基于控制区间牵引算法的地下施工变形预测  

Deformation prediction during underground construction based on traction algorithm in control phases

作　　者：马恩临 赖金星[1] 王立新[2] 汪珂[2] 雷升祥 李储军[2] 邱军领 MA En-lin;LAI Jin-xing;WANG Li-xin;WANG Ke;LEI Sheng-xiang;LI Chu-jun;QIU Jun-ling(School of Highway,Chang’an University,Xi’an,Shaanxi 710064,China;China Railway First Survey and Design Institute Group Ltd.,Xi’an,Shaanxi 710043,China;China Railway Construction Corporation Limited,Beijing 100855,China)

机构地区：[1]长安大学公路学院,陕西西安710064 [2]中铁第一勘察设计院集团有限公司,陕西西安710043 [3]中国铁建股份有限公司,北京100855

出　　处：《岩土力学》2023年第2期577-594,共18页Rock and Soil Mechanics

基　　金：国家重点研发计划项目(No.2018YFC0808706);长安大学博士研究生创新能力培养资助项目(No.300203211217);陕西省重点研发计划项目(No.2023-YBSF-511)。

摘　　要：变形是地下结构施工安全状态的重要评价指标。针对数据驱动变形预测方法中地下施工动态影响因素难以量化这一问题,提出了基于控制区间牵引算法的地下施工变形预测模型。以双向长短时记忆网络(Bi-LSTM)对变形监测时间序列进行预测,以数值模拟在关键施工阶段处的结果为牵引点。根据实测值随阶段更新牵引点,并基于注意力机制双向长短时记忆网络(Bi-LSTM-AM)以牵引点修正数据驱动模型在控制区间的预测结果,实现更准确、更智能的地下施工变形预测。设置牵引相对权重,使模型可自适应判断当前合理牵引程度,准确融合了Bi-LSTM与数值模拟的结果。通过相关历史案例与数据,验证了牵引预测模型的有效性。依托西安市西咸新区丰镐三路地下通道上跨地铁1号线自动化监测实例,采用牵引算法预测了地下结构变形。结果表明:在关键施工阶段处,牵引作用改善了数据驱动预测方法存在的滞后问题,各阶段误差平均降低了24.34%;不断优化的牵引点逐渐趋近真值,降低了数值模拟出现偏差时造成的影响。该方法可为地下施工变形预测问题提供新途径。Deformation control is essential when assessing the safety state of underground structures during construction.Due to the difficulty in quantifying the dynamic influence of underground construction,a deformation prediction model based on traction algorithm in control phases are proposed.The bidirectional long short-term memory(Bi-LSTM)is adopted to predict the time series of the monitoring data.The results of crucial construction stages obtained by numerical simulation are taken as traction points and are updated along with the stages according to the existing monitoring data.By using the attention mechanism combined with the bidirectional long short-term memory(Bi-LSTM-AM),the prediction results of the data-driven models in the control phases can thereafter be modified according to the updated traction points,achieving a more accurate and intelligent prediction of deformation during underground construction.Setting the traction relative weight allows the current reasonable traction degree to be adaptively determined,thereby realizing a valid fusion of Bi-LSTM and numerical simulation.The effectiveness of the traction prediction model is verified through relevant historical cases and data.Combined with the automatic monitoring case of Xi’an Metro Line 1 affected by the upper-span underpass of Fenghao third road in Xixian New District,the advantages and shortcomings of traction prediction are discussed.The results show that the traction effects improve the delay problem of data-driven prediction at the key construction stages,and the error is decreased by 24.34% on average.The continuously optimized traction points gradually approach the true values,which reduces the impact caused by the deviation of numerical simulation.The proposed model provides a fresh perspective on the deformation prediction during underground construction.

关 键 词：地下工程 变形预测 时间序列 牵引算法 Bi-LSTM 注意力机制 

分 类 号：TU94[建筑科学—建筑技术科学]