Underground Space最新文献_第3页

Low-carbon efforts for underground space development in Singapore 新加坡地下空间开发的低碳努力

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-11-10 DOI: 10.1016/j.undsp.2025.07.004

Tong Jiao , Pei Peng , Shixiang Li , Wei Wu

Singapore, a land- and resource-scarce nation, serves as a global example of how low-carbon initiatives can drive the sustainable development of underground space in densely populated urban environments. This critical review highlights major low-carbon efforts from both academia and the industry over the past decade, along with supportive policies that integrate these efforts into governance and decision-making processes. These efforts, including cutting carbon emissions through material efficiency, shaping carbon emissions through digitalized construction, and tracking carbon emissions through sustainable operation, not only reflect the national efforts to carbon reductions across the full lifecycle of underground infrastructure but also offer valuable insights for similar urban settings worldwide. Furthermore, the review identifies the development of a well-defined framework for lifecycle carbon assessment as an overarching trend to promote carbon reductions in underground space development. However, significant challenges remain, such as the need for comprehensive data collection and integration, as well as a deeper understanding of how human behavior interacts with operational efficiency. Addressing these challenges requires interdisciplinary collaborations among government agencies, academic researchers, and industry practitioners to develop robust frameworks and dynamic models that more reliably capture the impact of low-carbon strategies on urban underground environments.

新加坡是一个土地和资源稀缺的国家，在人口密集的城市环境中，低碳倡议如何推动地下空间的可持续发展，在全球树立了榜样。这篇批判性的综述强调了过去十年学术界和工业界的主要低碳努力，以及将这些努力纳入治理和决策过程的支持性政策。这些努力，包括通过材料效率减少碳排放，通过数字化建设塑造碳排放，以及通过可持续运营跟踪碳排放，不仅反映了国家在地下基础设施全生命周期内减少碳排放的努力，而且为全球类似的城市环境提供了宝贵的见解。此外，该综述确定了开发一个明确定义的生命周期碳评估框架是促进地下空间开发碳减排的总体趋势。然而，重大挑战仍然存在，例如需要全面的数据收集和集成，以及更深入地了解人类行为如何与运营效率相互作用。应对这些挑战需要政府机构、学术研究人员和行业从业者之间的跨学科合作，以开发强大的框架和动态模型，更可靠地捕捉低碳战略对城市地下环境的影响。

{"title":"Low-carbon efforts for underground space development in Singapore","authors":"Tong Jiao , Pei Peng , Shixiang Li , Wei Wu","doi":"10.1016/j.undsp.2025.07.004","DOIUrl":"10.1016/j.undsp.2025.07.004","url":null,"abstract":"<div><div>Singapore, a land- and resource-scarce nation, serves as a global example of how low-carbon initiatives can drive the sustainable development of underground space in densely populated urban environments. This critical review highlights major low-carbon efforts from both academia and the industry over the past decade, along with supportive policies that integrate these efforts into governance and decision-making processes. These efforts, including cutting carbon emissions through material efficiency, shaping carbon emissions through digitalized construction, and tracking carbon emissions through sustainable operation, not only reflect the national efforts to carbon reductions across the full lifecycle of underground infrastructure but also offer valuable insights for similar urban settings worldwide. Furthermore, the review identifies the development of a well-defined framework for lifecycle carbon assessment as an overarching trend to promote carbon reductions in underground space development. However, significant challenges remain, such as the need for comprehensive data collection and integration, as well as a deeper understanding of how human behavior interacts with operational efficiency. Addressing these challenges requires interdisciplinary collaborations among government agencies, academic researchers, and industry practitioners to develop robust frameworks and dynamic models that more reliably capture the impact of low-carbon strategies on urban underground environments.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"26 ","pages":"Pages 22-35"},"PeriodicalIF":8.3,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694741","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

Development of surface settlement under the combined effect of foundation pit dewatering and excavation: Insights from experimental modelling 基坑降水与开挖联合作用下地表沉降的发展：来自实验模型的启示

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-11-07 DOI: 10.1016/j.undsp.2025.07.003

Kai-Fang Yang , Min-Liang Chi , Chang-Jie Xu , Chao-Feng Zeng , Lu-Jv Liang , Zhi Ding , Ya-Shi Qiu

To investigate surface settlement under the combined effect of foundation pit dewatering and excavation, a series of experiments was conducted using a scaled model of a deep foundation pit at a metro station. During experimental simulations of the dry excavation and dewatering processes, data were collected on surface settlement, water heads outside the pit, and deflection of the diaphragm wall. The characteristics of surface settlement were compared and analyzed under different conditions with a focus on the development of surface settlement during dewatering and excavation at key locations outside the pit. The combined effect of dewatering and excavation was found to increase surface settlement outside the pit and expand its area of influence. The insertion ratio of the diaphragm wall (n) significantly affected surface settlement; as the insertion ratio increased, surface settlement, along with its area of influence, decreased. For n < 1.25, the area beyond twice the excavation depth was considered a minor area of settlement influence. In contrast, for n ≥ 1.25, this area wasn’t classified as a minor area of settlement influence. As excavation depth increased, the surface settlement pattern outside the pit transitioned from triangle-type to groove-type, groove-type settlement occurred when A_s ≥ 1.6A_c, whereas triangle-type settlement occurred under other conditions (A_s represents the area of the deep inward part of the convex deformation of the diaphragm wall; A_c refers to the cantilever part of the diaphragm wall). This study provides insights into the development of surface settlement during dewatering and excavation and serves as a valuable reference for innovations in sustainable and resilient underground design.

为了研究基坑降水和开挖联合作用下的地表沉降，采用地铁车站深基坑的比例模型进行了一系列试验研究。在干掘和降水过程的实验模拟中，收集了地表沉降、坑外水头和连续墙挠度的数据。对比分析了不同条件下的地表沉降特征，重点分析了基坑外关键位置降水和开挖过程中地表沉降的发展情况。降水和开挖的联合作用增加了基坑外地表沉降，扩大了其影响范围。连续墙插入比(n)显著影响地表沉降；随着插入比的增大，地表沉降及其影响面积减小。对于n <； 1.25，超过两倍开挖深度的区域被认为是沉降影响较小的区域。当n≥1.25时，该区域不属于沉降影响较小的区域。随着开挖深度的增加，基坑外地表沉降形态由三角形向沟槽型过渡，当As≥1.6Ac时出现沟槽型沉降，其他条件下均出现三角形沉降（As为连续墙凸面变形向内深处区域面积，Ac为连续墙悬臂部分）。该研究为降水和开挖过程中地表沉降的发展提供了见解，并为可持续和弹性地下设计的创新提供了有价值的参考。

{"title":"Development of surface settlement under the combined effect of foundation pit dewatering and excavation: Insights from experimental modelling","authors":"Kai-Fang Yang , Min-Liang Chi , Chang-Jie Xu , Chao-Feng Zeng , Lu-Jv Liang , Zhi Ding , Ya-Shi Qiu","doi":"10.1016/j.undsp.2025.07.003","DOIUrl":"10.1016/j.undsp.2025.07.003","url":null,"abstract":"<div><div>To investigate surface settlement under the combined effect of foundation pit dewatering and excavation, a series of experiments was conducted using a scaled model of a deep foundation pit at a metro station. During experimental simulations of the dry excavation and dewatering processes, data were collected on surface settlement, water heads outside the pit, and deflection of the diaphragm wall. The characteristics of surface settlement were compared and analyzed under different conditions with a focus on the development of surface settlement during dewatering and excavation at key locations outside the pit. The combined effect of dewatering and excavation was found to increase surface settlement outside the pit and expand its area of influence. The insertion ratio of the diaphragm wall (<em>n</em>) significantly affected surface settlement; as the insertion ratio increased, surface settlement, along with its area of influence, decreased. For <em>n</em> < 1.25, the area beyond twice the excavation depth was considered a minor area of settlement influence. In contrast, for <em>n</em> ≥ 1.25, this area wasn’t classified as a minor area of settlement influence. As excavation depth increased, the surface settlement pattern outside the pit transitioned from triangle-type to groove-type, groove-type settlement occurred when <em>A</em><sub>s</sub> ≥ 1.6<em>A</em><sub>c</sub>, whereas triangle-type settlement occurred under other conditions (<em>A</em><sub>s</sub> represents the area of the deep inward part of the convex deformation of the diaphragm wall; <em>A</em><sub>c</sub> refers to the cantilever part of the diaphragm wall). This study provides insights into the development of surface settlement during dewatering and excavation and serves as a valuable reference for innovations in sustainable and resilient underground design.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"26 ","pages":"Pages 305-320"},"PeriodicalIF":8.3,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145748052","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

Long-term horizontal displacement induced by shield tunneling in consolidating soft ground 软土地基固结中盾构开挖引起的长期水平位移

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-11-05 DOI: 10.1016/j.undsp.2025.06.007

Haibo Wang , Rongjun Zhang , Fengjuan Tao , Junjie Zheng

Shield tunneling often gives rise to excessive long-term horizontal displacement in consolidating soft ground, posing risks to the safety of adjacent structures. This study investigates the characteristics of long-term horizontal displacement induced by shield tunneling in consolidating soft ground, with the aim of providing practical guidance for optimizing ground treatment strategies. Firstly, a three-dimensional numerical model, validated by a case history in Shanghai, is employed to analyze the horizontal displacement of the soft ground. Comparisons are conducted between the horizontal displacements in normally-consolidated and consolidating cases. Subsequently, the influence of the consolidating state on the horizontal displacement is investigated by numerical analyses. The simulation results indicate that the short-term horizontal displacements follow a similar trend and comparable magnitude in both normally-consolidated and consolidating soft soil. However, the long-term horizontal displacements display a quite different pattern. The maximum discrepancy between normally-consolidated and consolidating cases is observed at the ground surface, where the long-term horizontal displacements of the two cases orient toward entirely opposite directions. The discrepancy at the ground surface increases as the degree of consolidation or the tunnel depth decreases, while it is relatively insensitive to the thickness of the newly filled layer. Finally, an empirical estimation method is proposed to predict the long-term horizontal displacement at the ground surface for shield tunneling in consolidating soft ground.

盾构隧道在加固软土地基过程中，经常产生过大的长期水平位移，对相邻结构的安全构成威胁。研究盾构隧道在软土地基加固过程中引起的长期水平位移特征，为优化地基处理策略提供实践指导。首先，建立了上海地区软土地基水平位移的三维数值模型，并进行了实例验证。对正常固结和固结情况下的水平位移进行了比较。随后，通过数值分析研究了固结状态对水平位移的影响。模拟结果表明，正常固结和固结软土的短期水平位移具有相似的趋势和量级。然而，长期水平位移表现出完全不同的模式。正常固结和固结情况的最大差异出现在地表，两种情况的长期水平位移方向完全相反。地表差异随固结程度或隧道深度的减小而增大，而对新填层厚度相对不敏感。最后，提出了一种预测软土地基固结中盾构隧道地表长期水平位移的经验估计方法。

{"title":"Long-term horizontal displacement induced by shield tunneling in consolidating soft ground","authors":"Haibo Wang , Rongjun Zhang , Fengjuan Tao , Junjie Zheng","doi":"10.1016/j.undsp.2025.06.007","DOIUrl":"10.1016/j.undsp.2025.06.007","url":null,"abstract":"<div><div>Shield tunneling often gives rise to excessive long-term horizontal displacement in consolidating soft ground, posing risks to the safety of adjacent structures. This study investigates the characteristics of long-term horizontal displacement induced by shield tunneling in consolidating soft ground, with the aim of providing practical guidance for optimizing ground treatment strategies. Firstly, a three-dimensional numerical model, validated by a case history in Shanghai, is employed to analyze the horizontal displacement of the soft ground. Comparisons are conducted between the horizontal displacements in normally-consolidated and consolidating cases. Subsequently, the influence of the consolidating state on the horizontal displacement is investigated by numerical analyses. The simulation results indicate that the short-term horizontal displacements follow a similar trend and comparable magnitude in both normally-consolidated and consolidating soft soil. However, the long-term horizontal displacements display a quite different pattern. The maximum discrepancy between normally-consolidated and consolidating cases is observed at the ground surface, where the long-term horizontal displacements of the two cases orient toward entirely opposite directions. The discrepancy at the ground surface increases as the degree of consolidation or the tunnel depth decreases, while it is relatively insensitive to the thickness of the newly filled layer. Finally, an empirical estimation method is proposed to predict the long-term horizontal displacement at the ground surface for shield tunneling in consolidating soft ground.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"25 ","pages":"Pages 410-430"},"PeriodicalIF":8.3,"publicationDate":"2025-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528517","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

Response law of rock-cutterhead interaction in intact sandstone through TBM tunnelling test 通过TBM隧道试验研究完整砂岩岩刀相互作用的响应规律

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-10-24 DOI: 10.1016/j.undsp.2025.06.006

Weiqiang Xie , Xiaoli Liu , Caifeng Zhang , Xiaoxiong Zhou , Jian Chen

The unclear response law of rock-cutterhead interaction seriously limits the tunnel boring machine (TBM) efficiency. Various influencing factors make it difficult to illustrate the law using the TBM tunnelling results in the field. In the present study, we develop a novel TBM tunnelling test platform (DGTBM-A) to analyze rock-cutterhead interaction. The components and functions of the platform are introduced. The cubic sandstone specimens (500 mm

\times

500 mm

\times

500 mm) with three distinct uniaxial compressive strengths (low (24.94 MPa), medium (61.22 MPa), and high (95.04 MPa) are used for TBM tunnelling test. The effects of cutterhead thrust, rotational speed and rock strength on the rock-cutterhead interaction are examined. Key tunnelling parameters, TBM performance indices, and rock muck characteristics are analyzed to reflect their effects. The findings revealed significant impacts of cutterhead thrust, rotational speed and rock strength on torque, advance rate, penetration rate, specific energy, and field penetration index. Additionally, the characteristics of the produced rock muck varied with the applied tunnelling parameters, providing insights into the efficiency and effectiveness of rock breaking. Correlations between the TBM performance indices and the influencing factors are established. The results contribute to a better understanding of the mechanics involved in TBM tunnelling in sandstone, aiding in optimizing operational parameters for improved performance and cost-efficiency in engineering practice.

岩刀相互作用的响应规律不明确，严重制约了隧道掘进机的掘进效率。由于各种因素的影响，难以在现场用隧道掘进机的开挖结果来说明这一规律。在本研究中，我们开发了一种新的TBM掘进试验平台（DGTBM-A）来分析岩石-刀盘相互作用。介绍了平台的组成和功能。采用单轴抗压强度低（24.94 MPa）、中（61.22 MPa）、高（95.04 MPa） 3种不同强度的立方体砂岩试件（500 mm × 500 mm × 500 mm）进行TBM掘进试验。研究了刀盘推力、转速和岩石强度对刀盘岩石相互作用的影响。分析了关键掘进参数、掘进机性能指标和岩屑特征，以反映其影响。研究结果表明，刀盘推力、转速和岩石强度对扭矩、推进速度、穿透速度、比能和现场穿透指数有显著影响。此外，所产生的岩石泥的特征随所应用的隧道参数而变化，这为岩石破碎的效率和有效性提供了见解。建立了掘进机性能指标与影响因素之间的相关性。研究结果有助于更好地理解隧道掘进机在砂岩中的掘进力学，有助于优化操作参数，以提高工程实践中的性能和成本效益。

{"title":"Response law of rock-cutterhead interaction in intact sandstone through TBM tunnelling test","authors":"Weiqiang Xie , Xiaoli Liu , Caifeng Zhang , Xiaoxiong Zhou , Jian Chen","doi":"10.1016/j.undsp.2025.06.006","DOIUrl":"10.1016/j.undsp.2025.06.006","url":null,"abstract":"<div><div>The unclear response law of rock-cutterhead interaction seriously limits the tunnel boring machine (TBM) efficiency. Various influencing factors make it difficult to illustrate the law using the TBM tunnelling results in the field. In the present study, we develop a novel TBM tunnelling test platform (DGTBM-A) to analyze rock-cutterhead interaction. The components and functions of the platform are introduced. The cubic sandstone specimens (500 mm <span><math><mrow><mo>×</mo></mrow></math></span> 500 mm <span><math><mrow><mo>×</mo></mrow></math></span> 500 mm) with three distinct uniaxial compressive strengths (low (24.94 MPa), medium (61.22 MPa), and high (95.04 MPa) are used for TBM tunnelling test. The effects of cutterhead thrust, rotational speed and rock strength on the rock-cutterhead interaction are examined. Key tunnelling parameters, TBM performance indices, and rock muck characteristics are analyzed to reflect their effects. The findings revealed significant impacts of cutterhead thrust, rotational speed and rock strength on torque, advance rate, penetration rate, specific energy, and field penetration index. Additionally, the characteristics of the produced rock muck varied with the applied tunnelling parameters, providing insights into the efficiency and effectiveness of rock breaking. Correlations between the TBM performance indices and the influencing factors are established. The results contribute to a better understanding of the mechanics involved in TBM tunnelling in sandstone, aiding in optimizing operational parameters for improved performance and cost-efficiency in engineering practice.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"26 ","pages":"Pages 152-174"},"PeriodicalIF":8.3,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694740","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

Thrust-vectoring automatic shield tunneling technology: Method, verification and application 推力矢量自动盾构掘进技术：方法、验证与应用

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-10-24 DOI: 10.1016/j.undsp.2025.01.008

Yeting Zhu , Di Wu , Zhihua Wang , Zixin Zhang , Shuaifeng Wang , Xin Huang , Yuan Qin , Yanfei Zhu , Fan Wang

Recognizing the formidable challenge of achieving millimeter-level precision in controlling shield machine attitudes amidst thrust forces exceeding thousands of tons on a global scale, a thrust-vectoring automatic shield tunneling technology was introduced to effectively mitigate potential inaccuracies stemming from human intervention. Initially, a load-thrust “dual-vector” motion control mechanism was adopted, grounded in defining the shield thrust vector and establishing the interactive correlation between shield attitude deviation points and thrust action points in both horizontal and vertical orientations through comprehensive data assessments. Subsequently, a parallel proportional-integral-derivative control law was devised for stability control of shield machines, delineating the functional link between alterations in shield attitudes and displacements of thrust action points, with initial validation conducted via full-scale model trials. A motion trajectory for correcting shield attitudes was devised, and a thrust vector control approach was formulated by amalgamating feedforward calculations with feedback adjustments. The application of this thrust-vectoring automatic tunneling technology in a large-diameter shield tunneling endeavor yielded the subsequent key findings: a consistent deviation of approximately 2.5% was upheld between target and actual thrust forces, with actual shield velocity managed within a –1 to +1 mm/min range from the target value. To ensure robust steering capability of the shield machine, target thrust moments in both horizontal and vertical directions marginally exceeded actual values, with satisfactory execution. The interplay between shield attitudes and thrust action points in both horizontal and vertical dimensions exhibited a characteristic akin to “sugar-coated haws on a stick”. Despite notable “kowtow” occurrences during segment assembly, statistical analysis indicated that deviations in shield attitude in horizontal and vertical planes were ultimately contained within –20 to +5 mm and –45 to –28 mm ranges, respectively, markedly surpassing average manual control standards.

认识到在全球范围内超过数千吨的推力下实现毫米级精度控制盾构机姿态的艰巨挑战，引入了推力矢量自动盾构隧道技术，以有效减轻人为干预造成的潜在不准确性。首先，采用载荷-推力“双矢量”运动控制机制，在确定盾构推力矢量的基础上，通过综合数据评估，建立盾构姿态偏差点与推力作用点在水平和垂直方向上的交互关系。随后，设计了用于盾构机稳定性控制的并联比例-积分-导数控制律，描述了盾构姿态变化与推力作用点位移之间的功能联系，并通过全尺寸模型试验进行了初步验证。设计了修正盾构姿态的运动轨迹，提出了前馈计算与反馈调整相结合的推力矢量控制方法。该推力矢量自动掘进技术在大直径盾构掘进中的应用取得了以下重要发现：目标推力与实际推力之间的偏差约为2.5%，实际盾构速度与目标值的偏差范围在-1 ~ +1 mm/min之间。为了保证盾构机稳定的转向能力，在水平和垂直方向上的目标推力力矩都略大于实际值，执行情况令人满意。在水平和垂直维度上，盾牌姿态和推力作用点之间的相互作用表现出类似于“棒子上的糖衣山楂果”的特征。尽管在分段装配过程中出现了明显的“磕头”现象，但统计分析表明，水平和垂直平面上的屏蔽姿态偏差最终分别被控制在-20至+5 mm和-45至-28 mm的范围内，明显超过了平均的手动控制标准。

{"title":"Thrust-vectoring automatic shield tunneling technology: Method, verification and application","authors":"Yeting Zhu , Di Wu , Zhihua Wang , Zixin Zhang , Shuaifeng Wang , Xin Huang , Yuan Qin , Yanfei Zhu , Fan Wang","doi":"10.1016/j.undsp.2025.01.008","DOIUrl":"10.1016/j.undsp.2025.01.008","url":null,"abstract":"<div><div>Recognizing the formidable challenge of achieving millimeter-level precision in controlling shield machine attitudes amidst thrust forces exceeding thousands of tons on a global scale, a thrust-vectoring automatic shield tunneling technology was introduced to effectively mitigate potential inaccuracies stemming from human intervention. Initially, a load-thrust “dual-vector” motion control mechanism was adopted, grounded in defining the shield thrust vector and establishing the interactive correlation between shield attitude deviation points and thrust action points in both horizontal and vertical orientations through comprehensive data assessments. Subsequently, a parallel proportional-integral-derivative control law was devised for stability control of shield machines, delineating the functional link between alterations in shield attitudes and displacements of thrust action points, with initial validation conducted via full-scale model trials. A motion trajectory for correcting shield attitudes was devised, and a thrust vector control approach was formulated by amalgamating feedforward calculations with feedback adjustments. The application of this thrust-vectoring automatic tunneling technology in a large-diameter shield tunneling endeavor yielded the subsequent key findings: a consistent deviation of approximately 2.5% was upheld between target and actual thrust forces, with actual shield velocity managed within a –1 to +1 mm/min range from the target value. To ensure robust steering capability of the shield machine, target thrust moments in both horizontal and vertical directions marginally exceeded actual values, with satisfactory execution. The interplay between shield attitudes and thrust action points in both horizontal and vertical dimensions exhibited a characteristic akin to “sugar-coated haws on a stick”. Despite notable “kowtow” occurrences during segment assembly, statistical analysis indicated that deviations in shield attitude in horizontal and vertical planes were ultimately contained within –20 to +5 mm and –45 to –28 mm ranges, respectively, markedly surpassing average manual control standards.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"26 ","pages":"Pages 126-151"},"PeriodicalIF":8.3,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694742","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

Evolution of mechanical properties of shield tunnels induced by water-soil gushing 水-土涌作用下盾构隧道力学特性演化

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-10-24 DOI: 10.1016/j.undsp.2024.12.008

Xiao-Chuang Xie , Dong-Mei Zhang , Ming-Liang Zhou

Water and soil gushing in shield tunnels pose a significant risk to tunnel structure safety. However, it is challenging to fully capture the evolution of the mechanical response of tunnel structures due to the limitations of conventional numerical methods in simulating large soil deformations around the tunnel due to gushing. This paper developed a coupled material point method (MPM) and finite element method (FEM) approach for water and soil gushing, where MPM was for modelling the soil deformation and FEM was for modelling the tunnel response. The developed approach was utilized to conduct the gushing-induced large deformation analyses and generate the varying soil and water pressures acting on the tunnel lining. Meanwhile, structural internal forces and joint deformations were identified based on the load-structure method. The findings suggest that the gushing process can be categorized into three stages: initial developing, rapid developing, and stable developing stages. The soil and water pressures around the gushing point decreased abruptly during the “rapid developing stage”, but the soil pressures on the tunnel crown and tunnel invert increase, causing a sharp rise in the bending moment of the lining and severe joint deformations, particularly at joints No. 2 and No. 3. Finally, the parametric analyses show that a lower gushing location, deeper tunnel depth, and higher soil shear strength will all exacerbate the influence of water-soil gushing on tunnel structural response, due to variations in the soil and water pressures acting on the tunnel lining throughout the whole process of gushing. These findings underscore the importance of revealing the evolution of tunnel responses to water-soil gushing for maintaining tunnel safety.

盾构隧道的涌水和涌土对隧道结构的安全构成重大威胁。然而，由于传统的数值方法在模拟隧道周围土体因涌水引起的大变形时存在局限性，因此难以完全捕捉隧道结构力学响应的演变过程。本文建立了土体涌水的材料点法和有限元耦合方法，其中材料点法模拟土体变形，有限元模拟隧道响应。利用该方法对隧道衬砌进行了喷流大变形分析，得到了作用在衬砌上的土、水压力的变化规律。同时，基于荷载-结构法对结构内力和节点变形进行了识别。研究结果表明，喷淋过程可分为初始发展阶段、快速发展阶段和稳定发展阶段。在“快速发展阶段”，涌点附近的土压力和水压力急剧下降，但隧道顶部和隧道仰拱处的土压力增加，导致衬砌弯矩急剧上升，节理变形严重，特别是2号和3号节理。参数分析结果表明，随着涌水位置越低、隧道深度越深、土体抗剪强度越高，由于整个涌水过程中作用在隧道衬砌上的土体和水压力的变化，会加剧水-土涌对隧道结构响应的影响。这些发现强调了揭示隧道对水-土涌反应的演变对维护隧道安全的重要性。

{"title":"Evolution of mechanical properties of shield tunnels induced by water-soil gushing","authors":"Xiao-Chuang Xie , Dong-Mei Zhang , Ming-Liang Zhou","doi":"10.1016/j.undsp.2024.12.008","DOIUrl":"10.1016/j.undsp.2024.12.008","url":null,"abstract":"<div><div>Water and soil gushing in shield tunnels pose a significant risk to tunnel structure safety. However, it is challenging to fully capture the evolution of the mechanical response of tunnel structures due to the limitations of conventional numerical methods in simulating large soil deformations around the tunnel due to gushing. This paper developed a coupled material point method (MPM) and finite element method (FEM) approach for water and soil gushing, where MPM was for modelling the soil deformation and FEM was for modelling the tunnel response. The developed approach was utilized to conduct the gushing-induced large deformation analyses and generate the varying soil and water pressures acting on the tunnel lining. Meanwhile, structural internal forces and joint deformations were identified based on the load-structure method. The findings suggest that the gushing process can be categorized into three stages: initial developing, rapid developing, and stable developing stages. The soil and water pressures around the gushing point decreased abruptly during the “rapid developing stage”, but the soil pressures on the tunnel crown and tunnel invert increase, causing a sharp rise in the bending moment of the lining and severe joint deformations, particularly at joints No. 2 and No. 3. Finally, the parametric analyses show that a lower gushing location, deeper tunnel depth, and higher soil shear strength will all exacerbate the influence of water-soil gushing on tunnel structural response, due to variations in the soil and water pressures acting on the tunnel lining throughout the whole process of gushing. These findings underscore the importance of revealing the evolution of tunnel responses to water-soil gushing for maintaining tunnel safety.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"26 ","pages":"Pages 82-105"},"PeriodicalIF":8.3,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145694744","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

EDA-TCNet: A dual-attention enhanced network for precise point cloud segmentation in tunnel construction EDA-TCNet：用于隧道施工中点云精确分割的双关注增强网络

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-10-15 DOI: 10.1016/j.undsp.2025.04.012

Xin Peng, Mingnian Wang, Bingxu Huang, Honglin Shen, Hao Zhong

To enhance the accuracy of point cloud semantic segmentation in tunnel face construction areas, this study proposes a novel model named enhanced dual attention-tunnel construction net (EDA-TCNet). EDA-TCNet introduces a 3D enhanced dual attention module (EDAM), which employs a parallel channel and spatial attention mechanism to strengthen the model’s focus on critical features. Additionally, a loss function named CELDAM is designed, combining cross-entropy loss and label-distribution-aware margin loss to effectively address data imbalance issues and improve the prediction capability for minority classes. Experiments conducted on three ongoing tunnel projects in Northwest China demonstrate that EDA-TCNet achieves a mean intersection over union (mIoU) of 0.8816 and an overall accuracy (OA) of 0.9406 on the test set. Compared to PointNet, PointNet++, DGCNN, and PointMLP, EDA-TCNet improves mIoU by 18.20%, 3.00%, 8.61%, and 32.23%, and OA by 15.98%, 1.74%, 5.48%, and 22.38%, respectively. Furthermore, the optimization of the balancing coefficient μ in CELDAM further enhances the model’s generalization capability. In conclusion, EDA-TCNet demonstrates exceptional performance in point cloud semantic segmentation tasks for tunnel construction areas and shows great potential for engineering applications.

为了提高隧道工作面施工区域点云语义分割的准确性，本文提出了一种新的增强双注意-隧道施工网（EDA-TCNet）模型。EDA-TCNet引入了3D增强双注意模块（EDAM），该模块采用平行通道和空间注意机制来加强模型对关键特征的关注。此外，设计了一个名为CELDAM的损失函数，结合交叉熵损失和标签分布感知的边际损失，有效地解决了数据不平衡问题，提高了对少数类的预测能力。在西北3个正在进行的隧道工程中进行的实验表明，EDA-TCNet在测试集上的平均交联（mIoU）为0.8816，总体精度（OA）为0.9406。与PointNet、pointnet++、DGCNN和PointMLP相比，EDA-TCNet的mIoU分别提高了18.20%、3.00%、8.61%和32.23%，OA分别提高了15.98%、1.74%、5.48%和22.38%。此外，CELDAM中平衡系数μ的优化进一步提高了模型的泛化能力。综上所述，EDA-TCNet在隧道施工领域的点云语义分割任务中表现出优异的性能，具有巨大的工程应用潜力。

{"title":"EDA-TCNet: A dual-attention enhanced network for precise point cloud segmentation in tunnel construction","authors":"Xin Peng, Mingnian Wang, Bingxu Huang, Honglin Shen, Hao Zhong","doi":"10.1016/j.undsp.2025.04.012","DOIUrl":"10.1016/j.undsp.2025.04.012","url":null,"abstract":"<div><div>To enhance the accuracy of point cloud semantic segmentation in tunnel face construction areas, this study proposes a novel model named enhanced dual attention-tunnel construction net (EDA-TCNet). EDA-TCNet introduces a 3D enhanced dual attention module (EDAM), which employs a parallel channel and spatial attention mechanism to strengthen the model’s focus on critical features. Additionally, a loss function named CELDAM is designed, combining cross-entropy loss and label-distribution-aware margin loss to effectively address data imbalance issues and improve the prediction capability for minority classes. Experiments conducted on three ongoing tunnel projects in Northwest China demonstrate that EDA-TCNet achieves a mean intersection over union (mIoU) of 0.8816 and an overall accuracy (OA) of 0.9406 on the test set. Compared to PointNet, PointNet++, DGCNN, and PointMLP, EDA-TCNet improves mIoU by 18.20%, 3.00%, 8.61%, and 32.23%, and OA by 15.98%, 1.74%, 5.48%, and 22.38%, respectively. Furthermore, the optimization of the balancing coefficient <em>μ</em> in CELDAM further enhances the model’s generalization capability. In conclusion, EDA-TCNet demonstrates exceptional performance in point cloud semantic segmentation tasks for tunnel construction areas and shows great potential for engineering applications.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"25 ","pages":"Pages 350-367"},"PeriodicalIF":8.3,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145425003","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

Incorporating smart computer vision and in-drilling information into rock quality evaluation via incomplete data-driven Bayesian networks 通过不完全数据驱动的贝叶斯网络，将智能计算机视觉和钻孔信息整合到岩石质量评价中

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-10-15 DOI: 10.1016/j.undsp.2025.03.007

Chen Wu , Minglun Tan , Yue Tong , Hongwei Huang

Tunnelling is a challenging task due to a lack of full understanding of the surrounding rock quality. This study proposes a solution driven by a refined computer vision (CV) method, complemented by rock mass drilling tests and Bayesian networks, to address this issue through a multi-source heterogeneous data approach. Initially, improvements are made to the popular Swin Transformer to improve the recognition and segmentation of intricate rock features. Notably, refined smart CV, owing to its U-shaped architecture and smart window self-attention computation, exhibits segmentation performance superior to that of conventional CV methods such as Swin Transformer, Deeplab V3+, and UNet. Building upon the segmentation outcomes of the refined CV, a parameter set comprising apparent rock parameters is established. Then, two datasets encompassing rock internal drilling parameters and mechanics, as well as design parameters, are curated. The combination of the aforementioned parameter sets is referred to as the rock quality comprehensive evaluation dataset. However, analysis reveals data incompleteness issues within these datasets. To mitigate this problem, a novel tree-augmented Bayesian network is designed, and a prediction accuracy of 91% is realized, surpassing popular decision trees, ensemble learning, and deep learning methods. Furthermore, evaluation services are provided in mountain and submarine tunnels, suggesting that drilling parameters significantly enhance the evaluation performance. Moreover, employing two sensitivity analysis metrics underscores the prominent influence of rotating pressure and drilling speed parameters. This study endeavor presents diverse solutions for achieving precise and expeditious predictions of rock quality through various parameter sets, tailored to cater to diverse requirements of tunnels.

由于缺乏对围岩质量的充分了解，隧道掘进是一项具有挑战性的任务。本研究提出了一种由精细计算机视觉（CV）方法驱动的解决方案，辅以岩体钻探试验和贝叶斯网络，通过多源异构数据方法解决这一问题。首先，对流行的Swin Transformer进行了改进，以提高对复杂岩石特征的识别和分割。值得注意的是，精细化的智能CV由于其u型架构和智能窗口自关注计算，其分割性能优于Swin Transformer、Deeplab V3+、UNet等传统CV方法。基于改进CV的分割结果，建立了包含表观岩石参数的参数集。然后，收集两个数据集，包括岩石内部钻井参数和力学以及设计参数。上述参数集的组合称为岩石质量综合评价数据集。然而，分析揭示了这些数据集中的数据不完整问题。为了缓解这一问题，设计了一种新的树增强贝叶斯网络，实现了91%的预测精度，超过了流行的决策树、集成学习和深度学习方法。此外，在山地和海底隧道中提供了评估服务，表明钻井参数显著提高了评估性能。此外，采用两个灵敏度分析指标强调了旋转压力和钻井速度参数的显著影响。本研究提出了多种解决方案，通过不同的参数集来实现精确和快速的岩石质量预测，以满足隧道的不同要求。

{"title":"Incorporating smart computer vision and in-drilling information into rock quality evaluation via incomplete data-driven Bayesian networks","authors":"Chen Wu , Minglun Tan , Yue Tong , Hongwei Huang","doi":"10.1016/j.undsp.2025.03.007","DOIUrl":"10.1016/j.undsp.2025.03.007","url":null,"abstract":"<div><div>Tunnelling is a challenging task due to a lack of full understanding of the surrounding rock quality. This study proposes a solution driven by a refined computer vision (CV) method, complemented by rock mass drilling tests and Bayesian networks, to address this issue through a multi-source heterogeneous data approach. Initially, improvements are made to the popular Swin Transformer to improve the recognition and segmentation of intricate rock features. Notably, refined smart CV, owing to its U-shaped architecture and smart window self-attention computation, exhibits segmentation performance superior to that of conventional CV methods such as Swin Transformer, Deeplab V3+, and UNet. Building upon the segmentation outcomes of the refined CV, a parameter set comprising apparent rock parameters is established. Then, two datasets encompassing rock internal drilling parameters and mechanics, as well as design parameters, are curated. The combination of the aforementioned parameter sets is referred to as the rock quality comprehensive evaluation dataset. However, analysis reveals data incompleteness issues within these datasets. To mitigate this problem, a novel tree-augmented Bayesian network is designed, and a prediction accuracy of 91% is realized, surpassing popular decision trees, ensemble learning, and deep learning methods. Furthermore, evaluation services are provided in mountain and submarine tunnels, suggesting that drilling parameters significantly enhance the evaluation performance. Moreover, employing two sensitivity analysis metrics underscores the prominent influence of rotating pressure and drilling speed parameters. This study endeavor presents diverse solutions for achieving precise and expeditious predictions of rock quality through various parameter sets, tailored to cater to diverse requirements of tunnels.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"26 ","pages":"Pages 321-340"},"PeriodicalIF":8.3,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145748050","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 hybrid review of sewer inspection tools and automated CCTV image analysis techniques 下水道检查工具和自动闭路电视图像分析技术的混合回顾

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-10-15 DOI: 10.1016/j.undsp.2025.06.004

Mohamed Nashat , Tarek Zayed

Maintaining the integrity of sewage networks is crucial for sustainable urban development. Despite extensive research on inspection tools, machine learning applications, and condition assessment for sewer defects, a holistic review of these elements remains absent. This paper addresses this gap by presenting a comprehensive review within a unified framework, employing a mixed-method approach that includes bibliometric, scientometric, and systematic analyses. Our findings reveal that integrating in-pipe and out-pipe inspection methods enhances outcomes. The current literature identifies modified RegNet, dilation segmentation with conditional random field (DilaSeg-CRF), you only look once (YOLO) models, and faster region-based convolutional neural network (Faster R-CNN) as effective algorithms for classification, segmentation, and object detection, both on-site and off-site, respectively. However, machine learning is an evolving field, and future algorithms may surpass these models. Identifying key challenges, we propose recommendations aimed at advancing research and enhancing replicability: notably, the expansion of international research collaborations, particularly in underrepresented regions such as the Middle East, Africa, Asia, and South America; applying the latest version of YOLOv11 in object detection; and investigating defect patterns in polyvinyl chloride (PVC) sewer and rehabilitated pipes using advanced diagnostic methods. This review anticipates aiding policymakers in adopting informed strategies, thereby contributing to the development of smarter, more sustainable cities.

保持污水管网的完整性对可持续城市发展至关重要。尽管对下水道缺陷的检测工具、机器学习应用和状态评估进行了广泛的研究，但对这些因素的全面审查仍然缺乏。本文采用文献计量学、科学计量学和系统分析的混合方法，在统一的框架内进行了全面的综述，解决了这一差距。我们的研究结果表明，整合管内和管外检测方法可以提高结果。目前的文献将改进的RegNet、条件随机场扩张分割（DilaSeg-CRF）、你只看一次（YOLO）模型和更快的基于区域的卷积神经网络（faster R-CNN）分别确定为现场和非现场分类、分割和目标检测的有效算法。然而，机器学习是一个不断发展的领域，未来的算法可能会超越这些模型。我们确定了关键挑战，提出了旨在推进研究和增强可复制性的建议：特别是扩大国际研究合作，特别是在中东、非洲、亚洲和南美洲等代表性不足的地区；应用最新版本的YOLOv11进行目标检测；并使用先进的诊断方法调查聚氯乙烯（PVC）下水道和修复管道的缺陷模式。本报告旨在帮助决策者采取明智的战略，从而为建设更智能、更可持续的城市做出贡献。

{"title":"A hybrid review of sewer inspection tools and automated CCTV image analysis techniques","authors":"Mohamed Nashat , Tarek Zayed","doi":"10.1016/j.undsp.2025.06.004","DOIUrl":"10.1016/j.undsp.2025.06.004","url":null,"abstract":"<div><div>Maintaining the integrity of sewage networks is crucial for sustainable urban development. Despite extensive research on inspection tools, machine learning applications, and condition assessment for sewer defects, a holistic review of these elements remains absent. This paper addresses this gap by presenting a comprehensive review within a unified framework, employing a mixed-method approach that includes bibliometric, scientometric, and systematic analyses. Our findings reveal that integrating in-pipe and out-pipe inspection methods enhances outcomes. The current literature identifies modified RegNet, dilation segmentation with conditional random field (DilaSeg-CRF), you only look once (YOLO) models, and faster region-based convolutional neural network (Faster R-CNN) as effective algorithms for classification, segmentation, and object detection, both on-site and off-site, respectively. However, machine learning is an evolving field, and future algorithms may surpass these models. Identifying key challenges, we propose recommendations aimed at advancing research and enhancing replicability: notably, the expansion of international research collaborations, particularly in underrepresented regions such as the Middle East, Africa, Asia, and South America; applying the latest version of YOLOv11 in object detection; and investigating defect patterns in polyvinyl chloride (PVC) sewer and rehabilitated pipes using advanced diagnostic methods. This review anticipates aiding policymakers in adopting informed strategies, thereby contributing to the development of smarter, more sustainable cities.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"25 ","pages":"Pages 295-326"},"PeriodicalIF":8.3,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145424897","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 lithology identification via spectral-image fusion 基于光谱图像融合的智能岩性识别

IF 8.3 1区工程技术 Q1 ENGINEERING, CIVIL

Underground Space

Pub Date : 2025-10-15 DOI: 10.1016/j.undsp.2025.05.011

Zhenhao Xu, Shan Li, Peng Lin, Qianji Li

Lithology identification is of vital significance for fundamental geological research and engineering applications. Traditional methods rely on rock image features and often cause confusion among visually similar rocks. To enhance identification accuracy, spectral features are integrated to better represent rock composition. Nonetheless, spectral testing inevitably damages samples and is prone to challenges of the occurrence of similar spectra for different materials. This study explores the advantages of hyperspectral imaging technology, enabling the integration of spectral and image data without damage or contact. A novel spectral-image fusion method is proposed for lithology identification. It uses a dual-channel residual neural network that combines spectral and texture feature channels. Additionally, key features are effectively captured by spectral-spatial attention mechanisms. Finally, a customized transfer learning approach is utilized to fine-tune the pre-trained network on a small dataset for lithology identification at the tunnel site, facilitating rapid model adaptation. The research indicates that employing the ResNetX2-50 network for integrating spectral-image information yields optimal identification results, with a fusion accuracy of over 99% on the test set, which is 2 percentage points higher than the accuracy of a single spectral model and about 20 percentage points higher than the accuracy of a single texture model. Research findings provide robust technical support for non-destructive, non-contact, fast lithology identification in field investigations and construction projects.

岩性识别对基础地质研究和工程应用具有重要意义。传统的方法依赖于岩石图像特征，并且经常在视觉上相似的岩石之间造成混淆。为了提高识别精度，结合光谱特征更好地表征岩石成分。然而，光谱测试不可避免地会损坏样品，并且容易遇到不同材料出现相似光谱的挑战。本研究探讨了高光谱成像技术的优势，实现了光谱和图像数据的集成，而不损坏或接触。提出了一种新的岩性识别光谱图像融合方法。它使用了一种结合了光谱和纹理特征通道的双通道残差神经网络。此外，关键特征被光谱空间注意机制有效捕获。最后，利用定制的迁移学习方法对小数据集上的预训练网络进行微调，以便在隧道现场进行岩性识别，从而促进模型的快速适应。研究表明，采用ResNetX2-50网络对光谱图像信息进行融合，获得了最优的识别效果，在测试集上的融合精度达到99%以上，比单一光谱模型的准确率提高了2个百分点，比单一纹理模型的准确率提高了约20个百分点。研究成果为野外调查和工程建设中无损、非接触、快速岩性识别提供了有力的技术支持。

{"title":"Intelligent lithology identification via spectral-image fusion","authors":"Zhenhao Xu, Shan Li, Peng Lin, Qianji Li","doi":"10.1016/j.undsp.2025.05.011","DOIUrl":"10.1016/j.undsp.2025.05.011","url":null,"abstract":"<div><div>Lithology identification is of vital significance for fundamental geological research and engineering applications. Traditional methods rely on rock image features and often cause confusion among visually similar rocks. To enhance identification accuracy, spectral features are integrated to better represent rock composition. Nonetheless, spectral testing inevitably damages samples and is prone to challenges of the occurrence of similar spectra for different materials. This study explores the advantages of hyperspectral imaging technology, enabling the integration of spectral and image data without damage or contact. A novel spectral-image fusion method is proposed for lithology identification. It uses a dual-channel residual neural network that combines spectral and texture feature channels. Additionally, key features are effectively captured by spectral-spatial attention mechanisms. Finally, a customized transfer learning approach is utilized to fine-tune the pre-trained network on a small dataset for lithology identification at the tunnel site, facilitating rapid model adaptation. The research indicates that employing the ResNetX2-50 network for integrating spectral-image information yields optimal identification results, with a fusion accuracy of over 99% on the test set, which is 2 percentage points higher than the accuracy of a single spectral model and about 20 percentage points higher than the accuracy of a single texture model. Research findings provide robust technical support for non-destructive, non-contact, fast lithology identification in field investigations and construction projects.</div></div>","PeriodicalId":48505,"journal":{"name":"Underground Space","volume":"25 ","pages":"Pages 327-349"},"PeriodicalIF":8.3,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145425002","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