A Novel Application of Deep Belief Networks in Learning Partial Discharge Patterns for Classifying Corona, Surface, and Internal Discharges

This paper introduces a new application of deep belief network (DBN) as an emerging artificial neural network for recognizing and classifying different partial discharge (PD) patterns. Phase resolved PD (PRPD) technique with different window intervals is used to manipulate three PD types, including corona, surface, and internal discharges measured in a high-voltage lab. Four approaches are proposed for extracting features from the raw measured data. In the first approach, the DBN is used as both a feature extractor and a PD classifier. The other three approaches extract discriminatory features using statistical and vector-norm-based operators to train a DBN classifier. The impact of the various phase windows through the PRPD method on the performance of the trained classifier is evaluated to obtain the best window interval. It is shown that the deep architectures are capable of learning important distinguishable features from PD data without any data preprocessing. This eliminates time-consuming feature extraction processes that produce the handcrafted features. Based on a comparison analysis, when the input data are corrupted by noise levels or no feature extraction technique is used to preprocess the data, the proposed approach outperforms other techniques, such as artificial neural networks, fuzzy logic classifiers, and support vector machines.

[1]  E. Gulski.  Digital analysis of partial discharges , 1995 .

[2]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[3]  Ruslan Salakhutdinov,et al.  Learning Deep Generative Models , 2009 .

[4]  E. Gulski,et al.  Computer-aided recognition of discharge sources , 1992 .

[5]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[6]  Terezinha Ferreira de Oliveira,et al.  A method for the behavioral analysis of partial discharges in hydrogenerators by generalized linear models , 2016 .

[7]  Ray Bartnikas,et al.  Partial discharges. Their mechanism, detection and measurement , 2002 .

[8]  E. Gulski,et al.  Neural networks as a tool for recognition of partial discharges , 1993 .

[9]  Xin Zhou,et al.  Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data , 2016 .

[10]  Rui Huang,et al.  Assessment of PD severity in gas-insulated switchgear with an SSAE , 2017 .

[11]  Sergio Escalera,et al.  Separability of ternary codes for sparse designs of error-correcting output codes , 2009, Pattern Recognit. Lett..

[12]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[13]  Hazlee Azil Illias,et al.  High noise tolerance feature extraction for partial discharge classification in XLPE cable joints , 2017, IEEE Transactions on Dielectrics and Electrical Insulation.

[14]  Hao Zhang,et al.  A novel wavelet transform technique for on-line partial discharge measurements. 1. WT de-noising algorithm , 2007, IEEE Transactions on Dielectrics and Electrical Insulation.

[15]  Gian Carlo Montanari,et al.  Random sampling and data processing for PD-pulse height and shape analysis , 2000 .

[16]  Mohammad Oskuoee,et al.  Improving pattern recognition accuracy of partial discharges by new data preprocessing methods , 2015 .

[17]  Mohammad Oskuoee,et al.  Partial discharge pattern recognition via sparse representation and ANN , 2015, IEEE Transactions on Dielectrics and Electrical Insulation.

[18]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[19]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[20]  Xuelong Li,et al.  Refined-Graph Regularization-Based Nonnegative Matrix Factorization , 2017, ACM Trans. Intell. Syst. Technol..

[21]  L. Satish,et al.  Wavelet-based denoising of partial discharge signals buried in excessive noise and interference , 2003 .

[22]  E. Gulski,et al.  Classification of partial discharges , 1993 .

[23]  Xuelong Li,et al.  Graph Regularized Non-Negative Low-Rank Matrix Factorization for Image Clustering , 2017, IEEE Transactions on Cybernetics.

[24]  Yu Han,et al.  Using improved self-organizing map for partial discharge diagnosis of large turbogenerators , 2003 .

[25]  L. Hao,et al.  Partial discharge source discrimination using a support vector machine , 2010, IEEE Transactions on Dielectrics and Electrical Insulation.

[26]  Yale Chang,et al.  Unsupervised Feature Learning via Sparse Hierarchical Representations [ 1 ] , 2014 .

[27]  B. Phung,et al.  Spectral features for the classification of partial discharge signals from selected insulation defect models , 2013 .

[28]  G. Montanari,et al.  Digital detection and fuzzy classification of partial discharge signals , 2002 .

[29]  Xuelong Li,et al.  Nonnegative Multiresolution Representation-Based Texture Image Classification , 2015, ACM Trans. Intell. Syst. Technol..

[30]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[31]  Dacheng Tao,et al.  SCE: A Manifold Regularized Set-Covering Method for Data Partitioning , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[32]  L. Satish,et al.  Partial discharge pattern classification using multilayer neural networks , 1993 .

[33]  Xuelong Li,et al.  Texture Classification and Retrieval Using Shearlets and Linear Regression , 2015, IEEE Transactions on Cybernetics.

[34]  R. Bartnikas,et al.  Trends in partial discharge pattern classification: a survey , 2005, IEEE Transactions on Dielectrics and Electrical Insulation.

[35]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[36]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[38]  Yongli Zhu,et al.  Partial discharge pattern recognition method based on variable predictive model-based class discriminate and partial least squares regression , 2016 .

[39]  B. T. Phung,et al.  Development of computer-based measurements and their application to PD pattern analysis , 1995 .

[40]  Zhuyun Chen,et al.  Machine fault classification using deep belief network , 2016, 2016 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[41]  Scott G. McMeekin,et al.  An investigative study into the sensitivity of different partial discharge φ-q-n pattern resolution sizes on statistical neural network pattern classification , 2016 .

[42]  A. Krivda,et al.  Automated recognition of partial discharges , 1995 .