CAJ | 학술논문

　　利用遗传算法优化概率神经网络的重要参数，以便获得最优的平滑因子，从而实现了电力变压器励磁涌流和内部故障电流的识别。采用MATLAB软件对变压器不同的运行状态进行建模仿真，并对保护方案进行测试。
　　이용유전산법우화개솔신경망락적중요삼수，이편획득최우적평활인자，종이실현료전력변압기려자용류화내부고장전류적식별。채용MATLAB연건대변압기불동적운행상태진행건모방진，병대보호방안진행측시。
In this paper, Genetic Algorithm is used to optimize the important parameter of Probabilistic Neural Network(PNN), so as to get the best smooth factors. Wavelet Transform(WT)is used for decomposition to extract energy feature vector of sig-nals and PNN for classification. The identification between inrush current and internal fault current is completed. Build simula-tion modeling of the transformer by MATLAB software, simulate different running states and test the protection algorithm.