基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究

doi:10.13722/j.cnki.jrme.2015.02.017

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (596 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要滑坡位移预测模型的选择及其参数的选取是滑坡位移预测中至关重要的2个问题，以往的模型在预测滑坡位移时具有诸多的限制和不足。以三峡库区白水河滑坡为研究对象，基于时间序列分析方法，分离提取出滑坡趋势性位移与周期性位移。前者主要受控于滑坡的内部因素(物质组成、地质构造、地形地貌等)，可用最小二乘法对其进行多项式拟合并预测；后者是由外部影响因素(季节性降雨、库水位变动等)导致，取当月降雨量、双月降雨量、库水位高程、月间库水位变化量、双月库水位变化量和年间累计位移增量作为周期性位移的影响因子，提出采用可优化选参的粒子群优化算法(PSO)与支持向量机回归(SVR)相结合的方法对其进行预测；将各分位移预测值叠加得到累计位移预测值。运用多种方法进行分析对比，结果表明，基于时间序列与PSO-SVR耦合模型的滑坡位移预测精度要明显高于BP神经网络模型、网格搜索法优化的支持向量机模型(GS)，其在滑坡位移预测中具有一定的理论基础和良好的应用前景。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：边坡工程, 滑坡, 位移预测, 时间序列, 粒子群优化算法, 支持向量机回归

Abstract：The choices of landslide displacement prediction models and relevant parameters are two of the most important issues in the landslide displacement prediction. The existing models have many limitations and shortcomings in predicting the landslide displacements. In this study，the trend displacement and the periodic displacement of Baishuihe landslide in the Three Gorges Reservoir area were separated based on the method of time series analysis. The former was considered to be mainly controlled by the internal factors of landslide(the composition，the geological structure，the topography，etc.)，and was fitted and predicted with the polynomial function. The latter was caused by the external influence factors(the seasonal rainfall，the water level changes of reservoir，etc.). Taking the rainfall of current month，the cumulative rainfall of anterior two months，the reservoir level，the fluctuation of reservoir level of current month，the fluctuation of reservoir level of anterior two months and the cumulative increment of total displacement in current year as the influencing factors of periodic displacement，a combination of the particle swarm optimization algorithm(PSO) optimizing the parameters of model and the support vector machine regression(SVR) method for the periodic displacement prediction was proposed. The predicted values of the two kinds of displacements were superimposed to obtain the cumulative displacement. The result showed that the landslide displacements based on the time series prediction and PSO-SVR model were better than those from the grid search SVM and the BP neural network models.

Key words： slope engineering landslide displacement prediction time series particle swarm optimization algorithm support vector regression

收稿日期: 2014-03-17

引用本文:

张俊1，殷坤龙1，王佳佳1，黄发明2. 基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J]. 岩石力学与工程学报, 2015, 34(02): 382-391.
ZHANG Jun1，YIN Kunlong1，WANG Jiajia1，HUANG Faming2. DISPLACEMENT PREDICTION OF BAISHUIHE LANDSLIDE BASED ON TIME SERIES AND PSO-SVR MODEL. , 2015, 34(02): 382-391.

链接本文:

http://www.rockmech.org/CN/10.13722/j.cnki.jrme.2015.02.017 或 http://www.rockmech.org/CN/Y2015/V34/I02/382

[12]	李秀珍，许强. 滑坡预报模型和预报判据[J]. 灾害学，2003，18(4)：72-79.(LI Xiuzhen，XU Qiang. Models and criteria of landslide prediction[J]. Journal of Catastrophology，2003，18(4)：72-79.(in Chinese))
[3]	刘晓，曾祥虎，刘春宇，等. 边坡非线性位移的神经网络-时间序列分析[J]. 岩石力学与工程学报，2005，24(19)：3 499-3 504. (LIU Xiao，ZENG Xianghu，LIU Chunyu，et al. Research on artificial neural network-time series analysis of slope nonlinear displacement[J]. Chinese Journal of Rock Mechanics and Engineering，2005，24(19)：3 499-3 504.(in Chinese)) " target="_blank">
[1]	殷坤龙. 滑坡灾害预测预报[M]. 武汉：中国地质大学出版社，2004：1-3.(YIN Kunlong. Landslide hazard prediction and evaluation[M]. Wuhan：China University of Geosciences Press，2004：1-3.(in Chinese)) " target="_blank">
[4]	郝小员，郝小红，熊红梅，等. 滑坡时间预报的非平稳时间序列方法研究[J]. 工程地质学报，1999，7(3)：279-283.(HAO Xiaoyuan，HAO Xiaohong，XIONG Hongmei，et al. Research on landslide time forecast by the unstable time series method[J]. Journal of Engineering Geology，1999，7(3)：279-283.(in Chinese))
[8]	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)：1 783-1 789.(DU Juan，YIN Kunlong，CHAI Bo. 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)： 1 783-1 789.(in Chinese))
[13]	李强，李瑞有. 滑坡位移监测动态预报时间序列分析技术研究[J]. 长江科学院院报，2005，22(6)：22-25.(LI Qiang，LI Ruiyou. Research of dynamic predication technique for landslide displacement monitoring[J]. Journal of Yangtze River Scientific Research Institute，2005，22(6)：22-25.(in Chinese))
[16]	VAPNIK V. The nature of statistical learning theory[M]. New York，USA：Springer-Verlag，2000：138-167. " target="_blank">
[5]	邢林啸. 三峡库区典型堆积层滑坡成因机制与预测预报研究——以白水河滑坡为例[硕士学位论文][D]. 武汉：中国地质大学，2012. (XING Linxiao. Research of genetic mechanism and prediction of typical debris landslide in the Three Gorges[M. S. Thesis][D]. Wuhan：China University of Geosciences，2012.(in Chinese))
[17]	YILMAZ I K. Comparison of landslide susceptibility mapping methodologies for Koyulhisar，Turkey：conditional probability，logistic regression，artificial neural networks，and support vector machine[J]. Environmental Earth Sciences，2010，61(4)：821-836.
[18]	USTUN B，MELSSEN W J，OUDENHUIJZEN M，et al. Determination of optimal support vector regression parameters by genetic algorithms and simplex optimization[J]. Analytica Chimica Acta，2005，544(1/2)：292-305. " target="_blank">
[20]	EBERHART R，KENNEDY J. A new optimizer using particle swarm theory[C]// Proceedings of the Sixth International Symposium on Micro Machine and Human Science. Nagoya，Japan：IEEE，1995：39-43. " target="_blank">
[22]	陈洪凯，魏来，谭玲. 降雨型滑坡经验性降雨阈值研究综述[J]. 重庆交通大学学报：自然科学版，2012，31(5)：990-996.(CHEN Hongkai，WEI Lai，TAN Ling. Review of research on empirical rainfall threshold of rainfall-induced landslide[J]. Journal of Chongqing Jiaotong University：Natural Science，2012，31(5)：990-996.(in Chinese))
[23]	刘小伟，刘高，谌文武，等. 降雨对边坡变形破坏影响的综合分析[J]. 岩石力学与工程学报，2003，22(增2)：2 715-2 718.(LIU Xiaowei，LIU Gao，CHEN Wenwu，et al. Analysis on rainfall influence on slope deformation and failure[J]. Chinese Journal of Rock Mechanics and Engineering，2003，22(Supp.2)：2 715-2 718.(in Chinese))
[14]	卢理. 时间序列加法模型的分解预测研究[硕士学位论文][D]. 成都：西南交通大学，2007.(LU Li. Research of time series addition model decomposition-foreasting[M. S. Thesis][D]. Chengdu：Southwest Jiaotong University，2007.(in Chinese)) " target="_blank">
[21]	缪海波. 三峡库区堆积层滑坡渐进破坏机理及其预测预报研究——以八字门滑坡为例[硕士学位论文][D]. 武汉：中国地质大学，2009. (MIAO Haibo. Research of progressive failure mechanism and prediction of debris landslide in the Three Gorges Reservoir—Taking Bazimen landslide for example[M. S. Thesis][D]. Wuhan：China University of Geosciences，2009.(in Chinese)) " target="_blank">
[24]	李晓，张年学，廖秋林，等. 库水位涨落与降雨联合作用下滑坡地下水动力场分析[J]. 岩石力学与工程学报，2004，23(21)：3 714- 3 720.(LI Xiao，ZHAMG Nianxue，LIAO Qiulin，et al. Analysis on hydrodynamic field influenced by combination of rainfall and reservoir level fluctuation[J]. Chinese Journal of Rock Mechanics and Engineering，2004，23(21)：3 714-3 720.(in Chinese))
[25]	汪洋，殷坤龙，安关峰. 滑坡敏感因子的灰色关联分析[J]. 岩土力学，2004，25(1)：91-93.(WANG Yang，YIN Kunlong，AN Guanfeng. Grey correlation analysis of sensitive factors of landslide[J]. Rock and Soil Mechanics，2004，25(1)：91-93.(in Chinese))
[2]	许强，黄润秋，李秀珍. 滑坡时间预测预报研究进展[J]. 地球科学进展，2004，19(3)：478-483.(XU Qiang，HUANG Runqiu，LI Xiuzhen. Research progress on the landslide time prediction[J]. Advance in Earth Sciences，2004，19(3)：478-483.(in Chinese))
[6]	彭令，牛瑞卿，吴婷. 时间序列分析与支持向量机的滑坡位移预测[J]. 浙江大学学报：工学版，2013，47(9)：1 672-1 679.(PENG Ling，NIU Ruiqing，WU Ting. Time series analysis and support vector machine for landslide displacement prediction[J]. Journal of Zhejiang University：Engineering Science，2013，47(9)：1 672-1 679.(in Chinese))
[7]	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.(in Chinese))
[9]	姜谙男，梁冰. 基于PSO-SVM的大坝渗流监测时间序列非线性预报模型[J]. 水利学报，2006，37(3)：331-335.(JIANG Annan，LIANG Bing. Nonlinear time series prediction model for dam seepage flow based on PSO-SVM[J]. Journal of Hydraulic Engineering，2006，37(3)：331-335.(in Chinese)) " target="_blank">
[10]	姜谙男. 基于PSO-SVM非线性时序模型的隧洞围岩变形预报[J]. 岩土力学，2007，28(6)：1 176-1 180.(JIANG Annan. Forecasting nonlinear time series of surrounding rock deformations of underground cavern based on PSO-SVM[J]. Rock and Soil Mechanics，2007，28(6)： 1 176-1 180.(in Chinese)) " target="_blank">
[11]	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 Feng，WANG Yang，DU Juan，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))
[15]	郑东健，顾冲时，吴中如. 边坡变形的多因素时变预测模型[J]. 岩石力学与工程学报，2005，24(17)：3 180-3 184.(ZHENG Dongjian，GU Chongshi，WU Zhongru. Time series evolution forecasting model of slope deformation based on multiple factors[J]. Chinese Journal of Rock Mechanics and Engineering，2005，24(17)：3 180-3 184.(in Chinese))
[19]	PRADHAN B. A comparative study on the predictive ability of the decision tree，support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS[J]. Computers and Geosciences，2013，51：350-365. " target="_blank">