基于TPE-GBT模型的地下水封洞库灌浆量预测研究  

Research on Grouting Volume Prediction for Underground Water-sealed Caverns Based on TPE-GBT Model

作　　者：欧阳劭明 丁长栋 丁祥 张宜虎[2] 曹磊 刘倩 OUYANG Shaoming;DING Changdong;DING Xiang;ZHANG Yihu;CAO Lei;LIU Qian(School of Civil Engineering and Architecture,Hubei University of Technology,Wuhan 430068;Key Laboratory of Geotechnical Mechanics and Engineering of the Ministry of Water Resources,Changjiang River Scientific Research Institute,Wuhan 430010;First Engineering Bureau Co.,Ltd.,China Anneng Construction Group,Nanning 530221)

机构地区：[1]湖北工业大学土木建筑与环境学院,武汉430068 [2]长江科学院水利部岩土力学与工程重点实验室,武汉430010 [3]中国安能集团第一工程局有限公司,南宁530221

出　　处：《现代隧道技术》2024年第5期138-145,共8页Modern Tunnelling Technology

基　　金：国家自然科学基金(52309123);央级公益性科研院所基本科研业务费资助项目(CKSF2023310/YT,CKSF2023319/YT,CKSF20231027/YT);岩土力学与工程安全重点实验室开放基金课题(SKLGME023013)。

摘　　要：为改善灌浆施工隐蔽性强带来的灌浆量及渗控效果难以预测的现状,基于大量现场施工数据和机器学习方法,探索建立高效、准确的灌浆量预测模型,优化并指导现场灌浆施工管理。引入梯度提升树(Gradient Boosting Trees,GBT)模型,旨在对灌浆过程中的单位耗灰量进行预测,并采用TPE(Tree-Structured Parzen Estimator)算法对GBT模型进行超参数优化,以提升模型预测的准确性和泛化能力。研究结果表明:(1)在预灌浆测试集数据中,TPE-GBT单位耗灰量预测模型的决定系数R~2达到0.80,平均绝对百分比误差(MAPE)为0.2414;在后灌浆测试集数据中,模型的R~2达到0.84,MAPE为0.2810,均处于可接受的预测精度范围内,相较于传统的线性回归模型和GBT模型预测精度明显提高;(2)通过SHAP(Shapley Additive Explanations)值对输入参数进行敏感性分析,发现灌前透水率对模型预测的贡献最为显著,是灌浆工程中的关键控制参数;(3)在围岩条件一定的情况下,选取合适的灌浆压力并采用分序施工的方式可以提升灌浆渗控效果。To improve the prediction of grouting volume and seepage control effects,which are difficult to assess due to the strong concealment of grouting construction,this study explores the establishment of an efficient and accurate grouting volume prediction model based on extensive on-site construction data and machine learning methods.The Gradient Boosting Trees(GBT)model is introduced to predict the unit cement consumption during the grouting pro-cess,and the Tree-Structured Parzen Estimator(TPE)algorithm is used to optimize the hyperparameters of the GBT model to enhance its prediction accuracy and generalization ability.The research results indicate that:(1)In the pre-grouting test dataset,the coefficient of determination(R)of the TPE-GBT unit cement consumption prediction model reaches 0.80,with a mean absolute percentage error(MAPE)of 0.2414.In the post-grouting test dataset,the model's R?reaches 0.84,with a MAPE of 0.2810,both of which are within an acceptable range of prediction accuracy,significantly improving the prediction accuracy compared to traditional linear regression models and GBT models;(2)Sensitivity analysis of input parameters using SHAP(Shapley Additive Explanations)values reveals that the pre-grouting permeability contributes most significantly to model predictions and is a key control parameter in grouting engineering;(3)Under certain surrounding rock conditions,selecting an appropriate grouting pressure and using se-quential construction methods can enhance grouting seepage control effects.

关 键 词：地下水封洞库 梯度提升树 超参数优化 灌浆量预测 单位耗灰量 

分 类 号：TV5433[水利工程—水利水电工程]