Abstract
Power utility providers and power industry service providers face a significant challenge in identifying the type of Power Quality Disturbances (PQD) automatically. This paper discusses a method to classify PQD using signal decomposition, statistical analysis and machine learning. Firstly, Discrete Wavelet Transform (DWT) is applied on the generated PQD signals to decompose the signal to obtain its representation in time and frequency domain. Secondly, first and second order statistical parameters are computed on the selected sub-band of DWT. These parameters are used as features vector for the machine learning based classifier. Our database consists of 2400 generated signals of PQD, which were divided into train and test set. Another set of noise corrupted signal database was generated to evaluate the capability of the system. SVM using quadratic kernel was selected as the classifier of the Power Quality Disturbances feature vector. Comparisons were also made with other types of classifiers and other types of mother wavelet filter functions. The results show that the combination of DWT and SVM managed to classify Power Quality Disturbances with high accuracy and has a strong resistance towards noise.
Highlights
Pure sinusoidal waveforms of voltage and current at 50 Hz (Malaysia’s power line frequency) without any disruptions or defect in waveform at the electrical incoming point is an important aspect of power quality
If Power Quality Disturbances (PQD) are not eliminated, it can cause severe damage which leads to failures or breakdown of loads that are sensitive in power systems
An example of widely used feature extraction tool in digital signal processing is Discrete Wavelet Transform (DWT), which was applied by Zhao et al [8], for decomposing the PQD signal into 8 layers using
Summary
Pure sinusoidal waveforms of voltage and current at 50 Hz (Malaysia’s power line frequency) without any disruptions or defect in waveform at the electrical incoming point is an important aspect of power quality. Feature extraction through signal transforms and statistical analysis with pattern recognition using machine learning methods are the most important steps in classifying PQD [7]. An example of widely used feature extraction tool in digital signal processing is Discrete Wavelet Transform (DWT), which was applied by Zhao et al [8], for decomposing the PQD signal into 8 layers using. Chang et al [9] introduced a hybrid approach using DWT with Discrete Fourier Transform (DFT) for extracting salient features from PQD. Hilbert Huang Transform was introduced by Saeed et al [10] as a tool to extract the features from PQD This signal analysis algorithm decomposes the signal into Intrinsic Mode Functions which provide the user with amplitude and frequency data.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Engineering & Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
