Switchgear is a very important component in a power distribution line. Failure in a switchgear can lead to catastrophic danger and losses. In this research, a fault detection system is proposed with the implementation of Extreme Learning Machine (ELM). This algorithm is capable to identify faults in a switchgear by analyzing the sound wave generated. Experiments are carried out to investigate the performance of the developed algorithm in identifying Corona faults in switchgears. The performances are analyzed in time and frequency domains, respectively. In time domain analysis, the results show 90.63%, 87.5%, and 87.5% of success rates in differentiating the Corona and non-Corona cases in training, validation and testing phases respectively. In frequency domain analysis, the results show 89.84%, 83.33%, and 87.5% success rates in training, validation and testing phases respectively. It can thus be concluded that the developed algorithm performed well in identifying Corona faults in switchgears.
ABSTRACT--Flexural wave analysis has been applied to the detection and quantitative assessment of delaminations in structures. To validate analytical methods, an extensive experimental study is conducted. The test beam is of infinite length, and a delamination of prescribed length is artificially created at predetermined locations. Using two different types of excitations and measurements, the effect on the beam response of delamination length and depth, the beam material, excitation frequencies and location of excitation are analyzed. A technique for predicting the location and size of the delamination is also proposed. On each case, good comparison between analytical and experimental results is achieved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.