基于RBF神经网络的输电线路覆冰短期预测研究

Short-term prediction for transmission lines icing based on RBF neural network

本文提出了一种基于RBF神经网络的输电线路覆冰短期预测方法。首先介绍了RBF神经网络的基本原理及算法;然后对覆冰监测终端实测数据进行了误差剔除、缺失数据补充以及数据归一化等预处理;在此基础上,通过比较不同输入因子下模型的准确度,确定最佳建模方案;进一步通过实例验证了这一覆冰预测模型的准确性。研究结果表明,基于RBF神经网络的输电线路覆冰短期预测模型,在选取了恰当的输入因子的情况下,可以较好的实现输电线路覆冰的短期预测。

This paper proposes a short-term prediction model for transmission lines icing based on RBF neural network. Our work begins with a review of basic principles of this model. Then, a series of preprocessing on the data obtained from on-line icing monitoring system, such as the elimination of data with crassitude error, the supplementation of missing data and the normalization of data, are carried out. On this basis, through comparing the accuracy of the model with different input factor, determined the best modeling solutions. Finally, tests are conducted to evaluate the validity of the proposed predicting model by using field data provided by online monitor system. Results have shown that the proposed model based on RBF neural network is fairly accurate for the short-term prediction of transmission lines icing.