基于分布式神经网络的变压器励磁涌流鉴别的研究

针对目前变压器保护中普遍采用的利用二次谐波原理识别变压器励磁涌流存在的缺陷,提出利用分布式人工神经网络实现基于半波叠加原理鉴别励磁涌流的新方案。经仿真实验,该方案能准确地判别出变压器内部故障和励磁涌流,不受系统谐波影响,具有很高的可靠性。

Study of Identification of the Inrush Based on Distributed Artificial Neural Network

Aimed at the disadvantages of second harmonic restraint, a new method is presented in this paper to distinguish inrush current. The new method is based on the theory of half-circle-added and realized by distributed Artificial Neural Network. The simulation tests show that the new method can judge correctly the transformer's inrush current and internal fault. The method can not affected by the harmonic and has good reliability.