檀梦皎;殷坤龙;郭子正;张俞;杨永刚;赵海燕;张怡悦;

• 1:中国地质大学(武汉)工程学院

摘要(Abstract)：

对三峡库区中具有"阶跃型"位移曲线的滑坡进行位移预测的难度较高,为此,提出了基于自适应噪声完整集合经验模态分解法的粒子群优化-极限学习机模型,并将该模型用于万州区塘角1号滑坡的位移预测。首先利用CEEMDAN法提取滑坡趋势项位移和波动项位移的不同IMF组分,并使用Elman神经网络对趋势项位移进行预测;其次结合历史监测资料,通过滑坡位移对降雨、库水位等诱发因素的响应分析,确定了7种不同的波动项位移影响因素,并使用CEEMDAN法分解得到上述因素的各IMF分量;然后通过模糊熵分析,将波动项位移和诱发因素的IMF分量一一对应,构建PSO-ELM模型进行波动项位移的预测;最后将趋势项位移预测值和波动项位移预测值叠加得到累积位移的预测值。结果表明:和ELM模型、PSO-ELM模型相比,基于CEEMDNAN的PSO-ELM模型的预测精度更高,其均方根误差(RMSE)和拟合优度(R~2)可达到0.54 mm和0.99,为滑坡位移预测提供了一种新手段。

关键词(KeyWords)： 自适应噪声完整集合经验模态分解;粒子群优化;极限学习机;滑坡位移预测;Elman神经网络

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划(2018YFC0809400);; 国家自然科学基金项目(41842062)

作者(Author): 檀梦皎;殷坤龙;郭子正;张俞;杨永刚;赵海燕;张怡悦;

Email:

DOI: 10.19509/j.cnki.dzkq.2019.0619

参考文献(References)：

• [1] Zhang C C,Zhu H H,Liu S P,et al.A kinematic method for calculating shear displacements of landslides using distributed fiber optic strain measurements[J].Engineering Geology,2018,234:83-96.
• [2] Calvello M,D Orsi R N,Piciullo L,et al.The Rio de Janeiro early warning system for rainfall-induced landslides:Analysis of performance for the years 2010-2013[J].International Journal of Disaster Risk Reduction,2015,12:3-15.
• [3] 王朝阳,许强,范宣梅,等.灰色新陈代谢GM(1,1)模型在滑坡变形预测中的应用[J].水文地质工程地质,2009,36(2):108-111.
• [4] 汤罗圣,殷坤龙,杜鹃.阶跃型位移特征滑坡时间预测预报研究[J].地质科技情报,2012,31(4):106-110.
• [5] 郭子正,殷坤龙,黄发明,等.基于地表监测数据和非线性时间序列组合模型的滑坡位移预测[J].岩石力学与工程学报,2018,37(增刊1):3392-3399.
• [6] 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):1783-1789.
• [7] 张凯翔,牛瑞卿,胡友健,等.基于小波变换及外因响应的滑坡位移预测[J].中国矿业大学学报,2017,46(4):924-931.
• [8] 陈亮青,邹宗兴,苑谊,等.考虑诱发因素影响滞后性的库岸滑坡位移预测[J].人民长江,2018,49(10):60-65.
• [9] 孟蒙,陈智强,黄达,等.基于H-P滤波法、ARIMA和VAR模型的库区滑坡位移综合预测[J].岩土力学,2016,37(增刊2):552-560.
• [10] 李骅锦,许强,何雨森,等.WA联合ELM与OS-ELM的滑坡位移预测模型[J].工程地质学报,2016,24(5):721-731.
• [11] Cao Y,Yin K,Alexander D E,et al.Using an extreme learning machine to predict the displacement of step-like landslides in relation to controlling factors[J].Landslides,2016,13(4):725-736.
• [12] Huang F,Yin K,Zhang G,et al.Landslide displacement prediction using discrete wavelet transform and extreme learning machine based on chaos theory[J].Environmental Earth Sciences,2016,75(20):1376.
• [13] 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.
• [14] 赵丽娟,马良玉,王晓霞.基于PSO-ELM的热力系统参数预测[J].电力科学与工程,2018,34(3):70-74.
• [15] Huang N E,Shen Z,Long S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings A,1998,454:903-995.
• [16] Yang A C,Tsai S,Huang N E.Decomposing the association of completed suicide with air pollution,weather,and unemployment data at different time scales[J].Journal of Affective Disorders,2011,129(1/3):275-281.
• [17] Wang T,Zhang M,Yu Q,et al.Comparing the applications of EMD and EEMD on time-frequency analysis of seismic signal[J].Journal of Applied Geophysics,2012,83:29-34.
• [18] Torres M E,Colominas M A,Schlotthauer G,et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP),Prague:IEEE.2011:4144-4147.
• [19] Jun W,Yuyan L,Lingyu T,et al.A new weighted CEEMDAN-based prediction model:An experimental investigation of decomposition and non-decomposition approaches[J].Knowledge-Based Systems,2018,160:188-199.
• [20] 朱莉,卢毅敏,罗建平.基于灰色-Elman神经网络的区域滑坡易发性模型[J].自然灾害学报,2013,22(5):120-126.
• [21] Kolanowski K,Swietlicka A,Kapela R,et al.Multisensor data fusion using Elman neural networks[J].Applied Mathematics and Computation,2018,319:236-244.
• [22] Achanta S,Gangashetty S V.Deep elman recurrent neural networks for statistical parametric speech synthesis[J].Speech Communication,2017,93:31-42.
• [23] Huang G,Zhu Q,Mao K Z,et al.Can threshold networks be trained directly[J].IEEE Transactions on Circuits & Systems II Express Briefs,2006,53(3):187-191.
• [24] Leuenberger M,Kanevski M.Extreme Learning Machines for spatial environmental data[J].Computers & Geosciences,2015,85:64-73.
• [25] Huang J,Huang F,Jiang S,et al.Landslide displacement prediction based on multivariate chaotic model and extreme learning machine[J].Engineering Geology,2017,218:173-186.
• [26] Huang G,Chen L.Enhanced random search based incremental extreme learning machine[J].Neurocomputing,2008,71(16/18):3460-3468.
• [27] 杨锡运,关文渊,刘玉奇,等.基于粒子群优化的核极限学习机模型的风电功率区间预测方法[J].中国电机工程学报,2015,35(增刊1):146-153.
• [28] Ahila R,Sadasivam V,Manimala K.An integrated PSO for parameter determination and feature selection of ELM and its application in classification of power system disturbances[J].Applied Soft Computing,2015,32:23-37.
• [29] 郭子正,殷坤龙,唐扬,等.库水位下降及降雨作用下麻柳林滑坡稳定性评价与预测[J].地质科技情报,2017,36(4):260-265.
• [30] Zhou C,Yin K,Cao Y,et al.Application of time series analysis and PSO-SVM model in predicting the Bazimen landslide in the Three Gorges Reservoir,China[J].Engineering Geology,2016,204:108-120.
• [31] Zhou C,Yin K,Cao Y,et al.Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method[J].Landslides,2018,15:2211-2225.
• [32] 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):3660-3669.
• [33] 李青,李军,马昊.基于互补型集成经验模态分解-模糊熵和回声状态网络的短期电力负荷预测[J].计算机应用,2014,34(12):3651-3655.
• [34] Wang Y,Zheng S,Zhang W,et al.Fuzzy entropy complexity and multifractal behavior of statistical physics financial dynamics[J].Physica A:Statistical Mechanics and Its Applications,2018,506:486-498.
• [35] Lohrmann C,Luukka P,Jablonska-Sabuka M,et al.A combination of fuzzy similarity measures and fuzzy entropy measures for supervised feature selection[J].Expert Systems with Applications,2018,110:216-236.
• [36] 高彩云,高宁.改进极限学习机的不同类型滑坡位移预测[J].西安科技大学学报,2018,38(4):683-689.
• [37] 王小川.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.