引用本文: | 刘帅,李智,林瑞淋,等.地球静止轨道高能电子通量在线预测模型[J].国防科技大学学报,2016,38(2):117-122.[点击复制] |
LIU Shuai,LI Zhi,LIN Ruilin,et al.Online prediction model for energetic electron flux at geostationary orbit[J].Journal of National University of Defense Technology,2016,38(2):117-122[点击复制] |
|
|
|
本文已被:浏览 7330次 下载 6047次 |
地球静止轨道高能电子通量在线预测模型 |
刘帅1, 李智1, 林瑞淋2, 龚建村2, 刘四清2 |
(1. 装备学院 航天指挥系, 北京 101416;2. 中国科学院 国家空间科学中心, 北京 100190)
|
摘要: |
利用粒子群优化算法和最小二乘支持向量机,建立地球静止轨道高能电子通量在线预测模型。针对粒子群优化算法,提出一种新的粒子群多样性测度计算方法,有效改善其早熟收敛现象。运用改进的粒子群优化算法优化最小二乘支持向量机的正则化参数和核参数。利用滑动时间窗口策略更新模型数据,选择触发机制以及模型的再学习机制为设计变量,实现模型的在线预测功能。对2000年电子通量监测数据和相关太阳风、地磁参数等实际数据进行的提前1~3天的预测实验,表明所建在线预测模型具有较高的预测性能,并具有一定的实用价值。 |
关键词: 粒子群优化算法 最小二乘支持向量机 变量选择 互信息 距离相关系数 高能电子通量 |
DOI:10.11887/j.cn.201602020 |
投稿日期:2015-06-22 |
基金项目:教育部新世纪优秀人才支持计划资助项目(Y52133A23S) |
|
Online prediction model for energetic electron flux at geostationary orbit |
LIU Shuai1, LI Zhi1, LIN Ruilin2, GONG Jiancun2, LIU Siqing2 |
(1. Space Command Department, Equipment Academy, Beijing 101416, China;2. National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China)
|
Abstract: |
An online prediction model for the energetic electron flux at the geostationary orbit was built based on the PSO (particle swarm optimization) algorithm and the LSSVM (least squares support vector machines) method. To overcome the premature convergence problem in PSO, a new diversity measure was put forward. The improved PSO was utilized to optimize the LSSVM′s parameters. Through a sliding time window strategy, a variable selection invoking threshold and a model re-training mechanism, the online characteristic of the model was realized. 1~3 day ahead prediction experiments were done on the basis of the electron flux data, solar wind parameters and geomagnetic parameters in 2000, and the analysis results show that the proposed online PSO-LSSVM model works well and has practicable value for prediction. |
Keywords: particle swarm optimization algorithm least squares support vector machines variable selection mutual information distance correlation energetic electron flux |
|
|