神经网络的粒子群优化算法及其在地震预测中的应用
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
BP神经网络具有较强的非线性问题处理能力,是目前一种较好的用于时间序列预测的方法,然而它存在易于陷入局部极小值、收敛速度慢等不足。针对以上缺点,利用改进粒子群优化BP神经网络的权值与阈值,有效地增强了算法的全局搜索能力和提高了收敛速度。针对地震预测的应用,用改进粒子群优化的BP算法对四川地区最大震级时间序列进行预测,通过训练预测次年的最大震级。结果表明此方法优于未经优化的算法,具有良好的预测效果。
Back propagation neural network is a good method used in time series prediction,which has a strong nonlinear capacity of ocessing problem.However,it is easy to fall into local minimum and slow convergence.To solve the above shortcomings,using improved rticle swarm algorithm optimize the weights and threshold of back propagation neural network can effectively enhance the ability of the orithm's global search and improve the convergence rate.For applications of earthquake prediction,using an improved particle swarm of e BP neural networks optimization algorithm to predict the time series of largest magnitude in Sichuan Province.Predict the largest seismic gnitude of the following year by training.Results show that this method is better than the BP algorithm without optimization and has good ult of prediction.
引文
[1]Maria Moustra,Marios Avraamides,Chris Christodoulou.Ar-tificial neural networks for earthquake prediction using time se-ries magnitude data or Seismic Electric Signals[J].Expert Sys-tems with Applications,2011,38(12):15032-15039.
    [2]盛涛,谢异同,曲高峰.基于SVR算法与BP神经网络的地震预测对比研究[J].长江大学学报:自然科学版,2009,6(1):63-64.SHENG Tao,XIE Yitong,QU Gaofeng.Comparison Between SVR and BP-ANN in Prediction of Earthquake[J].Journal of Yangtze University:Natural Science Edition,2009,6(1):63-64.
    [3]徐鹏飞.利用遗传神经网络技术对地震预测的研究[D].合肥:安徽大学,2010.XU Pengfei.Research on Earthquake Prediction Based on Ge-netic Neural Networks[D].Hefei:Anhui University,2010.
    [4]LANGDON W B,POLI R.Evolving Problems to Learn About Particle Swarm Optimizers and Other Search Algorithms[J].Evolutionary Computation,2007,11(5):561-578.
    [5]LING S H,IU H,LEUNG F H F,et al.Improved hybrid particle swarm optimized wavelet neural network for modeling the development of fluid dispensing for electronic packaging[J].Industrial Electron,2008,55(9):3447-3460.
    [6]JAMES Kennedy,RUSSELL Eberhart.Paticle Swarm Optimi-zation[R].Proceedings IEEE International Conference on,1995,11(1):275-280.
    [7]田野.粒子群优化算法及其应用研究[D].长春:吉林大学,2010.TIAN Ye.Research on Particle Swarm Optimization Algorithm and Its Application[D].Changchun:Jilin University,2010.
    [8]RATNAWEER A A,HALGAMUGE S K,WATSON H C.Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients[J].Evolutionary Computa-tion,IEEE Transactions on,2004,8(3):240-255.
    [9]郑华,李炜,邱剑锋,等.基于时间序列相似性匹配算法的地震预测研究[J].北京电子科技学院学报,2010,18(2):4-9.ZHENG Hua,LI Wei,QIU Jianfeng,et al.An Earthquake Prediction Research Based on Time Series Similarity Matching Algorithm[J].Journal of Beijing Electronic Science and Tech-nology Institute,2010,18(2):4-9.
    [10]王炜,谢端,宋先月,等.使用人工神经网络进行我国大陆强震时间序列预测[J].西北地震学报,2002,24(4):315-319.WANG Wei,XIE Duan,SONG Xianyue,et al.Forecasting method of earthquake time serial in mainland of china by using the artificial neural networks[J].Northwestern Seismological Journal,2002,24(4):315-319.
    [11]高法钦.神经网络在组合导航定位算法中的应用研究[J].舰船电子工程,2010,30(11).GAO Faqin.Study of Using Neural Network in Integrated Navigation Algorithm[J].Ship Electronic Engineering,2010,30(11).
    [12]孙成民.四川地震全记录[M].成都:四川人民出版社,2010.SUN Chengmin.Full Record of Sichuan's Earthquake[M].Chengdu:Sichuan people's publishing house,2010.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心