BP神经网络在变压器故障诊断中的应用

The Application of BP Neural Network in Transformer Fault Diagnosis

介绍了电力变压器内部常见的故障,采用BP神经网络算法建立了变压器的神经网络故障诊断模型,通过与传统的IEC三比值法相比较,表明基于BP网络的诊断方法达到了较好的故障识别与分类,诊断准确率也有显著的提高,在变电设备故障诊断中具有良好的应用前景。

Common faults in a transformer are introduced in this paper.An artificial neural network model based on BP algorithm is presented.The comparative analysis between BP algorithm and IEC shows that when BP is applied to transformer fault diagnosis,the network diagnostic method can achieve a better fault identification and classification and the accuracy is evidently enhanced compared to other conventional methods.Therefore,the new approach shows a promising future in the diagnostic field for power transformation equipment.