End-to-End Partial Discharge Detection in Power Cables via Time-Domain Convolutional Neural Networks

Cellulose particles present a significant concern within the oil‐paper insulation of transformers, posing potential risks to insulation performance. Under the influence of the electric field, the movement of cellulose particles can compromise the transformer's insulation, leading to potential failure. An experimental platform was established to synchronously record particle motion images, partial discharge (PD) pulses, and electric voltage waveforms in oil, aiming to observe the PD characteristics resulting from particle motion under alternating current (AC) voltage and investigate the relationship between different particle motion modes, motion positions, and PD signals. The findings reveal that the phase distribution of PD signals is correlated with the particle motion mode. Specifically, the phase distribution of PD pulses during the back‐and‐forth motion mode is between 4°–94° and 182°–275°. In the suspended oscillation motion mode, the PD pulses phase is concentrated between 20°–84° and 203°–268°. The generation of PD pulses is closely linked to the particle's motion position. PD pulses occur when the particle remains on the electrode during the back‐and‐forth motion mode, generally, PD pulses rarely occur during the jumping process between the two electrodes. In the suspended oscillation motion mode, PD pulses occur when the particle moves upward, but generally do not occur during downward movement. Furthermore, the Pulse Sequence Analysis technique was used to employ the PD characteristics caused by particle motion in transformer oil. The simulation calculations of the electric field distribution for two different particle motion modes show that the particle's motion can cause distortion of the electric field distribution, leading to the generation of PD. The study of the PD characteristics at different particle motion modes and positions obtained contributes to a deeper understanding of the PD induced by cellulose particle motion under AC voltage and provides a reference for the insulation evaluation of transformers.

Optimal selection of features of Partial Discharge (PD) signals recorded from defects in High Voltage (HV) cables will contribute not only to the improvement of PD pattern recognition accuracy and efficiency but also to PD parameter visualization in HV cable condition monitoring and diagnostics. This paper presents a novel Random Forest (RF)-based feature-selection algorithm for PD pattern recognition of HV cables. The algorithm is applied to feature selection of both PD signals and interference signals with the aim of obtaining the optimal features for data processing. First, the experimental data acquisition and feature extraction processes are introduced. PD signals were captured from faults created in a cable to obtain the raw PD data, and then, a set of 3500 transient PD pulses and a set of 3500 typical interference pulses were extracted, based on which 34 PD features were extracted for further processing. Furthermore, 119 two-dimensional features and 1082 three-dimensional features were generated. The paper then discusses the basic principle of the RF algorithm. Finally, RF-based feature selection was implemented to determine the optimal features for PD pattern recognition. The results were obtained and evaluated with the Back Propagation Neural Network and Support Vector Machine. Results show that the proposed RF-based method is effective for PD feature selection of HV cables with the potential for application to additional HV power apparatus.

Partial Discharge (PD) is always a challenge in power cable diagnosis, which is particularly difficult in online PD testing. The conventional procedure requires injecting a pulse into the tested cable, which indicates only offline PD testing system can be calibrated. The procedure assumes the measured PD pulse magnitude is linear to the charge value, which is true only if the measuring bandwidth is close to the DC component of the PD signal spectrum. However, the PD pulse bandwidth in a power cable varies with the distance between the testing location and the discharge source due to the frequency dependant attenuation in the power cables. Therefore, even in offline PD test, depending on the bandwidth of the PD testing device, the measured PD pulse magnitude is not always linear with the charge value, and significant error would be expected if the PD test is calibrated with the conventional procedure. A patented calibration method is introduced to obtain the apparent discharge value from the measured PD spectrum in frequency domain, which overcomes the drawbacks of the current procedure. The proposed calibration does not require injecting a pulse into the tested cables. This method reconstructs the time domain PD current pulse waveform from the measured PD spectrum with a reasonable assumption. Since the reconstructed PD current pulse does not contain interferences and has ideal waveform, the PD charge can be obtained by integrating the reconstructed PD current pulse without many difficulties. Moreover, this method is possible to be applied in online PD testing, as no pulse is required to be injected in the cables with this process.

On-site and on-line partial discharge (PD) measurements are well recognized as difficult tasks due to the large scale and diversity of interferences usually encountered in high voltage facilities. Several techniques have been proposed in literature to improve test conditions on the field, based either on analog and digital approaches. More recently, wavelets and their derivatives have shown to be very effective for the processing of PD signals due to their potential to identify transient, time-localized signals. This paper presents the development and results of a new technique to denoise PD signals based on data mining concepts applied to Undecimated Wavelet Transform (UWT) modulus maxima lines propagation. The theory of modulus maxima lines is introduced and their use is justified as an effective way to identify and localize PD pulses. The UWT was employed as a way to increase robustness against the effects of decimation, which is a characteristic of the orthogonal Wavelet Transform that causes random losses of PD pulses. We took advantage of the improved UWT capability to recover signals by using a modified version of the cycle spinning approach. Denoising was performed by separating the maxima lines related to PDs from those related to noise, followed by reconstruction using the inverse UWT. Separation was achieved by the use of data mining tools. The performances of several algorithms were evaluated and compared, including investigations regarding statistically divergent noise types, effects of data pre-processing like normalization and cleansing, procedures for training and comparisons of supervised and unsupervised techniques. Results obtained for both simulated and measured PD signals confirm that the approach is superior when compared to standard linear filters and non-linear wavelet-based techniques. This is particularly noticeable when processing non-stationary time-localized interferences, a situation in which these techniques fail completely.

Today the sensitive measurement of partial discharge (PD) signals in XLPE cable can be an important element for quality assurance and diagnostics in the factory and during the on-site test procedure. The results clearly indicate that PD analysis of XLPE cable is an excellent online tool to assess its dielectric condition. However, as the serious interference in-field, the acquired PD signals may be interrupted by periodic interferences and white noises, easily. This paper describes an intelligent morphological filter algorithm to remove the periodic pulse interference and white noise contained in the PD signals. The algorithm consists of two stages of morphological processing. The performance of the algorithm is evaluated with simulated and real PD signals. Compared with classical wavelet, there are substantial improvements in the indexes of average error, root mean square (rms) error and maximum error, especially in reducing distortion of the baseline waveform.

This paper analyzed the dynamic Partial discharge (PD) characteristic for onsite measurement based on zero crossing in high voltage power cable. According to IEC60270, high voltage measurement characteristic is required to identify correct PD signal. There is currently limited research operating on the trait, especially zero crossing, and because of this, comprehensive PD detection characteristics need to be further established in certain severe conditions. This occurrence has an erratic and sporadic characteristic that is challenging to identify. This paper explored the time of zero crossing for onsite measured PD signal for power cable through MATLAB simulation. This task is crucial to choose the range of zero crossing time based on the highest peak of detected PD signal. Based on the detailed analysis, it is substantially identified that there is an specific time only for PD signal with the highest amplitude, and based on detected times, a range of zero crossing characteristic was described for PD signal. It provided a useful analysis result for the guideline during onsite PD measurement for power cable.KeywordsPartial dischargeCharacteristicZero crossingPower cableHigh voltage

In this paper, a novel algorithm for partial discharge (PD) pulse waveform analysis and separation based on orthogonal series expansion using Laguerre polynomials is proposed. A system identification technique is also developed to help increase the accuracy rate of the signal classification. Laguerre polynomial series expansions are applied on the PD pulses to effectively extract important information and well-discriminative features. Laguerre expansion coefficients inherently contain information about the amplitude (intensity) and the relaxation time of a dynamic system and this helps direct characterization of PD pulses. The proposed technique is applied to PD pulses acquired from a laboratory set of multiple PD sources. It is shown that this statistical method can classify partial discharge signals with high accuracies, even when the signals are visually indistinguishable. In this research, two methods are developed for system identification. One is based on a deterministic approach in the form of a recursive formula and the other one is a stochastic method based on a group Lasso methodology. The aim of system identification is to improve the classification accuracy by removing the effect of the measurement system from the observed PD waveforms. The accuracy rate of the proposed algorithm is evaluated using the signals that are captured from simultaneous artificial defects in high pressure SF <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</inf> and in low pressure air.

The feature extraction and pattern recognition techniques are of great importance to assess the insulation condition of gas‐insulated switchgear. In this work, the ultra‐high‐frequency partial discharge (PD) signals generated from four types of typical insulation defects are analysed using S‐transform, and the greyscale image in time‐frequency representation is divided into five regions according to the cutoff frequencies of TEm1 modes. Then, the three low‐order moments of every subregion are extracted and the feature selection is performed based on the J criterion. To confirm the effectiveness of selected moment features after considering the electromagnetic modes, the support vector machine, k‐nearest neighbour and particle swarm‐optimised extreme learning machine (ELM) are utilised to classify the type of PD, and they achieve the recognition accuracies of 92, 88.5 and 95%, respectively. In addition, the results show that the ELM offers good generalisation performance at the fastest learning and testing speeds, thus more suitable for a real‐time PD detection.

Partial Discharge (PD) detection in High Voltage (HV) equipment is an essential technique for assessing the insulation condition in the power system apparatus. The presence of PD is one of the critical indications for the defect and deterioration of the insulating material. Effective signal processing techniques are required to acquire, analyse, and classify PD signals into a specific fault type. The PD measurement device is prone to be affected by various noise sources, which leads to misinterpretation of the PD signal. This research focuses on developing a suitable algorithm for denoising PD signals and proposes a novel feature extraction process for classifying PD signals. The signal decomposition-based denoising algorithms in various engineering disciplines have become popular, and such techniques are being applied to PD signals. A novel PD signal denoising using adaptive decomposition, optimized by entropy and statistical parameters is proposed. Furthermore, a novel entropy-driven PD signal classification method is proposed. Initially, the PD signal is decomposed using various adaptive decomposition methods to get Intrinsic Mode Functions (IMFs). Then, IMFs are analysed using statistical or information theory measures such as Kurtosis, Mutual Information (MI) and Dispersion Entropy (DE). The IMFs are classified as noise, noise–dominant and signal IMFs, based on Kurtosis and MI values. The DE value of IMFs is used to select the regularisation parameter of Group-Sparse Total Variation (GSTV). The noise–dominant IMFs are subjected to the GSTV method, and the signal IMFs are added to the output vector to reconstruct the denoised output. The noisy IMFs are discarded for further processing. The proposed methods are applied under different input signal-noise ratios, lengths, and noise sources. The proposed denoising methods with the results and findings are presented and discussed, along with the performance metrics related to the filters. In addition, Tsallis entropy and a novel Generalized Gaussian Distribution – Refined Composite Multiscale Dispersion Entropy (GGD–RCMDE) based features are proposed for the time series signal. The suggested feature extraction methods are applied to the PD dataset to extract the features from various PD signals such as ‘corona’, ‘surface’ and ‘void’. A novel preprocessing method followed by the min-redundancy max-relevance (mRMR) feature selection method is applied to select sensitive features. A multiclass classifier model is trained using the most sensitive features to classify PD faults. The robust experimental analysis of the feature extraction method was carried out and reported. The performance metrics are computed using the results obtained through the experiments. The effectiveness of the proposed denoising and classification methods was presented with a suitable discussion and conclusion.

Two signal classification methods have been examined to discover their suitability for the task of partial discharge (PD) identification. An experiment has been designed to artificially mimic signals produced by a range of PD sources that are known to occur within high voltage (HV) items of plant. The bushing tap point of a large Auto-transformer has been highlighted as a possible point on which to attach PD sensing equipment and is utilized in this experiment. Artificial PD signals are injected into the HV electrode of the bushing itself and a high frequency current transformer (HFCT) is used to monitor the current between the tap-point and earth. The experimentally produced data was analyzed using two different signal processing algorithms and their classification performance compared. The signals produced by four different artificial PD sources (surface discharge in air, corona discharge in air, floating discharge in oil and internal discharge in oil) have been processed, then classified using two machine learning techniques, namely the support vector machine (SVM) and probabilistic neural network (PNN). The feature extraction algorithms involve performing wavelet packet analysis on the PD signals recorded over a single power cycle. The dimensionality of the data has been reduced by finding the first four moments of the probability density function (Mean, Standard deviation, Skew and Kurtosis) of the wavelet packet coefficients to produce a suitable feature vector. Initial results indicate that very high identification rates are possible with the SVM able to classify PD signals with a slightly higher accuracy than a PNN.

Recent studies have shown that wavelet transform can effectively be used for noise reduction in the context of partial discharge (PD) signal detection and classification. Several thresholding approaches for wavelet denoising have been reported in the literature. In this study, a novel wavelet threshold estimation method, named energy conservation‐based thresholding (ECBT), is introduced. The proposed thresholding function is capable of conserving a significant portion of the original signal energy, while the threshold value is determined based on the relative difference between the original and noisy signal energies. The proposed method is first applied to PD signals contaminated with different levels of simulated noise. Results show that ECBT produces a denoised PD signal with higher signal‐to‐noise ratio (SNR) and less distortion than PDs produced by the existing wavelet methods. Then, ECBT is modified to address actual PD signals corrupted with real noise, where a robust SNR estimation method is derived to estimate the noise level embedded in the measured PD signals. The denoised PD signals indicate that the proposed method yields higher reduction in noise levels than other methods.

Combining multi-level feature extraction algorithm with residual graph convolutional neural network for partial discharge detection

Oscillating wave partial discharge detection technology has been widely used because of its powerful applicability. However, the detection process will produce short duration, burst, non-stationary impulse noise, whose characteristics are similar to partial discharge signals, and it is difficult to denoise by traditional methods such as filtering. In accordance with the above problems, this paper presents a method of recognition and noise reduction of oscillating partial discharge signal based on support vector machine. A classifier of noise pulse and partial discharge signal is established to eliminate impulse noise in partial discharge signal. Aiming at the difference of time-frequency characteristics between oscillating partial discharge signal and impulse noise, support vector machine classifier is used to identify partial discharge signal and impulse noise. It can overcome the defect that the traditional filtering method is difficult to suppress impulse noise. The experimental results show that, compared with the traditional empirical threshold method, the accuracy of partial discharge defect location is improved by more than 7.5%, which can effectively improve the accuracy of partial discharge location detection.

Power transformers and gas-insulated switchgear (GIS) play crucial roles in electrical power grids. However, they may suffer from degradation of insulation material due to wear and tear, leading to their imminent failure. Partial discharges (PDs) are an initial sign of insulation materials degradation which emit signals spanning various physical domains, including electromagnetic. PDs are temporally narrow, high-frequency, stochastic radiation sources. The Ultra-Wideband Vivaldi Antenna is the key element for the detection of PDs in power transformers and gas-insulated switchgear. However, they may be subject to different interference environments due to external sources of telecommunication radiation noise occupying the 2.4 GHz – 2.5 GHz band. Noise mixing with PD signals is challenging to resolve, especially for external sensors. Wi-Fi and Bluetooth signals from mobile devices easily overshadow faint PD signals. Band-reject frequency filters may be attached to the antenna, often at the detriment of the insertion loss. The integrated filter does not require any additional post-processing, making it less computationally demanding for smaller processors used in practice. Wi-Fi and Bluetooth degrade the PD signal, necessitating an integrated analog notch filter for noise removal. Therefore, an external ultra-wideband (UWB) Vivaldi antenna with an integrated noise-rejecting parasitic notch filter is designed, fabricated, and tested to detect PDs in electrical assets such as transformers, power cables, and GIS, with GIS being the focus in the experimental validation in this study. A comparative study of the proposed antenna is presented. This paper proposed an antenna that is designed to provide coverage of 95.516% of the 0.226 GHz – 3.506 GHz frequency band, with an average return loss of -16.04 dB and a peak gain of 5.5 in the working band, excluding the notched band. The peak return loss in the 2.4 GHz – 2.5 GHz rejection band is -2.68 dB, with an average attenuation of -35.74 dB. This wide coverage is demonstrated in this paper using simulation and experimentally.

Partial discharge (PD) signals generated by defects in a transformer insulation can be captured through measurement instruments and they may be used, after preprocessing, to discriminate the PD Sources. Some of the artificial defect models, such as: corona, internal cavity and surface discharge in air are developed in the laboratory. These defect models are put in parallel under a high voltage stress. The PD signals stemmed from these sets of multiple PD sources are captured. In this paper six bandpass Alters (with two MPD 600 devices) are used for feature extraction of these signals. For PD signals discrimination, the Density-Based Spatial Clustering of Applications with Noise density (DBSCAN) method is employed with two freedom parameters which resulted in an accurate discrimination of types of partial discharge sources.