基于支持向量机的气压辅助掘进条件下盾构隧道地表变形预测研究  

Prediction of Surface Deformation of a Shield Tunnel Using Air Pressure-Assisted Tunneling Based on Support Vector Machine

作　　者：李方毅 张晓平 许丹[2] 姜军 周智 沈婕 王浩杰 张心悦 LI Fangyi;ZHANG Xiaoping;XU Dan;JIANG Jun;ZHOU Zhi;SHEN Jie;WANG Haojie;ZHANG Xinyue(School of Civil Engineering,Wuhan University,Wuhan 430072,Hubei,China;China Railway 11th Bureau Group Co.,Ltd.,Wuhan 430061,Hubei,China;China Railway Construction South China Construction Co.,Ltd.,Guangzhou 511458,Guangdong,China;Guangzhou Metro Group Co.,Ltd.,Guangzhou 510330,Guangdong,China)

机构地区：[1]武汉大学土木建筑工程学院,湖北武汉430072 [2]中铁十一局集团有限公司,湖北武汉430061 [3]中铁建华南建设有限公司,广东广州511458 [4]广州地铁集团有限公司,广东广州510330

出　　处：《隧道建设（中英文）》2021年第7期1159-1165,共7页Tunnel Construction

摘　　要：与常规土压平衡盾构掘进相比,气压辅助掘进条件下的地表变形过程更为复杂。为提高预测模型的工程适应性,准确预测气压辅助条件下的地表变形量,保障该条件下盾构顺利掘进,引入支持向量机(SVM)理论,利用粒子群算法(PSO)对支持向量机的超参数组合进行优化;同时,优化模型输入参数,将隧道上覆黏土层厚度和气压值设为输入参数,并针对上覆非均质土层改进模型参数计算方法,建立适用于气压辅助掘进的PSO-SVM地表变形预测模型。为验证预测模型的准确性和实用性,以广州地铁18号线陇枕出入场线某一区间为例,使用优化了输入参数的模型进行预测,并在此基础上,综合采用PSO-SVM、SVM和PSO-BP 3种模型进行地表变形预测分析。结果表明:1)针对气压辅助掘进工法优化输入参数的PSO-SVM模型可以较好地满足工程需要;2)PSO-SVM模型的适应性显著高于PSO-BP和SVM模型,具有较好的工程适用性。Compared with the conventional earth pressure balance shield tunneling method,the surface deformation that results from air pressure-assisted tunneling is more complex.To improve the adaptability of the prediction model,accurately predict the surface deformation under the condition of air pressure,and ensure successful shield tunneling,the theory behind the support vector machine(SVM)is introduced,and particle swarm optimization(PSO)is used to optimize the superparameter combination for the SVM.The input parameters of the model are also optimized at the same time.The thickness of the clay layer that overlies the tunnel and the air pressure are set as the input parameters,and the method for calculating the model parameters is improved for the overlying heterogeneous soil layer.A PSO-SVM for model for air pressure-assisted tunneling is thus established.To verify the accuracy and practicability of the prediction model,the model is applied to a section of the Longzhen entrance and exit line of Guangzhou metro line 18,and the data with optimized input parameters are used for prediction.On this basis,an analysis of the predictions of the surface deformation is conducted using the PSO-SVM,SVM,and PSO-back-propagation(BP)3 models.The results show that:(1)the PSO-SVM model for optimizing the input parameters of air-pressure assisted tunneling can meet the engineering requirements;and(2)the PSO-SVM model is significantly more adaptable than the PSO-BP and SVM models,which indicates its applicability to engineering.

关 键 词：盾构隧道 气压辅助掘进 地表变形预测 支持向量机 粒子群算法 

分 类 号：U456.3[建筑科学—桥梁与隧道工程]