东北大学学报:自然科学版 ›› 2020, Vol. 41 ›› Issue (12): 1692-1698.DOI: 10.12068/j.issn.1005-3026.2020.12.004

• 信息与控制 • 上一篇    下一篇

混沌参数优化RBF算法的震前ENPEMF信号强度趋势预测

郝国成1,2,3,4, 锅娟1,2,3, 谭淞元1,3, 曾佐勋5   

  1. (1.中国地质大学(武汉) 机械与电子信息学院, 湖北 武汉430074; 2.中国科学院 测量与地球物理研究所 大地测量与地球动力学国家重点实验室, 湖北 武汉430077; 3.中国地质大学(武汉)复杂系统先进控制与智能自动化湖北省重点实验室, 湖北 武汉430074;4.中国地质大学(武汉) 智能地学信息处理湖北省重点实验室, 湖北 武汉430074; 5.中国地质大学(武汉) 地球科学学院, 湖北 武汉430074)
  • 收稿日期:2019-11-25 修回日期:2019-11-25 出版日期:2020-12-15 发布日期:2020-12-22
  • 通讯作者: 郝国成
  • 作者简介:郝国成(1975-),男,山东冠县人,中国地质大学(武汉)副教授,博士生导师.
  • 基金资助:
    武汉市科技局攻关计划项目(2016060101010073); 111计划项目(B17040); 大地测量与地球动力学国家重点实验室开放基金资助项目(SKLGED2018-5-4-E); 复杂系统先进控制与智能自动化湖北省重点实验室基金资助项目(ACIA2017002); 智能地学信息处理湖北省重点实验室开放课题资助项目(KLIGIP2017A01).

Intensity Trend Forecasting of the ENPEMF Signal Before Earthquake Based on Chaotic Parameters Optimized RBF Algorithm

HAO Guo-cheng1,2,3,4, GUO Juan1,2,3, TAN Song-yuan1,3, ZENG Zuo-xun5   

  1. 1.School of Mechanical Engineering and Electronic Information, China University of Geosciences
  • Received:2019-11-25 Revised:2019-11-25 Online:2020-12-15 Published:2020-12-22
  • Contact: HAO Guo-cheng
  • About author:-
  • Supported by:
    -

摘要: 提出了一种基于混沌参数优化径向基函数(radial basis function,RBF)神经网络的预测模型.通过混沌理论获得了ENPEMF信号的有效嵌入维数和最优时延,然后利用所获得的参数优化RBF神经网络.采用训练好的参数优化RBF神经网络预测ENPEMF.数值仿真结果表明,改进的RBF算法可以较为准确地预测Rossler混沌时间序列且误差较小.将优化的RBF模型应用于芦山Ms7.0级地震前ENPEMF数据,可以有效预测震前14d的ENPEMF数据强度趋势,且预测效果及精度优于传统RBF神经网络算法,期望为地质灾害及强震前的电磁监测分析提供支持.

关键词: 地球天然脉冲电磁场, 强度趋势预测, 混沌理论, 参数优化, RBF神经网络

Abstract: A chaotic parameter-optimized radial basis function (RBF) forecasting model was proposed. The chaos theory was used to obtain the embedded dimension and delay time of the ENPEMF, and the obtained parameters were used to optimize the RBF neural network. Finally, the trained optimized-RBF was utilized to forecast the strength trend of 14 d ENPEMF data. Numerical simulation results show that the improved RBF model could forecast the Rossler time series well with small error. Applying the improved RBF algorithm to the ENPEMF data before Ms7.0 earthquake in Lushan, it can effectively forecast the ENPEMF intensity trend 14 d before earthquake. The forecasting effect and accuracy are significantly better than that of the traditional RBF algorithm, which is expected to provide support for electromagnetic monitoring and analysis before earthquakes and geological disasters.

Key words: the Earth’s natural pulse electromagnetic field, intensity trend forecasting, chaos theory, parameter optimization, RBF neural network

中图分类号: