Tunnelling and Underground Space Technology最新文献_第8页

An interpretable and adaptive tunnel water inflow prediction method using data augmentation and AHP-Enhanced OP-LightGBM 基于数据增强和AHP-Enhanced OP-LightGBM的可解释自适应隧道涌水预测方法

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-08 DOI: 10.1016/j.tust.2026.107445

Jingqi Cui , Shunchuan Wu , Haiyong Cheng , Xiaowei Hou , Jiaxin Wang , Weihua Liu , Chaoqun Chu

Accurate prediction of tunnel water inflow is critical for ensuring construction safety and risk control in tunnel engineering. However, traditional regression methods face significant challenges, including limited sample sizes, imbalanced data, complex feature interactions, and difficulty in engineering deployment. To address these issues, this study proposes an intelligent prediction framework that integrates data augmentation, model optimization, interpretability, and online deployment, and additionally possesses strong adaptability to dynamic field conditions. First, the SMOGN undersampling method is employed to balance and augment the training dataset, effectively expanding sparse samples and suppressing the influence of outliers, thereby enhancing the model’s generalization ability. Subsequently, LightGBM is improved through Optuna-based hyperparameter optimization and Analytic Hierarchy Process (AHP)-based feature weight adjustment, forming the AHP-OP-LightGBM hybrid model. This approach reduces prediction error by 15.89 % while aligning feature weights more closely with physical constraints. Compared with conventional optimization strategies, the model demonstrates superior capability in representing hydrogeological characteristics due to the dual mechanism of automated hyperparameter tuning and feature weight correction. Correlation analysis and SHAP-based interpretability further clarify the nonlinear synergistic mechanisms governing the coupled geomechanical-hydrological processes controlling tunnel water inflow. To support engineering application, a cloud-deployed online prediction system is developed using web technologies, integrating SHAP for transparent decision support. Additionally, an incremental learning module is incorporated to accommodate dynamic data variations. Validation using a small set of local incremental samples yields a maximum prediction error of only 1.9169 m³/h, demonstrating strong compatibility and accuracy across different engineering scenarios. Comparative experiments show that, on average, the proposed model reduces prediction error by 39.65 % and improves fitting accuracy by 18.43 % compared with traditional regression methods. Overall, this study provides a high-precision, interpretable, and generalizable intelligent solution for predicting tunnel water inflow under complex geological conditions.

隧道涌水的准确预测是保证隧道工程施工安全和风险控制的关键。然而，传统的回归方法面临着样本量有限、数据不平衡、特征交互复杂、工程部署困难等重大挑战。针对这些问题，本研究提出了一种集数据扩充、模型优化、可解释性和在线部署于一体的智能预测框架，并对动态现场条件具有较强的适应性。首先，采用SMOGN欠采样方法对训练数据集进行平衡和扩充，有效扩展稀疏样本，抑制离群值的影响，从而增强模型的泛化能力。随后，通过基于optuna的超参数优化和基于AHP （Analytic Hierarchy Process）的特征权值调整对LightGBM进行改进，形成AHP- op -LightGBM混合模型。该方法将预测误差降低了15.89%，同时将特征权重与物理约束更紧密地对齐。与传统优化策略相比，该模型具有自动超参数整定和特征权值校正的双重机制，具有较好的表征水文地质特征的能力。相关分析和基于shap的可解释性进一步阐明了控制隧道涌水的耦合地质力学-水文过程的非线性协同机制。为了支持工程应用，利用web技术开发了一个云部署的在线预测系统，集成了SHAP以提供透明的决策支持。此外，还包含了一个增量学习模块，以适应动态数据变化。使用一小组局部增量样本进行验证，最大预测误差仅为1.9169 m3/h，显示了不同工程场景的强兼容性和准确性。对比实验表明，与传统回归方法相比，该模型的预测误差平均降低了39.65%，拟合精度平均提高了18.43%。总体而言，本研究为复杂地质条件下的隧道涌水预测提供了高精度、可解释性和通用性的智能解决方案。

{"title":"An interpretable and adaptive tunnel water inflow prediction method using data augmentation and AHP-Enhanced OP-LightGBM","authors":"Jingqi Cui , Shunchuan Wu , Haiyong Cheng , Xiaowei Hou , Jiaxin Wang , Weihua Liu , Chaoqun Chu","doi":"10.1016/j.tust.2026.107445","DOIUrl":"10.1016/j.tust.2026.107445","url":null,"abstract":"<div><div>Accurate prediction of tunnel water inflow is critical for ensuring construction safety and risk control in tunnel engineering. However, traditional regression methods face significant challenges, including limited sample sizes, imbalanced data, complex feature interactions, and difficulty in engineering deployment. To address these issues, this study proposes an intelligent prediction framework that integrates data augmentation, model optimization, interpretability, and online deployment, and additionally possesses strong adaptability to dynamic field conditions. First, the SMOGN undersampling method is employed to balance and augment the training dataset, effectively expanding sparse samples and suppressing the influence of outliers, thereby enhancing the model’s generalization ability. Subsequently, LightGBM is improved through Optuna-based hyperparameter optimization and Analytic Hierarchy Process (AHP)-based feature weight adjustment, forming the AHP-OP-LightGBM hybrid model. This approach reduces prediction error by 15.89 % while aligning feature weights more closely with physical constraints. Compared with conventional optimization strategies, the model demonstrates superior capability in representing hydrogeological characteristics due to the dual mechanism of automated hyperparameter tuning and feature weight correction. Correlation analysis and SHAP-based interpretability further clarify the nonlinear synergistic mechanisms governing the coupled geomechanical-hydrological processes controlling tunnel water inflow. To support engineering application, a cloud-deployed online prediction system is developed using web technologies, integrating SHAP for transparent decision support. Additionally, an incremental learning module is incorporated to accommodate dynamic data variations. Validation using a small set of local incremental samples yields a maximum prediction error of only 1.9169 m<sup>3</sup>/h, demonstrating strong compatibility and accuracy across different engineering scenarios. Comparative experiments show that, on average, the proposed model reduces prediction error by 39.65 % and improves fitting accuracy by 18.43 % compared with traditional regression methods. Overall, this study provides a high-precision, interpretable, and generalizable intelligent solution for predicting tunnel water inflow under complex geological conditions.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107445"},"PeriodicalIF":7.4,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent identification and deformation analysis of subsurface cavities in deep excavations using CNN-based inverse modeling 基于cnn逆建模的深基坑地下空腔智能识别与变形分析

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-08 DOI: 10.1016/j.tust.2025.107419

Wei Zhang , Ya-Dong Xue , Jin-Zhang Zhang , Gang Zheng , Zeng-Zhi Qian , Yu-Xin Zhai

Subsurface cavities in soft soil poses significant geotechnical challenges to the rapid expansion of urban underground spaces. This study presents a comprehensive framework for quantifying cavity-induced deformation amplification during deep excavation and develops an intelligent inversion system for cavity characterization using monitoring data. Through 1,800 finite element simulations, parametric analyses reveal that cavities located within 0.5 times the excavation depth (H_e) horizontally from the diaphragm wall and at depths of 1.5 H_e to 2.25 H_e constitute the most critical influence zone, amplifying horizontal wall displacement by up to 1.67 times and ground settlement by up to 2.2 times. K-means clustering analysis identifies five distinct settlement deformation patterns (Modes I–V) strongly correlated with cavity size and location. A convolutional neural network (CNN) based inversion model is developed to predict cavity dimensions and positions from deformation monitoring data, achieving over 85 % accuracy (R² > 0.85) on test datasets. The model demonstrates robust performance under soil parameter uncertainties modeled with random fields, maintaining acceptable prediction accuracy when spatial variability is considered. This integrated framework provides a practical tool for real-time cavity detection and risk mitigation in deep excavation projects within cavity-bearing strata, offering valuable guidance for construction safety management in complex urban geological conditions.

软土地下空腔对城市地下空间的快速扩张提出了重大的岩土工程挑战。本研究提出了一个综合框架来量化深基坑开挖过程中空洞引起的变形放大，并开发了一种利用监测数据进行空洞表征的智能反演系统。通过1800次有限元模拟，参数化分析表明，在距连续墙水平方向0.5倍开挖深度（He）范围内，深度在1.5 ~ 2.25 He范围内的空腔构成了最关键的影响区，使水平墙位移放大1.67倍，地面沉降放大2.2倍。K-means聚类分析确定了5种不同的沉降变形模式（I-V模式），这些模式与空洞的大小和位置密切相关。开发了一种基于卷积神经网络（CNN）的反演模型，从变形监测数据中预测空腔尺寸和位置，在测试数据集上实现了85%以上的精度（R2 > 0.85）。该模型在随机场模拟的土壤参数不确定性下表现出鲁棒性，在考虑空间变异性时保持可接受的预测精度。该集成框架为含空腔地层中深基坑工程的实时空腔探测和风险缓解提供了实用工具，为复杂城市地质条件下的施工安全管理提供了有价值的指导。

{"title":"Intelligent identification and deformation analysis of subsurface cavities in deep excavations using CNN-based inverse modeling","authors":"Wei Zhang , Ya-Dong Xue , Jin-Zhang Zhang , Gang Zheng , Zeng-Zhi Qian , Yu-Xin Zhai","doi":"10.1016/j.tust.2025.107419","DOIUrl":"10.1016/j.tust.2025.107419","url":null,"abstract":"<div><div>Subsurface cavities in soft soil poses significant geotechnical challenges to the rapid expansion of urban underground spaces. This study presents a comprehensive framework for quantifying cavity-induced deformation amplification during deep excavation and develops an intelligent inversion system for cavity characterization using monitoring data. Through 1,800 finite element simulations, parametric analyses reveal that cavities located within 0.5 times the excavation depth (<em>H</em><sub>e</sub>) horizontally from the diaphragm wall and at depths of 1.5 <em>H</em><sub>e</sub> to 2.25 <em>H</em><sub>e</sub> constitute the most critical influence zone, amplifying horizontal wall displacement by up to 1.67 times and ground settlement by up to 2.2 times. K-means clustering analysis identifies five distinct settlement deformation patterns (Modes I–V) strongly correlated with cavity size and location. A convolutional neural network (CNN) based inversion model is developed to predict cavity dimensions and positions from deformation monitoring data, achieving over 85 % accuracy (R<sup>2</sup> > 0.85) on test datasets. The model demonstrates robust performance under soil parameter uncertainties modeled with random fields, maintaining acceptable prediction accuracy when spatial variability is considered. This integrated framework provides a practical tool for real-time cavity detection and risk mitigation in deep excavation projects within cavity-bearing strata, offering valuable guidance for construction safety management in complex urban geological conditions.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107419"},"PeriodicalIF":7.4,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigation into the stress corrosion behavior of cable bolts under different tensile stresses 不同拉应力作用下锚杆的应力腐蚀行为研究

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-08 DOI: 10.1016/j.tust.2026.107452

Yongliang Li , Sheng Zhang , Renshu Yang , Shuaiyang Shi

Cable bolts are essential support materials in underground engineering. While subjected to long-term tensile stress, they are also exposed to harsh corrosive environments. The stress corrosion cracking (SCC) failure problem of cable bolts, caused by the coupling effect of stress and corrosion, is prominent and seriously threatens the safety and stability of underground engineering. To investigate the effect of different tensile stresses on the stress corrosion behavior of cable bolts, stress corrosion tests of cable bolts under different tensile stresses were carried out by using ammonium thiocyanate corrosion solution (NH₄SCN). The variation law of cable bolt SCC failure time was studied, and the macroscopic and microscopic characteristics of cable bolt SCC fracture surface were analyzed. The propagation laws of SCC cracks in cable bolts were obtained, and the influence mechanism of tensile stress on the stress corrosion behavior of cable bolts was revealed. The results indicate that an increase in tensile stress accelerates the SCC process of the cable bolt, and the failure time of the cable bolt SCC is negatively correlated with the stress level. As the stress increases, the range of the crack propagation zone decreases while the range of the overload fracture zone increases, and the crack deflection angle decreases. There are significant differences in the microscopic morphology of the crack initiation zone, crack propagation zone, and overload fracture zone of the cable bolt fracture under different tensile stresses. Tensile stress affects the initiation and propagation of stress corrosion cracks by affecting the passive film and microstructure of the cable bolt, stress intensity factor at the crack tip, diffusion and aggregation of hydrogen atoms in the solution. The greater the tensile stress, the higher the risk of SCC failure of the cable bolt.

锚杆是地下工程中必不可少的支护材料。在经受长期拉伸应力的同时，它们还暴露在恶劣的腐蚀环境中。由于应力与腐蚀的耦合作用，锚杆的应力腐蚀开裂破坏问题十分突出，严重威胁着地下工程的安全与稳定。为研究不同拉应力对电缆螺栓应力腐蚀行为的影响，采用硫氰酸铵腐蚀溶液（NH4SCN）对不同拉应力下的电缆螺栓进行了应力腐蚀试验。研究了锚杆SCC破坏时间的变化规律，分析了锚杆SCC断裂面的宏观和微观特征。获得了锚杆SCC裂纹的扩展规律，揭示了拉应力对锚杆应力腐蚀行为的影响机理。结果表明：拉应力的增大加速了锚杆自裂过程，锚杆自裂破坏时间与应力水平呈负相关；随着应力的增大，裂纹扩展区范围减小，过载断裂区范围增大，裂纹挠度减小。不同拉应力作用下锚杆断裂的裂纹起裂区、裂纹扩展区和过载断裂带的微观形貌存在显著差异。拉应力通过影响锚杆的钝化膜和组织、裂纹尖端的应力强度因子、溶液中氢原子的扩散和聚集等因素影响应力腐蚀裂纹的萌生和扩展。拉应力越大，锚杆SCC破坏风险越高。

{"title":"Investigation into the stress corrosion behavior of cable bolts under different tensile stresses","authors":"Yongliang Li , Sheng Zhang , Renshu Yang , Shuaiyang Shi","doi":"10.1016/j.tust.2026.107452","DOIUrl":"10.1016/j.tust.2026.107452","url":null,"abstract":"<div><div>Cable bolts are essential support materials in underground engineering. While subjected to long-term tensile stress, they are also exposed to harsh corrosive environments. The stress corrosion cracking (SCC) failure problem of cable bolts, caused by the coupling effect of stress and corrosion, is prominent and seriously threatens the safety and stability of underground engineering. To investigate the effect of different tensile stresses on the stress corrosion behavior of cable bolts, stress corrosion tests of cable bolts under different tensile stresses were carried out by using ammonium thiocyanate corrosion solution (NH<sub>4</sub>SCN). The variation law of cable bolt SCC failure time was studied, and the macroscopic and microscopic characteristics of cable bolt SCC fracture surface were analyzed. The propagation laws of SCC cracks in cable bolts were obtained, and the influence mechanism of tensile stress on the stress corrosion behavior of cable bolts was revealed. The results indicate that an increase in tensile stress accelerates the SCC process of the cable bolt, and the failure time of the cable bolt SCC is negatively correlated with the stress level. As the stress increases, the range of the crack propagation zone decreases while the range of the overload fracture zone increases, and the crack deflection angle decreases. There are significant differences in the microscopic morphology of the crack initiation zone, crack propagation zone, and overload fracture zone of the cable bolt fracture under different tensile stresses. Tensile stress affects the initiation and propagation of stress corrosion cracks by affecting the passive film and microstructure of the cable bolt, stress intensity factor at the crack tip, diffusion and aggregation of hydrogen atoms in the solution. The greater the tensile stress, the higher the risk of SCC failure of the cable bolt.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107452"},"PeriodicalIF":7.4,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deciphering the time-dependent behavior of underground rock tunnels: Insights from a generalized non-associative thermo-viscoplastic damage model 解读地下岩石隧道的时间依赖行为：来自广义非关联热粘塑性损伤模型的见解

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-07 DOI: 10.1016/j.tust.2025.107428

Zhi-Jie Wen , Jian Tao , Yu-Jun Zuo , Xing Zhu

The time-dependent deformation of underground rock tunnels in coupled geopressure and geothermal environments poses significant challenges to sustainable resource extraction and subsurface space utilization. In this study, a novel non-associative thermo-viscoplastic damage model is proposed within the thermodynamic framework for characterizing the rock creep behavior. By integrating the temperature and damage variables directly into the free energy and energy dissipation functions, the derived yield criterion can automatically capture the pressure- and thermally-induced rock hardening/softening response. The proposed model is systematically validated by laboratory triaxial compression and creep tests, and is then applied to investigate the long-term creep performance of underground rock tunnels at different temperatures. The underlying mechanisms responsible for time-dependent tunnel deformation and cracking are quantitatively elucidated through stress-displacement-damage coupling analysis. The calculated results reveal that the surrounding rock in major principal stress directions generally exhibits limited damage but significant displacement, prone to inducing rock extrusion and bulging. In contrast, the tunnel region in minor principal stress directions will experience smaller time-dependent deformation yet severe damage accumulation, rendering it susceptible to localized rock fracturing. Moreover, elevated temperatures are shown to accelerate the creep failure of underground tunnels owing to thermally-induced rock deterioration, and the timely support measures are thus indispensable for ensuring tunnel stability in geothermal settings. The findings of our study are believed to enhance the understanding of time-dependent rock deformation in coupled thermal–mechanical conditions and can thus provide a theoretical basis for guiding the adaptive support design of deep geothermal tunnels.

地压-地热耦合环境下地下岩石隧道的时效变形对资源的可持续开采和地下空间的利用提出了重大挑战。本文在热力学框架内提出了一种新的非关联热粘塑性损伤模型来表征岩石的蠕变行为。通过将温度和损伤变量直接积分到自由能和能量耗散函数中，导出的屈服准则可以自动捕获压力和热致岩石硬化/软化响应。通过室内三轴压缩和蠕变试验对该模型进行了系统验证，并应用于不同温度下地下岩石隧道的长期蠕变特性研究。通过应力-位移-损伤耦合分析，定量地阐明了随时间变化的隧道变形和开裂的潜在机制。计算结果表明，主应力方向上的围岩一般损伤有限，但位移较大，易发生岩石挤压胀形。而在主应力较小的隧洞区域，随时间的变形较小，但损伤积累严重，容易发生局部岩石破裂。此外，高温会加速地下隧道因热致岩石劣化而发生蠕变破坏，及时采取支护措施是保证地热环境下隧道稳定的必要条件。研究结果有助于加深对热-力耦合条件下岩石变形随时间变化的认识，为指导深部地热隧道的自适应支护设计提供理论依据。

{"title":"Deciphering the time-dependent behavior of underground rock tunnels: Insights from a generalized non-associative thermo-viscoplastic damage model","authors":"Zhi-Jie Wen , Jian Tao , Yu-Jun Zuo , Xing Zhu","doi":"10.1016/j.tust.2025.107428","DOIUrl":"10.1016/j.tust.2025.107428","url":null,"abstract":"<div><div>The time-dependent deformation of underground rock tunnels in coupled geopressure and geothermal environments poses significant challenges to sustainable resource extraction and subsurface space utilization. In this study, a novel non-associative thermo-viscoplastic damage model is proposed within the thermodynamic framework for characterizing the rock creep behavior. By integrating the temperature and damage variables directly into the free energy and energy dissipation functions, the derived yield criterion can automatically capture the pressure- and thermally-induced rock hardening/softening response. The proposed model is systematically validated by laboratory triaxial compression and creep tests, and is then applied to investigate the long-term creep performance of underground rock tunnels at different temperatures. The underlying mechanisms responsible for time-dependent tunnel deformation and cracking are quantitatively elucidated through stress-displacement-damage coupling analysis. The calculated results reveal that the surrounding rock in major principal stress directions generally exhibits limited damage but significant displacement, prone to inducing rock extrusion and bulging. In contrast, the tunnel region in minor principal stress directions will experience smaller time-dependent deformation yet severe damage accumulation, rendering it susceptible to localized rock fracturing. Moreover, elevated temperatures are shown to accelerate the creep failure of underground tunnels owing to thermally-induced rock deterioration, and the timely support measures are thus indispensable for ensuring tunnel stability in geothermal settings. The findings of our study are believed to enhance the understanding of time-dependent rock deformation in coupled thermal–mechanical conditions and can thus provide a theoretical basis for guiding the adaptive support design of deep geothermal tunnels.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107428"},"PeriodicalIF":7.4,"publicationDate":"2026-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An integrated analytical approach for predicting structural performance and cracking behavior in composite linings of deep hydraulic tunnels 深层水工隧道复合衬砌结构性能与开裂行为预测的综合分析方法

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-07 DOI: 10.1016/j.tust.2025.107429

Xueming Zhang , Zhiyun Deng , Baoguo Liu , Xiang Ma

Safety and serviceability of deep hydraulic tunnels are threatened by lining cracks, while links between mechanical response and key metrics, such as capacity, cracking load, and crack width, are rarely established under staged construction and complex loading, limiting performance-based design and risk-informed decisions. Therefore, an integrated analytical model grounded in complex-variable theory is developed to evaluate the stress field, ultimate bearing capacity, cracking load, and crack width, with staged construction explicitly considered. The model is validated against 3D numerical simulations (WMAPE ≤ 5.82 %, R² > 0.993) and physical model tests (WMAPE ≤ 18.95 %, R² > 0.919). A threshold effect of secondary-lining installation timing is revealed, contributing 10–25 % to ultimate capacity and markedly influencing cracking behavior. Internal water pressure is identified as the dominant driver of cracking (contribution >52 %), whereas ultimate capacity is governed primarily by the interaction between in situ stress and construction timing (contribution >80 %). A response-surface-based design envelope has been developed to optimize lining thickness and support installation timing for crack control, offering a tool for selecting the optimal secondary lining thickness and support timing under specified burial depths and internal water pressures. By linking mechanical response analysis to performance criteria under realistic construction and loading sequences, a key methodological gap is closed and performance-based design and evaluation of deep hydraulic tunnels are enabled. The approach provides a transparent, computationally efficient alternative to computationally intensive simulations and offers quantitative guidance for crack-control design.

深层水工隧道的安全性和可使用性受到衬砌裂缝的威胁，而机械响应与关键指标（如容量、裂缝载荷和裂缝宽度）之间的联系，在阶段施工和复杂荷载下很少建立起来，这限制了基于性能的设计和风险决策。因此，建立了基于复变量理论的综合分析模型，明确考虑了阶段施工的应力场、极限承载力、裂缝荷载和裂缝宽度。通过三维数值模拟（WMAPE≤5.82%,R2 > 0.993）和物理模型试验（WMAPE≤18.95%,R2 > 0.919）对模型进行了验证。二次衬砌时间存在阈值效应，对极限承载力的贡献为10 ~ 25%，对开裂行为有显著影响。内部水压被认为是裂缝的主要驱动因素（贡献>； 52%），而最终承载力主要由原位应力和施工时间之间的相互作用（贡献>； 80%）决定。研究人员开发了一种基于响应面的设计包线，用于优化衬砌厚度和支架安装时间，以控制裂缝，为在特定埋深和内部水压下选择最佳二次衬砌厚度和支架安装时间提供了一种工具。通过将力学响应分析与实际施工和加载顺序下的性能标准联系起来，缩小了关键的方法差距，使基于性能的深水水工隧道设计和评估成为可能。该方法提供了一种透明的、计算效率高的替代计算密集型模拟方法，并为裂缝控制设计提供了定量指导。

{"title":"An integrated analytical approach for predicting structural performance and cracking behavior in composite linings of deep hydraulic tunnels","authors":"Xueming Zhang , Zhiyun Deng , Baoguo Liu , Xiang Ma","doi":"10.1016/j.tust.2025.107429","DOIUrl":"10.1016/j.tust.2025.107429","url":null,"abstract":"<div><div>Safety and serviceability of deep hydraulic tunnels are threatened by lining cracks, while links between mechanical response and key metrics, such as capacity, cracking load, and crack width, are rarely established under staged construction and complex loading, limiting performance-based design and risk-informed decisions. Therefore, an integrated analytical model grounded in complex-variable theory is developed to evaluate the stress field, ultimate bearing capacity, cracking load, and crack width, with staged construction explicitly considered. The model is validated against 3D numerical simulations (WMAPE ≤ 5.82 %, <em>R</em><sup>2</sup> > 0.993) and physical model tests (WMAPE ≤ 18.95 %, <em>R</em><sup>2</sup> > 0.919). A threshold effect of secondary-lining installation timing is revealed, contributing 10–25 % to ultimate capacity and markedly influencing cracking behavior. Internal water pressure is identified as the dominant driver of cracking (contribution >52 %), whereas ultimate capacity is governed primarily by the interaction between in situ stress and construction timing (contribution >80 %). A response-surface-based design envelope has been developed to optimize lining thickness and support installation timing for crack control, offering a tool for selecting the optimal secondary lining thickness and support timing under specified burial depths and internal water pressures. By linking mechanical response analysis to performance criteria under realistic construction and loading sequences, a key methodological gap is closed and performance-based design and evaluation of deep hydraulic tunnels are enabled. The approach provides a transparent, computationally efficient alternative to computationally intensive simulations and offers quantitative guidance for crack-control design.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107429"},"PeriodicalIF":7.4,"publicationDate":"2026-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A damage constitutive model of gas-bearing coal under pre-static loading and cyclic impact 含气煤在预静载荷和循环冲击作用下的损伤本构模型

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-06 DOI: 10.1016/j.tust.2025.107421

Wei Wang , Hanpeng Wang , Xinyuan Xie , Zicheng Wang , Weibing Cai , Yunhao Wu , Yuguo Zhou

The increasing depth of coal mining has led to more severe dynamic disasters, such as coal and gas outbursts, under complex environments characterized by high in-situ stress, elevated gas pressure, and cyclic excavation-induced disturbances. However, existing damage constitutive models rarely comprehensively consider the combined effects of static loading, gas, and cyclic impact. To address this, a novel time-dependent damage constitutive model for gas-bearing coal under pre-static loading and cyclic impact is developed in this study. Based on the framework of the generalized Kelvin model, the elastic elements are replaced with damage elements. Following the strain equivalence principle, a coupling damage factor integrating static loading and gas effects is derived. The cyclic impact-induced damage, considering strain rate effects, is represented by a parallel configuration of a damage element and a viscous element. Meanwhile, an inverted S-shaped cyclic impact damage factor is established based on the inverse logistic function, effectively capturing the three-stage damage evolution (initial rapid increase, stabilization, and subsequent acceleration) by incorporating the effects of impact number, frequency, and peak amplitude. Numerical simulations of a coal and gas outburst induced by roadway excavation with cyclic disturbance are conducted using the proposed model. The results demonstrate consistency with physical simulations under identical conditions regarding stress evolution, gas pressure variation, and outburst cavity location, confirming the validity and applicability of the proposed damage constitutive model. The proposed model can accurately capture the inherent laws of damage evolution of gas containing coal under complex loads, providing a theoretical tool for understanding and predicting dynamic disasters induced by cyclic disturbances in deep mining.

随着煤层开采深度的增加，在高地应力、高瓦斯压力、循环开挖扰动等复杂环境下，煤与瓦斯突出等动力灾害更加严重。然而，现有的损伤本构模型很少全面考虑静载荷、气体和循环冲击的联合作用。为了解决这一问题，本文建立了含气煤在预静载荷和循环冲击作用下的时效损伤本构模型。在广义开尔文模型框架下，将弹性单元替换为损伤单元。根据应变等效原理，导出了静载荷和气体作用的耦合损伤系数。考虑应变率效应的循环冲击损伤由损伤单元和粘性单元的平行结构表示。同时，基于logistic逆函数建立倒s型循环冲击损伤因子，结合冲击次数、频率和峰值幅值的影响，有效地捕捉了损伤演化的三个阶段（初始快速增加、稳定和随后加速）。利用该模型对具有循环扰动的巷道开挖引起的煤与瓦斯突出进行了数值模拟。结果表明，在相同条件下，应力演化、瓦斯压力变化和突出空腔位置与物理模拟结果一致，验证了所建立的损伤本构模型的有效性和适用性。该模型能够准确捕捉复杂载荷下含气煤损伤演化的内在规律，为理解和预测深部开采循环扰动引起的动力灾害提供了理论工具。

{"title":"A damage constitutive model of gas-bearing coal under pre-static loading and cyclic impact","authors":"Wei Wang , Hanpeng Wang , Xinyuan Xie , Zicheng Wang , Weibing Cai , Yunhao Wu , Yuguo Zhou","doi":"10.1016/j.tust.2025.107421","DOIUrl":"10.1016/j.tust.2025.107421","url":null,"abstract":"<div><div>The increasing depth of coal mining has led to more severe dynamic disasters, such as coal and gas outbursts, under complex environments characterized by high in-situ stress, elevated gas pressure, and cyclic excavation-induced disturbances. However, existing damage constitutive models rarely comprehensively consider the combined effects of static loading, gas, and cyclic impact. To address this, a novel time-dependent damage constitutive model for gas-bearing coal under pre-static loading and cyclic impact is developed in this study. Based on the framework of the generalized Kelvin model, the elastic elements are replaced with damage elements. Following the strain equivalence principle, a coupling damage factor integrating static loading and gas effects is derived. The cyclic impact-induced damage, considering strain rate effects, is represented by a parallel configuration of a damage element and a viscous element. Meanwhile, an inverted S-shaped cyclic impact damage factor is established based on the inverse logistic function, effectively capturing the three-stage damage evolution (initial rapid increase, stabilization, and subsequent acceleration) by incorporating the effects of impact number, frequency, and peak amplitude. Numerical simulations of a coal and gas outburst induced by roadway excavation with cyclic disturbance are conducted using the proposed model. The results demonstrate consistency with physical simulations under identical conditions regarding stress evolution, gas pressure variation, and outburst cavity location, confirming the validity and applicability of the proposed damage constitutive model. The proposed model can accurately capture the inherent laws of damage evolution of gas containing coal under complex loads, providing a theoretical tool for understanding and predicting dynamic disasters induced by cyclic disturbances in deep mining.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107421"},"PeriodicalIF":7.4,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Temporal psychological and physiological responses to 120-hour isolation in an underground rescue chamber: A preliminary study 在地下救援室隔离120小时后的暂时心理和生理反应：初步研究

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-06 DOI: 10.1016/j.tust.2025.107442

Jie Zhang , Ligang Tan , Xueliang Xu , Cuibin Xie , Xuanhui Xu , Zhizhong Li , Feng Wang

The development of underground space has become a strategic focus in both infrastructure engineering and urban sustainability planning, drawing increasing attention to human health. While prior studies have primarily examined the health effects of routine exposure to controlled urban underground environments, their findings cannot be directly applied to emergency rescue chambers. Existing research on rescue chambers has been limited to no longer than 48-hour exposures, with a few thermal studies extending to 106 h but lacking analyses of psychological and physiological responses. Moreover, the moderating effects of individual characteristics have not been well understood. To address this gap, this study conducted a 120-hour simulated experiment with eight male participants to investigate how exposure duration interacts with individual characteristics to influence human psychological and physiological responses. The sample size was constrained by the rated capacity of the rescue chamber, and multiple runs were not allowed for this exploratory study due to participant health and safety concerns. The results showed that positive emotion and team relationship deteriorated over time, with a faster decline for participants with higher openness and mental health. Furthermore, positive emotion mediated team relationship changes, highlighting the critical role of affective states in maintaining interpersonal cohesion. Notably, participants with better mental health experienced more stable interpersonal dynamics, even in the face of emotional fluctuations. While no significant changes were observed in heart rate, heart rate variability, and breathing rate, some correlations were detected between physiological and psychological measures. Overall, these findings contribute to empirical evidence on human adaptation to confined underground environments and offer practical implications for rescue chamber design (e.g., increasing space and incorporating privacy features to sustain positive emotion and preserve team cohesion) and personnel training (e.g., developing psychological resilience, teamwork skills, and stress management strategies to prepare workers for prolonged confinement). However, the findings should be considered exploratory findings due to the small sample size. Future research with larger and more diverse samples in ecologically valid settings is warranted to further validate these findings.

地下空间的开发已成为基础设施工程和城市可持续发展规划的战略重点，日益引起人们对人类健康的关注。虽然先前的研究主要是检查常规暴露于受控制的城市地下环境对健康的影响，但他们的发现不能直接应用于紧急救援室。现有的救援舱研究仅限于不超过48小时的暴露，少数热研究延长至106小时，但缺乏对心理和生理反应的分析。此外，个体特征的调节作用尚未得到很好的理解。为了解决这一差距，本研究对8名男性参与者进行了120小时的模拟实验，以研究暴露时间如何与个体特征相互作用，从而影响人类的心理和生理反应。样本量受到救援室额定容量的限制，由于参与者的健康和安全考虑，本探索性研究不允许多次运行。结果表明，积极情绪和团队关系随着时间的推移而恶化，开放度和心理健康程度越高的参与者的积极情绪和团队关系下降越快。此外，积极情绪介导了团队关系的变化，强调了情感状态在维持人际凝聚力方面的关键作用。值得注意的是，心理健康状况较好的参与者经历了更稳定的人际关系动态，即使面对情绪波动。虽然在心率、心率变异性和呼吸频率方面没有观察到明显的变化，但在生理和心理测量之间发现了一些相关性。总的来说，这些研究结果为人类对密闭地下环境的适应提供了经验证据，并为救援室的设计（如增加空间和结合隐私特征以维持积极情绪和保持团队凝聚力）和人员培训（如培养心理弹性、团队合作技能和压力管理策略，以使工人为长时间的禁闭做好准备）提供了实际意义。然而，由于样本量小，研究结果应被视为探索性研究结果。未来的研究将在生态有效的环境中进行更大、更多样化的样本，以进一步验证这些发现。

{"title":"Temporal psychological and physiological responses to 120-hour isolation in an underground rescue chamber: A preliminary study","authors":"Jie Zhang , Ligang Tan , Xueliang Xu , Cuibin Xie , Xuanhui Xu , Zhizhong Li , Feng Wang","doi":"10.1016/j.tust.2025.107442","DOIUrl":"10.1016/j.tust.2025.107442","url":null,"abstract":"<div><div>The development of underground space has become a strategic focus in both infrastructure engineering and urban sustainability planning, drawing increasing attention to human health. While prior studies have primarily examined the health effects of routine exposure to controlled urban underground environments, their findings cannot be directly applied to emergency rescue chambers. Existing research on rescue chambers has been limited to no longer than 48-hour exposures, with a few thermal studies extending to 106 h but lacking analyses of psychological and physiological responses. Moreover, the moderating effects of individual characteristics have not been well understood. To address this gap, this study conducted a 120-hour simulated experiment with eight male participants to investigate how exposure duration interacts with individual characteristics to influence human psychological and physiological responses. The sample size was constrained by the rated capacity of the rescue chamber, and multiple runs were not allowed for this exploratory study due to participant health and safety concerns. The results showed that positive emotion and team relationship deteriorated over time, with a faster decline for participants with higher openness and mental health. Furthermore, positive emotion mediated team relationship changes, highlighting the critical role of affective states in maintaining interpersonal cohesion. Notably, participants with better mental health experienced more stable interpersonal dynamics, even in the face of emotional fluctuations. While no significant changes were observed in heart rate, heart rate variability, and breathing rate, some correlations were detected between physiological and psychological measures. Overall, these findings contribute to empirical evidence on human adaptation to confined underground environments and offer practical implications for rescue chamber design (e.g., increasing space and incorporating privacy features to sustain positive emotion and preserve team cohesion) and personnel training (e.g., developing psychological resilience, teamwork skills, and stress management strategies to prepare workers for prolonged confinement). However, the findings should be considered exploratory findings due to the small sample size. Future research with larger and more diverse samples in ecologically valid settings is warranted to further validate these findings.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107442"},"PeriodicalIF":7.4,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cooling energy demand for maintaining frozen wall thickness in artificial ground freezing 人工冻结中维持冻结壁厚的冷却能量需求

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-06 DOI: 10.1016/j.tust.2025.107407

Xu Li , Rui-ming Li , Xiao-kang Li , Shuang Liu , Zheng Yang

The frozen wall thickness (E) is critical for both freezing performance and expense in artificial ground freezing (AGF), while maintaining E precisely still poses a challenge. Accordingly, this study proposes a novel concept of cooling energy demand (

{\dot{Q}}_{d}

) at which E remains stable through a numerical orthogonal test on the heat exchange between the frozen wall and the surrounding stratum. Furthermore, a comprehensive

{\dot{Q}}_{d}

prediction model is developed and validated considering the initial stratum temperature, thermal conductivity of soil particles, saturated water content, and target frozen wall radius. Results show that heat flux between frozen wall and stratum remains uniform at the steady freezing state across an arbitrary section, laying a foundation for introducing the

{\dot{Q}}_{d}

. Additionally, the initial temperature and thermal conductivity of stratum are primary factors governing

{\dot{Q}}_{d}

, with a contribution rate of 70% and 24%, respectively, while the rest are secondary factors that can be normalized. Moreover, it has been verified that the proposed

{\dot{Q}}_{d}

model achieves higher precision than empirical approaches in controlling E. Overall, this study offers not only a theoretical basis but also practical guidance for precisely controlling frozen wall thickness in AGF engineering.

在人工冻结中，冻结壁厚(E)对冻结性能和成本都至关重要，而精确保持E仍然是一个挑战。据此，本研究通过冻结墙与围岩热交换的数值正交试验，提出了在E保持稳定时的冷却能量需求（Q³d）的新概念。在此基础上，建立了考虑地层初始温度、土壤颗粒导热系数、饱和含水量和目标冻结壁半径等因素的Q / d综合预测模型，并进行了验证。结果表明：在任意截面上，冻结壁与地层之间的热流密度在稳定冻结状态下保持均匀，为引入Q / d奠定了基础。另外，地层初始温度和热导率是决定Q (d)的主要因素，贡献率分别为70%和24%，其余为次要因素，可归一化。验证了所提出的Q (d)模型在控制e方面比经验方法具有更高的精度，为AGF工程中精确控制冻结壁厚提供了理论依据和实践指导。

{"title":"Cooling energy demand for maintaining frozen wall thickness in artificial ground freezing","authors":"Xu Li , Rui-ming Li , Xiao-kang Li , Shuang Liu , Zheng Yang","doi":"10.1016/j.tust.2025.107407","DOIUrl":"10.1016/j.tust.2025.107407","url":null,"abstract":"<div><div>The frozen wall thickness (<em>E</em>) is critical for both freezing performance and expense in artificial ground freezing (AGF), while maintaining <em>E</em> precisely still poses a challenge. Accordingly, this study proposes a novel concept of cooling energy demand (<span><math><msub><mover><mi>Q</mi><mo>̇</mo></mover><mtext>d</mtext></msub></math></span>) at which <em>E</em> remains stable through a numerical orthogonal test on the heat exchange between the frozen wall and the surrounding stratum. Furthermore, a comprehensive <span><math><msub><mover><mi>Q</mi><mo>̇</mo></mover><mtext>d</mtext></msub></math></span> prediction model is developed and validated considering the initial stratum temperature, thermal conductivity of soil particles, saturated water content, and target frozen wall radius. Results show that heat flux between frozen wall and stratum remains uniform at the steady freezing state across an arbitrary section, laying a foundation for introducing the <span><math><msub><mover><mi>Q</mi><mo>̇</mo></mover><mtext>d</mtext></msub></math></span>. Additionally, the initial temperature and thermal conductivity of stratum are primary factors governing <span><math><msub><mover><mi>Q</mi><mo>̇</mo></mover><mtext>d</mtext></msub></math></span>, with a contribution rate of 70% and 24%, respectively, while the rest are secondary factors that can be normalized. Moreover, it has been verified that the proposed <span><math><msub><mover><mi>Q</mi><mo>̇</mo></mover><mtext>d</mtext></msub></math></span> model achieves higher precision than empirical approaches in controlling <em>E</em>. Overall, this study offers not only a theoretical basis but also practical guidance for precisely controlling frozen wall thickness in AGF engineering.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107407"},"PeriodicalIF":7.4,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145903400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Plastic-hardening constitutive model-based hybrid machine learning framework for three-dimensional tunnel deformation prediction 基于塑性硬化本构模型的隧道三维变形预测混合机器学习框架

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-06 DOI: 10.1016/j.tust.2025.107415

Siyu Yin , Zheng Yang , Kunpeng Cao , Ben Wu , Siau Chen Chian

Accurately predicting tunnel deformation induced by excavation is critical for ensuring urban underground safety and optimizing reinforcement schemes. This study proposes a hybrid machine-learning framework that integrates particle swarm optimization (PSO), convolutional neural networks (CNN), and extreme gradient boosting (XGBoost). A large-scale database is generated through finite-difference analyses using a Plastic-Hardening (PH) soil model encompassing 242 excavation scenarios and 29,282 monitoring points that cover diverse excavation-tunnel configurations. The proposed PSO-CNN-XGBoost hybrid model demonstrates high predictive accuracy (R² = 0.96, RMSE = 0.91 mm, MAE = 0.63 mm), outperforming standalone CNN and XGBoost models. Shapley Additive Explanations (SHAP) analysis identifies dimensionless parameters (ΔH/H, D/B, and Y/L) as the dominant geometric drivers and quantifies interaction thresholds that are valuable for design control. A closed-form predictive expression derived via symbolic regression enables rapid screening of tunnel deformation zones. The proposed framework offers an efficient solution for point-level assessment of excavation-induced tunnel deformation, supporting low-disturbance development of underground space.

准确预测开挖引起的隧道变形对保证城市地下安全、优化加固方案至关重要。本研究提出了一种混合机器学习框架，该框架集成了粒子群优化（PSO）、卷积神经网络（CNN）和极端梯度增强（XGBoost）。通过使用塑性硬化（PH）土壤模型进行有限差分分析，生成了一个大型数据库，该数据库包含242个开挖场景和29,282个监测点，涵盖了不同的开挖隧道配置。提出的PSO-CNN-XGBoost混合模型具有较高的预测精度（R2 = 0.96, RMSE = 0.91 mm, MAE = 0.63 mm），优于独立的CNN和XGBoost模型。Shapley加性解释（SHAP）分析将无量纲参数（ΔH/H， D/B和Y/L）确定为主要的几何驱动因素，并量化对设计控制有价值的交互阈值。通过符号回归导出的封闭形式预测表达式可以快速筛选隧道变形区。该框架为隧道开挖变形的点水平评价提供了有效的解决方案，支持地下空间的低扰动开发。

{"title":"Plastic-hardening constitutive model-based hybrid machine learning framework for three-dimensional tunnel deformation prediction","authors":"Siyu Yin , Zheng Yang , Kunpeng Cao , Ben Wu , Siau Chen Chian","doi":"10.1016/j.tust.2025.107415","DOIUrl":"10.1016/j.tust.2025.107415","url":null,"abstract":"<div><div>Accurately predicting tunnel deformation induced by excavation is critical for ensuring urban underground safety and optimizing reinforcement schemes. This study proposes a hybrid machine-learning framework that integrates particle swarm optimization (PSO), convolutional neural networks (CNN), and extreme gradient boosting (XGBoost). A large-scale database is generated through finite-difference analyses using a Plastic-Hardening (PH) soil model encompassing 242 excavation scenarios and 29,282 monitoring points that cover diverse excavation-tunnel configurations. The proposed PSO-CNN-XGBoost hybrid model demonstrates high predictive accuracy (R<sup>2</sup> = 0.96, RMSE = 0.91 mm, MAE = 0.63 mm), outperforming standalone CNN and XGBoost models. Shapley Additive Explanations (SHAP) analysis identifies dimensionless parameters (Δ<em>H</em>/<em>H</em>, <em>D/B</em>, and <em>Y/L</em>) as the dominant geometric drivers and quantifies interaction thresholds that are valuable for design control. A closed-form predictive expression derived via symbolic regression enables rapid screening of tunnel deformation zones. The proposed framework offers an efficient solution for point-level assessment of excavation-induced tunnel deformation, supporting low-disturbance development of underground space.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107415"},"PeriodicalIF":7.4,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Influence of inclined groove on rock-crushing behavior of TBM cutter 斜槽对TBM刀具破岩性能的影响

IF 7.4 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Tunnelling and Underground Space Technology

Pub Date : 2026-01-06 DOI: 10.1016/j.tust.2025.107404

Xuhui Zhang , Zeren Peng , Hanwen Lai , Shenghui Kang , Yashi Liao , Yimin Xia

To investigate the impact of groove angle on rock-crushing behavior of a TBM cutter, the finite element method was employed to simulate both rock cutting and rock-crushing processes. Then, the average vertical load, average rolling load, and specific energy required for rock-crushing by TBM cutter were calculated and analyzed under varying groove angles and groove spacings. Furthermore, some rock-crushing tests were performed to show the cutter’s crushing behavior regarding the groove angle and groove spacing. The study’s results indicate that the effectiveness of crack propagation to the groove is influenced by the groove angle and groove spacing. Specifically, for the given groove angle, when the groove spacing remains at a low value, the cracks produced can effectively extend to grooves. However, when the groove spacing surpasses a certain threshold, the cracks fail to sufficiently reach the grooves. This threshold is referred to as the critical groove spacing, which varies with different groove angles. Notably, as the groove angle increases, the critical groove spacing also tends to increase. Furthermore, when the two cutting grooves can facilitate rock crushing, a rise from 0° to 60° in the groove angle results in a decrease in both the cutter’s vertical load and rolling load. Additionally, the specific energy initially falls and then rises with the growth of the groove angle. An optimal groove spacing that minimizes the specific energy exists for a certain groove angle. In particular, the optimal groove spacings at groove angles of 0°, 15°, 30°, 45°, and 60° are 70 mm, 70 mm, 80 mm, 80 mm, and 90 mm, respectively. Notably, when the grooves with different groove angles and groove spacings can provide an auxiliary crushing effect, the crushing load of the cutter is minimized at a groove angle of 60°, while the specific energy of the cutter reaches its lowest point at a groove angle of 30°.

为了研究槽角对TBM刀具破岩性能的影响，采用有限元方法模拟了切削和破岩过程。然后，计算分析了不同槽角和槽距条件下TBM刀破碎岩石所需的平均垂直载荷、平均滚动载荷和比能。此外，还进行了一些岩石破碎试验，以显示切割器在槽角和槽距方面的破碎行为。研究结果表明，裂纹扩展到沟槽的有效性受沟槽角度和沟槽间距的影响。在沟槽角度一定的情况下，当沟槽间距保持在一定值时，裂纹能够有效地扩展到沟槽中。然而，当沟槽间距超过一定阈值时，裂纹不能充分到达沟槽。这个阈值称为临界槽距，它随槽角的不同而变化。值得注意的是，随着槽角的增大，临界槽距也有增大的趋势。当两个切槽有利于破碎岩石时，当切槽角度从0°增大到60°时，切刀的垂直载荷和滚动载荷均减小。随着槽角的增大，比能呈先下降后上升的趋势。在一定的槽角下，存在比能量最小的最佳槽距。其中，槽角为0°、15°、30°、45°和60°时的最佳槽间距分别为70 mm、70 mm、80 mm、80 mm和90 mm。值得注意的是，当不同凹槽角度和凹槽间距的凹槽能够提供辅助破碎作用时，刀具的破碎载荷在凹槽角度为60°时最小，而刀具的比能在凹槽角度为30°时达到最低点。

{"title":"Influence of inclined groove on rock-crushing behavior of TBM cutter","authors":"Xuhui Zhang , Zeren Peng , Hanwen Lai , Shenghui Kang , Yashi Liao , Yimin Xia","doi":"10.1016/j.tust.2025.107404","DOIUrl":"10.1016/j.tust.2025.107404","url":null,"abstract":"<div><div>To investigate the impact of groove angle on rock-crushing behavior of a TBM cutter, the finite element method was employed to simulate both rock cutting and rock-crushing processes. Then, the average vertical load, average rolling load, and specific energy required for rock-crushing by TBM cutter were calculated and analyzed under varying groove angles and groove spacings. Furthermore, some rock-crushing tests were performed to show the cutter’s crushing behavior regarding the groove angle and groove spacing. The study’s results indicate that the effectiveness of crack propagation to the groove is influenced by the groove angle and groove spacing. Specifically, for the given groove angle, when the groove spacing remains at a low value, the cracks produced can effectively extend to grooves. However, when the groove spacing surpasses a certain threshold, the cracks fail to sufficiently reach the grooves. This threshold is referred to as the critical groove spacing, which varies with different groove angles. Notably, as the groove angle increases, the critical groove spacing also tends to increase. Furthermore, when the two cutting grooves can facilitate rock crushing, a rise from 0° to 60° in the groove angle results in a decrease in both the cutter’s vertical load and rolling load. Additionally, the specific energy initially falls and then rises with the growth of the groove angle. An optimal groove spacing that minimizes the specific energy exists for a certain groove angle. In particular, the optimal groove spacings at groove angles of 0°, 15°, 30°, 45°, and 60° are 70 mm, 70 mm, 80 mm, 80 mm, and 90 mm, respectively. Notably, when the grooves with different groove angles and groove spacings can provide an auxiliary crushing effect, the crushing load of the cutter is minimized at a groove angle of 60°, while the specific energy of the cutter reaches its lowest point at a groove angle of 30°.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"171 ","pages":"Article 107404"},"PeriodicalIF":7.4,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0