陈优良,肖钢,胡敏,黄劲松

• 1:江西理工大学建筑与测绘工程学院
• 2:浙江智谱工程技术有限公司

摘要(Abstract)：

针对使用传统极限学习机实现大坝变形预测中,因影响因子复杂导致隐藏层个数难以确定的问题,该文提出一种基于极限学习机与弹性网络支持下的大坝变形预测模型。采用极限学习机算法,将大坝变形影响因子由原本的空间映射到极限学习机的特征空间,建立影响因子与变形结果之间的非线性联系,同时将非线性模型转换成一个线性模式求解问题,并使用弹性网络求解该模型。对比基于极限学习机回归与最小二乘回归算法的实验表明:弹性网络拥有更好的稳定性,改善了极限学习机难以处理的过拟合现象,减弱了因训练集样本不同造成的预测误差大的影响,只需任意设置足够数量的隐含层神经元个数就能得到可靠的预测结果,简化了基于极限学习机的大坝变形预测面临的隐含层神经元个数取舍问题。

关键词(KeyWords)： 变形预测;极限学习机;线性模式求解;弹性网络

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41261093);; 江西省教育厅科技项目(GJJ170522)

作者(Author): 陈优良,肖钢,胡敏,黄劲松

DOI: 10.16251/j.cnki.1009-2307.2020.11.004

参考文献(References)：

• [1] 解建仓,王玥,雷社平.基于ARIMA模型的大坝安全监测数据分析与预测[J].人民黄河,2018,40(10):135-138.(XIE Jiancang,WANG Yue,LEI Sheping.Dam safety monitoring data analysis and prediction based on ARIMA model[J].People’s Yellow River,2018,40(10):135-138.)
• [2] 王新洲,范千,许承权,等.基于小波变换和支持向量机的大坝变形预测[J].武汉大学学报(信息科学版),2008,33(5):469-471.(WANG Xinzhou,FAN Qian,XU Chengquan,et al.Dam deformation prediction based on wavelet transform and support vector machine[J].Geomatics and Information Science of Wuhan Univers,2008,33(5):469-471.)
• [3] 张豪,许四法.基于经验模态分解和遗传支持向量机的多尺度大坝变形预测[J].岩石力学与工程学报,2011,30(S2):3681-3688.(ZHANG Hao,XU Sifa.Multi-scale dam deformation prediction based on empirical mode decomposition and genetic support vector machine[J].Journal of Rock Mechanics and Engineering,2011,30(S2):3681-3688.)
• [4]刘小生,于良.改进的SVR在大坝边坡位移预测中的应用[J].测绘通报,2018(6):129-132.(LIU Xiaosheng,YU Liang.Application of improved SVR in dam slope displacement prediction[J].Surveying and Mapping Bulletin,2018(6):129-132.)
• [5]卢献健,刘海锋,蒋园园,等.基于灰色遗传BP神经网络的大坝变形预测[J].桂林理工大学学报,2017,37(4):98-103.(LU Xianjian,LIU Haifeng,JIANG Yuanyuan,et al.Dam deformation prediction based on grey genetic BP neural network[J].Journal of Guilin University of Technology,2017,37(4):98-103.)
• [6]李明军,王均星,王亚洲.基于改进粒子群算法和极限学习机的混凝土坝变形预测[J].天津大学学报（自然科学与工程技术版）:2019(2):1-10.(LI Mingjun,WANG Junxing,WANG Yazhou.Deformation prediction of concrete dam based on improved particle swarm optimization and extreme learning machine[J].Journal of Tianjin University(Natural Science and Engineering Edition),2019(2):1-10.)
• [7] HUANG G,HUANG G,SONG S,et al.Trends in extreme learning machines:a review[J].Neural Networks,2015,61:32-48.
• [8]王一宾,裴根生,程玉胜.弹性网络核极限学习机的多标记学习算法[J].智能系统学报,2019(2):1-11.(WANG Yibin,PEI Gensheng,CHENG Yusheng.Multi-label learning algorithms for elastic network kernel limit learning machine[J].Journal of Intelligent Systems,2019(2):1-11.)
• [9] ZOU H,HASTIE T. Regularization and variable selection via the elastic net[J].Journal of the Royal Statistical Society,2005,67(2):301-320.
• [10]王诗琦,赵书敏,耿江东,等.变长增量型极限学习机及其泛化性能研究[J].计算机应用研究,2016(12):3696-3699.(WANG Shiqi,ZHAO Shumin,GENG Jiangdong,et al.Variable-length incremental extreme learning machine and its generalization performance[J].Computer Application Research,2016(12):3696-3699.)
• [11]安慧琳,李艳玲,曾贝佳,等.重力坝挠度多测点空间模型研究[J].水电能源科学,2016(11):77-81.(AN Huilin,LI Yanling,ZENG Beijia,et al.Research on multi-point space model of gravity dam deflection[J].Hydropower and Energy Science,2016(11):77-81.)