Partial Discharge Spectrogram Data Augmentation based on Generative Adversarial Networks

High voltage insulators are critical elements in power distribution and transmission systems, since their failure may represent losses in power quality and system reliability, leading to faults which bring problems to both consumer and electric utilities. Insulators in operation are subjected to all kinds of pollution which may cause the formation of dry bands when in presence of moisture, which leads to the formation of partial discharges which, in turn, causes degradation and aging of the surface material. Partial discharges origin can be identified by the pattern of their pulses. Machine learning algorithms are one of the most useful and efficient solutions for pattern recognition and classification tasks. In this paper, a methodology is proposed for data augmentation of the training set for an artificial neural network by means of generative adversarial networks.

[1]  Ron J. Weiss,et al.  Speech acoustic modeling from raw multichannel waveforms , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Martin D. Judd,et al.  A Convolutional Neural Network-Based Deep Learning Methodology for Recognition of Partial Discharge Patterns from High-Voltage Cables , 2019, IEEE Transactions on Power Delivery.

[3]  WU Yijiang,et al.  Partial Discharge Data Augmentation of High Voltage Cables based on the Variable Noise Superposition and Generative Adversarial Network , 2018, 2018 International Conference on Power System Technology (POWERCON).

[4]  Xiaohua Wang,et al.  Partial discharge patterns recognition with deep Convolutional Neural Networks , 2016, 2016 International Conference on Condition Monitoring and Diagnosis (CMD).

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[7]  Aijun Yang,et al.  Partial Discharge Recognition with a Multi-Resolution Convolutional Neural Network , 2018, Sensors.

[8]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[9]  Yue Hu,et al.  Partial Discharge Pattern Recognition with Data Augmentation based on Generative Adversarial Networks , 2018, 2018 Condition Monitoring and Diagnosis (CMD).

[10]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[11]  A. Enis Çetin,et al.  Deep Convolutional Generative Adversarial Networks Based Flame Detection in Video , 2019, ArXiv.