雷雨, 赵丹宁, 蔡宏兵. 利用结构自适应极端学习机预报导航卫星钟差[J]. 武汉大学学报 ( 信息科学版), 2018, 43(5): 664-668, 718. DOI: 10.13203/j.whugis20150252
引用本文: 雷雨, 赵丹宁, 蔡宏兵. 利用结构自适应极端学习机预报导航卫星钟差[J]. 武汉大学学报 ( 信息科学版), 2018, 43(5): 664-668, 718. DOI: 10.13203/j.whugis20150252
LEI Yu, ZHAO Danning, CAI Hongbing. Prediction of Navigation Satellite Clock Offset by Adaptive Extreme Learning Machine[J]. Geomatics and Information Science of Wuhan University, 2018, 43(5): 664-668, 718. DOI: 10.13203/j.whugis20150252
Citation: LEI Yu, ZHAO Danning, CAI Hongbing. Prediction of Navigation Satellite Clock Offset by Adaptive Extreme Learning Machine[J]. Geomatics and Information Science of Wuhan University, 2018, 43(5): 664-668, 718. DOI: 10.13203/j.whugis20150252

利用结构自适应极端学习机预报导航卫星钟差

Prediction of Navigation Satellite Clock Offset by Adaptive Extreme Learning Machine

  • 摘要: 针对卫星钟差难以用精确模型来进行预报的问题,将极端学习机(extreme learning machine,ELM)神经网络用于导航卫星钟差预报。针对ELM网络隐层结构难以确定的问题,提出了基于自适应共振理论(adaptive resonance theory,ART)网络思想的ELM网络结构设计算法。该算法将ART网络的聚类特性用于ELM网络结构设计中,通过对输入向量与已存模式的相似度比较将输入向量进行分类,自适应地确定隐层节点规模。使用GPS卫星钟差数据进行30 d的预报实验,结果表明,此方法的钟差预报精度明显优于二次多项式模型和灰色系统模型。

     

    Abstract: It is difficult to model and predict satellite clock offset with conventional approaches. In this paper, an extreme learning machine (ELM) is used to predict satellite clock offset in order to improve prediction accuracy. For the problem that it is arduous to determine the hidden layer structure of ELM neural network, a new algorithm for ELM network structure design is proposed based on the good online classified characteristic of adaptive resonance theory (ART) network. The proposed algorithm employs the clustering characteristic of ART network to design the ELM network structure. The number of hidden layer nodes can be determined adaptively through the similarity comparison of input vector. The experiment results show that the ART-ELM prediction model outperforms the quadratic polynomial model and grey model remarkably.

     

/

返回文章
返回