Power Quality Disturbances Recognition Using Modified S Transform and Parallel Stack Sparse Auto-encoder

Abstract The effective automatic recognition and classification of power quality (PQ) disturbance is of significance to the control of power grid pollution before any reasonable solution is taken. In this paper, a novel method to PQ disturbances recognition is proposed based on the modified S transform (MST) and parallel stacked sparse auto-encoder (PSSAE). A Kaiser window is used in MST for a better energy concentration in time-frequency matrix. Thereafter, not only the time-frequency matrix but also the Fourier transform spectrum is utilized to automatically extract features, as input of the two sub-model in PSSAE. Furthermore, the dimensionality reduction and visual analysis of features are achieved as an example. The recognition of PQ disturbances is then identified with the softmax classifier. The effectiveness and robustness of the proposed algorithm is validated by conducting a series of experiments with different types of single and combined signals.

[1]  Mrutyunjaya Sahani,et al.  Automatic Power Quality Events Recognition Based on Hilbert Huang Transform and Weighted Bidirectional Extreme Learning Machine , 2018, IEEE Transactions on Industrial Informatics.

[2]  Paolo Remagnino,et al.  Multi-Organ Plant Classification Based on Convolutional and Recurrent Neural Networks , 2018, IEEE Transactions on Image Processing.

[3]  Ruqiang Yan,et al.  A sparse auto-encoder-based deep neural network approach for induction motor faults classification , 2016 .

[4]  Pradipta Kishore Dash,et al.  Detection and characterization of multiple power quality disturbances with a fast S-transform and decision tree based classifier , 2013, Digit. Signal Process..

[5]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[6]  Jun Hu,et al.  A Framework for Automatically Extracting Overvoltage Features Based on Sparse Autoencoder , 2018, IEEE Transactions on Smart Grid.

[7]  Arturo Garcia-Perez,et al.  Detection and Classification of Single and Combined Power Quality Disturbances Using Neural Networks , 2014, IEEE Transactions on Industrial Electronics.

[8]  Qinghua Hu,et al.  Pattern-Based Wind Speed Prediction Based on Generalized Principal Component Analysis , 2014, IEEE Transactions on Sustainable Energy.

[9]  Yakup Demir,et al.  Automatic classification of power quality events and disturbances using wavelet transform and support vector machines , 2012 .

[10]  Zhaosheng Teng,et al.  Measurement of power system harmonic based on adaptive Kaiser self-convolution window , 2016 .

[11]  Wei Xiong,et al.  Stacked Convolutional Denoising Auto-Encoders for Feature Representation , 2017, IEEE Transactions on Cybernetics.

[12]  Zhaosheng Teng,et al.  Fast S-Transform for Time-Varying Voltage Flicker Analysis , 2014, IEEE Transactions on Instrumentation and Measurement.

[13]  Mahmoud Pesaran,et al.  A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances , 2015 .

[14]  Ranjana Sodhi,et al.  A Modified S-Transform and Random Forests-Based Power Quality Assessment Framework , 2018, IEEE Transactions on Instrumentation and Measurement.

[15]  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.

[16]  Nand Kishor,et al.  Optimal feature and decision tree based classification of power quality disturbances in distributed generation systems , 2014, 2014 IEEE PES General Meeting | Conference & Exposition.

[17]  Shahrokh Valaee,et al.  Locomotion Activity Recognition Using Stacked Denoising Autoencoders , 2018, IEEE Internet of Things Journal.

[18]  Trapti Jain,et al.  Tunable-Q Wavelet Transform and Dual Multiclass SVM for Online Automatic Detection of Power Quality Disturbances , 2018, IEEE Transactions on Smart Grid.

[19]  Math Bollen,et al.  Time-frequency and time-scale domain analysis of voltage disturbances , 2000 .

[20]  Jin Jiang,et al.  S-Transform with Frequency Dependent Kaiser Window , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[21]  Ljubisa Stankovic,et al.  Auto-term representation by the reduced interference distributions: a procedure for kernel design , 1996, IEEE Trans. Signal Process..

[22]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[23]  M. Sabarimalai Manikandan,et al.  Detection and Classification of Power Quality Disturbances Using Sparse Signal Decomposition on Hybrid Dictionaries , 2015, IEEE Transactions on Instrumentation and Measurement.

[24]  Ming Zhang,et al.  A Real-Time Power Quality Disturbances Classification Using Hybrid Method Based on S-Transform and Dynamics , 2013, IEEE Transactions on Instrumentation and Measurement.

[25]  D. Gabor,et al.  Theory of communication. Part 1: The analysis of information , 1946 .

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

[27]  S. Mishra,et al.  Detection and Classification of Power Quality Disturbances Using S-Transform and Probabilistic Neural Network , 2008, IEEE Transactions on Power Delivery.

[28]  Sovan Dalai,et al.  Diagnosis of Power Quality Events Based on Detrended Fluctuation Analysis , 2018, IEEE Transactions on Industrial Electronics.

[29]  Jianzhong Wu,et al.  Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images , 2016, IEEE Transactions on Medical Imaging.

[30]  Rodney A. Kennedy,et al.  Kaiser window based kernel for time-frequency distributions , 2009 .

[31]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.