Automatic Detection of Power Quality Disturbance Using Convolutional Neural Network Structure with Gated Recurrent Unit

Power quality disturbance (PQD) is essential for devices consuming electricity and meeting today’s energy trends. This study contains an effective artificial intelligence (AI) framework for analyzing single or composite defects in power quality. A convolutional neural network (CNN) architecture, which has an output powered by a gated recurrent unit (GRU), is designed for this purpose. The proposed framework first obtains a matrix using a short-time Fourier transform (STFT) of PQD signals. This matrix contains the representation of the signal in the time and frequency domains, suitable for CNN input. Features are automatically extracted from these matrices using the proposed CNN architecture without preprocessing. These features are classified using the GRU. The performance of the proposed framework is tested using a dataset containing a total of seven single and composite defects. The amount of noise in these examples varies between 20 and 50 dB. The performance of the proposed method is higher than current state-of-the-art methods. The proposed method obtained 98.44% ACC, 98.45% SEN, 99.74% SPE, 98.45% PRE, 98.45% F1-score, 98.19% MCC, and 93.64% kappa metric. A novel power quality disturbance (PQD) system has been proposed, and its application has been represented in our study. The proposed system could be used in the industry and factory.

[1]  Bhupendra Gupta,et al.  Visibility improvement and mass segmentation of mammogram images using quantile separated histogram equalisation with local contrast enhancement , 2019, CAAI Trans. Intell. Technol..

[2]  José Seixas,et al.  A method based on independent component analysis for single and multiple power quality disturbance classification , 2015 .

[3]  Miguel Angel Rodriguez,et al.  Power Quality Disturbance Classification via Deep Convolutional Auto-Encoders and Stacked LSTM Recurrent Neural Networks , 2020, 2020 International Conference on Smart Energy Systems and Technologies (SEST).

[4]  Dianguo Xu,et al.  Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest , 2016, Entropy.

[5]  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.

[6]  Utkarsh Singh,et al.  A new optimal feature selection scheme for classification of power quality disturbances based on ant colony framework , 2019, Appl. Soft Comput..

[7]  Seyed Hossein Hosseinian,et al.  Power quality disturbance classification using a statistical and wavelet-based Hidden Markov Model with Dempster–Shafer algorithm , 2013 .

[8]  M. Uyar,et al.  An effective wavelet-based feature extraction method for classification of power quality disturbance signals , 2008 .

[9]  Prasanta Kundu,et al.  Power quality disturbance classification employing S-transform and three-module artificial neural network , 2014 .

[10]  Dilbag Singh,et al.  Multiobjective evolutionary optimization techniques based hyperchaotic map and their applications in image encryption , 2020, Multidimensional Systems and Signal Processing.

[11]  Manohar Mishra,et al.  Power quality disturbance detection and classification using signal processing and soft computing techniques: A comprehensive review , 2019, International Transactions on Electrical Energy Systems.

[12]  Yang Xu,et al.  Human Activity Recognition and Embedded Application Based on Convolutional Neural Network , 2020, Journal of Artificial Intelligence and Technology.

[13]  Yanbo Che,et al.  Power Quality Disturbance Classification Based on DWT and Multilayer Perceptron Extreme Learning Machine , 2019 .

[14]  Abdulhamit Subasi,et al.  Power Quality Event Detection Using FAWT and Bagging Ensemble Classifier , 2019, 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe).

[15]  Daiyu Jiang,et al.  A Fully Convolutional Neural Network-based Regression Approach for Effective Chemical Composition Analysis Using Near-infrared Spectroscopy in Cloud , 2021 .

[16]  B. K. Panigrahi,et al.  Optimal feature selection for classification of power quality disturbances using wavelet packet-based fuzzy k-nearest neighbour algorithm , 2009 .

[17]  F. Choong,et al.  Expert System for Power Quality Disturbance Classifier , 2007, IEEE Transactions on Power Delivery.

[18]  Jianmin Li,et al.  Detection and Classification of Power Quality Disturbances Using Double Resolution S-Transform and DAG-SVMs , 2016, IEEE Transactions on Instrumentation and Measurement.

[19]  B. Kiruthiga,et al.  Detection and classification of power quality disturbances or events by adaptive NFS classifier , 2019, Soft Computing.

[20]  Fei Shen,et al.  Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks , 2018, IEEE Transactions on Industrial Electronics.

[21]  Misael Lopez-Ramirez,et al.  EMD-Based Feature Extraction for Power Quality Disturbance Classification Using Moments , 2016 .

[22]  Aslam P. Memon,et al.  A new optimal feature selection algorithm for classification of power quality disturbances using discrete wavelet transform and probabilistic neural network , 2017 .

[23]  Rengang Yang,et al.  Power-Quality Disturbance Recognition Using S-Transform , 2007, IEEE Transactions on Power Delivery.

[24]  Chun-Yao Lee,et al.  Optimal Feature Selection for Power-Quality Disturbances Classification , 2011, IEEE Transactions on Power Delivery.

[25]  Poras Khetarpal,et al.  A critical and comprehensive review on power quality disturbance detection and classification , 2020, Sustain. Comput. Informatics Syst..

[26]  Ping Wang,et al.  Power Quality Disturbance Classification Using the S-Transform and Probabilistic Neural Network , 2017 .

[27]  Şaban Öztürk,et al.  A healthcare evaluation system based on automated weighted indicators with cross-indicators based learning approach in terms of energy management and cybersecurity , 2020, Int. J. Medical Informatics.

[28]  T. Lobos,et al.  Automated classification of power-quality disturbances using SVM and RBF networks , 2006, IEEE Transactions on Power Delivery.

[29]  Manjit Kaur,et al.  Deep Neural Network-Based Screening Model for COVID-19-Infected Patients Using Chest X-Ray Images , 2020, Int. J. Pattern Recognit. Artif. Intell..

[30]  Manjit Kaur,et al.  Rapid COVID-19 diagnosis using ensemble deep transfer learning models from chest radiographic images , 2020, Journal of Ambient Intelligence and Humanized Computing.

[31]  R. Sukanesh,et al.  Power quality disturbance classification using Hilbert transform and RBF networks , 2010, Neurocomputing.

[32]  Maria Cristina Piccirilli,et al.  A Comparison of Power Quality Disturbance Detection and Classification Methods Using CNN, LSTM and CNN-LSTM , 2020, Applied Sciences.

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

[34]  Yue Shen,et al.  Complex power quality disturbances classification via curvelet transform and deep learning , 2018, Electric Power Systems Research.

[35]  E.F. El-Saadany,et al.  Power quality disturbance classification using the inductive inference approach , 2004, IEEE Transactions on Power Delivery.

[36]  Tong Lu,et al.  Graphology based handwritten character analysis for human behaviour identification , 2020, CAAI Trans. Intell. Technol..

[37]  Şaban Öztürk,et al.  Stacked auto-encoder based tagging with deep features for content-based medical image retrieval , 2020, Expert Syst. Appl..

[38]  Dinh Thanh Viet,et al.  Classification of power quality disturbances using wavelet transform and K-nearest neighbor classifier , 2013, 2013 IEEE International Symposium on Industrial Electronics.

[39]  Lassi Aarniovuori,et al.  Classification of Power Quality Disturbances Using Wigner-Ville Distribution and Deep Convolutional Neural Networks , 2019, IEEE Access.

[40]  Umamani Subudhi,et al.  Detection and classification of power quality disturbances using GWO ELM , 2021, J. Ind. Inf. Integr..

[41]  Guesh Dagnew,et al.  Deep learning approach for microarray cancer data classification , 2020, CAAI Trans. Intell. Technol..

[42]  Pradipta Kishore Dash,et al.  Measurement and Classification of Simultaneous Power Signal Patterns With an S-Transform Variant and Fuzzy Decision Tree , 2013, IEEE Transactions on Industrial Informatics.

[43]  Jian Yao,et al.  Power quality disturbance classification based on rule-based and wavelet-multi-resolution decomposition , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.

[44]  Şaban Öztürk,et al.  Gastrointestinal tract classification using improved LSTM based CNN , 2020, Multimedia Tools and Applications.

[45]  Dilbag Singh,et al.  Multi-modality medical image fusion technique using multi-objective differential evolution based deep neural networks , 2020, Journal of ambient intelligence and humanized computing.

[46]  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.

[47]  Dilbag Singh,et al.  Color image encryption using minimax differential evolution-based 7D hyper-chaotic map , 2020, Applied Physics B.