滑坡位移分解预测中的平滑先验分析方法
|
摘要
目前在滑坡位移预测研究中,先将滑坡位移数据分解为趋势项及周期项后再分别进行预测已成为普遍做法。平滑先验分析法(Smoothness Priors Approach,SPA)是一种计算过程简单、计算量极小,且能快速分离原始数据趋势项和周期项的数据处理方法。在介绍SPA基本原理基础上,以三峡库区白家包滑坡典型监测点位移数据为例,对通过调节SPA正则化参数而获得的不同趋势项及周期项进行特征分析;进而结合对滑坡变形演化机制过程的先验分析,根据位移分解特征确定合理的参数取值;最后针对不同参数SPA位移分解数据,采用支持向量机进行位移预测对比分析。结果表明,SPA是一种适用于滑坡位移预测的位移分解方法,通过调节正则化参数并结合滑坡变形机制先验分析,能够获得较为合理的位移分解结果,进而提高滑坡位移预测精度。
At present,in landslide displacement prediction,it has become a widespread practice that the original displacement is first decomposed into trend term and periodic term. Smoothness Priors Approach( SPA) is such a data decomposition method and has some advantages including simple calculation process,minimal computational effort,etc. Based on the introduction of the basic principle of the SPA,the typical displacement monitoring data of the Baijiabao landslide in the Three Gorges reservoir area is used to analyze the characteristics of trend and periodic term displacement according to different regularization parameter of SPA. The results show that the trend term is smoother,the amplitude is larger and the period is longer with the increase of parameters. Through the prior analysis of the landslide deformation mechanism and processes,the most reasonable parameters can be determined. Finally,landslide displacement prediction is carried out for different displacement decomposition data,which is obtained from different parameters of SPA and with the moving average method. The results show that there is very good prediction accuracy based on the SPA displacement decomposition. Comprehensive analysis indicates that the SPA is a suitable method for the displacement decomposition in the landslide displacement prediction,and the prediction accuracy can further be improved.
At present,in landslide displacement prediction,it has become a widespread practice that the original displacement is first decomposed into trend term and periodic term. Smoothness Priors Approach( SPA) is such a data decomposition method and has some advantages including simple calculation process,minimal computational effort,etc. Based on the introduction of the basic principle of the SPA,the typical displacement monitoring data of the Baijiabao landslide in the Three Gorges reservoir area is used to analyze the characteristics of trend and periodic term displacement according to different regularization parameter of SPA. The results show that the trend term is smoother,the amplitude is larger and the period is longer with the increase of parameters. Through the prior analysis of the landslide deformation mechanism and processes,the most reasonable parameters can be determined. Finally,landslide displacement prediction is carried out for different displacement decomposition data,which is obtained from different parameters of SPA and with the moving average method. The results show that there is very good prediction accuracy based on the SPA displacement decomposition. Comprehensive analysis indicates that the SPA is a suitable method for the displacement decomposition in the landslide displacement prediction,and the prediction accuracy can further be improved.
引文
[1]汤罗圣,殷坤龙.加卸载响应比理论在水库型滑坡时间预测预报中的应用研究[J].水文地质工程地质,2012,39(6):93-96.[TANG L S,YIN K L.Research on the application of load-unload response ratio theory on time prediction of reservoir-type landslides[J].Hydrogeology&Engineering Geology,2012,39(6):93-96.(in Chinese)]
[2]杨建国,晏鄂川,程温鸣.滑坡变形特征的GPS监测信息识别研究[J].长江科学院院报,2012,29(3):24-28.[YANG J G,YAN E C,CHENG W M.Identification of GPS monitoring information of landslide deformation characteristics[J].Journal of Yangtze River Scientific Research Institute,2012,29(3):24-28.(in Chinese)]
[3]杜娟,殷坤龙,柴波.基于诱发因素响应分析的滑坡位移预测模型研究[J].岩石力学与工程学报,2009,28(9):1783-1789.[DU J,YIN K L,CHAI B.Study of displacement prediction model of landslide based on response analysis of inducing factors[J].Chinese Journal of Rock Mechanics and Engineering,2009,28(9):1783-1789.(in Chinese)]
[4]陈建胜,陈从新,赵海斌,等.基于Fourier级数的滑坡位移预测模型研究[J].工程地质计算机应用,2011(4):28-32.[CHEN J S,CHEN C X,ZHAO H B,et al.Study of displacement prediction model of landslide based on Fourier series[J].Engineering Geology Computer Application,2011(4):28-32.(in Chinese)]
[5]贺可强,孙林娜,王思敬.滑坡位移分形参数Hurst指数及其在堆积层滑坡预报中的应用[J].岩石力学与工程学报,2009,28(6):1107-1115.[HE K Q,SUN L N,WANG S J.Displacement fractal parameter hurst index and its application to prediction of debris landslides[J].Chinese Journal of Rock Mechanics and Engineering,2009,28(6):1107-1115.(in Chinese)]
[6]马文涛.基于小波变换和GALSSVM的边坡位移预测[J].岩土力学,2009,30(增2):394-398.[MA W T.Prediction of slope displacement based on wavelet transform and genetic algorithm-least square support vector machine[J].Rock and Soil Mechanics,2009,30(Sup2):394-398.(in Chinese)]
[7]徐峰,汪洋,杜娟,等.基于时间序列分析的滑坡位移预测模型研究[J].岩石力学与工程学报,2011,30(4):746-751.[XU F,WANG Y,DU J,et al.Study of displacement prediction model of landslide based on time series analysis[J].Chinese Journal of Rock Mechanics and Engineering,2011,30(4):746-751.(in Chinese)]
[8]徐毅青,唐益群,李献勇,等.改进欧拉算法的GM(1,1)模型预测滑坡变形[J].水文地质工程地质,2011,38(1):110-113.[XU Y Q,TANG Y Q,LI X Y,et al.The landslide deformation prediction with improved Euler Method of Gray System Model GM(1,1)[J].Hydrogeology&Engineering Geology,2011,38(1):110-113.(in Chinese)]
[9]姚林林,殷坤龙,陈丽霞,等.基于影响因子分析的滑坡位移预测模型研究[J].安全与环境工程,2006,13(1):19-22.[YAO L L,YIN K L,CHEN L X,et al.Primary study on the model allowed for influencing factors for the deformation prediction of landslide[J].Safety and Environmental Engineering,2006,13(1):19-22.(in Chinese)]
[10]沈良峰.应用指数平滑技术预测边坡位移[J].中国工程科学,2007,9(6):94-97.[SHEN L F.Research of the exponential smoothing technology for forecasting slope displacement[J].Engineering Science,2007,9(6):94-97.(in Chinese)]
[11]林大超,安凤平,郭章林,等.滑坡位移的多模态支持向量机模型预测[J].岩土力学,2011,32(增1):451-458.[LIN D C,AN F P,GUO Z L,et al.Prediction of landslide displacements through multimode support vector machine model[J].Rock and Soil Mechanics,2011,32(Sup1):451-458.(in Chinese)]
[12]范千,花向红.基于相空间重构与支持向量机预测滑坡位移的一种新方法[J].武汉大学学报:信息科学版,2009,34(2):248-251.[FAN Q,HUA X H.A novel method for forecasting landslide displacement based on phase space reconstruction and support vector machine[J].Geomatics and Information Science of Wuhan University,2009,34(2):248-251.(in Chinese)]
[13]Tarvainen M P,Ranta-Aho P O,Karjalainen P A.An advanced detrending method with application to HRV analysis[J].IEEE Transactions on Biomedical Engineering,2002,49(2):172-175.
[14]周念成,王予疆,陈刚,等.低频振荡模式辨识中信号非线性去趋的平滑先验方法[J].电力系统保护与控制,2012,40(11):1-5.[ZHOU N C,WANG Y J,CHEN G,et al.Smoothness prior approach to removing nonlinear trends from signals in identification of low frequency oscillation mode[J].Power System Protection and Control,2012,40(11):1-5.(inChinese)]
[15]LI L P,LIU C C,LI K,et al.Comparison of detrending methods in spectral analysis of heart rate variability[J].World Academy of Science,Engineering and Technology,2011,57:828-832.
[16]Karjalainen P A.Regulatization and Bayesian methods for evoked potential estimation[D].Finland:Kuopio University,1997.
[17]Kitagawa G,Gersch W.Smootness Priors Análysis of Time Series[M].Germany:Springer-Verlag,1996.
[18]易武,孟召平,易庆林.三峡库区滑坡预测理论与方法[M].北京:科学出版社,2011:46-51.[YI W,MENG Z P,YI Q L.Theory and method of landslide stability prediction in the Three Gorges reservoir area[M].Beijing:Science Press,2011:46-51.(in Chinese)]
[19]戴上平,宋永东.基于遗传算法与粒子群算法的支持向量机参数选择[J].计算机工程与科学,2012,34(10):113-117.[DAI S P,SONG Y D.Parameter selection of support vector machines based on the fusion of genetic algorithm and particle swarm optimization[J].Computer Engineering&Sciences,2012,34(10):113-117.(in Chinese)]
[20]CHANG C,LIN C.LibSVM:A Library for Support Vector Machines[EB/OL].[2014-04-01](2014-05-01).http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
[2]杨建国,晏鄂川,程温鸣.滑坡变形特征的GPS监测信息识别研究[J].长江科学院院报,2012,29(3):24-28.[YANG J G,YAN E C,CHENG W M.Identification of GPS monitoring information of landslide deformation characteristics[J].Journal of Yangtze River Scientific Research Institute,2012,29(3):24-28.(in Chinese)]
[3]杜娟,殷坤龙,柴波.基于诱发因素响应分析的滑坡位移预测模型研究[J].岩石力学与工程学报,2009,28(9):1783-1789.[DU J,YIN K L,CHAI B.Study of displacement prediction model of landslide based on response analysis of inducing factors[J].Chinese Journal of Rock Mechanics and Engineering,2009,28(9):1783-1789.(in Chinese)]
[4]陈建胜,陈从新,赵海斌,等.基于Fourier级数的滑坡位移预测模型研究[J].工程地质计算机应用,2011(4):28-32.[CHEN J S,CHEN C X,ZHAO H B,et al.Study of displacement prediction model of landslide based on Fourier series[J].Engineering Geology Computer Application,2011(4):28-32.(in Chinese)]
[5]贺可强,孙林娜,王思敬.滑坡位移分形参数Hurst指数及其在堆积层滑坡预报中的应用[J].岩石力学与工程学报,2009,28(6):1107-1115.[HE K Q,SUN L N,WANG S J.Displacement fractal parameter hurst index and its application to prediction of debris landslides[J].Chinese Journal of Rock Mechanics and Engineering,2009,28(6):1107-1115.(in Chinese)]
[6]马文涛.基于小波变换和GALSSVM的边坡位移预测[J].岩土力学,2009,30(增2):394-398.[MA W T.Prediction of slope displacement based on wavelet transform and genetic algorithm-least square support vector machine[J].Rock and Soil Mechanics,2009,30(Sup2):394-398.(in Chinese)]
[7]徐峰,汪洋,杜娟,等.基于时间序列分析的滑坡位移预测模型研究[J].岩石力学与工程学报,2011,30(4):746-751.[XU F,WANG Y,DU J,et al.Study of displacement prediction model of landslide based on time series analysis[J].Chinese Journal of Rock Mechanics and Engineering,2011,30(4):746-751.(in Chinese)]
[8]徐毅青,唐益群,李献勇,等.改进欧拉算法的GM(1,1)模型预测滑坡变形[J].水文地质工程地质,2011,38(1):110-113.[XU Y Q,TANG Y Q,LI X Y,et al.The landslide deformation prediction with improved Euler Method of Gray System Model GM(1,1)[J].Hydrogeology&Engineering Geology,2011,38(1):110-113.(in Chinese)]
[9]姚林林,殷坤龙,陈丽霞,等.基于影响因子分析的滑坡位移预测模型研究[J].安全与环境工程,2006,13(1):19-22.[YAO L L,YIN K L,CHEN L X,et al.Primary study on the model allowed for influencing factors for the deformation prediction of landslide[J].Safety and Environmental Engineering,2006,13(1):19-22.(in Chinese)]
[10]沈良峰.应用指数平滑技术预测边坡位移[J].中国工程科学,2007,9(6):94-97.[SHEN L F.Research of the exponential smoothing technology for forecasting slope displacement[J].Engineering Science,2007,9(6):94-97.(in Chinese)]
[11]林大超,安凤平,郭章林,等.滑坡位移的多模态支持向量机模型预测[J].岩土力学,2011,32(增1):451-458.[LIN D C,AN F P,GUO Z L,et al.Prediction of landslide displacements through multimode support vector machine model[J].Rock and Soil Mechanics,2011,32(Sup1):451-458.(in Chinese)]
[12]范千,花向红.基于相空间重构与支持向量机预测滑坡位移的一种新方法[J].武汉大学学报:信息科学版,2009,34(2):248-251.[FAN Q,HUA X H.A novel method for forecasting landslide displacement based on phase space reconstruction and support vector machine[J].Geomatics and Information Science of Wuhan University,2009,34(2):248-251.(in Chinese)]
[13]Tarvainen M P,Ranta-Aho P O,Karjalainen P A.An advanced detrending method with application to HRV analysis[J].IEEE Transactions on Biomedical Engineering,2002,49(2):172-175.
[14]周念成,王予疆,陈刚,等.低频振荡模式辨识中信号非线性去趋的平滑先验方法[J].电力系统保护与控制,2012,40(11):1-5.[ZHOU N C,WANG Y J,CHEN G,et al.Smoothness prior approach to removing nonlinear trends from signals in identification of low frequency oscillation mode[J].Power System Protection and Control,2012,40(11):1-5.(inChinese)]
[15]LI L P,LIU C C,LI K,et al.Comparison of detrending methods in spectral analysis of heart rate variability[J].World Academy of Science,Engineering and Technology,2011,57:828-832.
[16]Karjalainen P A.Regulatization and Bayesian methods for evoked potential estimation[D].Finland:Kuopio University,1997.
[17]Kitagawa G,Gersch W.Smootness Priors Análysis of Time Series[M].Germany:Springer-Verlag,1996.
[18]易武,孟召平,易庆林.三峡库区滑坡预测理论与方法[M].北京:科学出版社,2011:46-51.[YI W,MENG Z P,YI Q L.Theory and method of landslide stability prediction in the Three Gorges reservoir area[M].Beijing:Science Press,2011:46-51.(in Chinese)]
[19]戴上平,宋永东.基于遗传算法与粒子群算法的支持向量机参数选择[J].计算机工程与科学,2012,34(10):113-117.[DAI S P,SONG Y D.Parameter selection of support vector machines based on the fusion of genetic algorithm and particle swarm optimization[J].Computer Engineering&Sciences,2012,34(10):113-117.(in Chinese)]
[20]CHANG C,LIN C.LibSVM:A Library for Support Vector Machines[EB/OL].[2014-04-01](2014-05-01).http://www.csie.ntu.edu.tw/~cjlin/libsvm/.