Tunnelling and Underground Space Technology最新文献

{"title":"Data-and experience-driven prediction method of twin shield tunneling-induced complicated settlement curve and its evolution","authors":"Rui-Di Chen ,&nbsp;Xing-Tao Lin ,&nbsp;Xiangsheng Chen ,&nbsp;Hui Zeng","doi":"10.1016/j.tust.2025.106824","DOIUrl":"10.1016/j.tust.2025.106824","url":null,"abstract":"<div><div>The application of machine learning algorithms in geotechnical engineering is increasingly prevalent. Solely data-driven machine learning algorithms suffer from the “black box” issue, lacking the ability to uncover causal relationships and exhibiting preferences in variable selection. Consequently, data-and experience-driven machine learning algorithms are gradually emerging. Addressing the prediction of complex ground settlement curves and their evolution, this paper proposes a novel data-and experience-driven machine learning prediction method. Specifically, it replaces the traditional “prediction of settlement points—settlement curve” approach with “prediction formula—settlement curve”. This method first selects an appropriate formula based on the characteristics of ground settlement curves, ensuring that formula parameters possess physical meanings. Subsequently, machine learning is employed to predict the parameters within the formula, which are then applied to derive the ground settlement curve. Sensitivity analysis of these parameters explores causal relationships and identifies model preferences. Finally, this approach is applied to predict ground settlement curves induced by twin shield tunnels excavation, using overlaid Peck curves as the prediction formula. GRNN and LSTM algorithms are employed to predict undetermined parameters within the ground settlement curve, yielding promising results that ensure accuracy in predicting key indices like maximum settlement while effectively capturing the overall shape of the settlement curve. This method enhances the explainability of machine learning in predicting ground settlement and provides valuable insights for forecasting the overall forms of complex ground settlement curves.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106824"},"PeriodicalIF":6.7,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548621","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}

{"title":"Impact of mechanical parameter correlations on reliability of stability of underground water-sealed storage caverns","authors":"Jingyi Ma ,&nbsp;Zhechao Wang ,&nbsp;Zhenhua Peng ,&nbsp;Liping Qiao ,&nbsp;Wei Li ,&nbsp;Junyan Li ,&nbsp;Chenghua Hong","doi":"10.1016/j.tust.2025.106839","DOIUrl":"10.1016/j.tust.2025.106839","url":null,"abstract":"<div><div>The stability of underground water-sealed oil storage (UWSOS) caverns is crucial for ensuring their long-term safe operation. In this study, a reliability analysis method for UWSOS caverns considering correlations between rock mass mechanical parameters was proposed. First, a statistical analysis was conducted on the rock mass mechanical parameters from five large UWSOS caverns projects in China, in which process the mean values, standard deviations, correlation coefficients, and distribution types were obtained. Based on the practical first-order reliability method (FORM), the impacts of parameter correlations on reliability analysis results with regard to the plastic zone and cavern convergence criteria were revealed. And the influence induced by parameter correlations was explained. The study demonstrated that correlations between rock mass mechanical parameters influence the reliability index, with the cohesion–friction angle relationship exhibiting a particularly significant impact. In the analysis based on the plastic zone criteria, a marked reduction in the reliability index is observed as the correlation coefficient between cohesion and friction angle increases. Finally, the reliability of a UWSOS facility in southern China was investigated. Comparative reliability assessments conducted with versus without considering parameter correlations reveal that neglecting such interdependencies leads to conservative reliability estimations. The study provides a valuable insight into the reliability design of UWSOS caverns and facilitates the accurate assessment of engineering risks.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106839"},"PeriodicalIF":6.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535829","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}

{"title":"Crowd safety assessment for flood evacuation in subway platform tunnels","authors":"Shuchao Cao ,&nbsp;Luhan Ma ,&nbsp;Yiping Zeng ,&nbsp;Yan Wang ,&nbsp;Peng Wang ,&nbsp;Li Xu","doi":"10.1016/j.tust.2025.106848","DOIUrl":"10.1016/j.tust.2025.106848","url":null,"abstract":"<div><div>Flood disasters occur frequently worldwide, causing a large number of casualties and property damage. Urban subway stations are one of the most vulnerable places to flooding. Therefore, to evaluate the flood hazard for passengers in subway stations, an evacuation safety assessment method is proposed in this paper. The flood inundation process is firstly simulated, and the flood depth and flow velocity in subway stations are obtained based on the hydrodynamic model. Secondly, a crowd evacuation model considering the dynamic flood impacts is established, and the simulation results are validated through the qualitative and quantitative methods. Thirdly, the ASET is calculated based on the critical instability status of pedestrians in floods, and the RSET is obtained based on the simulated evacuation time. Finally, the evacuation safety index (ESI), namely the difference between ASET and RSET, is proposed to accurately identify the danger and quantitatively assess the crowd safety at both micro and macro levels in flood scenarios. The results indicate that the staircase areas are more dangerous due to the large water speed, especially under the large inlet flow and evacuee number. Moreover, with the increase of preparation time, the ASET significantly decreases while the RSET increases notably, making it difficult for the crowd to evacuate safely. The study provides useful insights for flood hazard assessment in subway stations, which can help the emergency department to make timely decisions and formulate evacuation plans to ensure the safety of passengers in sudden flood events.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106848"},"PeriodicalIF":6.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548619","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}

{"title":"Axial behaviour of underground steel pipeline buried in unsaturated soils","authors":"Chang Guo ,&nbsp;Chao Zhou","doi":"10.1016/j.tust.2025.106831","DOIUrl":"10.1016/j.tust.2025.106831","url":null,"abstract":"<div><div>Soils surrounding underground pipelines are often unsaturated in field conditions. However, the effects of the unsaturated condition on the axial interaction between pipelines and soils are unclear and not considered in current design guidelines. This limitation may lead to unsafe designs, as the load from potentially moving soil to pipelines could be underestimated. To address this, six large-scale physical modeling tests were conducted to examine pipe pullout behavior using a rough steel pipe buried in saturated and unsaturated completely decomposed granite (CDG). Matric suctions around the pipe (0 ∼ 70.2 kPa) were adjusted by varying the initial water content and measured using tensiometers. The results show that axial pullout resistance, under constant nominal overburden pressure, increases with suction. At a suction of 70.2 kPa, the resistance was 1.69 times greater than in the saturated condition, highlighting significant risks in current design guidelines. 68 % of this axial resistance increment is attributed to the additional interface contact pressure induced by capillary forces of soil-pipe interface liquid menisci. The remaining 32 % is related to net interface contact pressure increases mainly due to suction effects on constrained dilatancy. A new and simple model was developed for calculating axial resistance in the unsaturated condition, based on elastic expanding cylinder theory, considering suction effects on Bishop’s stress, stiffness, and dilatancy.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106831"},"PeriodicalIF":6.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144549287","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}

{"title":"Closure: Modelling ground and tunnel response to water-soil gushing in stratified soil Zheng, G, Qiu, H.M., Zhang, T.Q., Cheng, H.Y., Diao, Y, Wang, K. Tunnelling and underground space, March 2025, https://doi.org/10.1016/j.tust.2025.106583","authors":"Tianqi Zhang","doi":"10.1016/j.tust.2025.106826","DOIUrl":"10.1016/j.tust.2025.106826","url":null,"abstract":"","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106826"},"PeriodicalIF":6.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535886","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}

{"title":"A new early warning method for rockbursts and compound rockburst–collapse hazards in deeply-buried tunnels based on energy density","authors":"Zhihao Kuang ,&nbsp;Shili Qiu ,&nbsp;Shaojun Li ,&nbsp;Yaxun Xiao ,&nbsp;Guangliang Feng ,&nbsp;Yong Huang ,&nbsp;Shuaipeng Chang","doi":"10.1016/j.tust.2025.106828","DOIUrl":"10.1016/j.tust.2025.106828","url":null,"abstract":"<div><div>Rockbursts and compound rockburst–collapse hazards frequently occur when deeply-buried tunnels are constructed in regions subject to significant geological variation and intense tectonic activity. These hazards are characterized by their sudden and highly destructive nature, thus posing a major threat to construction safety and engineering stability. The evolution of such hazards is usually accompanied by microseismic (MS) events that alternate between two different phases: long, quiet periods and short periods of eruption. Accurately identifying the transition interval between these phases (thus allowing hazard warnings to be issued in a timely manner) has thus become a critical issue that needs to be solved in current hazard warning systems. To address this issue, this paper proposes a new warning method based on the spatial evolution patterns of the MS events that occur during the development of rockbursts and compound rockburst–collapse hazards. We call it the ‘logarithmic energy density’ (logED) method as the indicator used is the logarithm of the energy density of the effective MS events released within the warning unit employed. It can be calculated using the WOA-DBSCAN clustering method and Quickhull3D algorithm. In this paper, five hazard cases are taken from a tunnel engineering project in southwestern China to use as study objects. The evolution characteristics of logED associated with these hazards as they evolve were systematically analyzed. The results show that logED can effectively capture the subtle and critical spatial distribution changes of the MS events in the precursor phase of the hazards and accurately identify the transition interval between long, quiet periods and short, eruption periods during the evolution phase. Compared with traditional hazard warning methods based on the logarithm of the MS energy released, logED has significant advantages in terms of improved prediction accuracy and sensitivity. Furthermore, the hazard warning method proposed in this paper is multi-parameter. That is, it combines an analysis of the changes in logarithmic MS energy released and logED, which allows it to precisely capture the subtle spatial distribution changes of the MS events and identify key transitional moments during the hazard evolution period. This effectively eliminates many misjudgments that often occur using single-parameter analysis methods. The proposed method provides new data dimensions and analytical tools for hazard prediction, significantly improves the scientificity and accuracy of the hazard warnings, and offers important theoretical support and practical guidance for the improvement and optimization of hazard warning systems.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106828"},"PeriodicalIF":6.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535887","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}

{"title":"A novel deep learning-based identification technology of cutting pile states during super-large diameter shield tunnelling","authors":"Yifan Chen ,&nbsp;Haibin Zhang ,&nbsp;Xiang Shen ,&nbsp;Xiangsheng Chen ,&nbsp;Dong Su ,&nbsp;Jiuqi Wu","doi":"10.1016/j.tust.2025.106836","DOIUrl":"10.1016/j.tust.2025.106836","url":null,"abstract":"<div><div>Accurately identifying the position and quantity of piles is critical for ensuring the safe tunnelling process in shield cutting pile projects. The vibration signals generated during the shield cutting pile process contain abundant information. To address the challenge of determining pile positions and quantities, this study proposes a method for the identification of strata based on vibration characteristics, integrating the dual advantages of knowledge-driven and data-driven approaches. The method includes a data processing module, a knowledge-driven module, a transformer-based model (MT), and a comprehensive evaluation module, and it has been validated in the Guangzhou Haizhu Bay shield tunnel project. The results show that the developed method achieves an accuracy of 99.56% in the identification of strata types, improving by 1.33%, 1.11%, and 14.16% compared to the MLP, RF, and LSTM models, respectively. As the number of cutting piles increases, the frequency of vibration signals gradually rises, while the amplitude shows no significant change. Based on this finding, the top five frequencies were used as input. Position encoding was employed to effectively learn the positional information of the frequency, enabling the MT model to achieve an accuracy of 65.71% in identifying multiple piles, improving by 10.51%, 19.14%, and 23.46% compared to the MLP, RF, and LSTM models, respectively. Comprehensive evaluation analysis indicates that this method demonstrates superior recall and weighted accuracy, highlighting its strong flexibility and applicability in engineering contexts.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106836"},"PeriodicalIF":6.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522988","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}

{"title":"A physics-guided hierarchical deep learning framework for underground rock reinforcement compliance check based on 4D point cloud data","authors":"Zhen Han ,&nbsp;Qian Li ,&nbsp;Xiangyu Wang ,&nbsp;Danqi Li","doi":"10.1016/j.tust.2025.106829","DOIUrl":"10.1016/j.tust.2025.106829","url":null,"abstract":"<div><div>Rock bolts have been extensively used for rock reinforcement in underground mines. The compliance check for rock bolts installation pattern becomes significantly important for ensuring an optimal balance between the cost and performance of rock reinforcement. The current manual compliance check process requires tremendous manpower and inevitably introduces human errors and data bias issues. In order to address this challenge, in this study, a novel physics-guided hierarchical deep learning framework for underground rock reinforcement compliance check based on 4D point cloud data, termed PGHDFramework, was proposed. In this framework, a physics-based forward approach for bolt-level classification named Intensity-based Forward Classification (IBFC) model was introduced first, which requires no training process. Then a hierarchical deep neural network based on PointNet++ that can concatenate spatial information (i.e., x, y, z coordinates) and physical property information (i.e., intensity value) at different levels of abstraction, termed 4D Bolt Detection Neural Network (4DBDNet), was developed. The SLAM-LiDAR point cloud data from five sections of an underground mine with different conditions containing 25,146,657 points were used for validating the framework as well as comparing its performance with the existing methods. The precision, recall, F1 score and IoU of the proposed approach at point level are 0.92, 0.94, 0.93 and 0.73 separately, and at bolt-level are 0.60, 0.84, 0.70 respectively, showing a much higher promising performance than other methods. The accuracy and effectiveness of the proposed framework was further confirmed by compliance checking a fresh underground mine drive to autonomously generate the rock bolts spacing and row spacing. This study ultimately provides the framework of a universal-applicable digital approach to the mining industry for a more cost-effective and accurate rock reinforcement compliance check in practice.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106829"},"PeriodicalIF":6.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523143","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}

{"title":"Investigation on the soil-machine interaction based on slurry shield machine operation data learning: A geological conditions recognition model","authors":"Xin Li ,&nbsp;Yiguo Xue ,&nbsp;Guangkun Li ,&nbsp;Chuanqi Qu ,&nbsp;Binghua Zhou","doi":"10.1016/j.tust.2025.106762","DOIUrl":"10.1016/j.tust.2025.106762","url":null,"abstract":"<div><div>Real-time perception of the geological condition is of great importance to efficient tunneling and hazard prevention in underwater shield tunneling. This study proposes a geological condition–shield machine mutual feedback perception method to address the issues of insufficient utilization of excavation data, lack of optimization of models, low prediction accuracy and efficiency in the current research on geological condition identification in soft soil shield tunneling. For implementation, first, the database of the slurry shield machine tunneling parameters containing 6 input features related to operation parameters were established, in which 269 tunneling cycles from a river-crossing shield tunnel in China were accommodated. Then, the outlier detection method is carried out to pre-process the data sample set and remove the outliers. Furthermore, the genetic algorithm is adapted to optimize the K-means clustering algorithm to cluster the geological conditions category. Four categories with better clustering performance were obtained. To obtain the identification model of the geological condition category with the best prediction performance, 75 % of the sample data is used for data learning, and the optimal training parameters of each model are determined through 10-fold cross-validation. The remaining 25 % of the data is used for validating the four classifiers’ performance. The accuracy levels of the proposed models were assessed using four statistical indices, i.e., the Accuracy, F1 score, Precision, and Recall. The testing results revealed that the PSO-ELM algorithm can better characterize and predict the geological conditions in SPB shield tunnelling among all three recognition models. Finally, the synthetic minority oversampling technique (SMOTE) was used to process the database to eliminate the impact of category imbalance on the recognition performance and obtain the best prediction effect. The validation results indicated the four models have improved the overall prediction performance of the minority samples (type-III) by about 0–45 %. Moreover, the Accuracy of (increased by 35–44 %), Recall of (increased by 0–31 %), F1 score of (increased by 25–37 %) and Precision of (increased by 35–44 %), respectively, for testing stages of the PSO-ELM model confirmed that this hybrid model is a powerful and applicable technique addressing problems related to shield tunnelling performance with a high level of accuracy using the proposed investigation flow.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106762"},"PeriodicalIF":6.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522990","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}

{"title":"Transitioning to zero emission construction: A comparative study of diesel and electric loaders and trucks in Norwegian tunnel construction","authors":"Asmat Ullah Khan ,&nbsp;Lizhen Huang ,&nbsp;Amund Bruland","doi":"10.1016/j.tust.2025.106847","DOIUrl":"10.1016/j.tust.2025.106847","url":null,"abstract":"<div><div>The construction industry is progressively seeking sustainable solutions to mitigate environmental impacts, particularly in the realm of heavy machinery operations. This study conducts a comprehensive comparative analysis between diesel and electric loaders and trucks in the context of tunnel construction, with a specific focus on transitioning to zero-emission practices. Analyzing data from 30 years of excavation projects in standard Norwegian roadway tunnels during drill and blast tunneling, the study evaluates environmental impacts, including carbon emissions, ozone depletion, particulate matter formation, and ecotoxicity and human toxicity potentials using life cycle assessment methodologies. Comparing diesel-powered machinery to battery-powered machinery for tunnel lengths ranging from 500 m to 5 km reveals that battery-powered equipment achieves significant environmental benefits, with reductions of 83 % and 80 % in global warming potential, 75 % and 73 % in ozone depletion potential, 81 % and 76 % in particulate matter formation, and 76 % and 71 % in terrestrial acidification potential, respectively. However, the use of battery engines results in a notable increase in toxicity potentials, with terrestrial eco-toxicity values rising approximately 10-fold to 11-fold and human toxicity increasing by 6 % to 7 % compared to internal combustion engine machines, spanning tunnel lengths from 0.5 to 5 km. This highlights a trade-off in the adoption of electrification, where CO₂ emissions are reduced but terrestrial eco-toxicity is increased. As tunnel length increases, transportation emissions surpass loading emissions due to increased transportation activities and improved loading efficiency. Thus, this research underscores the benefits of electrification for emission reduction and sustainability, offering valuable insights for policymakers seeking zero-emission construction practices aligned with Norway’s carbon neutrality commitment.</div></div>","PeriodicalId":49414,"journal":{"name":"Tunnelling and Underground Space Technology","volume":"164 ","pages":"Article 106847"},"PeriodicalIF":6.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523190","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}