变压器局放监测与改进BP神经网络预测模型研究

Research on transformer partial discharge monitoring and improved BP neural network forecasting model

采用传感系统监测变压器局部放电的变化情况,选取高频电流信号和超声波信号作为变压器局部放电的监测参量,利用改进逆传播(BP)神经网络算法对变压器局部放电量进行建模分析。以D9—QY—40000/220型电力变压器(220 k V变压器)为例进行实例研究,结果表明:基于改进BP神经网络的局放预测模型训练集误差系数为0.0118,测试集误差系数为0.0232。此模型的局放预测值与实际值的曲线趋势基本一致,有效地对变压器局部放电量进行预测,为变压器故障诊断奠定了基础。

Use sensing system to monitor the changing of the transformer partial discharge,ultrasonic and highfrequency current signal are selected as monitoring parameters of partial discharge and utilize improved backpropagation（ BP） neural network algorithm to make modeling analysis on partial discharge quantity of transformer.With 220 kV Model D9—QTY—40000/220 power transformer as an example for case study. The results show that the error coefficient of test set based on improved BP neural network is 0. 011 8 and the error coefficient of test set is0. 023 2. Prediction value of partial discharge the model is consistent with the actual value,it can effectively predict transformer magnitude of partial discharge and it lay foundation for transformer fault diagnosis.