Real-Time Power Quality Disturbances Detection and Classification System

• Main Authors: abidullah, Noor Athira, Abdullah, Abdul Rahim, Sha'ameri, Ahmad Zuri, Shamsudin, Nur Hazahsha, ahmad, Nur Hafizatul Tul Huda, JOPRI, MOHD HATTA
• Format: Article
• Language: English
• Published: International Digital Organization for Scientific Information 2014
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utem.edu.my/id/eprint/14370/2/2014_Journal_WASJ_Real-Time_Power_Quality_Disturbances_Detection_and_Classification.pdf; http://eprints.utem.edu.my/id/eprint/14370/; http://idosi.org/wasj/wasj32(8)14/23.pdf

Power quality disturbances present noteworthy ramifications on electricity consumers, which can affect manufacturing process, causing malfunction of equipment and inducing economic losses. Thus, an automated system is required to identify and classify the signals for diagnosis purposes. The development of power quality disturbances detection and classification system using linear time-frequency distribution (TFD) technique which is spectrogram is presented in this paper. The TFD is used to represent the signals in time-frequency representation (TFR), hence it is handy for analyzing power quality disturbances. The signal parameters such as instantaneous of RMS voltage, RMS fundamental voltage, total waveform distortion (TWD), total harmonic distortion (THD) and total non-harmonic distortion (TnHD) are estimated from the TFR to identify the characteristic of the signals. The signal characteristics are then served as the input for signal classifier to classify power quality disturbances. Referring to IEEE Std. 1159-2009, the power quality disturbances such as swell, sag, interruption, harmonic and interharmonic are discussed. Standard power line measurements, like voltage and current in RMS, active power, reactive power, apparent power, power factor and frequency are also calculated. To verify the performance of the system, power quality disturbances with various characteristics will be generated and tested. The system has been classified with 100 data at SNR from 0dB to 40dB and the outcomes imply that the system gives 100 percent accuracy of power quality disturbances classification at 34dB of SNR. Since the low absolute percentage error present, the system achieves highly accurate system and suitable for power quality detection and classification purpose.