基于NCL-ELM的混凝土坝变形监控模型NCL-ELM-based concrete dam deformation monitoring model
王霄,胡雅婷,谷静,胡林生,齐春舫
摘要(Abstract)：
针对传统混凝土坝变形监控模型在非线性处理、外延预测精度等方面的不足，充分利用集成学习的优势，提出一种负相关学习集成极限学习机(NCL-ELM)的混凝土坝变形监控模型。此模型选用不同激活函数的ELM作为基学习器，并基于负相关学习算法进行集成，增加ELM基学习器间的差异度，实现了集成模型预测性能的提升。以澜沧江中游河段某混凝土拱坝变形数据为例进行变形预测，结果表明：NCL-ELM模型可深入挖掘混凝土坝变形与环境量影响因子间的作用关系，对于选取的3个测点数据，模型预测性能指标均方根误差分别为0.506 mm、0.490 mm、0.430 mm,均方差分别为0.385 mm、0.445 mm、0.343 mm,预测命中率分别为90%、100%、100%;在预测精度和命中率方面均优于统计模型、ELM和M-ELM模型，同时可为变形性态的判别提供参考依据，具有良好的工程应用价值。
关键词(KeyWords)： 混凝土坝变形预测;变形性态判别;极限学习机;集成学习;负相关学习
基金项目(Foundation): 国家自然科学基金项目(51739003,52079046)
作者(Author): 王霄,胡雅婷,谷静,胡林生,齐春舫
DOI: 10.13928/j.cnki.wrahe.2022.12.004
参考文献(References)：
- [1] 顾冲时，吴中如.大坝与坝基安全监控理论和方法及其应用[M].南京：河海大学出版社，2006.GU Chongshi,WU Zhongru.Theory and method of dam and dam foundation safety monitoring and its application [M].Nanjing:Hohai University Press,2006.
- [2] 刘亮亮，陈旭东.基于分形插值的混凝土坝变形趋势分析[J].人民黄河，2020,42(8):146-149.LIU Liangliang,CHEN Xudong.Analysis of deformation trend of concrete dam based on fractal interpolation[J].Yellow River,2020,42(8):146-149.
- [3] GU H,YANG M,GU C,et al.A comprehensive evaluation method for concrete dam health state combined with gray-analytic hierarchy-optimization theory:[J].Structural Health Monitoring,2022,21(2):250-263.
- [4] HU Y,SHAO C,GU C,et al.Concrete dam displacement prediction based on an ISODATA-GMM clustering and random coefficient model[J].Water,2019,11(4):714.
- [5] 徐睿，梁循，齐金山，等.极限学习机前沿进展与趋势[J].计算机学报，2019,42(7):1640-1670.XU Rui,LIANG Xun,LI Jinshan,et al.Advances and trends in extreme learning machine[J].Chinese Journal of Computers,2019,42(7):1640-1670.
- [6] 范千.大坝变形预报的神经网络极限学习方法[J].江南大学学报(自然科学版),2011,10(4):435-438.FAN Qian.Extreme learning method of neural network for dam deformation prediction[J].Journal of Jiangnan University (Natural Science Edition),2011,10(4):435-438.
- [7] KANG F,LIU J,LI J J,LI S J.Concrete dam deformation prediction model for health monitoring based on extreme learning machine[J].Structural Control and Health Monitoring,2017,24(10):e1997.
- [8] 张海龙，范振东.基于改进PSO-ELM算法的混凝土坝变形非线性监控模型[J].水电能源科学，2018,36(1):82-84.ZHANG Hailong,FAN Zhendong.Nonlinear monitoring model of concrete dam deformation based on improved PSO-ELM algoritm[J].Water Resources and Power,2018,36(1):82-84.
- [9] 李明军，王均星，王亚洲.基于改进粒子群优化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),2019,52(11):1136-1144.LI Mingjun,WANG Junxing,WANG Yazhou.Deformation prediction of concrete dam based on improved particle swarm optimization algorithm and extreme learning machine[J].Journal of Tianjin University (Science and Technology),2019,52(11):1136-1144.
- [10] 胡德秀，屈旭东，杨杰，等.基于M-ELM的大坝变形安全监控模型[J].水利水电科技进展，2019,39(3):75-80.HU Dexiu,QU Xudong,YANG Jie,et al.A safety monitoring model of dam deformation based on M-ELM[J].Advances in Science and Technology of Water Resources,2019,39(3):75-80.
- [11] LIU Y,YAO X.Ensemble learning via negative correlation.Neural Networks,1999,12(10):1399-1404.
- [12] 盛伟国，单鹏霄.一种基于小生境的负相关神经网络集成算法[J].浙江工业大学学报，2016,44(5):482-486.SHENG Weiguo,SHAN Pengxiao.Negative correlation neural network ensemble based on a niching algorithm[J].Journal of Zhejiang University of Technology,2016,44(5):482-486.
- [13] CHEN H,JIANG B,YAO X.Semisupervised negative correlation learning[J].IEEE Transactions on Neural Networks and Learning Systems,2018:1-14.
- [14] CHEN H,XIN Y.Multiobjective neural network ensembles based on regularized negative correlation learning[J].IEEE Transactions on Knowledge & Data Engineering,2010,22(12):1738-1751.
- [15] ZHANG L,SHI Z,CHENG M M,et al.Nonlinear regression via deep negative correlation learning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,43(3):982-998.
- [16] HUANG G B,ZHU Q Y,SIEW C K.Extreme Learning Machine:theory and applications applications[J].Neurocomputing,2006,70:489-501.
- [17] HUANG G,HUANG G B,SONG S J,et al.Trends in extreme learning machines:A review[J].Neural Networks,2015,61:32-48.
- [18] CHEN H,YAO X.Regularized negative correlation learning for neural network ensembles[J].IEEE Transations on Neural Networks,2009,20(12):1962-1979.
- [19] MONTHER A,WANG D H.Fast decorrelated neural network ensembles with random weights[J].Information Sciences,2014,264(6):104-117.
- [20] 赵立杰，李彬，汪滢等.磨机负荷参数快速去相关神经网络集成模型[J].控制工程，2017,24(9):1952-1957.ZHAO Lijie,LI Bin,WANG Yin,et al.Mill load parameter model using fast decorrelated neural network ensemble[J].Control engineering of China,2017,24(9):1952-1957.