Feature Extraction and Classification of Power Quality Events Based on Fast Fourier Transformation and Artificial Neural Network

Year 2021, Volume: 4 Issue: 1, 14 - 21, 01.01.2021

Ezgi Güney , Çağri Kocaman

https://doi.org/10.34248/bsengineering.817238

Abstract

This paper presents an effective method for detection and classification of Power Quality Events (PQE), based on Fast Fourier Transformation (FFT) for event identification and Artificial Neural Network (ANN) technique for classifying of these events. Firstly, synthetic data such as pure sine as a reference, voltage sag, voltage swell, flicker, transient, voltage with harmonics are created in MATLAB based on TS EN 50160 standard. Database with 480 PQE waveforms is generated with 80 samples for each of the 6 types of the waveform with randomly different event amplitude, beginning occurrence time, time duration, frequency component and angle according to a type of event. FFT is used to extract features of the events by decomposing the signal. Then, 16384×480 data are reduced to 480×480 data by applying Principal Component Analysis (PCA) that is prevent over-learning, obtain less runtime using less computing power and reduce data and storage space. Finally, a total of 480 PQE are classified by using ANN. 336 of these PQE are used for training cluster, 72 of PQE are used for verification and the remaining 72 are used for testing. Firstly, the ANN has been trained correctly. The classification performance of the ANN in PQE has been examined by inserting the test into ANN. The performance of ANN is 99.8% for these PQE. The purpose of this research is to provide an artificial intelligence assistant that can fast and accurately advise the power system operators for the networks, and the results also show that the goal has been achieved.

Keywords

Power quality event, Feature extrac, Classification, FFT, PCA, ANN

References

• Abdelsalam AA, Eldesouky AA, Sallam AA. 2012. Characterization of power quality events using hybrid technique of linear Kalman filter and fuzzy-expert system. Electric power systems Research, 83: 41-50.
• Alshahrani S, Abbod M, Taylor G. 2016, September. Detection and classification of power quality events based on Hilbert-Huang transform and feed forward neural networks. In 2016 51st International Universities Power Engineering Conference (UPEC), 1-6, IEEE.
• Atapattu S, Tellambur C, Jiang H. 2010. Analysis of area under the ROC curve of energy detection. IEEE Transact Wireless Com, 9(3): 1216-1225.
• Changjie Z, Buxiang Z. 2015. The medium and long term power load forecasting model based on PCA-SVM. Electrical Measurt Instrument, (9): 2.
• Das D, Chakravorti T, Dash PK. 2017. Hilbert huang transform with fuzzy rules for feature selection and classification of power quality events. In 2017 4th IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics (UPCON), 439-445, IEEE.
• Daud K, Abidin AF, Ismail AP. 2017, August. Voltage sags and transient detection and classification using half/one-cycle windowing techniques based on continuous s-transform with neural network. In AIP Conference Proceedings, 1875: 030017.
• Deokar SA, Waghmare LM. 2014. Integrated DWT–FFT approach for detection and classification of power quality events. Int J Electrical Power Energy Sys, 61: 594-605.
• Feilat EA, Aljarrah RR, Rifai MB. 2017. Detection and classification of voltage variations using combined envelope-neural network based approach. Jordan J Electrical Eng, 3: 113.
• Ipinnimo O, Chowdhury S. 2013. ANN-based classification system for different windows of voltage dips in a power network. In 2013 48th International Universities' Power Engineering Conference (UPEC), 1-6, IEEE.
• Jamali S, Farsa AR, Ghaffarzadeh N. 2018. Identification of optimal features for fast and accurate classification of power quality events. Measurement, 116: 565-574.
• Karasu S, Saraç Z. 2018. Classification of power quality events signals with pattern recognition methods by using Hilbert transform and genetic algorithms. In 2018 26th Signal Processing and Communications Applications Conference (SIU), 1-4, IEEE.
• Khokhar S, Zin AAM, Memon A P, Mokhtar AS. 2017. A new optimal feature selection algorithm for classification of power quality events using discrete wavelet transform and probabilistic neural network. Measurement, 95: 246-259.
• Kow KW, Wong YW, Rajkumar RK. 2016. A review on performance of artificial intelligence and conventional method in mitigating PV grid-tied related power quality events. Renew Sustain Energy Reviews, 56: 334-346.
• Kumar R, Singh B, Shahani DT. 2015. Recognition of single-stage and multiple power quality events using Hilbert–Huang transform and probabilistic neural network. Electric Power Comps Sys, 43: 607-619.
• Li J, Teng Z, Tang Q, Song J. 2016. Detection and classification of power quality events using double resolution S-transform and DAG-SVMs. IEEE Transactions on Instrumentation and Measur, 65: 2302-2312.
• Lopez-Ramirez M, Ledesma-Carrillo L, Cabal-Yepez E, Rodriguez-Donate C, Miranda-Vidales H, Garcia-Perez A. 2016. EMD-based feature extraction for power quality event classification using moments. Energies, 9: 565.
• Luo Y, Li K, Li Y, Cai D, Zhao C, Meng Q. 2017. Three-layer bayesian network for classification of complex power quality events. IEEE Transactions on Industrial Informatics, 14: 3997-4006.
• Manjula M, Sarma AVRS. 2010. Classification of voltage sag causes using probabilistic neural network and hilbert–huang transform. Int J Computer App, 975: 8887.
• Naik CA, Kundu P. 2014. Power quality event classification employing S‐transform and three‐module artificial neural network. Int Transactions on Electrical Energy Sys, 24: 1301-1322.
• Peacock JA. 2014. Fourier Analysis. School of Physics and Astronomy, University of Edinburgh, UK.
• Polat K, Güneş S. 2007. Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Applied Mat Comput, 187: 1017-1026.
• Rodríguez A, Aguado JA, Martín F, López JJ, Muñoz F, Ruiz JE. 2012. Rule-based classification of power quality events using S-transform. Electric Power Sys Res, 86: 113-121.
• Sahani M, Dash PK. 2018. Automatic power quality events recognition based on Hilbert Huang transform and weighted bidirectional extreme learning machine. IEEE Trans on Industrial Informatics, 14: 3849-3858.
• Saini MK, Kapoor R. 2012. Classification of power quality events–a review. Int J Electrical Power Energy Sys, 43: 11-19.
• Satao SR, Kankale RS. 2016, August. A new approach for classification of power quality events using S-Transform. In 2016 International Conference on Computing Communication Control and automation (ICCUBEA), 1-4, IEEE.
• Shen Y, Abubakar M, Liu H, Hussain F. 2019. Power quality event monitoring and classification based on improved PCA and Convolution neural network for wind-grid distribution systems. Energies, 12: 1280.
• Shilpa R., Prabhu SS, Puttaswamy PS. 2015, December. Power quality events monitoring using Hilbert-Huang transform and SVM classifier. In 2015 International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), 6-10, IEEE.
• Stoica P, Moses RL. 2005. Spectral analysis of signals. (Vol. 1). Upper Saddle River, NJ: Pearson Prentice Hall, Nigeria.
• Tan RH, Ramachandaramurthy VK. 2010. Numerical model framework of power quality events. European J Sci Res, 43: 30-47.
• Ucar F, Alcin O, Dandil B, Ata F. 2018. Power quality event detection using a fast extreme learning machine. Energies, 11: 145.
• Uyar M, Kaya Y, Ataş M. 2013, April. Classification of power quality events based on S-transform and image processing techniques. In 2013 21st Signal Processing and Communications Applications Conference (SIU), 1-4, IEEE.
• Zweig MH, Campbell G. 1993. Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clinical Chem, 394: 561-577.