太阳黑子数的PSO-RBF预测模型  

The PSO-RBF Prediction Model of Sunspot Number

作　　者：李琳 刘龙 LI Lin ;LIU Long(School of Electronic and Information Engineering,North China Institute of Science&Technology,Yanjiao,East Beijing,101601,China)

机构地区：[1]华北科技学院电子信息工程学院,中国北京101601

出　　处：《科技视界》2018年第13期9-10,44,共3页Science & Technology Vision

摘　　要：为了提高RBF神经网络预测太阳黑子数的准确度,本文采用一种基于粒子群算法优化RBF神经网络预测模型。利用粒子群算法优化RBF神经网络的初始参数,并将其用于太阳黑子数月均值的预测。将实验结果与传统RBF神经网络预测模型预测结果进行比较,结果表明,该方法收敛快速、预测精度明显提高,表明了PSO-RBF预测模型在太阳黑子数预测中的有效性。In order to improve the accuracy of RBF neural network to predict the number of sunspots,this paper uses a particle swarm optimization algorithm to optimize RBF neural network prediction model.The initial parameters of RBF neural network were optimized by particle swarm optimization,and its prediction was used for the mean of sunspot.The experimental results are compared with traditional RBF neural network prediction model.The simulation results show that the proposed method has a fast convergence and a significant improvement in the prediction accuracy,indicating the effectiveness of the group optimization RBF prediction model in the prediction of sunspot number.

关 键 词：太阳黑子数 RBF神经网络 粒子群算法 预测 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]