Font Size: a A A

Research On Intelligent Line Selection Method Based On The Transient Travelling Wave Resonance Grounding System

Posted on:2016-04-28Degree:MasterType:Thesis
Country:ChinaCandidate:Y F LiFull Text:PDF
GTID:2322330482982511Subject:Power electronics and electric drive
Abstract/Summary:PDF Full Text Request
Through the arc suppression coil grounding method can effectively compensate the capacitive current in the circuit,is mostly used in our distribution network.When the grounding system occurs single-phase ground fault,there is no valid current loop, so the fault current is very small.But after Petersen coil grounding the fault current is very small that will cause difficulties to select lines.According to the steady and transient analysis of the arc suppression coil grounding system grounding fault features,the transient characteristics of the useful signal is stronger.And the characteristics parameters is not affected by the presence of noise signal and the sampling errors and other uncertainties problems.Combined transient traveling wave parameters and neural network algorithm to realize line selection, established the neural network model based on transient traveling wave current, determined the network learning algorithm, and realized intelligent arc suppression coil grounding system fault line selection criterion. The single-phase ground fault line selection method effectively solves the impact on the reliability of fault line selection caused by signal interference and sampling error, which significantly improves the accuracy of line selection. The simulation and experiment by a large number of power system and a large number of laboratory experiments show that the line selection method has very high reliability and sensitivity. The result is verified by experiment test, the line selection method can correctly select the fault line, and the protective device performance is good as well.
Keywords/Search Tags:Resonant grounding system, Faulty line selection, traveling wave, Binary wavelet transform, BP neural network
PDF Full Text Request
Related items