基于光纤监测和PSO-SVM模型的马家沟滑坡深部位移预测研究
|
摘要
滑坡位移预测效果一方面取决于预测模型的优劣,另一方面取决于野外监测数据的质量。针对目前滑坡常规监测技术与评价方法的不足,本文采用光纤监测技术、监测数据与PSO-SVM预测模型相结合的评价方法,对三峡马家沟Ⅰ号滑坡的深部位移进行了预测;通过对320个滑坡深部位移光纤监测数据分析,基于时间序列法,将滑坡位移分为趋势性位移和波动性位移;趋势性位移采用拟合法进行预测,波动性位移采用PSO-SVM模型进行预测;最后将趋势项和波动项位移预测值叠加得到累积位移的预测值。研究结果表明,PSO-SVM模型对波动性位移预测的均方根误差0. 51 mm,平均绝对百分误差0. 37 mm,能准确预测滑坡波动项位移;累积位移预测值与实测值的相关系数为0. 98,均方根误差为0. 54 mm,预测效果较好,可以用来对滑坡深部位移进行短期预测。
There are two main factors that influence the accuracy of landslide displacement prediction. One is the reliability of the prediction model and the other is the quality of field monitoring data. Currently,conventional landslide monitoring technology and evaluation methods have many limitations and shortcomings. In this paper,we propose a new evaluation methodology of the combination of fiber-optic monitoring technology,monitoring data and PSO-SVM prediction model. We use it to predict the deep displacement of Majiagou No. 1 landslide in the Three Gorges Reservoir. Firstly,by analyzing 320 fiber-optics monitoring data of landslide deep displacement,we decompose accumulative displacement into trend and fluctuant components based on the time series method. Then,the trend displacement is predicted with the fitting method. The fluctuant displacement is predicted with the PSOSVM model. Lastly,the prediction of cumulative displacement is computed with the predicted periodic and fluctuant displacement values. Research results show that the root mean square error is 0. 51 mm and an average absolute percentage error is 0. 37 mm,which demonstrate this model has a preferable prediction effect. The predicted total displacement show great consistency with the measured total displacement,with the RSME of 0. 54 mm and the correlation coefficient of 0. 98,respectively. This method can be used to make short-term predictions of landslide deep displacement.
There are two main factors that influence the accuracy of landslide displacement prediction. One is the reliability of the prediction model and the other is the quality of field monitoring data. Currently,conventional landslide monitoring technology and evaluation methods have many limitations and shortcomings. In this paper,we propose a new evaluation methodology of the combination of fiber-optic monitoring technology,monitoring data and PSO-SVM prediction model. We use it to predict the deep displacement of Majiagou No. 1 landslide in the Three Gorges Reservoir. Firstly,by analyzing 320 fiber-optics monitoring data of landslide deep displacement,we decompose accumulative displacement into trend and fluctuant components based on the time series method. Then,the trend displacement is predicted with the fitting method. The fluctuant displacement is predicted with the PSOSVM model. Lastly,the prediction of cumulative displacement is computed with the predicted periodic and fluctuant displacement values. Research results show that the root mean square error is 0. 51 mm and an average absolute percentage error is 0. 37 mm,which demonstrate this model has a preferable prediction effect. The predicted total displacement show great consistency with the measured total displacement,with the RSME of 0. 54 mm and the correlation coefficient of 0. 98,respectively. This method can be used to make short-term predictions of landslide deep displacement.
引文
Cortes C,Vapnik V.1995.Support-vector networks[J].Machine Learning,20(3):273-297.
Dai Z W,Yin Y P,Wei Y J,et al.2016.Deformation and failure mechanism of Outang landslide in Three Gorges Reservoir area[J].Journal of Engineering Geology,24(1):44-55.
Deng D M,Liang Y,Wang L Q,et al.2017.Displacement prediction method based on ensemble empirical mode decomposition and support vector machine regression:a case of landslides in Three Gorges Reservoir area[J].Rock and Soil Mechanics,38(12):3660-3669.
Ding Y,Wang Q C,Shi S Y,et al.2011.Analysis on kinetic characteristics of landslide by means of monitoring in deep ground[J].Journal of Engineering Geology,19(2):284-288.
He M C.2009.Real-time remote monitoring and forecasting system for geological disasters of landslides and its engineering application[J].Chinese Journal of Rock Mechanics and Engineering,28(6):1081-1090.
Jiang A N.2007.Forecasting nonlinear time series of surrounding rock deformations of underground cavern based on PSO-SVM[J].Rock and Soil Mechanics,28(6):1176-1180.
Jie Q,Shi B,Luo W Q,et al.2015.Analysis of DFOD-based association rules on multi-fields data monitoring of slope[J].Journal of Engineering Geology,23(6):1146-1152.
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,Zhang N X,Liao Q L,et al.2004.Analysis on hydrodynamic field influenced by combination of rainfall and reservoir level fluctuation[J].Chinese Journal of Rock Mechanics and Engineering,23(21):3714-3720.
Liu H P,Wang J G,Yang T L,et al.2006.Method to measure strain by separating temperature effect with fiber Bragg grating[J].Journal of Applied Optics,27(3):235-238.
Othonos A,Kalli K,Kohnke G E.2000.Fiber Bragg gratings:Fundamentals and applications in telecommunications and sensing[J].Physics Today,53(5):61-62.
Sun Y J.2015.Bank slop multi-fields monitoring based on fiber optic sensing technologies and stability evaluation study[D].Nanjing:Nanjing University.
Vapnik V,Golowich S E,Smola A.1996.Support vector method for function approximation,regression estimation,and signal processing[J].Advances in Neural Information Processing Systems,9:281-287.
Wang L N,Yan E C,Lu W B,et al.2016.Load-unload response of colluvial landslide with reservoir water level fluctuation and stability prediction[J].Journal of Engineering Geology,24(6):1048-1055.
Wang Q C.2017.Long-term monitoring and trend analysis of Majiagou landslide in Three Gorges project based on DFOS[D].Nanjing:Nanjing University.
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.
Xu Q,Huang R Q,Li X Z.2004.Research progress in time forecast and prediction of landslides[J].Advances in Earth Science,19(3):478-483.
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.
Zhang X,Tan Z Y,Zhou C M.2016.Seepage and stability analysis of landslide under the change of reservoir water levels[J].Chinese Journal of Rock Mechanics and Engineering,35(4):713-723.
Zhou C,Yin K L,Cao Y,et al.2016.Application of time series analysis and PSO-SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir,China[J].Engineering Geology,204:108-120.
Zhu H H,Yin J H,Hong C Y,et al.2010.Fiber optic based monitoring technologies of slope engineering.Geotechnical Investigation&Surveying,38(3):6-10.
代贞伟,殷跃平,魏云杰,等.2016.三峡库区藕塘滑坡变形失稳机制研究[J].工程地质学报,24(1):44-55.
邓冬梅,梁烨,王亮清,等.2017.基于集合经验模态分解与支持向量机回归的位移预测方法:以三峡库区滑坡为例[J].岩土力学,38(12):3660-3669.
丁瑜,王全才,石书云,等.2011.基于深部监测的滑坡动态特征分析[J].工程地质学报,19(2):284-288.
何满潮.2009.滑坡地质灾害远程监测预报系统及其工程应用[J].岩石力学与工程学报,28(6):1081-1090.
姜谙男.2007.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,28(6):1176-1180.
揭奇,施斌,罗文强,等.2015.基于DFOS的边坡多场信息关联规则分析[J].工程地质学报,23(6):1146-1152.
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):721-731.
李晓,张年学,廖秋林,等.2004.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,23(21):3714-3720.
刘汉平,王健刚,杨田林,等.2006.可分离温度影响的FBG应变测量方法[J].应用光学,27(3):235-238.
孙义杰.2015.库岸边坡多场光纤监测技术与稳定性评价研究[D].南京:南京大学.
汪其超.2017.基于DFOS的三峡马家沟滑坡长期监测与趋势分析[D].南京:南京大学.
王鲁男,晏鄂川,陆文博,等.2016.库水变动下堆积层滑坡加卸载响应规律与稳定性预测[J].工程地质学报,24(6):1048-1055.
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.
许强,黄润秋,李秀珍.2004.滑坡时间预测预报研究进展[J].地球科学进展,19(3):478-483.
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.
张旭,谭卓英,周春梅.2016.库水位变化下滑坡渗流机制与稳定性分析[J].岩石力学与工程学报,35(4):713-723.
朱鸿鹄,殷建华,洪成雨,等.2010.基于光纤传感的边坡工程监测技术[J].工程勘察,38(3):6-10.
Dai Z W,Yin Y P,Wei Y J,et al.2016.Deformation and failure mechanism of Outang landslide in Three Gorges Reservoir area[J].Journal of Engineering Geology,24(1):44-55.
Deng D M,Liang Y,Wang L Q,et al.2017.Displacement prediction method based on ensemble empirical mode decomposition and support vector machine regression:a case of landslides in Three Gorges Reservoir area[J].Rock and Soil Mechanics,38(12):3660-3669.
Ding Y,Wang Q C,Shi S Y,et al.2011.Analysis on kinetic characteristics of landslide by means of monitoring in deep ground[J].Journal of Engineering Geology,19(2):284-288.
He M C.2009.Real-time remote monitoring and forecasting system for geological disasters of landslides and its engineering application[J].Chinese Journal of Rock Mechanics and Engineering,28(6):1081-1090.
Jiang A N.2007.Forecasting nonlinear time series of surrounding rock deformations of underground cavern based on PSO-SVM[J].Rock and Soil Mechanics,28(6):1176-1180.
Jie Q,Shi B,Luo W Q,et al.2015.Analysis of DFOD-based association rules on multi-fields data monitoring of slope[J].Journal of Engineering Geology,23(6):1146-1152.
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,Zhang N X,Liao Q L,et al.2004.Analysis on hydrodynamic field influenced by combination of rainfall and reservoir level fluctuation[J].Chinese Journal of Rock Mechanics and Engineering,23(21):3714-3720.
Liu H P,Wang J G,Yang T L,et al.2006.Method to measure strain by separating temperature effect with fiber Bragg grating[J].Journal of Applied Optics,27(3):235-238.
Othonos A,Kalli K,Kohnke G E.2000.Fiber Bragg gratings:Fundamentals and applications in telecommunications and sensing[J].Physics Today,53(5):61-62.
Sun Y J.2015.Bank slop multi-fields monitoring based on fiber optic sensing technologies and stability evaluation study[D].Nanjing:Nanjing University.
Vapnik V,Golowich S E,Smola A.1996.Support vector method for function approximation,regression estimation,and signal processing[J].Advances in Neural Information Processing Systems,9:281-287.
Wang L N,Yan E C,Lu W B,et al.2016.Load-unload response of colluvial landslide with reservoir water level fluctuation and stability prediction[J].Journal of Engineering Geology,24(6):1048-1055.
Wang Q C.2017.Long-term monitoring and trend analysis of Majiagou landslide in Three Gorges project based on DFOS[D].Nanjing:Nanjing University.
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.
Xu Q,Huang R Q,Li X Z.2004.Research progress in time forecast and prediction of landslides[J].Advances in Earth Science,19(3):478-483.
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.
Zhang X,Tan Z Y,Zhou C M.2016.Seepage and stability analysis of landslide under the change of reservoir water levels[J].Chinese Journal of Rock Mechanics and Engineering,35(4):713-723.
Zhou C,Yin K L,Cao Y,et al.2016.Application of time series analysis and PSO-SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir,China[J].Engineering Geology,204:108-120.
Zhu H H,Yin J H,Hong C Y,et al.2010.Fiber optic based monitoring technologies of slope engineering.Geotechnical Investigation&Surveying,38(3):6-10.
代贞伟,殷跃平,魏云杰,等.2016.三峡库区藕塘滑坡变形失稳机制研究[J].工程地质学报,24(1):44-55.
邓冬梅,梁烨,王亮清,等.2017.基于集合经验模态分解与支持向量机回归的位移预测方法:以三峡库区滑坡为例[J].岩土力学,38(12):3660-3669.
丁瑜,王全才,石书云,等.2011.基于深部监测的滑坡动态特征分析[J].工程地质学报,19(2):284-288.
何满潮.2009.滑坡地质灾害远程监测预报系统及其工程应用[J].岩石力学与工程学报,28(6):1081-1090.
姜谙男.2007.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,28(6):1176-1180.
揭奇,施斌,罗文强,等.2015.基于DFOS的边坡多场信息关联规则分析[J].工程地质学报,23(6):1146-1152.
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):721-731.
李晓,张年学,廖秋林,等.2004.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,23(21):3714-3720.
刘汉平,王健刚,杨田林,等.2006.可分离温度影响的FBG应变测量方法[J].应用光学,27(3):235-238.
孙义杰.2015.库岸边坡多场光纤监测技术与稳定性评价研究[D].南京:南京大学.
汪其超.2017.基于DFOS的三峡马家沟滑坡长期监测与趋势分析[D].南京:南京大学.
王鲁男,晏鄂川,陆文博,等.2016.库水变动下堆积层滑坡加卸载响应规律与稳定性预测[J].工程地质学报,24(6):1048-1055.
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.
许强,黄润秋,李秀珍.2004.滑坡时间预测预报研究进展[J].地球科学进展,19(3):478-483.
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.
张旭,谭卓英,周春梅.2016.库水位变化下滑坡渗流机制与稳定性分析[J].岩石力学与工程学报,35(4):713-723.
朱鸿鹄,殷建华,洪成雨,等.2010.基于光纤传感的边坡工程监测技术[J].工程勘察,38(3):6-10.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |