Pattern Recognition of DC Partial Discharge on XLPE Cable Based on ADAM-DBN

Pattern recognition of DC partial discharge (PD) receives plenty of attention and recent researches mainly focus on the static characteristics of PD signals. In order to improve the recognition accuracy of DC cable and extract information from PD waveforms, a modified deep belief network (DBN) supervised fine-tuned by the adaptive moment estimation (ADAM) algorithm is proposed to recognize the four typical insulation defects of DC cable according to the PD pulse waveforms. Moreover, the effect of the training sample set size on recognition accuracy is analyzed. Compared with naive Bayes (NB), K-nearest neighbor (KNN), support vector machine (SVM), and back propagation neural networks (BPNN), the ADAM-DBN method has higher accuracy on four different defect types due to the excellent ability in terms of the feature extraction of PD pulse waveforms. Moreover, the increase of training sample set size would lead to the increase of recognition accuracy within a certain range.

[1]  D. Liang,et al.  A Cost-Effective Technique for PD Testing of MV Cables Under Combined AC and Damped AC Voltage , 2018, IEEE Transactions on Power Delivery.

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

[3]  Yacine Oussar,et al.  Partial discharges and noise classification under HVDC using unsupervised and semi-supervised learning , 2020 .

[4]  Hui Ma,et al.  Statistical learning techniques and their applications for condition assessment of power transformer , 2012, IEEE Transactions on Dielectrics and Electrical Insulation.

[5]  Yigang He,et al.  Transformer Incipient Hybrid Fault Diagnosis Based on Solar-Powered RFID Sensor and Optimized DBN Approach , 2019, IEEE Access.

[6]  U. Fromm,et al.  Interpretation of partial discharges at dc voltages , 1995 .

[7]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[8]  Yang Xu,et al.  Special requirements of high frequency current transformers in the on-line detection of partial discharges in power cables , 2016, IEEE Electrical Insulation Magazine.

[9]  M. Salama,et al.  PD pattern recognition with neural networks using the multilayer perceptron technique , 1993 .

[10]  Yong Qian,et al.  Partial discharge pattern recognition of XLPE cables at DC voltage based on the compressed sensing theory , 2017, IEEE Transactions on Dielectrics and Electrical Insulation.

[11]  Yigang He,et al.  Analog Circuit Incipient Fault Diagnosis Method Using DBN Based Features Extraction , 2018, IEEE Access.

[12]  Fang Liu,et al.  POL-SAR Image Classification Based on Wishart DBN and Local Spatial Information , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[13]  David Birtwhistle,et al.  Condition assessment of XLPE cable insulation using short-time polarisation and depolarisation current measurements , 2008 .

[14]  Kenji Kaminaga,et al.  Development of 500-kV XLPE cables and accessories for long-distance underground transmission lines. V. Long-term performance for 500-kV XLPE cables and joints , 1996 .

[15]  B. Gregory.  Cable technology and applications in the 21st century , 2000 .

[16]  Yacine Oussar,et al.  Feature extraction and ageing state recognition using partial discharges in cables under HVDC , 2020, Electric Power Systems Research.