A prediction model for landslide creep displacement based on Genetic Algorithm
-
摘要: 滑坡位移预测是预报滑坡灾害的重要依据,以往的滑坡位移预测模型多数为时间序列预测模型、BP神经网络预测模型、Gaussian拟合预测模型以及其他一些非线性预测模型。这些滑坡位移预测模型在建立上缺乏力学理论支撑,对不同力学特性产生的滑坡位移预测分析上没有针对性。文中针对力学特性为重力蠕变型滑坡位移的预测,提出一种基于遗传优化算法的滑坡蠕滑位移非线性预测模型。以鲁家坡滑坡东侧J05监测点的累计水平位移为例,划定测试区域与预测区域进行模型预测分析,并将新模型预测结果与Gaussian拟合预测模型、BP神经网络预测模型预测结果进行对比分析。结果表明,相较于传统预测模型,新模型的预测效果有所提升,有一定的工程价值与实践价值。Abstract: Landslide displacement prediction is an important basis of predicting landslide disasters. Most of the previous landslide displacement prediction models include time series prediction models, BP neural network prediction models, Gaussian fitting prediction models, and various other nonlinear prediction models. However, these landslide displacement prediction models lack the foundation of mechanical theory in the establishment and have no pertinence in the prediction and analysis of landslide displacement resulting from diverse mechanical properties. In this paper, a nonlinear prediction model of landslide creep displacement based on Genetic optimization Algorithm is proposed for the prediction of Gravity Creep landslide displacement. Using the cumulative horizontal displacement data from monitoring point J05 on the eastern side of the Lujiapo landslide as a case study, the test area and prediction area are delimited for model prediction analysis. The results of the new model are compared with those of Gaussian fitting model and BP neural network model. The results indicate that, in comparison to the traditional prediction models, the new model exhibits improved predictive performance, offering a certain engineering value and practical value.
-
Key words:
- Landslide Prediction /
- Genetic Algorithm /
- Creep Displacement /
- Function Model /
- Comparative Analysis
-
表 1 遗传算法迭代参数
Table 1. Iteration parameter of Genetic Algorithm
参数名称 符号 种群数量 npop 迭代次数 maxit 染色体数 nv 交叉算子 npc 变异算子 nmu 子代数量 nc 表 2 遗传算法迭代参数设定表
Table 2. Genetic Algorithm iteration parameter configuration table
迭代参数 数值 npop 30 maxit 500 nvar 23 npc 0.9 nmu 0.1 nc 27 表 3 测试数据拟合模型迭代进化表
Table 3. Iterative Evolution Table of Test Data Fitting Models
进化阶段 迭代次数 统一决定系数RNL 0 1 0.828 0 1 101 0.839 6 2 106 0.839 8 3 151 0.840 6 4 221 0.845 0 表 4 拟合模型各进化阶段求解参数
Table 4. Parameters solutions at each Evolution Stage of the Fit Model
参数 a1 b1 c1 d1 D RNL 进化阶段 0 +388.3 −1.351E-02 −3.786E+01 +2.179E-02 −383.2 0.828 0 1 +421.8 −1.937E-01 −1.003E-03 −1.770E-02 −351.0 0.839 6 2 +454.2 −9.954E-02 −1.257E-03 −5.410E-03 −411.1 0.839 8 3 +136.4 −8.182E-01 −1.667E-03 −2.010E-02 −72.96 0.840 6 4 +6.379 −2.524E+04 −4.264E-02 +1.620E-02 +3.167 0.845 0 表 5 三种预测模型预测区域统计学指标
Table 5. Statistical Metrics for Prediction Regions of Three Prediction Models
预测方法 遗传算法拟合预测 高斯拟合预测 BP神经网络预测 统计学
指标RNL 0.897 5 0.817 4 0.888 2 RMSE 2.596 7 4.639 1 2.790 4 FR 0.994 9 0.992 7 0.994 8 R2 0.991 2 −1.216 2 0.826 7 -
[1] 吴明辕,罗明,刘岁海. 基于光学遥感与InSAR技术的潜在滑坡与老滑坡综合识别——以滇西北地区为例[J]. 中国地质灾害与防治学报,2022,33(3):84 − 93. [WU Mingyuan,LUO Ming,LIU Suihai. Comprehensive identification of potential and old landslides based on optical remote sensing and InSAR technologies:A case study in northwestern Yunnan Province[J]. The Chinese Journal of Geological Hazard and Control,2022,33(3):84 − 93. (in Chinese with English abstract) WU Mingyuan, LUO Ming, LIU Suihai . Comprehensive identification of potential and old landslides based on optical remote sensing and InSAR technologies: A case study in northwestern Yunnan Province[J]. The Chinese Journal of Geological Hazard and Control,2022 ,33 (3 ):84 −93 . (in Chinese with English abstract)[2] 曹博,汪帅,宋丹青,等. 基于蚁群算法优化极限学习机模型的滑坡位移预测[J]. 水资源与水工程学报,2022,33(2):172 − 178. [CAO Bo,WANG Shuai,SONG Danqing,et al. Landslide displacement prediction based on extreme learning machine optimized by ant colony algorithm[J]. Journal of Water Resources and Water Engineering,2022,33(2):172 − 178. (in Chinese with English abstract) CAO Bo, WANG Shuai, SONG Danqing, et al . Landslide displacement prediction based on extreme learning machine optimized by ant colony algorithm[J]. Journal of Water Resources and Water Engineering,2022 ,33 (2 ):172 −178 . (in Chinese with English abstract)[3] 陈嘉伟. 基于ARIMA模型与PSO-BP神经网络算法的滑坡位移预测及研究[D]. 宜昌:三峡大学,2020. [CHEN Jiawei. Displacement forecast and research based on ARIMA model and PSO-BP neural network[D]. Yichang:China Three Gorges University,2020. (in Chinese with English abstract)CHEN Jiawei. Displacement forecast and research based on ARIMA model and PSO-BP neural network[D]. Yichang: China Three Gorges University, 2020. (in Chinese with English abstract) [4] 王江荣. 高斯函数模型在变形监测数据处理中的应用[J]. 金属矿山,2015(4):178 − 181. [WANG Jiangrong. Application of the Gauss function model in data processing of deformation monitoring[J]. Metal Mine,2015(4):178 − 181. (in Chinese with English abstract) WANG Jiangrong . Application of the Gauss function model in data processing of deformation monitoring[J]. Metal Mine,2015 (4 ):178 −181 . (in Chinese with English abstract)[5] 杨伟东,王再旺,赵涵卓,等. 基于APSO-SVR-GRU模型的白水河滑坡周期项位移预测[J]. 中国地质灾害与防治学报,2022,33(6):20 − 28. [YANG Weidong,WANG Zaiwang,ZHAO Hanzhuo,et al. Displacement prediction of periodic term of Baishuihe landslide based on APSO-SVR-GRU model[J]. The Chinese Journal of Geological Hazard and Control,2022,33(6):20 − 28. (in Chinese with English abstract) YANG Weidong, WANG Zaiwang, ZHAO Hanzhuo, et al . Displacement prediction of periodic term of Baishuihe landslide based on APSO-SVR-GRU model[J]. The Chinese Journal of Geological Hazard and Control,2022 ,33 (6 ):20 −28 . (in Chinese with English abstract)[6] 袁于思,冯小鹏,李勇,等. 基于PSO-DSRVM的边坡变形预测[J]. 中国地质灾害与防治学报,2023,34(1):1 − 7. [YUAN Yusi,FENG Xiaopeng,LI Yong,et al. Prediction of mine slope deformation based on PSO-DSRVM[J]. The Chinese Journal of Geological Hazard and Control,2023,34(1):1 − 7. (in Chinese with English abstract) YUAN Yusi, FENG Xiaopeng, LI Yong, et al . Prediction of mine slope deformation based on PSO-DSRVM[J]. The Chinese Journal of Geological Hazard and Control,2023 ,34 (1 ):1 −7 . (in Chinese with English abstract)[7] 胡鹏,文章,胡新丽,等. 基于遗传算法-支持向量机的滑坡渗透系数反演[J]. 水文地质工程地质,2021,48(4):160 − 168. [HU Peng,WEN Zhang,HU Xinli,et al. Estimation of hydraulic conductivity of landslides based on support vector machine method optimized with genetic algorithm[J]. Hydrogeology & Engineering Geology,2021,48(4):160 − 168. (in Chinese with English abstract) HU Peng, WEN Zhang, HU Xinli, et al . Estimation of hydraulic conductivity of landslides based on support vector machine method optimized with genetic algorithm[J]. Hydrogeology & Engineering Geology,2021 ,48 (4 ):160 −168 . (in Chinese with English abstract)[8] 张艳,宦飞. 一种应用遗传算法的彩色图像分割方法[J]. 计算机应用与软件,2011,28(3):237 − 239. [ZHANG Yan,HUAN Fei. A colour image segmentation method using genetic algorithm[J]. Computer Applications and Software,2011,28(3):237 − 239. (in Chinese with English abstract) ZHANG Yan, HUAN Fei . A colour image segmentation method using genetic algorithm[J]. Computer Applications and Software,2011 ,28 (3 ):237 −239 . (in Chinese with English abstract)[9] 王晓峰,石东伟. 数值分析[M]. 郑州:河南大学出版社,2019. [WANG Xiaofeng,SHI Dongwei. Numerical analysis[M]. Kaifeng,China:Henan University Press,2019. (in Chinese with English abstract)WANG Xiaofeng, SHI Dongwei. Numerical analysis[M]. Kaifeng, China: Henan University Press, 2019. (in Chinese with English abstract) [10] 张世强. 曲线回归的拟合优度指标的探讨[J]. 中国卫生统计,2002,19(1):9 − 11. [ZHANG Shiqiang. Approach on the fitting optimization index of curve regression[J]. Chinese Journal of Health Statistics,2002,19(1):9 − 11. (in Chinese with English abstract) ZHANG Shiqiang . Approach on the fitting optimization index of curve regression[J]. Chinese Journal of Health Statistics,2002 ,19 (1 ):9 −11 . (in Chinese with English abstract)[11] 张倬元,王士天,王兰生. 工程地质分析原理[M]. 4版. 北京:地质出版社,2016. [ZHANG Zhuoyuan,WANG Shitian,WANG Lansheng. Principles of engineering geological analysis[M]. 4th ed. Beijing:Geological Publishing House,2016. (in Chinese with English abstract)ZHANG Zhuoyuan, WANG Shitian, WANG Lansheng. Principles of engineering geological analysis[M]. 4th ed. Beijing: Geological Publishing House, 2016. (in Chinese with English abstract) [12] 许强,汤明高,黄润秋,等. 大型滑坡监测预警与应急处置[M]. 北京:科学出版社,2015. [XU Qiang,TANG Minggao,HUANG Runqiu. Monitoring,early warning and emergency disposal of large landslide[M]. Beijing:Science Press,2015. (in Chinese with English abstract)XU Qiang, TANG Minggao, HUANG Runqiu. Monitoring, early warning and emergency disposal of large landslide[M]. Beijing: Science Press, 2015. (in Chinese with English abstract) [13] 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(增刊2):3705 − 3711. [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(Sup 2):3705 − 3711. (in Chinese with English abstract)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(Sup 2): 3705 − 3711. (in Chinese with English abstract) [14] 石达顺,唐朝晖. 基于统计高斯拟合的圆形光斑中心定位方法[J]. 测控技术,2020,39(7):51 − 56. [SHI Dashun,TANG Zhaohui. Circular spot center location method based on statistical Gaussian fitting[J]. Measurement & Control Technology,2020,39(7):51 − 56. (in Chinese with English abstract) SHI Dashun, TANG Zhaohui . Circular spot center location method based on statistical Gaussian fitting[J]. Measurement & Control Technology,2020 ,39 (7 ):51 −56 . (in Chinese with English abstract)[15] 陈航,张贝贝,旷华江,等. 基于BP神经网络反演分析的隧道塌方机理研究[J]. 水文地质工程地质,2023,50(3):149 − 158. [CHEN Hang,ZHANG Beibei,KUANG Huajiang,et al. A study of the tunnel collapse mechanism based on the BP neural network inversion analysis[J]. Hydrogeology & Engineering Geology,2023,50(3):149 − 158. (in Chinese with English abstract) CHEN Hang, ZHANG Beibei, KUANG Huajiang, et al . A study of the tunnel collapse mechanism based on the BP neural network inversion analysis[J]. Hydrogeology & Engineering Geology,2023 ,50 (3 ):149 −158 . (in Chinese with English abstract)[16] 邵毅明,钟颖,吴文文,等. 基于熵权TOPSIS法的短时交通流预测模型性能综合评价[J]. 重庆理工大学学报(自然科学),2020,34(7):205 − 211. [SHAO Yiming,ZHONG Ying,WU Wenwen,et al. Comprehensive evaluation of short-term traffic flow prediction model based on entropy TOPSIS model[J]. Journal of Chongqing University of Technology (Natural Science),2020,34(7):205 − 211. (in Chinese with English abstract) SHAO Yiming, ZHONG Ying, WU Wenwen, et al . Comprehensive evaluation of short-term traffic flow prediction model based on entropy TOPSIS model[J]. Journal of Chongqing University of Technology (Natural Science),2020 ,34 (7 ):205 −211 . (in Chinese with English abstract)[17] 严干贵,宋薇,杨茂,等. 风电场风功率实时预测效果综合评价方法[J]. 电网与清洁能源,2012,28(5):1 − 6. [YAN Gangui,SONG Wei,YANG Mao,et al. A comprehensive evaluation method of the real-time prediction effects of wind power[J]. Power System and Clean Energy,2012,28(5):1 − 6. (in Chinese with English abstract) YAN Gangui, SONG Wei, YANG Mao, et al . A comprehensive evaluation method of the real-time prediction effects of wind power[J]. Power System and Clean Energy,2012 ,28 (5 ):1 −6 . (in Chinese with English abstract)[18] 殷坤龙. 滑坡灾害预测预报[M]. 武汉:中国地质大学出版社,2004:1 − 3. [YIN Kunlong. Landslide hazard prediction and evaluation[M]. Wuhan:China University of Geosciences Press,2004:1 − 3. (in Chinese with English abstract)YIN Kunlong. Landslide hazard prediction and evaluation[M]. Wuhan: China University of Geosciences Press, 2004: 1 − 3. (in Chinese with English abstract) -