基于RBF神经网络的光纤电流互感器温度补偿

Temperature Compensation for Fiber Optic Current Transformer Based on RBF Neural Network

光纤电流互感器在实际运行中易受外界温度影响,其输出精度会出现漂移偏差。为提高光纤电流互感器测量比值误差的温度稳定性,提出了基于RBF神经网络的光纤电流互感器温度补偿方法。将温度和温变率作为神经网络输入、光纤电流互感器的比值误差作为输出,建立了RBF神经网络温度补偿模型。相比BP神经网络,仿真结果显示,基于RBF神经网络的温度补偿模型准确度较高,预测结果误差低于3%。同时,经过RBF神经网络温度补偿,实验结果表明,光纤电流互感器在输出比差小于±0.1%,满足GBT20840.8标准规定的0.2S级准确度。

The fiber optic current transformer(FOCT)is susceptible to external temperature in actual operation,which will lead to accuracy deviation.In order to improve the temperature stability of ration error outputted by the FOCT,a temperature compensation method for FOCT based on RBF neural network was proposed.Taking temperature and temperature variability as input and ration error as output,RBF neural network temperature compensation model was established.Compared with BP neural network,the simulation results show that the temperature compensation model based on RBF neural network has better accuracy whose prediction error is less than 3%.At the same time,the experimental results show that the drift deviation of ratio error can remain as low as±0.1%and the 0.2S level accuracy of GBT20840.8 standard can be achieved.