联合多种数据驱动建模方法的滑坡位移预测研究
|
摘要
边坡位移是滑坡演化的宏观体现,分析并预测滑坡位移发展态势对于防灾减灾具有重要意义。由于滑坡位移曲线具有明显的非线性特征,单一模型往往难以刻画其非线性与复杂性。为发展一种普遍适用于滑坡位移的预测方法,提出了一种联合多种数据驱动模型的新方法。该方法根据时间序列分析理论,将滑坡位移序列分解为趋势项和周期项,趋势项采用并联型灰色神经网络处理,周期项则采用人工蜂群算法(ABC)优化后的极限学习机模型(ELM)处理,从而充分应用各种模型的优点。以三峡库区白水河和八字门滑坡为例,对位移数据进行分析处理后,灰色神经网络模型预测其趋势性位移,改进后的极限学习机模型对周期性位移进行训练及预测。结果表明:在预测精度上,优化后的极限学习机模型准确度高于极限学习机模型及小波神经网络等方法,提出的灰色神经网络与ABC-ELM的组合模型可作为实际工程的一个参考。。
Slope displacement is a macroscopic manifestation of landslide evolution. Analyzing and predicting landslide displacement are of great significance for disaster prevention and mitigation. Since the landslide displacement is obvious nonlinear characteristics,single model is often difficult to delineate the complexity and nonlinearity of landslide displacement. To find a universal method for predicting landslide displacement,a new method combined with multiple data-driven modeling methods is proposed to predict the landslide displacement. The new method is based on time series analysis. The landslide displacement sequence is decomposed into trend term and periodic term. The trend term is treated using parallel grey neural network,and uses the artificial bee conony( ABC) to find the optimal extreme learning machine model( ELM) to predict the periodic term. This paper takes Baishuihe landslide and Bazimen landslide for examples. After statistically analyzing the displacement data,the gray neural network model predicts trending displacement,and the optimized learning machine model train and predictthe periodic term. The result shows that the optimized extreme learning machine model is better than the extreme learning machine model and wavelet neural network. Therefore,the proposed combination of grey neural network and ABC-ELM can be used as a reference for practical engineering.
Slope displacement is a macroscopic manifestation of landslide evolution. Analyzing and predicting landslide displacement are of great significance for disaster prevention and mitigation. Since the landslide displacement is obvious nonlinear characteristics,single model is often difficult to delineate the complexity and nonlinearity of landslide displacement. To find a universal method for predicting landslide displacement,a new method combined with multiple data-driven modeling methods is proposed to predict the landslide displacement. The new method is based on time series analysis. The landslide displacement sequence is decomposed into trend term and periodic term. The trend term is treated using parallel grey neural network,and uses the artificial bee conony( ABC) to find the optimal extreme learning machine model( ELM) to predict the periodic term. This paper takes Baishuihe landslide and Bazimen landslide for examples. After statistically analyzing the displacement data,the gray neural network model predicts trending displacement,and the optimized learning machine model train and predictthe periodic term. The result shows that the optimized extreme learning machine model is better than the extreme learning machine model and wavelet neural network. Therefore,the proposed combination of grey neural network and ABC-ELM can be used as a reference for practical engineering.
引文
Chen S Y,Wang W.2004.Grey neural network forecasting for traffic flow[J].Journal of Southeast University(Natural Science Edition),34(4):541-544.
Chen W G,He K Q,Zhang J.2013.System dynamics based unload-load response ratio parameter and its application to evaluating debris landslide stability[J].Journal of Engineering Geology,21(4):570-576.
Du J,Yin K L,Chai B.2009.Study of displacement prediction model of landslide based on response analysis of inducing factors[J].Chinese Journal of Rock Mechanics and Engineering,28(9):1783-1789.
Gao C Y.2017.Displacement prediction of landslide based on new intelligent algorithm of ELM[J].Yangtze River,48(7):46-49.
Hao X Y,Hao X H,Xiong H M,et al.1999.Research on landslide time forecast by the unstable time series method[J].Journal of Engineering Geology,7(3):279-283.
Huang C Z.2011.Prediction of landsliding time under action of groundwater[J].Journal of Engineering Geology,19(6):816-822.
Jin H Y,Xu W Y.2008.Prediction of slope deformation modes with weighted function combination method[J].Journal of Engineering Geology,16(4):518-521.
Karaboga D.2005.An idea based on honey bee swarm for nu-merical optimization[R].Kayseri,Turkey:Computers Engineering Department,Engineering Faculty,Erciyes University.
Li H J,Xu Q,He Y S,et al.2016.Predictive modeling of landslide displacement by wavelet analysis and multiple extreme learning machines[J].Journal of Engineering Geology,24(5):721-731.
Li X Z,Wang C H,Kong J M.2009.Actual case based prediction models for landslide deformation[J].Journal of Engineering Geology,17(4):538-544.
Miao F S,Wu Y P,Xie Y H,et al.2016.Displacement prediction of Baishuihe landslide based on multi-algorithm optimization and SVRmodel[J].Journal of Engineering Geology,24(6):1136-1144.
Miao H B,Yin K L,Chai B,et al.2009.Deformation prediction of landslide based on the analysis of non-stationary time series[J].Geological Science and Technology Information,28(4):107-111.
Mufundirwa A,Fujii Y,Kodama J.2010.A new practical method for prediction of geo mechanical failure time[J].International Journal of Rock Mechanics and Mining Scientific,47(7):1079-1090.
Pan Y M,Deng Y H,Zhang Q Z.2013.Deter ministic prediction of wavelet neural network model and its application[J].Journal of Computer Applications,33(4):1001-1005.
Wang M T.2000.Study on method of calculating optimal approximate solution about weight coefficients of combined forecasting methods[J].System Engineering Theory and Practice,20(3):104-109.
Xu F,Wang Y,Du J,et al.2011.Study of displacement prediction model of landslide based on time series analysis[J].Chinese Journal of Rock Mechanics and Engineering,30(4):746-751.
Yan T Z.1989.New mode of forecasting land subsidence regularity[J].Earth Science-Journal of China University of Geosciences,14(2):181-188.
Zhang J,Yin K L,Wang J J,et al.2015.Displacement prediction of Baishuihe landslide based on time series and PSO-SVR model[J].Chinese Journal of Rock Mechanics and Engineering,34(2):382-391.
陈淑燕,王炜.2004.交通量的灰色神经网络预测方法[J].东南大学学报(自然科学版),34(4):541-544.
陈为公,贺可强,张娟.2013.基于系统动力学的卸加载响应比参数及其在堆积层滑坡稳定性评价中的应用[J].工程地质学报,21(4):570-576.
杜鹃,殷坤龙,柴波.2009.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,28(9):1783-1789.
郝小员,郝小红,熊红梅,等.1999.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,7(3):279-283.
黄承中.2011.考虑地下水作用的滑坡时间预测研究[J].工程地质学报,19(6):816-822.
金海元,徐卫亚.2008.加权函数组合预测边坡变形模型的研究[J].工程地质学报,16(4):518-521.
李骅锦,许强,何雨森,等.2016.WA联合ELM与OS-ELM的滑坡位移预测模型[J].工程地质学报,24(5):721-730.
李秀珍,王成华,孔纪名.2009.基于最优加权组合模型及高斯-牛顿法的滑坡变形预测研究[J].工程地质学报,17(4):538-544.
苗发盛,吴益平,谢媛华,等.2016.基于多算法参数优化与SVR模型的白水河滑坡位移预测[J].工程地质学报,24(6):1136-1144.
缪海波,殷坤龙,柴波,等.2009.基于非平稳时间序列分析的滑坡变形预测[J].地质科技情报,28(4):107-111.
潘玉民,邓永红,张全柱.2013.小波神经网络模型的确定性预测及应用[J].计算机应用,33(4):1001-1005.
王明涛.2000.确定组合预测权系数最优近似解的方法研究[J].系统工程理论与实践,20(3):104-109.
徐峰,汪洋,杜娟,等.2011.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,30(4):746-751.
晏同珍.1989.地面沉降规律预测新模式[J].地球科学-中国地质大学学报,14(2):181-188.
张俊,殷坤龙,王佳佳,等.2015.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,34(2):382-391.
Chen W G,He K Q,Zhang J.2013.System dynamics based unload-load response ratio parameter and its application to evaluating debris landslide stability[J].Journal of Engineering Geology,21(4):570-576.
Du J,Yin K L,Chai B.2009.Study of displacement prediction model of landslide based on response analysis of inducing factors[J].Chinese Journal of Rock Mechanics and Engineering,28(9):1783-1789.
Gao C Y.2017.Displacement prediction of landslide based on new intelligent algorithm of ELM[J].Yangtze River,48(7):46-49.
Hao X Y,Hao X H,Xiong H M,et al.1999.Research on landslide time forecast by the unstable time series method[J].Journal of Engineering Geology,7(3):279-283.
Huang C Z.2011.Prediction of landsliding time under action of groundwater[J].Journal of Engineering Geology,19(6):816-822.
Jin H Y,Xu W Y.2008.Prediction of slope deformation modes with weighted function combination method[J].Journal of Engineering Geology,16(4):518-521.
Karaboga D.2005.An idea based on honey bee swarm for nu-merical optimization[R].Kayseri,Turkey:Computers Engineering Department,Engineering Faculty,Erciyes University.
Li H J,Xu Q,He Y S,et al.2016.Predictive modeling of landslide displacement by wavelet analysis and multiple extreme learning machines[J].Journal of Engineering Geology,24(5):721-731.
Li X Z,Wang C H,Kong J M.2009.Actual case based prediction models for landslide deformation[J].Journal of Engineering Geology,17(4):538-544.
Miao F S,Wu Y P,Xie Y H,et al.2016.Displacement prediction of Baishuihe landslide based on multi-algorithm optimization and SVRmodel[J].Journal of Engineering Geology,24(6):1136-1144.
Miao H B,Yin K L,Chai B,et al.2009.Deformation prediction of landslide based on the analysis of non-stationary time series[J].Geological Science and Technology Information,28(4):107-111.
Mufundirwa A,Fujii Y,Kodama J.2010.A new practical method for prediction of geo mechanical failure time[J].International Journal of Rock Mechanics and Mining Scientific,47(7):1079-1090.
Pan Y M,Deng Y H,Zhang Q Z.2013.Deter ministic prediction of wavelet neural network model and its application[J].Journal of Computer Applications,33(4):1001-1005.
Wang M T.2000.Study on method of calculating optimal approximate solution about weight coefficients of combined forecasting methods[J].System Engineering Theory and Practice,20(3):104-109.
Xu F,Wang Y,Du J,et al.2011.Study of displacement prediction model of landslide based on time series analysis[J].Chinese Journal of Rock Mechanics and Engineering,30(4):746-751.
Yan T Z.1989.New mode of forecasting land subsidence regularity[J].Earth Science-Journal of China University of Geosciences,14(2):181-188.
Zhang J,Yin K L,Wang J J,et al.2015.Displacement prediction of Baishuihe landslide based on time series and PSO-SVR model[J].Chinese Journal of Rock Mechanics and Engineering,34(2):382-391.
陈淑燕,王炜.2004.交通量的灰色神经网络预测方法[J].东南大学学报(自然科学版),34(4):541-544.
陈为公,贺可强,张娟.2013.基于系统动力学的卸加载响应比参数及其在堆积层滑坡稳定性评价中的应用[J].工程地质学报,21(4):570-576.
杜鹃,殷坤龙,柴波.2009.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,28(9):1783-1789.
郝小员,郝小红,熊红梅,等.1999.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,7(3):279-283.
黄承中.2011.考虑地下水作用的滑坡时间预测研究[J].工程地质学报,19(6):816-822.
金海元,徐卫亚.2008.加权函数组合预测边坡变形模型的研究[J].工程地质学报,16(4):518-521.
李骅锦,许强,何雨森,等.2016.WA联合ELM与OS-ELM的滑坡位移预测模型[J].工程地质学报,24(5):721-730.
李秀珍,王成华,孔纪名.2009.基于最优加权组合模型及高斯-牛顿法的滑坡变形预测研究[J].工程地质学报,17(4):538-544.
苗发盛,吴益平,谢媛华,等.2016.基于多算法参数优化与SVR模型的白水河滑坡位移预测[J].工程地质学报,24(6):1136-1144.
缪海波,殷坤龙,柴波,等.2009.基于非平稳时间序列分析的滑坡变形预测[J].地质科技情报,28(4):107-111.
潘玉民,邓永红,张全柱.2013.小波神经网络模型的确定性预测及应用[J].计算机应用,33(4):1001-1005.
王明涛.2000.确定组合预测权系数最优近似解的方法研究[J].系统工程理论与实践,20(3):104-109.
徐峰,汪洋,杜娟,等.2011.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,30(4):746-751.
晏同珍.1989.地面沉降规律预测新模式[J].地球科学-中国地质大学学报,14(2):181-188.
张俊,殷坤龙,王佳佳,等.2015.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,34(2):382-391.