Identification of the Source of Power Quality Degradation Using Signature Extraction from Voltage Waveforms
This paper provides the understanding of features and method used for classifying the root cause of the fault event using those unique features. In particular, the paper focuses on identification of fault caused by the animal, lighting, tree, equipment and vehicle events. Different features are extracted to provide the input to neural network. For extracting features voltage and current samples collected during the fault at the monitoring, stations were analyzed. Artificial neural network with multilayer perceptron model is trained for the classification. Features were calculated using 154 real-world fault events and applied to the classifier. It estimated to be having 76.47% of classification rate.
KeywordsDiagnosis (faults) Power quality disturbance Wavelet decomposition Artificial neural network Classification
- 2.Kulkarni S, Lee D, Allen AJ, Santoso S, Short TA (2010) Waveform characterization of animal contact, tree contact, and lightning induced faults. In: IEEE power and energy society general meeting, IEEE, July 2010, pp 1–7Google Scholar
- 4.Nunez VB, Kulkarni S, Santoso S, Joaquim MF (2010) Feature analysis and classification methodology for overhead distribution fault events. In: IEEE power and energy society general meeting, IEEE, July 2010, pp 1–8Google Scholar
- 5.Nunez VA, Kulkarni S, Santoso S, Melendez J (2010) SVM-based classification methodology for overhead distribution fault events. In: 14th international conference on harmonics and quality of Power (ICHQP), IEEE, 26 Sep 2010, pp 1–6Google Scholar
- 6.Kaewarsa S (2009) November Classification of power quality disturbances using S-transform based artificial neural networks. In: 2009 IEEE international conference on intelligent computing and intelligent systems (ICIS), vol 1. IEEE, pp 566–570Google Scholar