基于BP神经网络的变压器故障诊断

Fault Diagnosis of Transformer Based on BP Neural Network

针对变压器故障类型的特征,结合油中气体分析法及三比值法,应用BP神经网络对变压器进行故障诊断。根据BP神经网络的概念、结构和算法原理,探讨了不同隐含层的神经元个数对神经网络训练性能的影响。通过对仿真结果的分析与测试,结果表明BP神经网络对变压器故障诊断具有较好的应用效果。

According to the characteristics of fault types of the transformer, BP neural network is used to diagnose trans-former fault with the data of dissolved gas analysis and the 3 ratio method. This paper described the concept, structure and algorithm of BP neural network in details. The number of neurons in hidden layer has a great effect on training perform-ance. Through the analysis and test of the simulation results, BP neural network has better application effect.