吉林大学学报(地球科学版) ›› 2021, Vol. 51 ›› Issue (5): 1316-1323.doi: 10.13278/j.cnki.jjuese.20200310
秦胜伍, 张延庆, 张领帅, 苗强, 程秋实, 苏刚, 孙镜博
Qin Shengwu, Zhang Yanqing, Zhang Lingshuai, Miao Qiang, Cheng Qiushi, Su Gang, Sun Jingbo
摘要： 为了提高机器学习对深基坑地面沉降的预测能力，本文提出了一种基于Stacking集成学习方式的多模型融合的地面沉降预测方法，并以深圳某深基坑为例，采用斯皮尔曼相关性系数对基坑地面沉降的影响因子进行筛选；运用筛选后的8个影响因子建立Stacking深基坑地面沉降预测模型，以验证该方法的适用性。结果表明：Stacking预测模型的平均绝对误差为0.34、平均绝对误差百分比为2.22%，均方根误差为0.13，相较于传统基模型（随机森林、支持向量机和人工神经网络），Stacking预测模型的平均绝对误差、平均绝对误差百分比和均方根误差值皆为最小。
中图分类号:
| [1] 胡之锋, 陈健, 邱岳峰, 等. 一种黏土层中深基坑开挖地表沉降预测方法[J]. 长江科学院院报, 2019, 36(6):60-67. Hu Zhifeng, Chen Jian, Qiu Yuefeng, et al. A Simplified Method for Predicting Ground Surface Settlement Induced by Deep Excavation of Clay Stratum[J]. Journal of Changjiang Academy of Sciences, 2019, 36(6):60-67. [2] 魏纲, 周洋, 魏新江. 盾构隧道施工引起的工后地面沉降研究[J]. 岩石力学与工程学报, 2013, 32(增刊1):2891-2896. Wei Gang, Zhou Yang, Wei Xinjiang. Research on Post-Construction Surface Settlement Caused by Shield Tunneling[J]. Chinese Journal of Rock Mechanics and Engineering, 2013, 32(Sup.1):2891-2896. [3] Sangyoub L, Daniel W H. Predictive Tool for Estimating Accident Risk[J]. Journal of Construction Engineering and Management, 2003, 129(4):431-436. [4] 孙超, 许成杰. 基坑开挖对周边环境的影响[J]. 吉林大学学报(地球科学版), 2019, 49(6):1698-1705. Sun Chao, Xu Chengjie. Influence of Excavation of a Deep Excavation on the Surrounding Environment[J]. Journal of Jilin University (Earth Science Edition), 2019, 49(6):1698-1705. [5] Yoo C, Lee D. Deep Excavation-Induced Ground Surface Movement Characteristics:A Numerical Investigation[J]. Computers and Geotechnics, 2008, 35(2):231-252. [6] Zhou Y, Su W, Ding L, et al. Predicting Safety Risks in Deep Foundation Pits in Subway Infrastructure Projects:Support Vector Machine Approach[J]. Journal of Computing in Civil Engineering, 2017, 31(5):040170525. [7] 刘贺, 张弘强, 刘斌.基于粒子群优化神经网络算法的深基坑变形预测方法[J]. 吉林大学学报(地球科学版), 2014, 44(5):1609-1614. Liu He, Zhang Hongqiang, Liu Bin. A Prediction Method for the Deformation of Deep Foundation Pit Based on Particle Swarm Optimization Neural Network[J]. Journal of Jilin University (Earth Science Edition), 2014, 44(5):1609-1614. [8] 齐干, 朱瑞钧. 基于BP网络的基坑周围地表沉降影响因素分析[J]. 地下空间与工程学报, 2007, 3(5):863-867. Qi Gan, Zhu Ruijun. Analysis of Factors Affecting Ground Settlement Around Deep Foundation Pit Based on BP Neural Network[J]. Chinese Journal of Underground Space and Engineering, 2007, 3(5):863-867. [9] 石祥锋, 王丽芬, 沈阳, 等. 基于GA-SVM的基坑施工地面沉降时间序列预测研究[J]. 施工技术, 2017, 46(8):16-19. Shi Xiangfeng, Wang Lifen, Shen Yang, et al. Research on Time Series Predication of Foundation Excavation Construction Land Settlement Based on the GA-SVM[J]. Construction Technology, 2017, 46(8):16-19. [10] 林楠, 陈永良, 李伟东, 等. 极限学习机模型在季冻区深基坑地表沉降预测中的应用[J]. 世界地质, 2018, 37(4):1281-1287. Lin Nan, Chen Yongliang, Li Weidong, et al. Application of Extreme Learning Machine Model in Ground Settlement Prediction of Deep Foundation Pit in Seasonal Frozen Area[J]. Global Geology, 2018, 37(4):1281-1287. [11] 李珩, 朱靖波, 姚天顺. 基于Stacking算法的组合分类器及其应用于中文组块分析[J]. 计算机研究与发展, 2005(5):844-848. Li Heng, Zhu Jingbo, Yao Tianshun. Combined Multiple Classifiers Based on a Stacking Algorithm and Their Application to Chinese Text Chunking[J]. Journal of Computer Research and Development, 2005(5):844-848. [12] 王荣政, 廖贤艺, 陈湘萍, 等. 基于集成学习融合模型的血糖预测[J]. 医学信息学杂志, 2019, 40(1):59-62. Wang Rongzheng, Liao Xianyi, Chen Xiangping, et al. Blood Glucose Prediction Based on Integrated Learning Fusion Model[J]. Journal of Medical Informatics, 2019, 40(1):59-62. [13] Jiang M Q, Liu J P, Zhang L, et al. An Improved Stacking Framework for Stock Index Prediction by Leveraging Tree-Based Ensemble Models and Deep Learning Algorithms[J]. Physica A:Statistical Mechanics and Its Applications, 2020, 541(1):122272. [14] 史佳琪, 张建华. 基于多模型融合Stacking集成学习方式的负荷预测方法[J]. 中国电机工程学报, 2019, 39(14):4032-4042. Shi Jiaqi, Zhang Jianhua. Load Forecasting Method Based on Multi-Model by Stacking Ensemble Learning[J]. Proceedings of the CSEE, 2019, 39(14):4032-4042. [15] 刘安强, 王子童. 基于Stacking集成学习的采空区地面塌陷危险性预测[J]. 能源与环保, 2020, 42(9):54-58. Liu Anqiang, Wang Zitong. Prediction of the Risk of Ground Collapse in Goaf Based on Stacking Integrated Learning[J]. China Energy and Environmental Protection, 2020, 42(9):54-58. [16] Wang J, Xu J, Peng Y, et al. Prediction of Forest Unit Volume Based on Hybrid Feature Selection and Ensemble Learning[J]. Evolutionary Intelligence, 2020, 13(1):21-32. [17] Wolpert D H. Stacked Generalization[J]. Neural Networks, 1992, 5(2):241-259. [18] 王牧帆, 罗周全, 于琦. 基于Stacking模型的采空区稳定性预测[J]. 黄金科学技术, 2020, 28(6):894-901. Wang Mufan, Luo Zhouquan, Yu Qi. Stability Prediction of Goaf Based on Stacking Model[J]. Gold Science and Technology, 2020, 28(6):894-901. [19] Breiman L, Random Forests[J]. Mach Learn, 2001, 45(1):5-32. [20] Vapnik V N. The Nature of Statistical Learning Theory[M]. New York:Springer, 1995. [21] Kasabov N, Scott N M, Tu E, et al. Evolving Spatio-Temporal Data Machines Based on the Neu Cube Neuromorphic Framework:Design Methodology and Selected Applications[J]. Neural Networks, 2016, 78(Sup.1):1-14. [22] 谭震霖. 基于支持向量回归的地铁深基坑地表沉降预测[D]. 武汉:华中科技大学, 2019. Tan Zhenlin. Surface Subsidence Prediction of Deep Foundation Pit Based on Support Vector Regression[D]. Wuhan:Huazhong University of Science and Technology, 2019. [23] 钟国强, 王浩, 李莉, 等. 基于SFLA-GRNN模型的基坑地表最大沉降预测[J]. 岩土力学, 2019, 40(2):792-798. Zhong Guoqiang, Wang Hao, Li Li, et al. Prediction of Maximum Settlement of Foundation Pit Based on SFLA-GRNN Model[J]. Rock and Soil Mechanics, 2019, 40(2):792-798. |
| [1] | 孙超, 薄景山, 刘红帅, 齐文浩. 采空区地表沉降影响因素研究[J]. J4, 2009, 39(3): 498-502. |
|