An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

Current transformer (CT) saturation is one of the significant problems for protection engineers. If CT saturation is not tackled properly, it can cause a disastrous effect on the stability of the power system, and may even create a complete blackout. To cope with CT saturation properly, an accurate detection or classification should be preceded. Recently, deep learning (DL) methods have brought a subversive revolution in the field of artificial intelligence (AI). This paper presents a new DL classification method based on unsupervised feature extraction and supervised fine-tuning strategy to classify the saturated and unsaturated regions in case of CT saturation. In other words, if protection system is subjected to a CT saturation, proposed method will correctly classify the different levels of saturation with a high accuracy. Traditional AI methods are mostly based on supervised learning and rely heavily on human crafted features. This paper contributes to an unsupervised feature extraction, using autoencoders and deep neural networks (DNNs) to extract features automatically without prior knowledge of optimal features. To validate the effectiveness of proposed method, a variety of simulation tests are conducted, and classification results are analyzed using standard classification metrics. Simulation results confirm that proposed method classifies the different levels of CT saturation with a remarkable accuracy and has unique feature extraction capabilities. Lastly, we provided a potential future research direction to conclude this paper.

[1]  Soon-Ryul Nam,et al.  Phasor Estimation in the Presence of DC Offset and CT Saturation , 2009, IEEE Transactions on Power Delivery.

[2]  Ridha Djemal,et al.  Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique , 2016, Brain sciences.

[3]  Derek C. Rose,et al.  Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] , 2010, IEEE Computational Intelligence Magazine.

[4]  Jin Hur,et al.  Accurate Short-Term Power Forecasting of Wind Turbines: The Case of Jeju Island’s Wind Farm , 2017 .

[5]  Hongseok Kim,et al.  Deep Neural Network Based Demand Side Short Term Load Forecasting , 2016 .

[6]  David He,et al.  Detection of Pitting in Gears Using a Deep Sparse Autoencoder , 2017 .

[7]  W. W. L. Keerthipala,et al.  Improved simulation models for current and voltage transformers in relay studies , 1992 .

[8]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

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

[10]  Pei Liu,et al.  A series multiresolution morphological gradient-based criterion to identify CT saturation , 2006, IEEE Transactions on Power Delivery.

[11]  Y. Sheng,et al.  Decision Trees and Wavelet Analysis for Power Transformer Protection , 2002, IEEE Power Engineering Review.

[12]  Pei Liu,et al.  A series multiresolution morphological gradient-based criterion to identify CT saturation , 2006 .

[13]  Carlos A. Duque,et al.  Current-Transformer Saturation Detection Using Savitzky-Golay Filter , 2016, IEEE Transactions on Power Delivery.

[14]  Khoi Vu,et al.  An efficient compensation algorithm for current transformer saturation effects , 2004, IEEE Transactions on Power Delivery.

[15]  Xian-Bo Wang,et al.  Representational Learning for Fault Diagnosis of Wind Turbine Equipment: A Multi-Layered Extreme Learning Machines Approach , 2016 .

[16]  Stan Szpakowicz,et al.  Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation , 2006, Australian Conference on Artificial Intelligence.

[17]  Seyed Hossein Hosseinian,et al.  Current Transformer Saturation Detection Using Gaussian Mixture Models , 2013 .

[18]  Subhojit Ghosh,et al.  Protection scheme for power transmission lines based on SVM and ANN considering the presence of non-linear loads , 2017 .

[19]  E.C. Segatto,et al.  A differential relay for power transformers using intelligent tools , 2006, IEEE Transactions on Power Systems.

[20]  Mehdi Vakilian,et al.  Current-Transformer Saturation Compensation for Transformer Differential Relays , 2015, IEEE Transactions on Power Delivery.

[21]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[22]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[23]  Junyong Wu,et al.  Using Trajectory Clusters to Define the Most Relevant Features for Transient Stability Prediction Based on Machine Learning Method , 2016 .

[24]  E.C. Segatto,et al.  A power transformer protection with recurrent ANN saturation correction , 2005, IEEE Power Engineering Society General Meeting, 2005.

[25]  M.A. Rahman,et al.  Modeling and protection of a three-phase power transformer using wavelet packet transform , 2005, IEEE Transactions on Power Delivery.

[26]  Zahra Moravej,et al.  Artificial Intelligence Based Approach for Identification of Current Transformer Saturation from Faults in Power Transformers , 2014 .

[27]  Manoj Tripathy,et al.  Power Transformer Differential Protection Based on Neural Network Principal Component Analysis, Harmonic Restraint and Park's Plots , 2012, Adv. Artif. Intell..

[28]  Bhavesh R. Bhalja,et al.  Fault discrimination scheme for power transformer using random forest technique , 2016 .

[29]  Nagy I. Elkalashy,et al.  Detection of Partial Saturation and Waveform Compensation of Current Transformers , 2015, IEEE Transactions on Power Delivery.

[30]  Jianqiang Yi,et al.  Building Energy Consumption Prediction: An Extreme Deep Learning Approach , 2017 .

[31]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[32]  Ali Akbar Abdoos,et al.  Intelligent busbar protection scheme based on combination of support vector machine and S-transform , 2017 .

[33]  Shukai Duan,et al.  Self-Taught Learning Based on Sparse Autoencoder for E-Nose in Wound Infection Detection , 2017, Sensors.

[34]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[35]  Peter Crossley,et al.  Design and evaluation of an algorithm for detecting current transformer saturation , 2004 .