Partial Discharge Pattern Recognition in Oil-Immersed Transformers via DDPM-Based AOK Time-Frequency Data Augmentation

In view of the fact that the statistical feature quantity of traditional partial discharge (PD) pattern recognition relies on expert experience and lacks certain generalization, this paper develops PD pattern recognition based on the convolutional neural network (cnn) and long-term short-term memory network (lstm). Firstly, we constructed the cnn-lstm PD pattern recognition model, which combines the advantages of cnn in mining local spatial information of the PD spectrum and the advantages of lstm in mining the PD spectrum time series feature information. Then, the transformer PD UHF (Ultra High Frequency) experiment was carried out. The performance of the constructed cnn-lstm pattern recognition network was tested by using different types of typical PD spectrums. Experimental results show that: (1) for the floating potential defects, the recognition rates of cnn-lstm and cnn are both 100%; (2) cnn-lstm has better recognition ability than cnn for metal protrusion defects, oil paper void defects, and surface discharge defects; and (3) cnn-lstm has better overall recognition accuracy than cnn and lstm.

This paper discusses the results of an on-going project on the application of artificial intelligence techniques for recognition of partial discharge (PD) patterns from hydrogenerators. The main purpose of the project is to classify data according to the origin of a PD source and create an early warning system for stator winding insulation. More than nine hundreds PD patterns recorded during last two years on more than thirty generators were analysed. The patterns in the form of the maximum and mean pulse height and pulse count discharge distributions were described by statistical parameters such as the skewness, kurtosis, etc., and stored in a data base as a fingerprint. Classification of unknown discharge patterns was carried out by statistical pattern recognition techniques. The results indicate that satisfactory classifications took place.

<span>Partial discharge (PD) pattern recognition is useful to diagnose insulation condition. PD measurement data is commonly represented in phase-resolved partial discharge (PRPD) format. PRPD is useful as it provides a visible pattern for different PD source and various features can be extracted for PD pattern recognition. Shorter PRPD duration will enable more training data but the information in each data is less and vice versa. This works aims to investigate the effects of using very short duration PRPD data on the accuracy of PD pattern recognition. The results conclude that machine learning models such as Artificial Neural Network (ANN) and Support Vector Machine (SVM) are robust enough such that reduction of PRPD duration from 15-seconds to 1-second causes less than 5 % drop in the classification accuracy. However, this is only true for noise free condition. <span>When the same PD data is overlapped with random noise, the classification accuracy suffers a significant reduction up to 19%. Therefore, longer PRPD duration is recommended to withstand the effects of noise contamination.</span></span>

This paper presents a feature extraction algorithm combining S transform (ST) and two-directional two-dimensional principal component analysis ((2D) <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> PCA) for partial discharge (PD) pattern recognition. S transform (ST) is firstly employed to obtain a time-frequency representation of the recorded UHF signals. Then, (2D) <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> PCA is applied to compress the ST amplitude(STA) matrices to extract various feature vectors with different (d <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> , d <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) combinations, i.e. (5, 5), (5, 10), (10, 5) and (10, 10). The extracted features are examined by both PSO-SVM classifier and BPNN. Experimental results show that the classification accuracies by PSO-SVM are all higher than that by BPNN under four circumstances of (d <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> , d <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) combinations. The success rates of the PSO-SVM with the four feature vectors are above 94% in all cases. It can be found that the proposed feature extraction and classification algorithm can be effectively applied to PD pattern recognition.

Different types of partial discharge (PD) cause different damage to gas-insulated switchgear (GIS), so it is very important to correctly identify the type of PD for evaluating the GIS insulation condition. The traditional PD pattern recognition algorithm has the limitations of low recognition accuracy and slow recognition speed in engineering applications. This work proposed a Convolutional Block Attention Module Residual Network (CBAM-ResNet) for the GIS PD pattern recognition. In particular, the Squeeze-and-Excitation mechanism was used to improve the recognition accuracy. The GIS phase resolved partial discharge (PRPD) image is used as the input of the pattern recognition model. The results show that the recognition accuracy of the proposed method is as high as 89%, and has a recognition accuracy of 92.72%, 90.19%, 89.36%, and 93.62% for the four PD types, respectively. Compared with normal CNN and SVM recognition algorithms, the PD pattern recognition accuracy of the proposed method has been greatly improved. And the CBAM-ResNet for PD pattern recognition has a good application prospect in engineering practice.

To improve the accuracy of partial discharge pattern recognition under unbalanced and small sample conditions, a method of partial discharge data augmentation and pattern recognition using the generative adversarial network embedded deep auto-encoder (DAE-GAN) is proposed. First, deep Auto-encoder (DAE) is embedded into a Generative Adversarial Network (GAN), and DAE is used to guide the generation process to improve the authenticity of generated samples. Second, complement samples of PD samples are added to the training process of the Generative Adversarial Network to solve the problem of small PD samples. Finally, extended equalization training samples are used to fine-tune the discriminator of the model to realize PD pattern recognition. DAE-GAN is used for data augmentation and pattern recognition of partial discharge experimental signals. The results show that, compared with other algorithms, the authenticity and probability distribution fitting accuracy of partial discharge samples generated by DAE-GAN are higher and the accuracy of partial discharge recognition is improved by 8.24% after data augmentation.

Pattern recognition of partial discharge (PD) has various beneficial applications in academia and industry. However, it is hard and expensive to obtain extensively annotated PD data to build a high-performance classification model. Given there is potential to use PD data more effectively, this paper presents a novel data generative model based on generative adversarial networks (GAN). GAN are able to learn deep feature representations of existing PD signals and synthesizes more extensive UHF PD signals. An original PD data set of UHF PD signals is established by the partial discharge experiment. With the result of the original PD signals dataset as baseline, we evaluated the performance of some classifiers on the augmented dataset. The results show that UHF PD classification model benefits from GAN-based data augmentation techniques. Clearly, the GAN-based model has good potential in industry diagnosis of PD, especially when the data are sparse.

Partial Discharge (PD) characteristics of typical defects in oil-paper insulation under AC, DC and AC-DC combined voltages have been studied extensively. However, there is still limited material available for the pattern recognition of partial discharge under actual stress withstood by valve side windings in converter transformers. In this paper, the PD of needle-plane defect is measured under actual stress in converter transformers. The stress is DC voltage superimposed harmonics, which has been analyzed in PSCAD at first. Then DC voltage superimposed both single harmonic and multiple harmonics, including simulated actual stress and approximate square waveform, have been applied on electrode. PD parameters and patterns are acquired by detector using pulse current method. The test results indicate that the inception voltage and pulse repetition rate of PD have no direct relationship with harmonic order due to the accumulation of space charges injected by DC voltage. PD amplitude shows a growing trend and phase distributions of PD expand with the increase of harmonic order. PD patterns are also closely related to the waveform of applied voltage. PD amplitude rises with the increase of voltage change rate, and the majority of PD pulses occur in the phase range which has a higher voltage change rate. Experimental results show that harmonic order exerts a great effect on PD characteristics of needle-plane defect under DC superimposed harmonic waveforms. The findings of the current study are useful in further research on the pattern recognition of PD and diagnose in converter 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.

In order to deal with the limitations on the feature extraction of strong random signals in DC XLPE cables, this paper proposes a self-adaptive pattern recognition method based on convolutional neural network (CNN). Convolutional Architecture for Fast Feature Embedding (Caffe) has great performance on image recognition using CNN. Four typical insulation defects are designed and PD signals are collected for pattern recognition. Four different Caffe frameworks are constructed to analyze the impact of the network structures and solver parameters on training effect. Compared with Quick-CIFAR-IO and original Alexnet network, the modified Alexnet network proposed by this paper has great adaptability to pattern recognition of partial discharges in DC XLPE cables.

Different types of partial discharge (PD) cause different damages to gas-insulated substation (GIS), so it is very important to correctly identify the type of PD for evaluating the GIS insulation condition. The traditional PD pattern recognition algorithm has the limitations of low recognition accuracy and slow recognition speed in engineering applications. To effectively diagnose the GIS PD type and safeguard the safe and reliable operation of the distribution network, a GIS PD method based on improved CBAM-ResNet was proposed in this paper. And the improved CBAM-ResNet takes advantage of the residual neural network and attention mechanism. In particular, the channel attention module and the spatial attention module are connected in parallel in the improved CBAM. The experimental results showed that the GIS PD pattern recognition method proposed herein has a recognition rate of 93.58%, 95.00%, 93.55%, and 93.88% against the four PD types. Compared with the traditional PD pattern recognition algorithm, the algorithm has the advantages of a lightweight model and more accurate recognition results, which carry better engineering application values.

An experimental study of pattern recognition of partial discharge (PD) in a crosslinked polyethylene (XLPE) cable by using a neural network (NN) system is described. The NN system was a three-layer artificial neural network system with feedforward connections, and its learning method was a backpropagation algorithm incorporating an external teacher signal. Input information for the NN was a combination of the discharge magnitude, the number of pulse counts and the phase angle of applied voltage in which PD is produced. PD measurement was carried out using a PD pulse recorder for a 66 kV XLPE cable with an artificial defect under a 38 kV AC applied voltage. After learning 30 typical input patterns, the NN discriminated unknown patterns with 90% correct responses. The time duration including measuring time required for the NN to discriminate PD signal was approximately 30 s. In a long-term performance test of a 66 kV XLPE cable with an artificial defect, the NN-based alarm processor was able to recognize the presence of PD 1 h before breakdown of the cable, and successfully alerted the operator. >

The traditional machine learning algorithms have already been implemented on the partial discharge pattern recognition of cross-linked polyethylene (XLPE) power cables. However, the slow convergence speed and low recognition accuracy limit its practical engineering applications. To solve the drawbacks, this paper presents an XLPE cable partial discharge pattern recognition method based on a stacked sparse noise reduction autoencoder. This proposed method determines the hyperparameters by category weights and adds Gaussian white noise to the original input. The autoencoder can fully extract effective features, and then obtains an effective deep feature extraction model. The Softmax classifier is employed to deliver the diagnosis results. The analysis results of the case study show that compared with the partial discharge pattern recognition methods such as decision tree, BP neural network and SVM, the proposed method can further improve the recognition accuracy by adding Gaussian white noise and determining the optimal number of hidden layers.KeywordsCablePattern recognitionSoftmax classifierStacked sparse noise reduction autoencoder

Convolutional neural networks (CNNs) have been widely used for gas‐insulated switchgear (GIS) partial discharge (PD) pattern recognition due to their powerful feature extraction ability. However, there is commonly a scarcity of fault samples due to low insulation failure rate of GIS equipment, which degrades the diagnostic performance of these CNN networks when directly applied to small and unbalanced datasets. Therefore, we propose a novel auxiliary classifier generative adversarial network for GIS PD pattern recognition for small and unbalanced samples. First, we propose using synchrosqueezed wavelet transform to extract time‐frequency characteristics of PD pulses and obtain a time‐frequency image with high energy aggregation and time‐frequency distribution rate. Then, we propose an improved generative adversarial network with an auxiliary classier and self‐attention mechanism, which can generate high‐quality PD samples for situations with few classes. Experiments show that our proposed method can reach 95.75% recognition accuracy for small datasets, which is the highest among several comparable methods. Furthermore, the proposed method has excellent and stable recognition performance for various unbalanced datasets.

This paper presents a state-of-the-art review on machine learning (ML) based intelligent diagnostics that have been applied for partial discharge (PD) detection, localization, and pattern recognition. ML techniques, particularly those developed in the last five years, are examined and classified as conventional ML or deep learning (DL). Important features of each method, such as types of input signal, sampling rate, core methodology, and accuracy, are summarized and compared in detail. Advantages and disadvantages of different ML algorithms are discussed. Moreover, technical roadblocks preventing intelligent PD diagnostics from being applied to industry are identified, such as insufficient/imbalanced dataset, data inconsistency, and difficulties in cost-effective real-time deployment. Finally, potential solutions are proposed, and future research directions are suggested.