Recognition of partial discharge patterns

Liao, Ruijin; Fernandess, Y.; Tavernier, K.; Irving, M.R.

doi:10.1109/pesgm.2012.6344929

Cited by 19 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PARTIAL discharge is one of the main causes of electrical insulation failures in the long term [1]. Because electrical insulation breakdowns mostly lead to electrical equipment outages especially in HV and EHV levels and cascading failures, on-line PD monitoring schemes have gained importance both in industry and academic studies in recent years [2].…”

Section: Introductionmentioning

confidence: 99%

Partial discharge pattern recognition via sparse representation and ANN

Majidi

Fadali

Etezadi-Amoli

et al. 2015

IEEE Trans. Dielect. Electr. Insul.

View full text Add to dashboard Cite

In this study, seventeen samples were created for classifying internal, surface, and corona partial discharges (PDs) in a high voltage lab. Next, PDs were measured experimentally to provide a dictionary comprising the types. Due to the huge size of the recorded dataset, a new and straightforward preprocessing method based on signal norms was used to extract the appropriate features of various samples. The new sparse representation classifier (SRC) was computed using ℓ 1 and stable ℓ 1 -norm minimization by means of Primal-Dual Interior Point (PDIP) and Basis Pursuit De-noise (BPDN) algorithms, respectively. The pattern recognition was also performed with an artificial neural network (ANN) and compared with the sparse method. It is shown that both methods have comparable performance if training process, tuning options, and other tasks for finding the best result from ANN are not taken into account. Even with this assumption, it is shown that SRC still performs better than ANN in some cases. In addition, the SRC technique presented in this paper converges to a fixed result, while the results after training the ANN vary with every run due to random initial weights.Index Termssparse representation, compressive sensing, partial discharges, pattern recognition, ℓ 1 and stable ℓ 1 -norm minimization, ANN, signal norms. MehrdadMajidi received the B.Sc. and M.Sc. degrees in power electrical engineering from Power and Water University of Technology (PWUT), Tehran, Iran with honors in 2009 and 2011, respectively. He is currently a Graduate Research Assistant in the

show abstract

Section: Introductionmentioning

confidence: 99%

Partial discharge pattern recognition via sparse representation and ANN

Majidi

Fadali

Etezadi-Amoli

et al. 2015

IEEE Trans. Dielect. Electr. Insul.

View full text Add to dashboard Cite

show abstract

“…A number of other commonly used methods in extracting a PD signal are available for UHF pulse signal to recognize PD in power equipment. Examples of such methods are the time-frequency method, wavelet analysis method, empirical mode decomposition, and frequency domain analysis [3][4][5][6]. Information extracted by one method only reflects the signal characteristics from a point of view.…”

Section: Introductionmentioning

confidence: 99%

Partial Discharge Identification Using Multiple Features Fusion Based on Evidence Theory and Support Vector Machine

2013

AMM

View full text Add to dashboard Cite

The time resolved partial discharge (TRPD) signals collected by Ultra High Frequency (UHF) sensors of transformer contain important informations of the properties of faults. Wealth of information can be utilized for fault identification by different signal analyzing techniques, such as time domain analysis, frequency domain analysis and the wavelet analysis. An integrated characteristic information fusion system based on the Platt posterior probability model and support vector machine (SVM) one-against-one method is proposed. From the recognition result of the four typical insulation defects, the recognition system shows strong advantages in accuracy and reliability.

show abstract

“…To demonstrate the applications of SVD, Liao et al (2012) introduced an SVD-based data mining framework to recognize the pattern of partial discharge, the underlying cause of an electrical equipment failure, while the authors of [Mu et al (2011)] discussed the optimization of SVD usage in accelerating the exact recovery from visual data with corrupted components.…”

Section: Singular Value Decompositionmentioning

confidence: 99%

“…Among the classical solutions for PCA, Singular Value Decomposition (SVD) is the most popular technique to approximate high-dimensional data through orthogonal transformations. SVD-based PCA has been used in many signal processing applications such as image processing, computer vision, pattern recognition and remote sensing [Xu et al (2012);Mu et al (2011);Liao et al (2012)]. However, SVD is a computationally-expensive procedure, which makes its use unlikely to meet the requirements of many time-sensitive designs, especially when it is processed iteratively in those applications.…”

Section: Introductionmentioning

confidence: 99%

Using reconfigurable computing technology to accelerate matrix decomposition and applications

Wang¹

View full text Add to dashboard Cite

Recognition of partial discharge patterns

Cited by 19 publications

References 15 publications

Partial discharge pattern recognition via sparse representation and ANN

Partial discharge pattern recognition via sparse representation and ANN

Partial Discharge Identification Using Multiple Features Fusion Based on Evidence Theory and Support Vector Machine

Using reconfigurable computing technology to accelerate matrix decomposition and applications

Contact Info

Product

Resources

About