基于Bayes-LSTM的公路隧道围岩变形预测方法研究  

Prediction Method of Surrounding Rock Deformation of Highway Tunnels Based on Bayes‑LSTM

作　　者：刘智[1] 李欣雨 李震[1] 孔宪光[2] 常建涛[2] LIU Zhi;LI Xinyu;LI Zhen;KONG Xianguang;CHANG Jiantao(CCCC First Highway Consultants Co.,Ltd.,Xi'an,Shaanxi 710076,China;Xidian University,Xi'an,Shaanxi 710065,China)

机构地区：[1]中交第一公路勘察设计研究院有限公司,陕西西安710076 [2]西安电子科技大学,陕西西安710065

出　　处：《中外公路》2024年第1期166-176,共11页Journal of China & Foreign Highway

基　　金：中国交建科技研发项目(编号:2019-ZJKJ-08);中交第一公路勘察设计研究院有限公司科技研发项目(编号:KYHT2020-43);中交第一公路勘察设计研究院有限公司科创基金项目(编号:KCJJ2020-19)。

摘　　要：在公路隧道施工过程中,围岩的稳定性对隧道施工的影响较大。因此公路隧道围岩变形的监控量测与准确预测是保障隧道施工安全的关键。针对当前隧道围岩变形的预测精度较低以及泛化能力较差等问题,该文提出一种基于贝叶斯(Bayes)优化长短期记忆网络(LSTM)的方法,该方法首先对拱顶沉降和周边收敛的原始监测数据进行预处理,而后构建公路隧道拱顶沉降与周边收敛的初始LSTM模型,并利用Bayes优化模型中的超参数,最终得出预测结果。利用该模型对某公路隧道拱顶沉降和周边收敛进行预测,将预测结果以均方根误差为评价指标与神经网络(CNN)和支持向量回归(SVR)进行对比。预测拱顶沉降时,Bayes-LSTM模型的平均预测精度相较于CNN与SVR模型分别提高了1.0与1.26;预测周边收敛时,Bayes-LSTM模型平均精度相较于CNN与SVR分别提高了0.3与0.32。表明Bayes-LSTM模型的预测精度较高,同时其能在训练模型过程中对历史信息进行判断和取舍,极大地提高了时序数据处理的效率,为公路隧道围岩变形预测提供了新的思路和探索。In the process of highway tunnel construction,the stability of surrounding rock has a great impact on tunnel construction.Therefore,the monitoring measurement and accurate prediction of surrounding rock deformation of highway tunnels are the keys to ensuring the safety of tunnel construction.In view of the low prediction accuracy and poor generalization ability of tunnel surrounding rock deformation,this paper proposed a Bayesian(Bayes)-based method to optimize the long-term and short-term memory(LSTM)network.The method first preprocessed the original monitoring data of crown settlement and peripheral convergence,then constructed the initial LSTM model of crown settlement and peripheral convergence of highway tunnels,and used the super parameters in the Bayes optimization model to obtain the prediction results.The model was used to predict the crown settlement and peripheral convergence of a highway tunnel,and the prediction results were compared with convolutional neural network(CNN)and support vector regression(SVR)using root mean square error as the evaluation index.When the crown settlement was predicted,the average prediction accuracy of the Bayes-LSTM model was 1.0 and 1.26 higher than that of the CNN and SVR models,respectively.When peripheral convergence was predicted,the average accuracy of the Bayes-LSTM model was 0.3 and 0.32 higher than that of CNN and SVR,respectively.The results show that the Bayes-LSTM model has higher prediction accuracy,and it can judge and choose the historical information in the process of model training,which greatly improves the efficiency of time series data processing.The model provides a new idea for the prediction of surrounding rock deformation of highway tunnels.

关 键 词：公路隧道 围岩变形 数据分析 LSTM 贝叶斯优化 

分 类 号：U456.3[建筑科学—桥梁与隧道工程]