传统的统计模型泛化能力较弱且容易引入高维变量,这将对基于神经网络预测模型的输出结果产生负面影响,同时增加了过拟合风险。因此,有必要建立一个具有适当维度的数据驱动模型,以实现对大坝变形的准确监控。选用极限学习机(ELM)作为基础预测模型,提出基于平均影响值MIV-ELM模型的变量筛选法,以消除初始变量集中的冗余信息,从而降低模型复杂度,提高预测精度。分析结果表明,与传统预测模型相比,HST-MIV-ELM不仅具有最高的预测精度和预测性能,同时也有较强的可拓展性,为大坝安全监控系统的构建提供了可靠的理论基础。
Abstract
Traditional statistical models are of weak generalization capability and are prone to introduce high-dimensional variables,which will negatively affect the output of neural network-based prediction models and increase the risk of overfitting.It is necessary to build a data-driven model with appropriate dimensionality to accomplish accurate monitoring of dam deformation.In this paper,extreme learning machine(ELM)is selected as the base prediction model,and a variable selection method based on mean impact value(MIV)-ELM model is proposed to eliminate redundant information in the initial variable set,thus reducing the model's complexity and improving the prediction accuracy.Analysis results demonstrate that compared with traditional prediction models,HST-MIV-ELM not only has the highest prediction accuracy and robustness,but also has strong scalability.The study provides a reliable theoretical basis for the construction of dam safety monitoring system.
关键词
混凝土坝变形预测 /
变量筛选 /
极限学习机 /
平均影响值 /
反向逐变量剔除法
Key words
deformation prediction for concrete dam /
variable selection /
extreme learning machine /
mean impact value /
reverse variable-by-variable elimination method
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 吴中如.水工建筑物安全监控理论及其应用[M].北京:高等教育出版社,2003.
[2] CHEN B,HU T,HUANG Z,et al.A Spatio-temporal Clustering and Diagnosis Method for Concrete Arch Dams Using Deformation Monitoring Data[J].Structural Health Monitoring,2019,18:1355-1371.
[3] 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.
[4] CAO E,BAO T,GU C,et al.A Novel Hybrid Decomposition-Ensemble Prediction Model for Dam Deformation[J].Applied Sciences,2020,10(16):5700,doi:10.3390/app10165700.
[5] YANG J,QU X,CHANG M.An Intelligent Singular Value Diagnostic Method for Concrete Dam Deformation Monitoring[J].Water Science and Engineering,2019,12(3):205-212.
[6] 赵二峰,李 波,朱延涛.基于PPA-POT的RCCD变形监测控制值拟定方法[J].人民黄河,2021,43(3):135-139.
[7] 曹恩华,包腾飞,刘永涛,等.基于EMD-RVM-Arima的大坝变形预测模型及其应用[J].水利水电技术,2018,49(12):59-64.
[8] 康传利,陈 洋,张临炜,等.小波和混沌神经网络在大坝变形预测中的应用[J].人民黄河,2020,42(3):101-104,116.
[9] 袁冬阳.基于多元时空信息挖掘的混凝土重力坝变形体征监控方法[D].南昌:南昌大学,2019:62-64.
[10] BELMOKRE A,MIHOUBI K,SANTILLÁN D.Analysis of Dam Behavior by Statistical Models:Application of the Random Forest Approach[J].KSCE Journal of Civil Engineering,2019,23:4800-4811.
[11] LI D,ZHOU Y,GAN X.Research on Multiple Points Deterministic Displacement Monitoring Model of Concrete Arch Dam[J].Journal of Hydraulic Engineering,2011,42:981-985.
[12] DAI B,GU C,ZHAO E,et al.Statistical Model Optimized Random Forest Regression Model for Concrete Dam Deformation Monitoring[J].Structural Control & Health Monitoring,2018,25(6):e2170.1-e2170.15.
[13] 胡雨菡,包腾飞,朱 征,等.基于IABC-FCM-RVM算法的拱坝变形预测模型[J].武汉大学学报(工学版),2020,53(12):1055-1064.
[14] MATA J.Interpretation of Concrete Dam Behaviour with Artificial Neural Network and Multiple Linear Regression Models[J].Engineering Structures,2011,33:903-910.
[15] SU H,LI X,YANG Z,et al.Wavelet Support Vector Machine-based Prediction Model of Dam Deformation[J].Mechanical Systems and Signal Processing,2018,110:412-427.
[16] 鄢 涛,陈 波,曹恩华,等.基于EEMD-ELM的大坝变形预测模型[J].raybet体育在线
院报,2020,37(11):70-73,80.
[17] 牛景太.基于奇异谱分析与PSO优化SVM的混凝土坝变形监控模型[J].水利水电科技进展,2020,40(6):60-65,77.
[18] 谢国权,戚 蓝,曾新华.基于小波和神经网络拱坝变形预测的组合模型研究[J].武汉大学学报(工学版),2006,39(2):16-19.
[19] HUANG G,ZHU Q,SIEW C.Extreme Learning Machine:Theory and Applications[J].Neurocomputing,2006,70:489-501.
[20] DOMBI G W,NANDI P,SAXE J M,et al.Prediction of Rib Fracture Injury Outcome by an Artificial Neural Network[J].Journal of Trauma,1995,39:915-921.
基金
国家重点研发计划项目(2018YFC1508603,2016YFC0401601);国家自然科学基金项目(51579086,51739003)
PDF(6239 KB)
