Identification of Different Types of Partial Discharge Sources from Acoustic Emission Signals in the Time-Frequency Representation

Chai, Mengqiu; Thayoob, Yasmin Hanum Md; Ghosh, P.S.; Sha’ameri, Ahmad Zuri; Talib, Manar Abu

doi:10.1109/pecon.2006.346718

Cited by 15 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Spectrogram is a time-dependent frequency analysis [9] and it is widely used in the field related of voice analysis. An analogy to the problem of recognising different PD sources by this method might be that of recognising by computer different words spoken into a microphone.…”

Section: Spectrogram Analysismentioning

confidence: 99%

“…Moreover, the differences of PD among 3 different sensors are also investigated because they may provide a way of using only a few key features in order to distinguish among these data. Examples of key features extracted from these spectrograms are shown in Table I, which uses some of the principles outlined in [9]. As in Fig.…”

Section: Spectrogram Analysismentioning

confidence: 99%

“…Two novel approaches based on frequency and time characteristics are investigated; spectrogram analysis [9] and envelope analysis combined with a similarity calculation. Although previous research [4] has shown that the similarity function based on wavelet transform can distinguish between different PD sources, it uses a computationally intensive process.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Methods for distinguishing between partial discharges based on the UHF detection technique

Pinpart

Fletcher

Judd

2008

2008 International Conference on Condition Monitoring and Diagnosis

View full text Add to dashboard Cite

Partial discharges (PDs) are a cause of concern in power systems. Many detection methods and analysis techniques for PDs are available, such as UHF detection, conventional IEC 60270 method, acoustic detection, etc. This paper focuses on analysing signals obtained by the UHF method in order to distinguish between different sources of PD. Two methods based on the frequency and time characteristics are investigated with the aim of testing PD recognition based on the calculation of similarity or difference of two UHF signals. It has previously been shown that PDs can be recognized by a similarity function based on a time-frequency representation constructed using a wavelet transform. However, this is a computationally intensive process that needs to be simplified for practical implementation. Two new approaches are investigated in this paper. The first method uses spectrogram analysis to represent the UHF signal in terms of time, frequency and amplitude, from which a few key features can be extracted. The second method uses a smoothing kernel to capture the envelope of the UHF signal, effectively reducing the quantity of data to be analysed. The results from the two methods of comparing PD signals are discussed to determine their ability to measure similarity, while the results of non-PD signals are compared to show the different behaviours between PD and non-PD signals.

show abstract

Section: Spectrogram Analysismentioning

confidence: 99%

Section: Spectrogram Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Methods for distinguishing between partial discharges based on the UHF detection technique

Pinpart

Fletcher

Judd

2008

2008 International Conference on Condition Monitoring and Diagnosis

View full text Add to dashboard Cite

show abstract

“…Identifying sources of PD activities has been an important research area due to the PD's direct effect on insulation failure [10][11][12][13][14][15][16][17][18]. There are many attempts to achieve high recognition rate using AE signals for different PD types in the literature [1], [14][15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

“…There are many attempts to achieve high recognition rate using AE signals for different PD types in the literature [1], [14][15][16][17][18]. In [16], a wide band piezoelectric transducer, DC-1 MHz, was used to measure eight simulated PD types.…”

Section: Introductionmentioning

confidence: 99%

Classification of common partial discharge types in oil-paper insulation system using acoustic signals

Harbaji

Shaban

El-Hag

2015

IEEE Trans. Dielect. Electr. Insul.

View full text Add to dashboard Cite

This paper addresses classifying different common partial discharge (PD) types under different acoustic emission (AE) measurement conditions. Four types of PDs are considered for the multi-class classification problem, namely; PD from a sharp point to ground plane, surface discharge, PD from a void in the insulation, and PD from semi parallel planes. The collected AE signals are processed using pattern classification techniques to identify their corresponding PD types. The measurement conditions include the influences of various PD locations, oil temperatures, and having a barrier in the line-of-sight between the PD source and the AE sensor. A recognition rate of 94% is achieved when classifying the different PD types measured at the same conditions. In addition, it has been found that the different PD source locations, oil temperatures, and barrier insertion have an impact on the recognition rate. However, by including AE samples at these different conditions in the training process, a recognition rate around 90% for all cases is achieved.

show abstract

Classification of EMI discharge sources using time–frequency features and multi-class support vector machine

Mitiche

Morison

Nesbitt

et al. 2018

Electric Power Systems Research

View full text Add to dashboard Cite

This paper introduces the first application of feature extraction and machine learning to Electromagnetic Interference (EMI) signals for discharge sources classification in high voltage power generating plants. This work presents an investigation on signals that represent different discharge sources, which are measured using EMI techniques from operating electrical machines within power plant. The analysis involves Time-Frequency image calculation of EMI signals using General Linear Chirplet Analysis (GLCT) which reveals both time and frequency varying characteristics. Histograms of uniform Local Binary Patterns (LBP) are implemented as a feature reduction and extraction technique for the classification of discharge sources using Multi-Class Support Vector Machine (MCSVM). The novelty that this paper introduces is the combination of GLCT and LBP applications to develop a new feature extraction algorithm applied to EMI signals classification. The proposed algorithm is demonstrated to be successful with excellent classification accuracy being achieved. For the first time, this work transfers expert's knowledge on EMI faults to an intelligent system which could potentially be exploited to develop an automatic condition monitoring system.

show abstract

Identification of Different Types of Partial Discharge Sources from Acoustic Emission Signals in the Time-Frequency Representation

Cited by 15 publications

References 3 publications

Methods for distinguishing between partial discharges based on the UHF detection technique

Methods for distinguishing between partial discharges based on the UHF detection technique

Classification of common partial discharge types in oil-paper insulation system using acoustic signals

Classification of EMI discharge sources using time–frequency features and multi-class support vector machine

Contact Info

Product

Resources

About