rotor, and backlash. Tests are carried out at different load and voltage levels to show the proposed method performance.

An Improved Method for Error Analysis of Intelligent Distribution Terminal

“…The minimum residual error sum is set as rmin=10-4, then the improved results of Lagrange multipliers are listed in Table 1. Additionally, the conventional maximum entropy method and the Botev method are respectively adopted to solve the probability density function with the same measurement data [9]. The comparison of different distribution methods is displayed in Fig.…”

“…To compare the evaluation accuracy of the above three methods, the standard deviations are calculated. In addition, by taking the Botev method as the standard [9], the relative standard deviations of the proposed method and the conventional method are shown in Table 2. The relative standard deviation of the proposed method is less than 5%, which illustrates the correctness and validity of this method.…”

Electric motor defects diagnosis based on kernel density estimation and Kullback–Leibler divergence in quality control scenario

“…For many data sample sets N and points M at which the PDF needs to be evaluated, KDE computation by classical algorithm (4) is prohibitive (Giantomassi et al, 2015). This fact is a drawback for all applications where KDE must estimate online the PDF.…”

“…A probabilistic monitoring system, for defect detection and diagnosis, is developed by employs Kernel Density Estimation (KDE) and Kullback-Leibler (K-L) divergence. KDE allows to estimate the 2-D probability density function of Concordia transformed patterns, these estimations are used as signature of the motor condition; K-L performs fault diagnosis by divergence indexes (Giantomassi et al, 2015).…”

A Method of Bearing Fault Diagnosis Using Singular Spectrum Analysis, Sparse Filtering and Anfis

“…Online identifying bearing fault to exploit, maintain or repair systems actively is really meaningful work [1,2,3,4,5,6,7]. Because mechanical faults cause changes in system dynamic response, actually this work is often carried out via vibration signal.…”