National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [51207014, 71371065]; Hunan Province 100 Talent Program Fund; State Scholarship Fund of China [201308430317]; Scientific Research Fund of the Hunan Provincial Education DepartmentHunan Provincial Education Department [15B006]; Natural Science Foundation of Hunan ProvinceNatural Science Foundation of Hunan Province [2015JJ4001, 13JJ6044]
机构署名：
本校为第一且通讯机构
院系归属：
电气与信息工程学院
摘要：
Some traditional protection schemes cannot detect the faulted Powerformer when a stator single line-to-ground fault occurs in parallel Powerformers. A new discrimination method based on kernel principal component analysis (KPCA) and Fisher discrimination analysis considering the distribution characteristics of the data is proposed in this paper. First, algorithms of KPCA and Fisher discrimination are introduced. In order to increase correct rate of the fault recognition, the kernel function for distribution characteristics of the data is selected according to error rate under historical fault ...
