Identification of Partial Discharges in Gas-insulated Switchgear by Ultra-high-frequency Technique and Classification by Adopting Multi-class Support Vector Machines

Umamaheswari, R.; Sarathi, R.

doi:10.1080/15325008.2011.596506

Cited by 34 publications

(23 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [6][7][8][9] it was presented that using wavelet or wavelet packet decomposition extraction of energy features and the classification results were satisfactory, while the methods mentioned in these papers focused on selecting energy features among the leaf nodes in WPD tree. In this paper, according to the analysis of WPD of EM signals, it is found that, if the level of decomposition is not deep enough, there would not be effective parameters for classification.…”

Section: Features Selection For Em Signalsmentioning

confidence: 99%

“…It can be seen that, conducted by SVD, E of floating PD, oil clearance PD and void PD in pressboard is constructed with a primary singular vector, while E of needle PD is constructed with two primary singular vectors. After executing these steps above, seven energy features are finally extracted, which are (8, 31), (8,10), (8,8), (7,7), (7,13), (5,3), (3,0). The first digit in bracket denotes the level of WPD; the second digit denotes the position of tree node in the level indicated by the first digit.…”

Section: Features Selection For Em Signalsmentioning

confidence: 99%

“…Wavelet or wavelet packet decomposition (WPD) are always treated as the common feature selection method in classification of EM signals. Some of the previous research adopted the information in different frequency band as classification features, which can be got from each tree node in WPD tree, including energy features, fractal dimension features, etc [6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Applying WPD and SVD to Classification of EM Wave Induced by Partial Discharge in Power Transformer

Zhao¹,

Cheng²,

Yu³

et al. 2013

Journal of Electrical Engineering

View full text Add to dashboard Cite

Partial discharge (PD) current is an impulse signal at nanosecond level, which can generate electromagnetic (EM) wave containing broadband frequency information. The frequency band of EM signal is from MHz up to GHz. Due to different PD patterns, impulse currents with different shapes induce different EM waves containing different frequency information. Therefore, using the features extracted from frequency domain of EM signals, the classification of PD patterns can be effectively got. It is good to use wavelet or wavelet packet decomposition to select features. However, if the decomposition level is too shallow to find enough effective features, it cannot group the EM signals to the right pattern. On the contrary, although it is easier to find features to distinguish the PD pattern if the decomposition level is deep, there will be a lot of redundancy variables and it is hard to select features among so many variables. In this paper, a method is presented, which selected features in the whole decomposition tree instead of selecting among the leaf node of the tree, because more potential features can be found in the whole tree. With the present method, it is possible not only to get enough features, but also to eliminate the redundancy variables effectively. In order to validate the method, large EM signals from four PD patterns in a power transformer are acquired as the training data and testing data for feature selection and classification, and three common classification methods are introduced to classify the PD patterns using the features selected by the method. Most of the classification results are satisfactory indicating that the proposed method is effective.

show abstract

Section: Features Selection For Em Signalsmentioning

confidence: 99%

Section: Features Selection For Em Signalsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Applying WPD and SVD to Classification of EM Wave Induced by Partial Discharge in Power Transformer

Zhao¹,

Cheng²,

Yu³

et al. 2013

Journal of Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…The signals are preprocessed with a wavelet decomposition and use the coefficients of the levels as one of the features to train a binary SVM. In [19] the rejection of noise is not taken into account when testing the effectiveness of the algorithms. In a previous work [20], the authors of this paper systematically addressed the classification of PD with SVM.…”

Section: Introductionmentioning

confidence: 99%

Robust Condition Assessment of Electrical Equipment with One Class Support Vector Machines Based on the Measurement of Partial Discharges

et al. 2018

View full text Add to dashboard Cite

This paper presents a system for the detection of partial discharges (PD) in industrial applications based on One Class Support Vector Machines (OCSVM). The study stresses the detection of Partial Discharges (PD) as they represent a major source of information related to degradation in the equipment. PD measurement is a widely extended technique for condition monitoring of electrical machines and power cables to avoid catastrophic failures and the consequent blackouts. One of the most important keystones in the interpretation of partial discharges is their separation from other signals considered as not-PD especially in low SNR measurements. In this sense, the OCSVM is an interesting alternative to binary SVMs since it does not need a training set with examples of all the output classes correctly labelled. On the contrary, the OCSVM learns a model of the signals acquired when the equipment is in PD-free mode, defined as a state where no degradation mechanism is active, so one only needs to make sure that the training signals were recorded under this setting. These default mode signals are easier to characterize and acquire in industrial environments than PD and lead to more robust detectors that practically do not need domain adaptation to perform in scenarios prone to different types of PD. In fact, the experimental results show that the performance of the OCSVM is comparable to that achieved by a binary SVM trained using both noise and PD pulses. Finally, the method is successfully applied to a more realistic scenario involving the detection of PD in a damaged distribution power cable.

show abstract

“…In Peiqing et al (2012), the representation is based on a time-frequency map already used in measurements with high-frequency transformers in conventional methods with PRPD. Finally, in Umamaheswari and Sarathi (2011), support vector machines are used to classify signals but a previous training of the SVM is needed.…”

Section: Introductionmentioning

confidence: 99%

Separation of sources in radiofrequency measurements of partial discharges using time–power ratio maps

2015

View full text Add to dashboard Cite

Partial discharges measurement is one of the most useful tools for condition monitoring of high-voltage (HV) equipment. These phenomena can be measured on-line with antennas provided that the signal to noise ratio is improved by reducing common radiofrequency (RF) emission. One approach to this problem is the use of specific sensors like Vivaldi antennas which reject FM radio and low-frequency TV broadcasting bands. Additionally, the application of advanced signal processing techniques is paramount to separate noise and interferences from the signals of interest. In this paper, the power ratios (PR), a technique based on the power distribution of the incoming signals in frequency bands, is used to characterize different sources of PD and electromagnetic noise (EMN). The calculation of the time length of the pulses is introduced to separate signals where the PR alone do not give a conclusive solution. Thus, if several EM sources could be isolated and previously calibrated, it is possible to detect pulses that correspond to other events, quite possibly from PD activity.

show abstract

Identification of Partial Discharges in Gas-insulated Switchgear by Ultra-high-frequency Technique and Classification by Adopting Multi-class Support Vector Machines

Cited by 34 publications

References 25 publications

Applying WPD and SVD to Classification of EM Wave Induced by Partial Discharge in Power Transformer

Applying WPD and SVD to Classification of EM Wave Induced by Partial Discharge in Power Transformer

Robust Condition Assessment of Electrical Equipment with One Class Support Vector Machines Based on the Measurement of Partial Discharges

Separation of sources in radiofrequency measurements of partial discharges using time–power ratio maps

Contact Info

Product

Resources

About