Detection and Analysis of Acoustic Signals of Power Transformers On-Load Tap Changers for Assessment of Their Faults
Subject Areas : electrical and computer engineering
adel younesi
1
(University of Zanjan)
Abbas Ghayebloo
2
(Zanjan University)
Hasanreza Mirzaei
3
(University of Zanjan)
Keywords: Transformer, tap changer, fault detection, vibration signal, wavelet transform, support vector machine,
Abstract :
On load tap changers are very important equipment of the power transformers. Due to the strongly mechanical movements and high-energy arcs, this equipment has a much higher failure rate with respect to other internal transformer equipment. Online and accurate evaluation of well operation of these equipment by indicators with no interfere on the normal operation of the transformer, is very important issue. In this paper, various faults detecting methods in the tap changer have been discussed an investigated by some extracted features of acoustic signals. These signals have been captured experimentally in various tap changing periods by an accelerometer sensor mounted on a power transformer body. In this paper, in addition to common features, two new feathers entitled time and frequency indicators have been introduced. Finally, for selecting the proper features to faults detection and proposing an effective classification method, some available experimental data were randomly defected by results in the references, and classified successfully as healthy and defective data by support vector machine (SVM) method.