基于BP神经网络的大气条件对空气间隙放电特性的影响研究  

Analysis on the Effect of Atmosphere Condition on Discharge Characteristic of Air Gap Based on BP Neural Network

作　　者：罗新[1] 牛海清[1] 游勇[1] 林浩然[1] 

机构地区：[1]华南理工大学电力学院,广州

出　　处：《智能电网（汉斯）》2012年第1期30-34,共5页Smart Grid

摘　　要：空气间隙的击穿电压是决定外绝缘水平的重要因素之一。本文讨论了BP神经网络在气隙击穿电压预测中的应用。使用人工气候室中获得的样本数据对网络进行训练,用训练好的网络对击穿电压进行预测。结果表明BP神经网络对气隙击穿电压的预测是可行的,模型具有很高的精度,预测值与实际值的相对误差在5%以内。Breakdown voltage of air gap is an important factor to determine the level of external insulation. This paper discusses the application of BP neural network in the prediction of breakdown voltage of air gap. Neural network is trained by the sample data got in artificial climate can, then it is used to predict the breakdown voltage. The result shows that the prediction of BP neural network is feasible, and this model has a high accuracy. The relative error be-tween predicted value and actual value is less than 5%.

关 键 词：空气间隙 击穿电压 大气条件 BP神经网络 

分 类 号：F2[经济管理—国民经济]