Back close

Fisher vector encoding for improving the performance of fault diagnosis in a synchronous generator

Publication Type : Journal Article

Publisher : Measurement: Journal of the International Measurement Confederation

Source : Measurement: Journal of the International Measurement Confederation, Elsevier B.V., Volume 111, p.264-270 (2017)

Url : https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026452937&doi=10.1016%2fj.measurement.2017.07.051&partnerID=40&md5=fc24a8cfebf0a4f4240f38b25876d1ff

Keywords : Codes (symbols), Computationally efficient, Electric fault currents, Encoding (symbols), Failure analysis, Fault detection, Feature vectors, Fisher vectors, Higher-dimensional, Inter-turn fault, Linear coding, Linear Support Vector Machines, Sparse coding, Support vector machines, Synchronous generators, Vector spaces, Vectors

Campus : Coimbatore

School : School of Engineering

Center : Computational Engineering and Networking

Department : Mechanical Engineering

Year : 2017

Abstract : In this work, we experiment with Fisher vector encoding to map the feature vectors into a higher dimensional space and use linear support vector machine (SVM) for improving the performance of inter turn fault diagnosis in a 3 kVA synchronous generator. Fisher vector encoding computes the first and second order differences between the feature vectors and Gaussians. We compare the performance of Fisher vector encoding with sparse coding and locality constrained linear coding (LLC). From the experiments and results, we observed that Fisher vector encoding is the most computationally efficient algorithm when compared to feature mapping using sparse coding and locality constrained linear coding (LLC). © 2017 Elsevier Ltd

Cite this Research Publication : R. Gopinath, Kumar, C. S., and Dr. K. I. Ramachandran, “Fisher vector encoding for improving the performance of fault diagnosis in a synchronous generator”, Measurement: Journal of the International Measurement Confederation, vol. 111, pp. 264-270, 2017.

Admissions Apply Now