摘要
为了有效地评估绝缘的寿命,研究了采用径向基神经网络评估发电机主绝缘剩余击穿电压的方法。通过研究剩余击穿电压与主绝缘非坏性参量的相关性,得到用于评估击穿电压的神经网络的输入参数,即Δtanδ、ΔC、Sk+和Sk-;利用多因子老化平台对真机线棒进行加速老化,并进行相关测量,从中选择24组数据作为对神经网络训练、检测,及击穿电压预测的样本。结果表明该预测模型在测试样本数量为训练样本数量25%的情况下,剩余击穿电压预测值与实际测量值的最大相对误差<6%,平均相对误差<3%。评估结果对于在样本数量较少的情况下准确预测发电机定子绝缘剩余寿命具有一定的参考价值。
A radial basis fuction neural network （RBFNN） is built to evaluate the risidual breakdown voltage of generator stator insulation. The input parameters of RBFNN are selected from the nondestructive parameters, which have big related coefficient. To ivestigate the nondestructive insulation diagnosic data, the accelerated multi-stress aging experiments have been carried out on some actual stator bars of generator. AC breakdown voltages of the bars are detected after the nondestructive data has been measured. According to the selection rule,Δtanδ、ΔC、Sk＋ and Sk- of Hqn（φ） are selected as the input parameters of RBFNN, and the output parameter is the risidual breakdown voltage. The nondestructive parameters from twenty-four samples of bars have been used to train, exam the developed RBFNN and to predict the residual breakdown voltage by it. These samples are selected randomly, thus these parameters should be standardized to reduce their dispersity before being used. The numerical results show that the biggest relative error between the prediction by RBFNN and the measured breakdown voltage is smaller than 6% and the average relative error is smaller than 3%. The risidual breakdown voltage is useful for estimating the residual life of large generator insulation. According to the IEC standard, the life of stator insulation arrives at the end point if the risidual breakdown voltage falls down to 50% of its initial value. This research may be important to estimate condition of the insulation and to predicte residual life of stator insulation in the case of a few available samples.
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2007年第8期151-154,共4页
High Voltage Engineering
基金
国家自然科学基金重点项目(59837260)。~~
关键词
定子绝缘
状态诊断
加速老化
剩余击穿电压
径向基函数
人工神经网络
stator insulation
insulation condition diagnosis
life assessment
residual breakdown voltage
radial ba- sis function
artificial neural network
作者简介
赵磊1981-，男，硕士，主要从事发电机绝缘状态监测和寿命评估方面的研究。E-mail：zhao_lei@stu．xjtu．edu．cn
