Cable Incipient Fault Identification with a Sparse Autoencoder and a Deep Belief Network

Incipient faults in power cables are a serious threat to power safety and are difficult to accurately identify. The traditional pattern recognition method based on feature extraction and feature selection has strong subjectivity. If the key feature information cannot be extracted accurately, the recognition accuracy will directly decrease. To accurately identify incipient faults in power cables, this paper combines a sparse autoencoder and a deep belief network to form a deep neural network, which relies on the powerful learning ability of the neural network to classify and identify various cable fault signals, without requiring preprocessing operations for the fault signals. The experimental results demonstrate that the proposed approach can effectively identify cable incipient faults from other disturbances with a similar overcurrent phenomenon and has a higher recognition accuracy and reliability than the traditional pattern recognition method.

[1]  Meiqin Liu,et al.  Data-Based Line Trip Fault Prediction in Power Systems Using LSTM Networks and SVM , 2018, IEEE Access.

[2]  Jun Ueda,et al.  Support Vector Machine classification of muscle cocontraction to improve physical human-robot interaction , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[4]  Nina F. Thornhill,et al.  Real-Time Detection of Power System Disturbances Based on $k$ -Nearest Neighbor Analysis , 2017, IEEE Access.

[5]  T. Czaszejko,et al.  Conditions of discharge-free operation of XLPE insulated power cable systems , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[6]  Seong-Whan Lee,et al.  Latent feature representation with stacked auto-encoder for AD/MCI diagnosis , 2013, Brain Structure and Function.

[7]  Zhihan Xu,et al.  Detection of Incipient Faults in Distribution Underground Cables , 2010, IEEE Transactions on Power Delivery.

[8]  Rui Zhang,et al.  Learning object classes from image thumbnails through deep neural networks , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Teymoor Ghanbari,et al.  Kalman filter based incipient fault detection method for underground cables , 2015 .

[10]  Geoffrey E. Hinton.  Deep belief networks , 2009, Scholarpedia.

[11]  W. H. Kersting,et al.  Radial distribution test feeders , 1991, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[12]  Justin Salamon,et al.  Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification , 2016, IEEE Signal Processing Letters.

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

[14]  Ehud D. Karnin,et al.  A simple procedure for pruning back-propagation trained neural networks , 1990, IEEE Trans. Neural Networks.

[15]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[16]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[17]  L. A. Kojovic,et al.  Sub-cycle detection of incipient cable splice faults to prevent cable damage , 2000, 2000 Power Engineering Society Summer Meeting (Cat. No.00CH37134).

[18]  Jun Li,et al.  Deep Convolutional Neural Network with Independent Softmax for Large Scale Face Recognition , 2016, ACM Multimedia.

[19]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[20]  Shan Suthaharan,et al.  Machine Learning Models and Algorithms for Big Data Classification , 2016 .

[21]  U. Rajendra Acharya,et al.  Tunable-Q Wavelet Transform Based Multivariate Sub-Band Fuzzy Entropy with Application to Focal EEG Signal Analysis , 2017, Entropy.

[22]  Seref Sagiroglu,et al.  A comprehensive visualized roadmap to gain new insights , 2017, 2017 International Conference on Computer Science and Engineering (UBMK).

[23]  Xiaomin Li,et al.  Fuel-Type Identification Using Joint Probability Density Arbiter and Soft-Computing Techniques , 2012, IEEE Transactions on Instrumentation and Measurement.

[24]  Mark W. White,et al.  A neural network approach to the detection of incipient faults on power distribution feeders , 1990 .

[25]  Yindi Jing,et al.  Multicycle Incipient Fault Detection and Location for Medium Voltage Underground Cable , 2017, IEEE Transactions on Power Delivery.

[26]  N.D. Hatziargyriou,et al.  Application of Machine Learning on Power System Dynamic Security Assessment , 2007, 2007 International Conference on Intelligent Systems Applications to Power Systems.