中国科技核心期刊
RCCSE中国核心学术期刊
JST China收录期刊
中国建筑科学领域高质量科技期刊分级目录

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于递归特征消除选择的粒子群优化-支持向量机回归模型的滑坡位移预测方法

唐菲菲,  胡佳赢,  马英,  周泽林,  王俊,  郝亚飞

downloadPDF
文章导航 > 工业建筑  > 2024 >  54(11): 50-60
唐菲菲, 胡佳赢, 马英, 周泽林, 王俊, 郝亚飞. 基于递归特征消除选择的粒子群优化-支持向量机回归模型的滑坡位移预测方法[J]. 工业建筑, 2024, 54(11): 50-60. doi: 10.3724/j.gyjzG23071806
引用本文: 唐菲菲, 胡佳赢, 马英, 周泽林, 王俊, 郝亚飞. 基于递归特征消除选择的粒子群优化-支持向量机回归模型的滑坡位移预测方法[J]. 工业建筑, 2024, 54(11): 50-60. doi: 10.3724/j.gyjzG23071806
shu
TANG Feifei, HU Jiaying, MA Ying, ZHOU Zhelin, WANG Jun, HAO Yafei. A Landslide Displacement Prediction Method of Particle Swarm Optimization Combined with Support Vector Machine Regression Based on Recursive Feature Elimination Selection[J]. INDUSTRIAL CONSTRUCTION, 2024, 54(11): 50-60. doi: 10.3724/j.gyjzG23071806
Citation: TANG Feifei, HU Jiaying, MA Ying, ZHOU Zhelin, WANG Jun, HAO Yafei. A Landslide Displacement Prediction Method of Particle Swarm Optimization Combined with Support Vector Machine Regression Based on Recursive Feature Elimination Selection[J]. INDUSTRIAL CONSTRUCTION, 2024, 54(11): 50-60. doi: 10.3724/j.gyjzG23071806
shu

基于递归特征消除选择的粒子群优化-支持向量机回归模型的滑坡位移预测方法

doi: 10.3724/j.gyjzG23071806

  • 1. 重庆交通大学智慧城市学院, 重庆 402260;

  • 2. 中国十九冶集团有限公司, 成都 610031;

  • 3. 中信科智联科技有限公司, 重庆 400030;

  • 4. 中国葛洲坝集团易普力股份有限公司, 重庆 401121

基金项目: 

重庆市研究生联合培养基地资助项目(JDLHPYJD2021002)

重庆市技术创新与应用发展专项重点项目(CSTB2022TIAD-KPX0098)

重庆交通大学研究生科研创新项目(2023S0131)。

详细信息
    作者简介:

    唐菲菲,博士,教授,主要从事三维激光扫描技术、无人机倾斜摄影技术、实景三维地理信息技术在灾害监测预警、智能交通、国土自然资源规划等方面研究,fftang80@126.com。

    通讯作者:

    胡佳赢,硕士研究生,主要从事地质灾害监测预警的研究,tsywz0001@163.com。

A Landslide Displacement Prediction Method of Particle Swarm Optimization Combined with Support Vector Machine Regression Based on Recursive Feature Elimination Selection

  • 1. College of Smart City, Chongqing Jiaotong University, Chognqing 402260, China;

  • 2. China 19th Metallurgical Group Corporation Limited, Chengdu 610031, China;

  • 3. CICT Connected and Intelligent Technologies Co., Chognqing 400030, China;

  • 4. Explosives Corporation Limited, CGGC, Chognqing 401121, China

    摘要
  • 摘要: 在季节性降水及水库水位变化的影响下,部分山体会产生滑坡,滑坡位移的累积位移-时间曲线表现为明显的"阶跃型"动态变形特征。针对阶跃型滑坡位移,提出基于递归特征消除(RFE)算法的粒子群优化算法(PSO)-支持向量机回归(SVR)阶跃型滑坡位移预测模型,并以新铺滑坡为例展开研究。探究了滑坡位移数据的异常值剔除及缺失值填充方法,采用基于中位数法与集合经验模态分解的方法进行异常值剔除,采用基于统计学变量的方法进行缺失值填充;然后采用指数平滑法将阶跃型滑坡的累积位移拆分为趋势项和周期项。其中对趋势项位移采用傅里叶曲线进行拟合预测;对周期项位移通过基于SVR的RFE筛选出与周期项位移相关性高的影响因子,建立周期项位移预测模型,采用PSO对预测模型参数进行优化;最后,叠加周期项与趋势项位移预测结果,得到滑坡累积位移预测值,所提模型拟合优度为0.999,均方根误差为9.974 mm,平均绝对误差为7.037 mm。与网络搜索交叉验证算法-优化支持向量机模型(GSCV、SVR模型)、遗传算法优化-支持向量机模型(GA-SVR模型)对比,该模型对于突变位移的预测能力较强,适用于阶跃型滑坡中位移加速变化时期的风险预警。
    Abstract: Affected by the seasonal precipitation and changes in water levels of reservoirs, parts of mountains will generate landslides in which the cumulative displacement-time curve of some landslides exhibits obvious "step type" dynamic deformation characteristics. In the light of that displacement, a landslide displacement prediction model was proposed, which was combined the particle swarm optimization (PSO) algorithm with the support vector regression (SVR) based on the recursive feature elimination (RFE) algorithm. and the research was performed combined with the Xinpu landslide. Firstly, the methods of outlier removal and missing value filling for landslide displacement data were explored. Outlier rejection was adopted a median-based method with ensemble empirical mode decomposition, and missing value filling was adopted a statistical variable-based method. Then, the "step type" cumulative displacement of landslides was split into the trend and period terms by the exponential smoothing method. The displacement of the trend term was fitted by Fourier curve. For the displacement of the periodic term, the influence factors with high correlation with the displacement of the periodic term were selected based on the SVR-RFE method, and the prediction model for the displacement of the periodic term was established. Subsequently, the prediction model parameters were optimized by the PSO algorithm. Finally, the predicted displacement of the period term was superimposed on the predicted displacement of the trend term to obtain the final predicted cumulative displacement of landslides, in which the goodness of fit was 0.999, the root mean square error was 9.974 mm, and the average absolute error was 7.037 mm. Comparing the proposed model with the GSCV-SVR model and the GA-SVR model, the proposed model was of a strong predictive capability for sudden displacement and was suitable for risk warning during periods of accelerated displacement changes of "step type" displacement of landslides.
    • HTML全文
    • 参考文献(24)
  • [1] 许强, 黄润秋, 李秀珍.滑坡时间预测预报研究进展[J].地球科学进展, 2004(3):478-483.
    [2] KALANTAR B, UEDA N, AL-NAJJAR H A H, et al. A comparison between three conditioning factors dataset for landslide prediction in the Sajadrood catchment of Iran[C]//Proceedings of XXIV ISPRS Congress: ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences.2020:625-635.
    [3] SHIHABUDHEEN K V, PILLAI G N, PEETHAMBARAN B. Prediction of landslide displacement with controlling factors using extreme learning adaptive neuro-fuzzy inference system (ELANFIS)[J]. Applied Soft Computing, 2017, 61: 892-904.
    [4] 彭令, 牛瑞卿, 赵艳南, 等. 基于核主成分分析和粒子群优化支持向量机的滑坡位移预测[J]. 武汉大学学报(信息科学版), 2013, 38(2):148-152, 161.
    [5] 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.
    [6] 黄健, 李桥, 巨能攀, 等. 基于主控因子分析与GM-IAGA-WNN联合模型的平推式滑坡位移预测研究:以垮梁子滑坡为例[J]. 工程地质学报, 2019, 27(4):862-872.
    [7] ZHANG W, XIAO R, SHI B, et al. Forecasting slope deformation field using correlated grey model updated with time correction factor and background value optimization[J/OL]. Engineering Geology, 2019, 260[2023-07-18]. https://doi.org/10.1016/j.enggeo.2019.105215.
    [8] 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.
    [9] 王朝阳, 李丽敏, 温宗周, 等.基于时间序列和CNN-LSTM的滑坡位移动态预测[J].国外电子测量技术, 2022, 41(3):1-8.
    [10] LI Y Y, SUN R L, YIN K L, et al. Forecasting of landslide displacements using a chaos theory based wavelet analysis-Volterra filter model[R/OL]. 2019[2023-07-18]. chrome-extension://bnjoienjhhclcabnkbhhfndecoipmcdg/background/jgpdf/layout/index.html?file=https://www.nature.com/articles/s41598-019-56405-y.pdf.
    [11] 陈曦, 高雅萍, 涂锐.基于EMD-TAR组合模型的滑坡位移预测研究[J].人民珠江, 2022, 43(3):96-101

    , 108.
    [12] 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.
    [13] DENG D M, LIANG Y, WANG L Q, 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]. Yantu Lixue/Rock and Soil Mechanics, 2017, 38(12):3660-3669.
    [14] 李秀珍, 许强.滑坡预报模型和预报判据[J].灾害学, 2003, 18(4):71-78.
    [15] 李强, 李端有.滑坡位移监测动态预报时间序列分析技术研究[J].长江科学院院报, 2005, 22(6):22-25.
    [16] XING Y, YUE J P, CHENG C. Interval estimation of landslide displacement prediction based on time series decomposition and long short-term memory network[J].IEEE Access, 2020, 8:3187-3196.
    [17] SHARIFI S, HENDRY M, MACCIOTTA R, et al. Evaluation of filtering methods for use on high-frequency measurements of landslide displacements[J]. Natural Hazards and Earth System Sciences, 2022, 22(2):411-430.
    [18] 罗袆沅, 蒋亚楠, 许强, 等.GPS滑坡位移监测时序分析与组合建模预测[J].防灾科技学院学报, 2020, 22(4):20-28.
    [19] LIN H, LU Y, DING R, et al. A multi-feature fusion apple classification method based on image processing and improved SVM[J]. Agricultural Biotechnology, 2022, 11(5):84-91.
    [20] VAPNIK V N. The nature of statistical learning theory[M]. Berlin: Springer, 1995.
    [21] GUYON I, WESTON J, BARNHILL S, et al. Gene Selection for cancer classification using support vector machines[J]. Machine Learning, 2002, 46(1/2/3):389-422.
    [22] YIN Y H, JANG-JACCARD J, XU W, et al. IGRF-RFE: a hybrid feature selection method for MLP-based network intrusion detection on UNSW-NB15 dataset[J/OL]. Journal of Big Data, 2023, 10 [2023-07-18]. https://doi.org/10.1186/s40537-023-00694-8.
    [23] CROZIER M J, EYLES R J. Assessing the probability of rapid mass movement[C]//Proceedings of the 3rd Australia-New Zealand Conference on Geomechanics. Wellington: New Zealand Institution of Engineers, 1980:47-51.
    [24] QI L P. A course recommender system of MOOC based on collaborative filtering algorithm with improved pearson correlation coefficient[D]. 武汉:华中师范大学, 2019.
    • 相关文章
    • 施引文献
  • 资源附件(0)
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  28
  • HTML全文浏览量:  3
  • PDF下载量:  4
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-07-18
  • 网络出版日期:  2024-12-05

目录

    /

    返回文章
    返回

    期刊在线

    作者中心

    友情链接

    版权所有 ©《工业建筑》杂志社有限公司 京ICP备11033253号-1

    本系统由北京仁和汇智信息技术有限公司 设计开发   百度统计