Share
Export Citation
Automating power quality disturbance analysis using the IPQDA software tool
Hasniaty
Scored 2006 Proceedings of 2006 4th Student Conference on Research and Development Towards Enhancing Research Excellence in the Region
Abstract
Automatic recognition of power quality (PQ) disturbances with regards to PQ monitoring is highly desired by both utilities and commercial customers. This paper presents the development of the intelligent power quality data analysis (IPQDA) software tool for the purpose of automatic disturbance classification. The main capabilities of the software include analysis of disturbance waveforms, classification of various types of PQ disturbances and notification of a disturbance. An important feature of the software is that it can automatically send email or short messaging notifications upon identification of a disturbance so as to alert a system operator of a disturbance. In the software development, the two main tasks performed are feature extraction and automatic disturbance classification. Initially, disturbance waveforms are analyzed using the signal processing techniques such as the linear predictive coding and the fast Fourier transform techniques. The feature extraction process of PQ disturbance waveforms is to project a PQ signal into a low-dimension time frequency representation which is deliberately design for maximizing the separability between classes. The unique features of the PQ disturbances are extracted and used in the intelligent analysis too. The second task is to automatically classify the PQ disturbances into different categories of disturbances based on the features extracted from the processed waveform signal. The classification task was performed by developing a rule based expert system in Visual Basic. To verify the accuracy of the developed software tool, it has been tested with 500 recorded voltage disturbance signals which are obtained from PQ monitoring at various sites. In this paper, the focus is to highlight on the accuracy of the software in automatically classifying the distinct categories of PQ disturbance types such as voltage sag, swell, notching and transient. In addition, a statistical analysis has also been performed to further validate the results obtained.