基于蠕滑趋势影响和特征优化算法的阶跃型滑坡位移预测模型

doi:10.3724/1000-6915.jrme.2024.0554

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1129 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要在滑坡位移预测模型构建过程中，为了清晰地分离出各类特征影响的滑坡位移部分，增强位移预测模型的力学可解释性与泛化能力，提出一种基于蠕滑趋势影响和特征优化算法的阶跃型滑坡位移预测模型。该预测模型首先运用粒子群算法优化变分模态分解(PSO-VMD)方法将训练数据分解为具有西原蠕变特征的趋势项位移及其他数据曲线；然后，综合选取滑坡位移的外界影响特征，对其他数据曲线运用遗传特征优化算法(GA)分离重构得到具有傅里叶波动特征的波动项位移及最大化与外界影响特征间相关性的影响项位移；分别运用西原蠕变泰勒展开多项式模型，傅里叶波动模型及卷积神经网络–挤压激励注意力模块–门控循环单元模型(CNN-SE-GRU)对趋势项位移，波动项位移及影响项位移进行预测；令各项位移训练时的误差为随机项位移，运用核密度区间估计约束下灰狼算法优化极限学习机(KDE-GWO-ELM)模型对该位移进行预测；最终，各项位移预测值叠加后实现对阶跃型滑坡位移的预测。以阶跃型滑坡——白水河滑坡为例，选取ZG118与ZG93监测点2005年11月～2009年10月累积水平位移数据为训练数据，2009年11月～2010年7月累积水平位移数据为预测数据进行研究。结果表明，预测模型下ZG118与ZG93监测点的均方根误差RMSE分别为5.85与10.61 mm，平均绝对百分比误差MAPE分别为0.27%与0.43%，与CNN-SE-GRU/LSTM模型、GWO-ELM模型、VMD-GWO-ELM模型及EEMD-CNN-GRU模型相比，该模型不仅预测精度有所提升，且清晰地解释了时间特征、外界影响特征及误差特征对预测模型的影响，具有较好的可解释性与泛化能力。

	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
	冯谕1
	2
	曾怀恩1
	2
	3
	邓华锋1
	2
	涂鹏飞1
	2

关键词 ：边坡工程, 阶跃型滑坡, 蠕滑趋势, PSO-VMD模型, 傅里叶波动函数, GA特征优化算法, CNN-SE-GRU模型, KDE-GWO-ELM模型

Abstract：In the construction process of the landslide displacement prediction model，in order to clearly separate the landslide displacement parts affected by various features to enhance the mechanical interpretability and generalization ability of the displacement prediction model，a step-type landslide displacement prediction model based on the influence of creep trend and feature optimization algorithm is proposed. Firstly，the Particle Swarm Optimization-Based Variational Modality Decomposition(PSO-VMD) Method is used to decompose the training data into other data curves and trend displacement with influence of Nishihara creep model. Secondly，the external influence features of landslide displacement are comprehensively selected，other data curves are separated and reconstructed with the genetic feature optimization algorithm(GA) to obtain the fluctuation displacement with Fourier characteristics and the influence displacement that maximizes the correlation with external influence features. The Nishihara creep Taylor expansion polynomial model，Fourier function model and Convolutional Neural Network-Squeeze Excitation Attention Module-Gated Recurrent Unit Model(CNN-SE-GRU) are used to respectively fit and predict the trend displacement，fluctuation displacement and influence displacement. The errors of each displacement model training fit are defined as the random displacement；it is predicted by the Gray Wolf Optimization-Based Extreme Learning Machines model under the constraint of kernel density estimation(KDE-GWO-ELM). Finally，the prediction of step-type landslide displacement is accomplished by superimposing all displacement prediction model results. Taking the step-type landslide- namely Baishuihe landslide as an example，the cumulative horizontal displacement data of monitoring points ZG118 and ZG93 from November 2005 to October 2009 are selected as training data，and the data from November 2009 to July 2010 are selected as prediction data for research. The prediction results show that the root mean square error(RMSE) of monitoring points ZG118 and ZG93 under the prediction model 5.85 mm and 10.61mm respectively，the mean absolute percentage error(MAPE) are 0.27% and 0.43% respectively. Compared with the CNN-SE-GRU/LSTM model，GWO-ELM model，VMD-GWO-ELM model and EEMD-CNN-GRU model，the novel prediction model not only improves the prediction accuracy，but also shows clearly the influence of time features，external influence features and error features for prediction model. Thus，it has excellent interpretability and generalization ability.

Key words： slope engineering step-type landslide creep trend PSO-VMD model Fourier fluctuation function GA feature optimization algorithm CNN-SE-GRU model KDE-GWO-ELM model

引用本文:

冯谕1，2，曾怀恩1，2，3，邓华锋1，2，涂鹏飞1，2. 基于蠕滑趋势影响和特征优化算法的阶跃型滑坡位移预测模型[J]. 岩石力学与工程学报, 2025, 44(3): 705-720.
FENG Yu1，2，ZENG Huaien1，2，3，DENG Huafeng1，2，TU Pengfei1，2. A step-type landslide displacement prediction model based on creep trend influence and feature optimization algorithm. , 2025, 44(3): 705-720.

链接本文:

https://rockmech.whrsm.ac.cn/CN/10.3724/1000-6915.jrme.2024.0554 或 https://rockmech.whrsm.ac.cn/CN/Y2025/V44/I3/705

[1]	段梦凡. 基于GRU的边坡位移预测研究[硕士学位论文][D]. 石家庄：石家庄铁道大学，2022.(DUAN Mengfan. Study on slope displacement prediction based on GRU[M. S. Thesis][D]. Shijiazhuang：Shijiazhuang Tiedao University，2022.(in Chinese))
[2]	李振洪，宋闯，余琛，等. 卫星雷达遥感在滑坡灾害探测和监测中的应用：挑战与对策[J]. 武汉大学学报：信息科学版，2019，44(7)：967-979.(LI Zhenhong，SONG Chuang，YU Chen，et al. Application of satellite radar remote sensing to landslide detection and monitoring：Challenges and solutions[J]. Geomatics and Information Science of Wuhan University，2019，44(7)：967-979.(in Chinese))
[3]	许强，汤明高，徐开祥，等. 滑坡时空演化规律及预警预报研究[J]. 岩石力学与工程学报，2008，27(6)：1 104-1 112.(XU Qiang，TANG Minggao，XU Kaixiang，et al. Research on space-time evolution laws and early warning-prediction of landslides[J]. Chinese Journal of Rock Mechanics and Engineering，2008，27(6)：1 104-1 112.(in Chinese))
[4]	冯谕，涂鹏飞，曾怀恩. 降雨及库水位共同作用下滑坡阶跃位移临界面的识别方法[J]. 岩石力学与工程学报，2023，42(11)：2 788-2 805.(FENG Yu，TU Pengfei，ZENG Huaien. A method for identifying critical displacement threshold of landslide step under combined effects of rainfall and reservoir water level[J]. Chinese Journal of Rock Mechanics and Engineering，2023，42(11)：2 788-2 805.(in Chinese))
[5]	ZHANG Y G，TANG J，HE Z Y，et al. A novel displacement prediction method using gated recurrent unit model with time series analysis in the Erdaohe landslide[J]. Natural Hazards，2021，105(1)：783-813.
[6]	黄发明，殷坤龙，杨背背，等. 基于时间序列分解和多变量混沌模型的滑坡阶跃式位移预测[J]. 地球科学，2018，43(3)：887-898.(HUANG Faming，YIN Kunlong，YANG Beibei，et al. Step-like displacement prediction of landslide based on time series decomposition and multivariate chaotic model[J]. Earth Science，2018，43(3)：887-898.(in Chinese))
[7]	宋丽伟. 基于经验模态分解和LSTM模型的滑坡位移预测[J]. 人民长江，2020，51(5)：144-148.(SONG Liwei. Landslide displacement prediction based on empirical mode decomposition and long short-term memory neural network model[J]. Yangtze River，2020，51(5)：144-148.(in Chinese))
[8]	邓冬梅，梁烨，王亮清，等. 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，2017，38(12)：3 660-3 669.(DENG Dongmei，LIANG Ye，WANG Liangqing，et al. 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，2017，38(12)：3 660-3 669.(in Chinese))
[9]	李龙起，王梦云，赵皓璆，等. 基于CEEMDAN-BA-SVR-Adaboost模型的白水河滑坡位移预测[J]. 长江科学院院报，2021，38(6)：52-59.(LI Longqi，WANG Mengyun，ZHAO Haoqiu，et al. Predicting displacement of baishuihe landslide using CEEMDAN-BA-SVR-adaboost model[J]. Journal of Yangtze River Scientific Research Insititute，2021，38(6)：52-59.(in Chinese))
[10]	李博，李欣，芮红，等. 基于变分模态分解和灰狼优化极限学习机的隧道口边坡位移预测[J]. 吉林大学学报：工学版，2023，53(6)：1 853-1 860.(LI Bo，LI Xin，RUI Hong，et al. Displacement prediction of tunnel entrance slope based on variational model decomposition and grey wolf optimized extreme learning machine[J]. Journal of Jilin University：Engineering and Technology，2023，53(6)：1 853-1 860.(in Chinese))
[11]	李麟玮，吴益平，苗发盛，等. 基于变分模态分解与GWO-MIC-SVR模型的滑坡位移预测研究[J]. 岩石力学与工程学报，2018，37(6)：1 395-1 406.(LI Linwei，WU Yiping，MIAO Fasheng，et al. Displacement prediction of landslide based on variational mode decomposition and GWO-MIC-SVR model[J]. Chinese Journal of Rock Mechanics and Engineering，2018，37(6)：1 395-1 406.(in Chinese))
[12]	杨背背，殷坤龙，杜娟. 基于时间序列与长短时记忆网络的滑坡位移动态预测模型[J]. 岩石力学与工程学报，2018，37(10)：2 334-2 343.(YANG Beibei，YIN Kunlong，DU Juan. A model for predicting landslide displacement based on time series and long and short term memory neural network[J]. Chinese Journal of Rock Mechanics and Engineering，2018，37(10)：2 334-2 343.(in Chinese))
[13]	GUO Z Z，CHEN L X，GUI L，et al. Landslide displacement prediction based on variational mode decomposition and WA-GWO-BP model[J]. Landslides，2020，17(3)：567-583.
[14]	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))
[15]	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)：2 674-2 680.(ZHOU Chao，YIN Kunlong，HUANG Faming. Application of the chaotic sequence WA-ELM coupling model in landslide displacement prediction[J]. Rock and Soil Mechanics，2015，36(9)：2 674-2 680. (in Chinese))
[16]	张俊，殷坤龙，王佳佳，等. 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(2)：382-391.(ZHANG Jun，YIN Kunlong，WANG Jiajia，et al. Displacement prediction of baishuihe landslide base on time series and pso-svr model[J]. Chinese Journal of Rock Mechanics and Engineering，2015，34(2)：382-391.(in Chinese))
[17]	李麟玮. 三峡库区库岸堆积层滑坡位移预测与稳定性评价方法研究[博士学位论文][D]. 武汉：中国地质大学，2021.(LI Linwei. Displacement prediction and stability evaluation methods of reservoir colluvial landslides in Three Gorges Reservoir area[Ph. D. Thesis][D]. Wuhan：China University of Geosciences，2021.(in Chinese))
[18]	廖康，吴益平，李麟玮，等. 基于时间序列与GWO-ELM模型的滑坡位移预测[J]. 中南大学学报：自然科学版，2019，50(3)：619-626.(LIAO Kang，WU Yiping，LI Linwei，et al. Displacement prediction model of landslide based on time series and GWO-ELM[J]. Journal of Central South University：Science and Technology，2019，50(3)：619-626.(in Chinese))
[19]	薛阳，吴益平，苗发盛，等. 库水升降条件下考虑饱和渗透系数空间变异性的白水河滑坡渗流变形分析[J]. 岩土力学，2020，41(5)：1 709-1 720.(XUE Yang，WU Yiping，MIAO Fasheng，et al. Seepage and deformation analysis of Baishuihe landslide considering spatial variability of saturated hydraulic conductivity under reservoir water level fluctuation[J]. Rock and Soil Mechanics，2020，41(5)：1 709-1 720.(in Chinese))
[20]	MIAO F，WU Y，XIE Y，et al. Prediction of landslide displacement with step-like behavior based on multialgorithm optimization and a support vector regression model[J]. Landslides，2018，(15)：475-488.
[21]	叶振南. 三峡库区白水河滑坡复活机理与活动趋势预测[硕士学位论文][D]. 北京：中国地质大学(北京)，2014.(YE Zhennan. Reactivation mechanism analysis and dynamic behavior prediction for the Baishuihe landslide in Three Gorges Reservoir Area[M. S. Thesis][D]. Beijing：China University of Geosciences(Beijing)，2014.(in Chinese))
[22]	张倬元，王仕天，王兰生. 工程地质分析原理[M]. 4版. 北京：地质出版社，2016：276-277.(ZHANG Zhuoyuan，WANG Shitian，WANG Lansheng. Principles of engineering geology analysis[M]. 4th ed. Beijing：Geology Press，2016：276-277.(in Chinese))
[23]	冯谕，曾怀恩，涂鹏飞. 一种滑动检测算法下的滑坡位移时序分解方法[J]. 长江科学院院报，2024，41(3)：126-133.(FENG Yu，ZENG Huaien，TU Pengfei. A time series decomposition method of landslide displacement based on sliding detection algorithm[J]. Journal of Yangtze River Scientific Research Institute，2024，41(3)：126-133.(in Chinese))
[24]	XU T，XU Q，TANG C A，et al. The evolution of rock failure with discontinuities due to shear creep[J]. Acta Geotechnica，2013，8(6)：567-581.
[25]	董秀军，许强，唐川，等. 滑坡位移-时间曲线特征的物理模拟试验研究[J]. 工程地质学报，2015，23(3)：401-407.(DONG Xiujun，XU Qiang，TANG Chuan，et al. Characteristics of landslide displacement-time curve by physical simulation experiment[J]. Journal of Engineering Geology，2015，23(3)：401-407.(in Chinese))
[26]	陈浩，杨春和，任伟中. 蠕动滑坡变形机制的理论分析与模型试验研究[J]. 岩石力学与工程学报，2008，27(增2)：3 705-3 711. (CHEN Hao，YANG Chunhe，REN Weizhong. Theoretical analysis and model test study on deformation mechanism of creep landslide[J]. Chinese Journal of Rock Mechanics and Engineering，2008，27(Supp.2)：3 705-3 711.(in Chinese))
[27]	何云明，吴德伦. 岩质边坡蠕变模型及其蠕变机制研究[C]// 第八次全国岩石力学与工程学术大会论文集. [S. l.]：[s. n.]，2004：723-728.(HE Yunming，WU Delun. Study on the creep model and creep mechanism of rock slope[C]// Proceedings of the Eigth National Congress of Rock Mechanics and Engineering. [S. l.]：[s. n.]，2004：723-728.(in Chinese))
[28]	齐亚静，姜清辉，王志俭，等. 改进西原模型的三维蠕变本构方程及其参数辨识[J]. 岩石力学与工程学报，2012，31(2)：347-355.(QI Yajing，JIANG Qinghui，WANG Zhijian，et al. 3D creep constitutive equation of modified nishihara model and its parameters identification[J]. Chinese Journal of Rock Mechanics and Engineering，2012，31(2)：347-355.(in Chinese))
[29]	DRAGOMIRETSKIY K，ZOSSO D. Variational mode decomposition[J]. ISSE Transactions on Signal Processing，2014，62(3)：531-544.
[30]	EBERHART R，KENNEDY J. A new optimizer using particle swarm theory[C]// Preceedings of the Sixth International Symposium on Micro Machine and Human Science. Nagoya，Japan：IEEE，1995：39-43.
[31]	CHEN W T，WANG Z Z，XIE H G，et al. Characterization of surface EMC signal based on fuzzy entropy[J]. ISSE Transactions on Neural Systems and Rehabilitation Engineering，2007，15(2)：267-272.
[32]	刘慧，谢洪波，和卫星，等. 基于模糊熵的脑电睡眠分期特征提取与分类[J]. 数据采集与处理，2010，25(4)：484-489.(LIU Hui，XIE Hongbo，HE Weixing，et al. Characterization and classification of eeg sleep stage based on fuzzy entropy[J]. Journal of Data Acquisition and Processing，2010，25(4)：484-489.(in Chinese))
[33]	吴益平，张秋霞，唐辉明，等. 基于有效降雨强度的滑坡灾害危险性预警[J]. 地球科学：中国地质大学学报，2014，39(7)：889-895.(WU Yiping，ZHANG Qiuxia，TANG Huiming，et al. Landslide hazard warning based on effective rainfall intensity[J]. Earth Science—Journal of China University of Geosciences，2014，39(7)：889-895. (in Chinese))
[34]	郭璐，贺可强，周云，等. 水库型滑坡复合水动力增载位移响应比物理预测模型及其应用[J]. 工程地质学报，2022，30(5)：1 561- 1 572.(GUO Lu，HE Keqiang，ZHOU Yun，et al. Physical prediction model and application of compound hydrodynamic displacement response ratio with dynamics increment in reservoir landslide[J]. Journal of Engineering Geology，2022，30(5)：1 561-1 572.(in Chinese))
[35]	卢书强，易庆林，易武，等. 库水下降作用下滑坡动态变形机制分析——以三峡库区白水河滑坡为例[J]. 工程地质学报，2014，22(5)：869-875.(LU Shuqiang，YI Qinglin，YI Wu，et al. Study on dynamic deformation mechanism of landslide in drawdown of reservoir water level—Take Baishuihe landslide in Three Gorges Reservoir Area for example[J]. Journal of Engineering Geology，2014，22(5)：869-875.(in Chinese))
[36]	高晨曦，刘艺梁，薛欣，等. 三峡库区典型堆积层滑坡变形滞后时间效应研究[J]. 工程地质学报，2021，29(5)：1 427-1 436.(GAO Chenxi，LIU Yiliang，XUE Xin，et al. Study on deformation lag time effect of typical colluvial landslide in Three Gorges Reservoir Area[J]. Journal of Engineering Geology，2021，29(5)：1 427-1 436.(in Chinese))
[37]	肖捷夫. 库水涨落和降雨条件下藕塘滑坡变形演化机制及其预测模型研究[博士学位论文][D]. 武汉：中国地质大学，2021.(XIAO Jiefu. Deformation evolution mechanism and displacement prediction model of outang landslide under water level fluctuation and rainfall[Ph. D. Thesis][D]. Wuhan：China University of Geosciences，2021.(in Chinese))
[38]	朱智杰，卢书强，梅军. 基于有效降雨量的滑坡位移-降雨相关性研究[J]. 长江科学院院报，2023，40(12)：162-168.(ZHU Zhijie，LU Shuqiang，MEI Jun. Study on landslide displacement-rainfall correlation based on effective rainfall[J]. Journal of Yangtze River Scientific Research Institute，2023，40(12)：162-168.(in Chinese))
[39]	高华喜，股坤龙. 降雨与滑坡灾害相关性分析及预警预报阀值之探讨[J]. 岩土力学，2007，28(5)：1 055-1 060.(GAO Huaxi，YIN Kunlong. Discuss on the correlations between landslides and rainfall and threshold for landslide early-warning and prediction[J]. Rock and Soil Mechanics，2007，28(5)：1 055-1 060.(in Chinese))
[40]	李志刚，张鑫. CNN-GRU模型预测高炉煤气产生量[J]. 机械设计与制造，2022，(4)：69-72.(LI Zhigang，ZHANG Xin. CNN-GRU model predicts blast furnace gas production[J]. Machinery Design and Manufacture，2022，(4)：69-72.(in Chinese))
[41]	HE K M，ZHANG X Y，REN S Q，et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos：IEEE Computer Society Press，2016：770-778.
[42]	HU J，SHEN L，SUN G，et al. Squeeze-and-excitation networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos：IEEE Computer Society Press，2018：7 132-7 141.
[43]	CHUNG J，GUICEHRE C，CHO K，et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[Z]. arXiv Preprint arXiv，2014，1412. 3555.
[44]	LEE D H，KIM K. PV power prediction in a peak zone using recurrent neural networks in the absence of future meteorological information[J]. Renewable Energy，2021，173：1 098-1 110.
[45]	ROSENBLATT M. Remarks on some nonparametric estimates of a density function[J]. The Annals of Mathematical Statistics，1956，27：832-837.
[46]	PARZEN E. On estimation of probability density function and mode[J]. The Annals of Mathematical Statistics，1962，33(3)：1 065-1 076.
[47]	郭田丽，宋松柏，张特，等. 基于两阶段粒子群优化算法的新型逐步分解集成径流预测模型[J]. 水利学报，2022，53(12)：1 456-1 466.(GUO Tianli，SONG Songbai，ZHANG Te，et al. A new stepwise decomposition ensemble model based on two-stage particle swarm optimization algorithm for the runoff prediction[J]. Journal of Hydraulic Engineering，2022，53(12)：1 456-1 466.(in Chinese))