Tunable Q-Factor Wavelet Transform for Classifying Mechanical Deformations in Power Transformer

Mechanical deformations in the power transformer are the result of short circuit forces and improper handling of transformer during transportation. Such deformations grow with the time and might lead to complete breakdown of the transformer. Hence, monitoring the condition of the transformer is essential. This paper presents a technique to analyse the terminal behaviour of the transformer winding. To this end, high frequency circuit model of the transformer winding comprises of inductances, capacitances and resistances is considered initially. Mechanical deformations are then introduced by changing these circuit parameters. Frequency response analysis (FRA) is performed to obtain terminal behavior of the circuit model under both healthy and unhealthy conditions. Signals obtained from FRA are decomposed into five subbands (SBs) using tunable Q-Factor wavelet transform (TQWT). Afterwards, with the help of Shannon Entropy (SE), features of the SBs are extracted. These features are then classified using K-nearest neighbour (KNN) and Ensemble Bagged algorithm (EB). The statistical parameters like p-value and t-test clearly indicated that the signals are classified in to healthy and faulty states. Further, data have been classified properly with an accuracy of 99.2%.

[1]  M. S. Aldayel.  K-Nearest Neighbor classification for glass identification problem , 2012, 2012 International Conference on Computer Systems and Industrial Informatics.

[2]  C. Burrus,et al.  Introduction to Wavelets and Wavelet Transforms: A Primer , 1997 .

[3]  Cheng Hao Jin,et al.  Ensemble method for classification of high-dimensional data , 2014, 2014 International Conference on Big Data and Smart Computing (BIGCOMP).

[4]  Ivan W. Selesnick,et al.  Wavelet Transform With Tunable Q-Factor , 2011, IEEE Transactions on Signal Processing.

[5]  Ming Liang,et al.  A kurtosis-guided adaptive demodulation technique for bearing fault detection based on tunable-Q wavelet transform , 2013 .

[6]  Trapti Jain,et al.  Tunable-Q Wavelet Transform and Dual Multiclass SVM for Online Automatic Detection of Power Quality Disturbances , 2018, IEEE Transactions on Smart Grid.

[7]  U. Rajendra Acharya,et al.  Entropies for detection of epilepsy in EEG , 2005, Comput. Methods Programs Biomed..

[8]  U. Rajendra Acharya,et al.  A new approach to characterize epileptic seizures using analytic time-frequency flexible wavelet transform and fractal dimension , 2017, Pattern Recognit. Lett..

[9]  Yasin Khan,et al.  A Review of Frequency Response Analysis Methods for Power Transformer Diagnostics , 2016 .

[10]  M. S. Naderi,et al.  Advanced transformer winding deformation diagnosis: moving from off-line to on-line , 2012, IEEE Transactions on Dielectrics and Electrical Insulation.

[11]  Ram Bilas Pachori,et al.  Optimal duration-bandwidth localized antisymmetric biorthogonal wavelet filters , 2017, Signal Process..

[12]  Wei Fan,et al.  Application of Wavelet Transform with Tunable Q-Factor to Analysis of Non-Stationary Harmonics , 2014 .

[13]  Jin Chen,et al.  Feature extraction of rolling bearing’s early weak fault based on EEMD and tunable Q-factor wavelet transform , 2014 .

[14]  E.P. Dick,et al.  Transformer Diagnostic Testing by Frequuency Response Analysis , 1978, IEEE Transactions on Power Apparatus and Systems.

[15]  T. Kailath.  The Divergence and Bhattacharyya Distance Measures in Signal Selection , 1967 .

[16]  Jorge Pleite Guerra,et al.  Application of Wavelet Transform to Obtain the Frequency Response of a Transformer From Transient Signals—Part 1: Theoretical Analysis , 2013, IEEE Transactions on Power Delivery.