杨帆;王小兵;邵阳;

• 1:辽宁工程技术大学测绘与地理科学学院
• 2:辽宁工程技术大学外语系

摘要(Abstract)：

针对灰色神经网络权值阈值的不确定性,该文提出改进型果蝇优化算法优化的灰色神经网络预测模型。通过添加逃脱系数修改适应度函数,同时引入三维空间搜索的概念扩大了果蝇搜索范围对基本果蝇优化算法进行改进,避免算法陷入早熟收敛的陷阱,加快收敛速度,有效地提高了算法的优化性能。利用改进型果蝇优化算法优化灰色神经网络参数建立预测模型。选用实际工程沉降数据仿真模拟,验证该模型的预测性能,并将预测结果与果蝇优化算法灰色神经网络、粒子群优化灰色神经网络和灰色神经网络进行比较。结果表明,改进型果蝇优化算法优化的灰色神经网络预测模型预测精度更高,拟合程度更好。

关键词(KeyWords)： 权值阈值;灰色神经网络;果蝇优化算法;预测

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(50604009);; 辽宁省“百千万人才工程”人选资助项目(2010921099)

作者(Authors): 杨帆;王小兵;邵阳;

DOI: 10.16251/j.cnki.1009-2307.2018.02.012

参考文献(References)：

• [1]张正禄.工程的变形监测分析与预报[M].北京:测绘出版社,2007.(ZHANG Zhenglu.Deformation monitoring analysis and prediction of engineering[M].Beijing:Surveying and Mapping Press,2007.)
• [2]吴飞宇.基于灰色神经网络模型的基坑变形预测研究[J].测绘通报,2013(S1):154-157.(WU Feiyu.Study on deformation prediction of foundation pit based on grey neural network model[J].Bulletin of Surveying and Mapping,2013(S1):154-157.)
• [3]吴益平,滕伟福,李亚伟.灰色-神经网络模型在滑坡变形预测中的应用[J].岩石力学与工程学报,2007,26(3):632-636.(WU Yiping,TENG Weifu,LI Yawei.Application of grey neural network model to landslide deformation prediction[J].Chinese Journal of Rock Mechanics and Engineering,2007,26(3):632-636.)
• [4]方毅,花向红,李海英.灰色神经网络模型在建筑物变形预报中的应用[J].测绘工程,2008,17(2):51-53.(FANG Yi,HUA Xianghong,LI Haiying.The application of grey neural network model to deformation forecasting of buildings[J].Engineering of Surveying and Mapping,2008,17(2):51-53.)
• [5]杨森,孟晨,王成.AFSA优化灰色神经网络的某电源组合故障预测[J].计算机测量与控制,2012,20(10):2648-2650.(YANG Sen,MENG Chen,WANG Cheng.Fault prediction of power supply using grey neural network optimized with AFSA[J].Computer Measurement&Control,2012,20(10):2648-2650.)
• [6]王英博,聂娜娜,王铭泽.修正型果蝇算法优化GRNN网络的尾矿库安全预测[J].计算机工程,2015,41(4):267-272.(WANG Yingbo,NIE Nana,WANG Mingze.Mine tailings facilities safety evaluation of GRNN optimized by modified fruit fly algorithm[J].Computer Engineering,2015,41(4):267-272.)
• [7]范良,赵国忱,苏运强.果蝇算法优化的广义回归神经网络在变形监测预报中的应用[J].测绘通报,2013(11):87-89.(FAN Liang,ZHAO Guochen,SU Yunqiang.Fruit fly optimization algorithm optimized general regression neural network in deformation monitoring and prediction[J].Bulletin of Surveying and Mapping,2013(11):87-89.)
• [8]邹兵,陈西宏,薛伦生,等.果蝇优化算法优化灰色神经网络的卫星钟差预报[J].测绘科学,2014,39(9):44-48.(ZOU Bing,CHEN Xihong,XUE Lunsheng,et al.Grey neural network based on FOA for prediction of satellite clock error[J].Science of Surveying&Mapping,2014,39(9):44-48.)
• [9]张宏伟,朱志洁,霍丙杰,等.基于改进的FOA-SVM导水裂隙带高度预测研究[J].中国安全科学学报,2013,23(10):9-14.(ZHANG Hongwei,ZHU Zhijie,HUO Bingjie,et al.Water flowing fractured zone height prediction based on improved FOA-SVM.[J].China Safety Science Journal,2013,23(10):9-14.)
• [10]韩俊英,刘成忠.自适应变异的果蝇优化算法[J].计算机应用研究,2013,30(9):2641-2644.(HAN Junying,LIU Chengzhong.Fruit fly optimization algorithm with adaptive mutation[J].Application Research of Computers,2013,30(9):2641-2644.)
• [11]YANG Jing.Vinyl acetate polymerization rate prediction based on FOA-GNN[C]//2014 9th International Conference on P2P,Parallel,Grid,Cloud and Internet Computing(3PGCIC).[S.l.]:IEEE,2014:205-208.
• [12]潘文超.果蝇最佳化演算法[M].台湾:沧海书局,2013.(PAN Wenchao.The optimal algorithm of fruit fly[M].Taiwan:Changhai Publishing House,2013.)
• [13]PAN Wenchao.Using modified fruit fly optimization algorithm to perform the function test and case studies[J].Connection Science,2013,25(2/3):151-160.
• [14]ISCAN H,GUNDUZ M.A survey on fruit fly optimization algorithm[C]//International Conference on Signal-Image Technology&Internet-Based Systems.[S.l.]:IEEE,2016:520-527.
• [15]刘贺,张弘强,刘斌.基于粒子群优化神经网络算法的深基坑变形预测方法[J].吉林大学学报(地球科学版),2014,44(5):1609-1614.(LIU He,ZHANG Hongqiang,LIU Bin.A prediction method for the deformation of deep foundation pit based on the particle swarm optimization neural network[J].Journal of Jilin University(Earth Science Edition),2014,44(5):1609-1614.)
• [16]王小川.Matlab神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.(WANG Xiaochuan.43cases of Matlab neural network[M].Beijing:Beihang University Press,2013.)