关键词:核主成分分析; BP神经网络; 电力变压器; 故障诊断
Transformer fault diagnosis based on kernel PCA and BPNN
HU Qing, DU Lin, YANG Li-jun, SUN Cai-xin
(State Key Laboratory of Power TransmissionEquipment & SystemSecurity & New Technology, Chongqing University, Chongqing400030, China)
Abstract:To improve the accuracy and anti-noise ability for transformer fault diagnosis, this paper proposed a novel BP neural network based on kernel features. Samples were nonlinearly mapped from the low-dimensional feature space into the high-dimensional kernel space by kernel PCA, which improved samples’separability, thenbuiltBP neural network in kernel space. Experiments compared performances of BP neural networks with silimar constructures, different input features, the results show that diagnostic models with kernel features achieve better performance and anti-noise ability. ......