A novel three-dimensional deep learning algorithm for classification of power system faults

Abstract A three-dimensional (3D) deep learning algorithm (DLA) has been proposed to classify Power System Faults. The proposed network is novel and requires fewer data to identify the power system faults with very high accuracy. The proposed network overcomes the issue of overfitting due to fewer layers and dropout provision. Also, it can be designed with basic knowledge of deep learning. The input to the DLA is a 4D image split into RGB channels. The 4D image is obtained after transforming the fault currents recorded in an IEEE-9 Bus system to a time-frequency domain. The individual color channel matrix is stored as a 4D matrix and then fed to the DLA to identify the power system fault type. The proposed 3D CNN is trained multiple times by changing the number of epochs and learning rates. The proposed model can classify the type of power system faults with an accuracy of 93.75 and 100% for a dropout value of 0.4 & 0.5. The training-validation sample size is considered as 1600 4D-images for both the dropout values.

[1]  Muhammad Buhari,et al.  Optimal distributed generation planning in distribution networks: A comparison of transmission network models with FACTS , 2019, Engineering Science and Technology, an International Journal.

[2]  Ruben Morales-Menendez,et al.  Signal Processing and Deep Learning Techniques for Power Quality Events Monitoring and Classification , 2019, Electric Power Components and Systems.

[3]  Shouxiang Wang,et al.  A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network , 2019, Applied Energy.

[4]  Wei Qiu,et al.  An Automatic Identification Framework for Complex Power Quality Disturbances Based on Multifusion Convolutional Neural Network , 2020, IEEE Transactions on Industrial Informatics.

[5]  Zesong Fei,et al.  3D-CNN-Based Fused Feature Maps with LSTM Applied to Action Recognition , 2019, Future Internet.

[6]  Yang Liu,et al.  Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization , 2020, Computational Materials Science.

[7]  Madeleine Gibescu,et al.  Deep learning for power system data analysis , 2018 .

[8]  George D. Montanez,et al.  Limits of Transfer Learning , 2020, LOD.

[9]  Mohammad Tahir,et al.  A Strategic and Significant Method for the Optimal Placement of Phasor Measurement Unit for Power System Network , 2020, Symmetry.

[10]  Chen Chen,et al.  An Efficient 3D CNN for Action/Object Segmentation in Video , 2019, BMVC.

[11]  Lalu Mansinha,et al.  Localization of the complex spectrum: the S transform , 1996, IEEE Trans. Signal Process..

[12]  R. G. Stockwell,et al.  S-transform analysis of gravity wave activity from a small scale network of airglow imagers , 1999 .

[13]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Himanshu Sharma,et al.  2D-3D CNN Based Architectures for Spectral Reconstruction from RGB Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[15]  Russ B. Altman,et al.  3D deep convolutional neural networks for amino acid environment similarity analysis , 2017, BMC Bioinformatics.

[16]  Xuebin Xu,et al.  Novel Method Based on Variational Mode Decomposition and a Random Discriminative Projection Extreme Learning Machine for Multiple Power Quality Disturbance Recognition , 2019, IEEE Transactions on Industrial Informatics.

[17]  Feng Li,et al.  A Sequence-to-Sequence Deep Learning Architecture Based on Bidirectional GRU for Type Recognition and Time Location of Combined Power Quality Disturbance , 2019, IEEE Transactions on Industrial Informatics.

[18]  Jing Li.  Parallel two-class 3D-CNN classifiers for video classification , 2017, 2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS).

[19]  Konstantinos Kamnitsas,et al.  Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation , 2016, Medical Image Anal..

[20]  Mustafa Baysal,et al.  Deep learning methods and applications for electrical power systems: A comprehensive review , 2020, International Journal of Energy Research.

[21]  James O' Neill.  Learning To Avoid Negative Transfer in Few Shot Transfer Learning , 2019 .

[22]  Sina Faizollahzadeh Ardabili,et al.  Demand prediction with machine learning models: State of the art and a systematic review of advances , 2019 .

[23]  Marek Dabrowski,et al.  How effective is Transfer Learning method for image classification , 2017, FedCSIS.

[24]  Sanja Fidler,et al.  SurfConv: Bridging 3D and 2D Convolution for RGBD Images , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Yue Shen,et al.  Power Quality Disturbance Monitoring and Classification Based on Improved PCA and Convolution Neural Network for Wind-Grid Distribution Systems , 2019, Energies.

[26]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[27]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[28]  Rehan Khan,et al.  Assessing the Integration of Large-Scale Solar PV to a Nine-Bus Power System , 2019, IOP Conference Series: Earth and Environmental Science.