改进极限学习机的不同类型滑坡位移预测
|
摘要
针对经典智能算法用于滑坡位移预测时存在的网络结构参数选取复杂、易陷入局部极小等缺陷,提出了基于改进极限学习机ELM(Extreme Learning Machine)的滑坡位移预测模型。在滑坡变形位移状态辨识基础上,根据其位移变化特征,将滑坡位移曲线类型划分减速-匀速型、匀速-增速型、减速-匀速-增速型、复合型4类,将改进的ELM算法分别用于4种不同类型的滑坡位移预测。基于改进ELM算法构建滑坡位移预测模型时,采用二值区间搜索算法选定最佳隐含层神经元个数和激励函数,并融入数据滚动建模思想,以期提高网络泛化能力和预测精度。以链子崖、卧龙寺、古树屋、新滩滑坡体为例,对ELM预测的适用性进行讨论,实验结果表明,基于ELM构建不同类型滑坡位移预测模型时,具有较高的预测精度,且在网络学习速度等方面优势明显,适用于复杂状况下滑坡体的位移预测。
Considering complication to the parameter selection of conventional intelligent algorithm and being easy to fall into local minimum in prediction of landslide displacement,this paper proposes a new prediction model of landslide displacement based on improved Extreme Learning Machine. Characteristics of the landslide deformation accumulative displacement curve are studied and according to patterns,it is divided into four types: decelerating-uniform velocity,uniform velocity-accelerating,decelerating-uniform velocity-accelerating and compound type. The optimum number of neurons on hidden layer and excitation function of ELM are searched out according to the 2 D range query-based and the technique of rolling modeling adopted in prediction in order to improve the prediction results. Taking landslides in Lianziya,Wolongsi,Gushuwu and Xintan examples,the applicability of improved ELM algorithm to landslide deformation displacement prediction is analyzed and compared. The experimental re-sults show that ELM is valid and feasible in prediction of landslide under complicated conditions with higher precision.
Considering complication to the parameter selection of conventional intelligent algorithm and being easy to fall into local minimum in prediction of landslide displacement,this paper proposes a new prediction model of landslide displacement based on improved Extreme Learning Machine. Characteristics of the landslide deformation accumulative displacement curve are studied and according to patterns,it is divided into four types: decelerating-uniform velocity,uniform velocity-accelerating,decelerating-uniform velocity-accelerating and compound type. The optimum number of neurons on hidden layer and excitation function of ELM are searched out according to the 2 D range query-based and the technique of rolling modeling adopted in prediction in order to improve the prediction results. Taking landslides in Lianziya,Wolongsi,Gushuwu and Xintan examples,the applicability of improved ELM algorithm to landslide deformation displacement prediction is analyzed and compared. The experimental re-sults show that ELM is valid and feasible in prediction of landslide under complicated conditions with higher precision.
引文
[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.YIN Kun-long.Landslide hazard prediction and evalution[M].Wuhan:China University of Geosciences Press,2004.
[2]高彩云.基于智能算法的滑坡位移预测与危险性评价研究[D].北京:中国矿业大学(北京),2016.GAO Cai-yun.Research on displacement prediction and risk assessment of landslide based on intelligent algorithm[D].Beijing:China University of Mining and Technology(Beijing),2016.
[3]张军,刘祖强.滑坡监测分析预报的非线性理论和方法[M].北京:中国水利水电出版社,2010.ZHANG Jun,LIU Zu-qiang.Landslide deformation monitoring analysis and prediction based on nonlinear theory and mothod[M].Beijing:China Water&Power Press,2010.
[4]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 Yi-ping,TENG Wei-fu,LI Ya-wei.Application of grey neural network model to landslide deformation prediction[J].Chinese Journal of Rock Mechanics and Engineering,2007,26(3):632-636.
[5]董辉,傅鹤林,冷伍明.滑坡位移时序预测的核函数构造[J].岩土力学,2008,29(4):1087-1092.DONG Hui,FU He-lin,LENG Wu-ming.Kernel design for displacement time series of landslide[J].Rock and Soil Mechanics,2008,29(4):1087-1092.
[6]马文涛.基于灰色最小二乘支持向量机的边坡位移预测[J].岩土力学,2010,31(5):1670-1674.MA Wen-tao.Forecasting slope displacements based on grey least square support vector machines[J].Rock and Soil Mechanics,2010,31(5):1670-1674.
[7]杨虎,吴北平,汪利.混沌序列PSO-RBF耦合模型在滑坡位移预测中的应用[J].科学技术与工程,2013,13(30):9118-9121.YANG Hu,WU Bei-ping,WANG Li.Application of PSO-RBF coupling model based on chaos theory in forecast displacement of landslide[J].Science Technology and Engineering,2013,13(30):9118-9121.
[8]曾耀,李春峰.基于RBF多变量时间序列的滑坡位移预测研究[J].长江科学院院报,2012,29(4):29-34.ZENG Yao,LI Chun-feng.Landslide displacement prediction by using multivariable time series based on RBF neural network[J].Journal of Yangtze River Scientific Research Institute,2012,29(4):29-34.
[9]GAO Cai-yun,CUI Xi-min.Nonlinear time series of deformation forecasting using improved BP neural networks[J].Computer Modelling and New Technologies,2014,18(8):249-253.
[10]Hu Q C,Hu B,Jiang H F.Application of BP artifical neural network to the displacement prediction of deep foundation pile[J].Safety and Environment Engineering,2013,20(3):154-158.
[11]周超,殷坤龙,黄发明.混沌序列WA-ELM耦合模型在滑坡位移预测中的应用[J].岩土力学,2015,36(9):2674-2680.ZHOU Chao,YIN Kun-long,HUANG Fa-ming.Application of the chaotic sequence WA-ELM coupling model in landslide displacement prediction[J].Rock and Soil Mechanics,2015,36(9):2674-2680.
[12]李骅锦,许强,何雨森,等.WA联合ELM与OSELM的滑坡位移预测模型[J].工程地质学报,2016,24(5):721-731.LI Hua-jin,XU Qiang,HE Yu-sen,et al.Predictive modeling of landslide displacement by wavelet analysis and multiple extreme learning machine[J].Journal of Engineering Geology,2016,24(5):721-731.
[13]仲维清,孙健巍.极限学习机在采空区自然发火预测中的应用[J].辽宁工程技术大学学报:自然科学版,2016,35(6):581-585.ZHONG Wei-qing,SUN Jian-wei.Application of ELM in prediction of coal spontaneous combustion in caving zone[J].Journal of Liaoning Technical University:Natural Science Edition,2016,35(6):581-585.
[14]王东升,靳晓.基于JADE-ELM的煤巷围岩稳定性预测[J].煤矿安全,2017,48(11):198-201.WANG Dong-sheng,JIN Xiao.Prediction of surrounding rock stability in coal roadway based on JADE-ELM method[J].Safety in Coal Mines,2017,48(11):198-201.
[15]王保义,赵硕,张少敏.基于云计算和极限学习机的分布式电力负荷预测算法[J].电网技术,2014,38(2):526-531.WANG Bao-yi,ZHAO Shuo,ZHANG Shao-min.A distributed load forecasting algorithm based on cloud computing and extreme learning machine[J].Power System Technology,2014,38(2):526-531.
[16]刘念,张清鑫,李小芳.基于核函数极限学习机的分布式光伏短期功率预测[J].农业工程学报,2014,30(4):152-159.LIU Nian,ZHANG Qing-xin,LI Xiao-fang.Distributed photovoltaic short-term power output forecasting based on extreme learning machine with kernel[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(4):152-159.
[17]高彩云,崔希民.熵权遗传算法及极限学习机地铁隧道沉降预测[J].测绘科学,2016,41(2):71-75.GAO Cai-yun,CUI Xi-min.Metro tunnel settlement prediction based on entropy weight GA-ELM mode[J].Science of Surveying and Mapping,2016,41(2):71-75.
[18]HUANG Guang-bin,ZHU Qin-yu.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1):489-501.
[19]Huang G B,Zhu Q Y,Siew C K.Universal approximation using incremental constructive feed forward networks with random hidden nodes[J].IEEE Transaction on Neural Networks,2006,17(4):879-892.
[20]LI Bao-jian,CHENG Chun-tian.Monthly discharge forecasting using wavelet neural networks with extreme learning machine[J].Science China Technological Sciences,2014,57(12):2441-2452.
[21]DONG Xiao,WANG Ji-chun,MAO Zhi-zhong.The research on the modeling method of batch process based on OS-ELM-RMPLS[J].Chemometrics and Intelligent Laboratory Systems,2014,134(5):118-122.
[22]LIAN Cheng,ZENG Zhi-gang,YAO Wei.Ensemble of extreme learning machine for landslide displacement prediction based on time series analysis[J].Neural Computing and Applications,2014,24(1):99-107.
[23]LUO Xiao-zhuo,Liu F,YANG Shu-yuan,et al.Joint sparse regularization based sparse semi-supervised extreme learning machine(S3ELM)for classification[J].Knowledge Based Systems,2014,73:149-160.
[24]翟会君,翟亚锋,朱涛.基于回归-神经网络模型的滑坡变形及失稳预测模型[J].河北工业科技,2017,34(6):440-446.ZHAI Hui-jun,ZHAI Ya-feng,ZHU Tao.Prediction model of landslide deformation and instability based on regression ELM neural network model[J].Hebei Journal of Industrial Science and Technology,2017,34(6):440-446.
[25]李德营.三峡库区具台阶状位移特征的滑坡预测预报研究[D].武汉:中国地质大学,2010.LI De-ying.Prediction study of landslides with step like deformation in the three gorges reservoir[D].Wuhan:China University of Geosciences,2010.
[2]高彩云.基于智能算法的滑坡位移预测与危险性评价研究[D].北京:中国矿业大学(北京),2016.GAO Cai-yun.Research on displacement prediction and risk assessment of landslide based on intelligent algorithm[D].Beijing:China University of Mining and Technology(Beijing),2016.
[3]张军,刘祖强.滑坡监测分析预报的非线性理论和方法[M].北京:中国水利水电出版社,2010.ZHANG Jun,LIU Zu-qiang.Landslide deformation monitoring analysis and prediction based on nonlinear theory and mothod[M].Beijing:China Water&Power Press,2010.
[4]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 Yi-ping,TENG Wei-fu,LI Ya-wei.Application of grey neural network model to landslide deformation prediction[J].Chinese Journal of Rock Mechanics and Engineering,2007,26(3):632-636.
[5]董辉,傅鹤林,冷伍明.滑坡位移时序预测的核函数构造[J].岩土力学,2008,29(4):1087-1092.DONG Hui,FU He-lin,LENG Wu-ming.Kernel design for displacement time series of landslide[J].Rock and Soil Mechanics,2008,29(4):1087-1092.
[6]马文涛.基于灰色最小二乘支持向量机的边坡位移预测[J].岩土力学,2010,31(5):1670-1674.MA Wen-tao.Forecasting slope displacements based on grey least square support vector machines[J].Rock and Soil Mechanics,2010,31(5):1670-1674.
[7]杨虎,吴北平,汪利.混沌序列PSO-RBF耦合模型在滑坡位移预测中的应用[J].科学技术与工程,2013,13(30):9118-9121.YANG Hu,WU Bei-ping,WANG Li.Application of PSO-RBF coupling model based on chaos theory in forecast displacement of landslide[J].Science Technology and Engineering,2013,13(30):9118-9121.
[8]曾耀,李春峰.基于RBF多变量时间序列的滑坡位移预测研究[J].长江科学院院报,2012,29(4):29-34.ZENG Yao,LI Chun-feng.Landslide displacement prediction by using multivariable time series based on RBF neural network[J].Journal of Yangtze River Scientific Research Institute,2012,29(4):29-34.
[9]GAO Cai-yun,CUI Xi-min.Nonlinear time series of deformation forecasting using improved BP neural networks[J].Computer Modelling and New Technologies,2014,18(8):249-253.
[10]Hu Q C,Hu B,Jiang H F.Application of BP artifical neural network to the displacement prediction of deep foundation pile[J].Safety and Environment Engineering,2013,20(3):154-158.
[11]周超,殷坤龙,黄发明.混沌序列WA-ELM耦合模型在滑坡位移预测中的应用[J].岩土力学,2015,36(9):2674-2680.ZHOU Chao,YIN Kun-long,HUANG Fa-ming.Application of the chaotic sequence WA-ELM coupling model in landslide displacement prediction[J].Rock and Soil Mechanics,2015,36(9):2674-2680.
[12]李骅锦,许强,何雨森,等.WA联合ELM与OSELM的滑坡位移预测模型[J].工程地质学报,2016,24(5):721-731.LI Hua-jin,XU Qiang,HE Yu-sen,et al.Predictive modeling of landslide displacement by wavelet analysis and multiple extreme learning machine[J].Journal of Engineering Geology,2016,24(5):721-731.
[13]仲维清,孙健巍.极限学习机在采空区自然发火预测中的应用[J].辽宁工程技术大学学报:自然科学版,2016,35(6):581-585.ZHONG Wei-qing,SUN Jian-wei.Application of ELM in prediction of coal spontaneous combustion in caving zone[J].Journal of Liaoning Technical University:Natural Science Edition,2016,35(6):581-585.
[14]王东升,靳晓.基于JADE-ELM的煤巷围岩稳定性预测[J].煤矿安全,2017,48(11):198-201.WANG Dong-sheng,JIN Xiao.Prediction of surrounding rock stability in coal roadway based on JADE-ELM method[J].Safety in Coal Mines,2017,48(11):198-201.
[15]王保义,赵硕,张少敏.基于云计算和极限学习机的分布式电力负荷预测算法[J].电网技术,2014,38(2):526-531.WANG Bao-yi,ZHAO Shuo,ZHANG Shao-min.A distributed load forecasting algorithm based on cloud computing and extreme learning machine[J].Power System Technology,2014,38(2):526-531.
[16]刘念,张清鑫,李小芳.基于核函数极限学习机的分布式光伏短期功率预测[J].农业工程学报,2014,30(4):152-159.LIU Nian,ZHANG Qing-xin,LI Xiao-fang.Distributed photovoltaic short-term power output forecasting based on extreme learning machine with kernel[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(4):152-159.
[17]高彩云,崔希民.熵权遗传算法及极限学习机地铁隧道沉降预测[J].测绘科学,2016,41(2):71-75.GAO Cai-yun,CUI Xi-min.Metro tunnel settlement prediction based on entropy weight GA-ELM mode[J].Science of Surveying and Mapping,2016,41(2):71-75.
[18]HUANG Guang-bin,ZHU Qin-yu.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1):489-501.
[19]Huang G B,Zhu Q Y,Siew C K.Universal approximation using incremental constructive feed forward networks with random hidden nodes[J].IEEE Transaction on Neural Networks,2006,17(4):879-892.
[20]LI Bao-jian,CHENG Chun-tian.Monthly discharge forecasting using wavelet neural networks with extreme learning machine[J].Science China Technological Sciences,2014,57(12):2441-2452.
[21]DONG Xiao,WANG Ji-chun,MAO Zhi-zhong.The research on the modeling method of batch process based on OS-ELM-RMPLS[J].Chemometrics and Intelligent Laboratory Systems,2014,134(5):118-122.
[22]LIAN Cheng,ZENG Zhi-gang,YAO Wei.Ensemble of extreme learning machine for landslide displacement prediction based on time series analysis[J].Neural Computing and Applications,2014,24(1):99-107.
[23]LUO Xiao-zhuo,Liu F,YANG Shu-yuan,et al.Joint sparse regularization based sparse semi-supervised extreme learning machine(S3ELM)for classification[J].Knowledge Based Systems,2014,73:149-160.
[24]翟会君,翟亚锋,朱涛.基于回归-神经网络模型的滑坡变形及失稳预测模型[J].河北工业科技,2017,34(6):440-446.ZHAI Hui-jun,ZHAI Ya-feng,ZHU Tao.Prediction model of landslide deformation and instability based on regression ELM neural network model[J].Hebei Journal of Industrial Science and Technology,2017,34(6):440-446.
[25]李德营.三峡库区具台阶状位移特征的滑坡预测预报研究[D].武汉:中国地质大学,2010.LI De-ying.Prediction study of landslides with step like deformation in the three gorges reservoir[D].Wuhan:China University of Geosciences,2010.