An intelligent algorithm for autorecognition of power system faults using superlets. (June 2021)

• Record Type: Journal Article
• Authors: Srikanth, Pullabhatla; Koley, Chiranjib
• Is Part Of: Sustainable energy, grids and networks. Volume 26(2021)
• Publication Date: 2021-06
• Subjects: Power system faults -- Identification -- Signal processing -- time–frequency​ technique -- Artificial intelligence -- Support Vector Machine; Renewable energy sources -- Periodicals; Smart power grids -- Periodicals; Electric power systems -- Periodicals; 333.794
• DOI: 10.1016/j.segan.2021.100450
• Languages: English
• ISSNs: 2352-4677

Abstract

Abstract: A time–frequency resolution technique based recognition of power system faults is proposed in the present work. Superlet transformation, a modified and super-resolution form of the wavelet transform, has been used to recognize the type of power system faults occurring in an interconnected power system. The Superlets were tested for sample power system disturbances and found advantageous. An IEEE-9 Bus system has been used to implement the proposed technique wherein it was observed that unique signatures were obtained for each type of fault. Further, to automatically recognize the type of power system faults, a Support Vector Machine (SVM) classifier has been introduced. The SVM is provided with the inputs from the extracted parameters of the proposed Superlets technique. It was found that the proposed methodology of Superlets with SVM has excelled in comparison with other techniques and provided 100% accuracy in the classification of all the events considered.