<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Uncertainty-aware prediction and decision support for disc-cutter consumption in hard-rock TBM tunnelling</title>
      <link>https://trid.trb.org/View/2692509</link>
      <description><![CDATA[Disc cutter consumption is a major source of downtime and maintenance cost in hard-rock tunnel boring machine (TBM) excavation, yet reliable forecasting remains difficult because cutter replacement is jointly influenced by geological variability and operating conditions. This study developed a ring-scale workflow for predicting disc cutter consumption and supporting maintenance decisions using 144 ring-level samples. Geological descriptors and operating signals were aligned at ring scale, and cutter consumption was represented by an equivalent replacement rate to improve comparability across cutter sizes. To identify robust predictors under multicollinearity and coupled rock–machine conditions, a multi-perspective feature-screening strategy was applied by jointly considering target association, structural influence among variables, and nonlinear predictive contribution. Based on the selected predictors, an SVR model optimized by the sparrow search algorithm was developed for prediction. Predictive uncertainty was quantified using conformal prediction, and the outputs were translated into intervention policies through a cost-sensitive decision module. The model achieved an MAE of 0.5140, RMSE of 1.0026, MAPE of 9.08%, and R² of 0.9634. The 90% prediction intervals achieved a coverage of 0.95 with a mean interval size of 0.62. Under the selected engineering setting, the intervention rule reduced the expected cost to 0.279 per sample, compared with 0.465 for the never-intervene policy and 0.953 for the always-intervene policy. The proposed workflow provides practical support for ring-scale cutter inspection and replacement planning in hard-rock TBM tunnelling.]]></description>
      <pubDate>Fri, 24 Jul 2026 08:40:26 GMT</pubDate>
      <guid>https://trid.trb.org/View/2692509</guid>
    </item>
    <item>
      <title>Assessing Shaft Excavation in Underground Metro Construction: A Comparative Study Using PLAXIS 2D and 3D</title>
      <link>https://trid.trb.org/View/2580997</link>
      <description><![CDATA[The construction of an underground metro system in India involved a crucial aspect of the excavation of a shaft, a 20 m× 20 m box structure, for the launch of Tunnel Boring Machines (TBMs). Diaphragm walls (D-walls) were selected as one of the preferred shoring methods as they not only provide shoring support during excavation but also contribute to the permanent structure of the metro system. To comprehensively analyze the behavior of the excavation process, both PLAXIS 2D and 3D analyses were conducted. Initially, PLAXIS 2D was employed to assess the response of the excavation in the given geological conditions. However, it indicated higher than anticipated deformations for a shaft box. One critical aspect that PLAXIS 2D failed to capture was the box effect of the launching shaft. In the PLAXIS 3D simulation, the excavation of the launching shaft was modeled, allowing for a more accurate representation of the box effect. The results obtained from the PLAXIS 3D analysis demonstrate that the deformations and the settlements are comparatively less to 2D, indicating the effective simulation of the launching shaft's box. This comparative study between PLAXIS 2D and 3D provides a thorough understanding of the benefits and limitations associated with numerical modeling.]]></description>
      <pubDate>Tue, 21 Jul 2026 09:49:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2580997</guid>
    </item>
    <item>
      <title>Simplified Finite-Element Modeling of TBM Advancement: A Novel Computational Approach</title>
      <link>https://trid.trb.org/View/2690972</link>
      <description><![CDATA[Developing a numerical model of tunnel excavation using a tunnel boring machine (TBM) is a difficult task due to the complexity of the phenomena involved in the advancement of the machine through the ground. The ease of use of calculation software often masks (at least in part) the representation in the numerical simulation of the actual phenomenon. Many simulations use nodal forces to account for stress relaxation at the boundary of the excavated ground and for the interaction between the TBM, the grout, and the surrounding soil. However, calibrating these models may prove difficult. This paper proposes a simple approach called the swelling method, which aims to take into account the TBM control parameters, especially the grout injection parameters. This approach allows directly defining the final stress applied to the tunnel contour, taking into account the grout pressure. The conventional and the new approaches are implemented in the finite-element code CESAR (version 2024.0.5) and tested to simulate surface settlements and lateral soil displacements induced by tunneling using a full-scale research project called TULIP (Tunneling and Limitation of Impacts on Piles) as a background. The results show a strong agreement between the two methods, but the swelling method is easier to handle and has the potential to capture the complex interactions between the TBM and the surrounding soil. The influence of the model parameters on the width of the surface settlement trough is discussed.]]></description>
      <pubDate>Thu, 16 Jul 2026 09:10:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2690972</guid>
    </item>
    <item>
      <title>Operational Parameter–Based Prediction of Shield TBM Advance Rate Using Explainable Computational Intelligence</title>
      <link>https://trid.trb.org/View/2683180</link>
      <description><![CDATA[The advance rate (AR) of a tunnel boring machine (TBM) governs construction scheduling, cost control, and overall project efficiency; thus, its accurate prediction is essential for effective resource allocation and mitigation of delays arising from geological and operational variability. This study develops an optimal soft-computing framework by comparatively evaluating support vector regression (SVR), feedforward neural networks (FFNN), gene expression programming (GEP), gated recurrent units (GRU), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM) models. A dataset comprising 1,197 TBM operational records was utilized, incorporating cutterhead rotation speed (CRS), mean thrust (F/A), mean cutterhead torque (T/D³), upper earth pressure (UEP), lower earth pressure (LEP), and torque penetration index (TPI). Multicollinearity among predictors was quantified using the variance inflation factor (VIF), while feature sensitivity was assessed via the cosine amplitude method. Model performance was evaluated using eight statistical indices, three reliability measures, regression error characteristic (REC) curves, generalizability assessment, and the Wilcoxon signed-rank test. Comparative analysis demonstrated the superior predictive capability of the BiLSTM model, achieving accuracy exceeding 98.60% across training, testing, and validation phases. Reliability indices confirmed its robustness. Nevertheless, curve-fitting analysis indicated mild overfitting during testing (2.49) and validation (1.98), examined through the interaction between feature multicollinearity and sensitivity.]]></description>
      <pubDate>Thu, 30 Apr 2026 11:27:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2683180</guid>
    </item>
    <item>
      <title>Digital twin–enabled real-time control of tunnel boring machines using deep reinforcement learning for cumulative settlement management</title>
      <link>https://trid.trb.org/View/2665092</link>
      <description><![CDATA[The increasing complexity of urban tunneling requires the optimization of TBM operational parameters to ensure excavation stability and effective ground control. This paper introduces a Deep Reinforcement Learning (DRL)-based methodology that integrates geological conditions and settlement status within a structured decision-making framework. A tailored reward function is designed to simultaneously address stability, settlement, and cost. Furthermore, the incorporation of Monte Carlo Tree (MCT) search enhances the decision-making process by improving foresight. A digital twin, constructed from sparse geotechnical data, models the geological conditions and settlement accumulation, thus facilitating the virtual training of the RL agent. When applied to the Nanjing Metro Line 11 project in China, the proposed method effectively captures the intricate relationship between TBM parameters and ground response. Results indicate that the DRL-based approach significantly minimizes settlement and outperforms the NSGA-II algorithm in optimization performance. This paper demonstrates the significant potential of DRL-driven strategies for intelligent and adaptive tunneling control.]]></description>
      <pubDate>Tue, 10 Feb 2026 09:47:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2665092</guid>
    </item>
    <item>
      <title>Design of Grouting Procedures to Prevent Ground Subsidence over Shallow Tunnels</title>
      <link>https://trid.trb.org/View/2200038</link>
      <description><![CDATA[Tunnels 3 m (10 feet) in diameter used for road and railroad crossings of water pipelines in Hillsborough County, Florida suffered ground surface subsidence problems due to their shallow depth and sand soil cover. The soil depth above the top of the tunnels was typically no more than 3 m (10 feet). A controlled low strength cementitious grout was designed to fill the void between the tunnel and the liner plates, and to maintain pressure around the tunnel boring machine (TBM) equal to the overburden pressure. Pre-grouting could not be done due to the low permeability of the fine sand soils and the lack of surface access. Therefore, the grout had to be designed for injection from ports inside the TBM without causing damage to the machine. This paper describes the design of the grout and the testing program to document the engineering properties of the grout, as well as the field grouting procedures developed for the project. The results of field measurements and laboratory test results are also presented.]]></description>
      <pubDate>Fri, 06 Feb 2026 13:53:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2200038</guid>
    </item>
    <item>
      <title>Multi-objective optimization of TBM-induced building settlement control considering physical constraints</title>
      <link>https://trid.trb.org/View/2628578</link>
      <description><![CDATA[Tunnel Boring Machine (TBM) excavation faces the challenge of inducing building settlement. Current intelligent methods for addressing this issue often lack physical interpretability and fail to account for multilayered soil conditions. This paper introduces the Physics-Informed Machine Learning incorporating Multilayered Soils (PIMLMS). The PIMLMS is integrated into a Multi-Objective Optimization (MOO) algorithm, aiming to minimize the impact of TBM on building settlement by controlling TBM parameters. A case study on Wuhan Metro Line 19 in China demonstrates the feasibility of this approach, with significant improvements observed. In the comparative study, PIMLMS showed a 7.4 % improvement in R² and a 104 % improvement in robustness compared to the machine learning models. The proposed hybrid approach has proven effective in considering multilayered soil conditions, improving the interpretability and robustness of the model, and offering a feasible solution to mitigate TBM-induced building settlement.]]></description>
      <pubDate>Wed, 26 Nov 2025 14:13:08 GMT</pubDate>
      <guid>https://trid.trb.org/View/2628578</guid>
    </item>
    <item>
      <title>Face Stability of Twin Tunnels Excavated in Opposite Directions Using Large-Diameter Slurry Shield Machines</title>
      <link>https://trid.trb.org/View/2582081</link>
      <description><![CDATA[The construction of twin tunnels excavated by simultaneous drive of two opposite tunnel boring machines presents a challenge for the tunneling industry, in particular the assurance of tunnel face stability due to a mutual effect when both tunnels are approaching each other. To ensure the stability of the tunnel face over the whole construction phase and along the complete alignment, it is important to correctly assess the response of the individual tunnel face with respect to the effect of the opposite tunneling process. For the assessment of such tunnel face stability, a three-dimensional (3D) numerical model that allows one to examine the 3D stress and pore water distribution at the tunnel face is used. This contribution presents a case study based on a real tunneling project in the city of Shenzhen, China, in which twin tunnels are excavated simultaneously in the opposite directions using two large-diameter slurry shield machines. The influence of slurry infiltration as well as the clear distance between the tunnel faces are investigated through comparison with simulations in which a standard face stability assessment technique is employed. It is shown that the additional seepage force induced by the pore pressure gradient between the two faces leads to the increase of the limit support stress ratio.]]></description>
      <pubDate>Fri, 26 Sep 2025 13:39:51 GMT</pubDate>
      <guid>https://trid.trb.org/View/2582081</guid>
    </item>
    <item>
      <title>Performance monitoring of TBM tunnel: a case study of the West Qinling tunnel</title>
      <link>https://trid.trb.org/View/2571841</link>
      <description><![CDATA[TBM tunnels cause less disturbance to the surrounding rock mass than drill-and-blast tunnels, resulting in significant differences in the deformation of the surrounding rock mass and the forces on the support structure. Field tests are conducted on the West Qinling tunnel to examine the extent of surrounding rock mass disturbance using TBM and drill-and-blast methods. The analysis encompasses the pressure variation in the surrounding rock mass and the force characteristics of the support structure. The findings demonstrate that the excavation method greatly influences the disturbance of the surrounding rock mass. The height of the loosened zone in TBM excavation is approximately 30% less than that in drill-and-blast excavation. During TBM excavation, the stress in the surrounding rock mass gradually transitions to a secondary stress state. The loosened pressure constitutes a small fraction of the total pressure of the surrounding rock mass, with the latter being predominantly deformation pressure. The secondary lining in TBM-excavated sections is governed by the compressive strength of concrete, with axial force being the primary internal force affecting structural safety. The tunnel hance exhibits the highest safety factor, while the tunnel roof has the lowest. Numerical models are developed to investigate the distribution of the shear slip and plastic zones in the surrounding rock mass. The results indicated that the depth of the plastic zone is about 0.5 m deeper than that of the loosened zone. The field-tested pressure of the surrounding rock mass corresponds to the self-weight of the surrounding rock mass in the 10 mm shear slip zone. This 10 mm shear slip zone can approximate the pressure values of the surrounding rock mass.]]></description>
      <pubDate>Fri, 29 Aug 2025 16:51:24 GMT</pubDate>
      <guid>https://trid.trb.org/View/2571841</guid>
    </item>
    <item>
      <title>Data-Based Real-Time TBM Surrounding Rock Characterization and Tunneling Parameter Prediction</title>
      <link>https://trid.trb.org/View/2582227</link>
      <description><![CDATA[Real-time intelligent perception of complex surrounding rock conditions is essential for achieving automated and intelligent control of Tunnel Boring Machines (TBMs). Leveraging the extensive big data obtained from the TBM excavation of a water resources allocation project, this study applied deep learning algorithms to enable real-time characterization of surrounding rock features and to predict key tunneling parameters. The raw data were first processed, followed by the establishment of pre-training models for surrounding rock feature characterization based on three deep temporal algorithms. These models enabled real-time acquisition of surrounding rock feature vectors. The results of Multi-Layer Perceptron (MLP) surrounding rock classification based on the derived feature vectors indicated that the Long Short-Term Memory (LSTM) pre-training model exhibited the highest prediction accuracy among the three models. The effectiveness of the surrounding rock feature vectors in characterizing rock conditions was further validated through similarity analysis and dimensionality reduction visualization. Subsequently, a baseline model for real-time prediction of tunneling performance parameters was developed, along with two improved models that incorporated either the rock grade or the surrounding rock feature vectors as additional input. Experimental results demonstrated that both improved models effectively enhanced prediction accuracy and stability. Notably, the model utilizing surrounding rock feature vectors as input enabled real-time performance prediction, thereby overcoming the inherent delay associated with traditional rock grade acquisition.]]></description>
      <pubDate>Tue, 12 Aug 2025 10:18:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2582227</guid>
    </item>
    <item>
      <title>Numerical and experimental analysis of contact pressure in rock-disc cutter interaction using displacement discontinuity method and digital image correlation</title>
      <link>https://trid.trb.org/View/2557042</link>
      <description><![CDATA[Accurately predicting contact pressure distribution in rock-disc cutter interaction is crucial for optimizing tunnel boring machine (TBM) performance. This study presents a numerical and experimental investigation of contact pressure using the Higher-Order Displacement Discontinuity Method (HODDM) and Digital Image Correlation (DIC). The numerical model was developed to analyze stress and strain distributions under varying cutter force conditions, and its results were validated through controlled experimental testing using a linear cutting simulator. The numerical analysis reveals that pressure distribution follows a downward parabolic trend, with peak values concentrated in the central contact zone. This trend was also confirmed from experimental DIC measurements. The study further investigates the influence of the rotational-to-normal force ratio (Fr/Fn) on stress concentration, showing that increasing this ratio amplifies peak pressure and alters crack propagation patterns. Additionally, the proposed FWxM criterion quantifies pressure distribution zones, demonstrating that higher Fr/Fn ratios lead to a broader pressure spread beneath the cutter, potentially improving rock fragmentation efficiency. These findings enhance the understanding of rock fracturing mechanisms and provide a validated approach for predicting cutter forces, aiding in TBM cutter design optimization. The results indicate that accurate pressure distribution modeling can contribute to reducing cutter wear and enhancing excavation efficiency in hard rock tunneling.]]></description>
      <pubDate>Wed, 16 Jul 2025 09:51:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2557042</guid>
    </item>
    <item>
      <title>Multistep Probabilistic Forecasting Approach for Tunnel Boring Machine Cutterhead Torque and Thrust Based on VMD-BDNN</title>
      <link>https://trid.trb.org/View/2539883</link>
      <description><![CDATA[Accurate prediction of cutterhead torque and thrust is crucial for achieving efficient and safe propulsion of a tunnel boring machine (TBM). However, several uncertainties within the predictions of TBM parameters may diminish prediction accuracy and credibility. To address this issue, a multistep probabilistic forecasting approach that combines variational mode decomposition (VMD) and a Bayesian deep neural network (BDNN) is first proposed for cutterhead torque and thrust. In this approach, the nonlinear original series is decomposed initially into multiple subsequences and residual sequences to reduce complexity. Then, the multistep probabilistic prediction-based independent subsequence is implemented using three BDNN models, and the results, including multistep point and probabilistic predictions, are obtained by summing all the subsequences. The final results show that all three models, especially the VMD-bidirectional gated recurrent unit model, have excellent performance in terms of multistep prediction, with prediction accuracy exceeding 99.414% and 99.554% for cutterhead torque and thrust in the five-step prediction, respectively. In addition, a high-quality evaluation of uncertainty is obtained via multistep prediction, confirmed by a mean prediction interval width (MPIWep) above 0.8 and all PICPal up to 1. Compared with preexisting models, this approach not only achieves high accuracy in multistep prediction but also infers high-quality aleatoric and epistemic uncertainties in predicting cutterhead torque and thrust.]]></description>
      <pubDate>Wed, 21 May 2025 09:52:10 GMT</pubDate>
      <guid>https://trid.trb.org/View/2539883</guid>
    </item>
    <item>
      <title>Physical model to study tunnel squeezing under true-triaxial stress state (UTI-UTC 30)
</title>
      <link>https://trid.trb.org/View/2543423</link>
      <description><![CDATA[This project develops a novel physical modeling framework to investigate the phenomenon of tunnel squeezing in weak or highly stressed rock masses under true-triaxial stress conditions. Tunnel squeezing—characterized by excessive and time-dependent ground deformation around the tunnel perimeter—poses significant challenges to safe and cost-effective tunnel construction. To simulate this behavior, a miniature tunnel boring machine (TBM) is integrated into a true-triaxial apparatus capable of replicating realistic in-situ stress states. The model allows for controlled excavation in synthetic clay-rich rock analogs and incorporates real-time measurement of displacement, strain, and support system response. Experimental data are complemented with analytical and numerical analyses to evaluate failure mechanisms and the interaction between the TBM, tunnel liner, and surrounding ground. The research aims to provide a deeper understanding of tunnel-ground interactions under squeezing conditions and guide the development of robust tunneling strategies and support systems for use in challenging geological environments.
]]></description>
      <pubDate>Wed, 07 May 2025 17:23:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2543423</guid>
    </item>
    <item>
      <title>Mechanical Characterizations of Joints in Segmented Tunnel Liners Due to Flexural and Thrust Jack Loading (UTI-UTC 28)
</title>
      <link>https://trid.trb.org/View/2543421</link>
      <description><![CDATA[This research investigates the structural behavior of joints in segmented tunnel liners subjected to flexural and thrust jack loading, which are critical conditions encountered during tunnel construction and operation. The project focuses on quantifying the mechanical response of these joints, particularly under load scenarios simulating bending moments and axial forces applied by tunnel boring machines (TBMs). Experimental testing is conducted on full-scale precast concrete segments, including those from the Chesapeake Bay Tunnel project, to assess parameters such as joint stiffness, rotational capacity, and load-bearing performance. The study is complemented by detailed numerical modeling and analytical evaluations to validate test results and improve segmental design methodologies. The outcomes are expected to inform design guidelines and enhance the durability, safety, and reliability of segmented tunnel systems used in modern underground transportation infrastructure.
]]></description>
      <pubDate>Wed, 07 May 2025 17:37:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2543421</guid>
    </item>
    <item>
      <title>Incorporating Spatial Uncertainty to Advance the Practice of Site-Investigations, Geological-Geotechnical Characterization and TBM Performance Prediction (UTI-UTC 24) 

</title>
      <link>https://trid.trb.org/View/2543418</link>
      <description><![CDATA[This research project addresses the challenges posed by spatial variability and uncertainty in subsurface conditions during tunneling operations. By integrating geostatistical methods with tunneling data, the study aims to enhance geological and geotechnical site characterization and improve the predictive accuracy of tunnel boring machine (TBM) performance. The framework incorporates probabilistic models to quantify and propagate spatial uncertainty across soil and rock interfaces, enabling better-informed decisions during design and construction phases. Case studies involving TBM tunneling projects in Washington, D.C. and Seattle demonstrate the effectiveness of the approach, particularly in forecasting ground condition transitions and identifying geohazards such as karstic voids. The methodology supports more reliable risk assessments, adaptive tunneling strategies, and cost-effective infrastructure delivery through improved data interpretation and uncertainty management.
]]></description>
      <pubDate>Wed, 07 May 2025 17:56:20 GMT</pubDate>
      <guid>https://trid.trb.org/View/2543418</guid>
    </item>
  </channel>
</rss>