<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>Research on Pig Movement and Wax Transport during the Wax Removal Process of Oil Pipelines</title>
      <link>https://trid.trb.org/View/2709127</link>
      <description><![CDATA[Research on the process of wax transport during pipeline pigging is of great significance for the maintenance and safe operation of pipelines. To elucidate the transportation mechanism of oil–wax mixtures during pigging and its impact on pig velocity, this study integrates pig dynamics with a computational fluid dynamics (CFD) model for oil–wax mixture transport, utilizing the moving reference frame (MRF) method. The transient interactions between the oil–wax two-phase flow and the pig are systematically investigated under varying bypass rates and wax layer thicknesses. A 6-inch loop experiment was conducted to comparatively analyze wax transport behavior and pig motion. Experimental results reveal that the wax migration process is in good agreement with CFD simulations, and the predicted pig velocities are consistent with experimental measurements within the uncertainty range of the experimental parameters, thereby validating the reliability of the CFD model. Simulation results indicate that wax transport downstream of the pig proceeds through three distinct stages: formation of the oil–wax mixed slug, formation of oil–wax agglomerates, and stable transport of the agglomerates. During the slug formation stage, significant fluctuations in pig velocity are observed, whereas after the development of agglomerates, the pig velocity stabilizes and exhibits a positive correlation with the viscosity of the upstream oil–wax mixture. Jet flow is shown to effectively promote downstream wax transport, thereby reducing wax accumulation at the pig front. The velocity of oil–wax mass transport ranges from 0.6 to 1.3 times the pipeline flow velocity. Maintaining the pig velocity below 0.6 times the pipeline flow velocity can further mitigate the risk of wax blockage. These findings provide essential insights for the optimization of intelligent pig design and the reduction of operational risks associated with crude oil pipelines.]]></description>
      <pubDate>Mon, 31 Aug 2026 10:31:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2709127</guid>
    </item>
    <item>
      <title>An Experimental Study on Investigating the Impacts of a localised saturated zone around an intact buried pipe on a Pavement</title>
      <link>https://trid.trb.org/View/2700578</link>
      <description><![CDATA[The interdependencies between road, the ground and buried utilities within an urban infrastructure system complicate the management of an urban infrastructure system. Consequently, it is crucial to adopt a comprehensive approach to infrastructure maintenance, by considering the interdependencies within the entire system. Understanding the correlation between these components can help identify the main causes of failure leading to more efficient management practices. While various studies have investigated the effect of traffic loads on buried pipes, fewer studies have examined how a localised saturated zone around an intact buried pipe influences road surface deterioration. In this study, laboratory experiments were conducted to investigate the coupled response of the pavement, soil, and pipe under cyclic loading when such a localised saturated zone was introduced. The results showed that localised surface depression of the road was exacerbated when a saturated zone was present around the intact buried pipe, which indicates a greater potential for accelerated pavement deterioration. The study is intended as a comparative reduced-scale physical model for mechanism interpretation rather than a direct prototype prediction. The findings suggest that localised saturation around buried utilities may contribute to accelerated pavement deterioration and may therefore be relevant to condition assessment and maintenance prioritisation.]]></description>
      <pubDate>Fri, 28 Aug 2026 08:35:03 GMT</pubDate>
      <guid>https://trid.trb.org/View/2700578</guid>
    </item>
    <item>
      <title>Mechanical response of buried corroded pipelines under coupled soil, traffic, and internal fluid loads</title>
      <link>https://trid.trb.org/View/2698848</link>
      <description><![CDATA[Buried metallic pipelines, as essential components of urban underground transportation and utility systems, are typically installed beneath roadways and are continuously subjected to multiple coupled effects, including soil pressure, internal fluid pressure, stray current corrosion, and repeated traffic loads. These interacting factors give rise to complex multi-field coupling effects that significantly influence the stability and service performance of road structures and surrounding transportation infrastructure. This study establishes a refined three-dimensional finite element model that integrates the corroded pipeline, surrounding soil, and internal fluid domains to capture the coupled mechanical behavior under realistic loading conditions. The model is validated through full-scale experimental tests, demonstrating its capability in reproducing the stress and deformation characteristics of buried corroded pipelines beneath traffic loads. Parametric analyses are conducted to quantify the influence of corrosion geometry, pipe and soil properties, and loading conditions on the geotechnical-structural response. Furthermore, a Morris global sensitivity analysis identifies the most influential factors affecting pipeline stress and soil deformation, with corrosion depth, internal pressure, and corrosion length being dominant. The proposed multi-field coupling framework and sensitivity-based insights provide theoretical support for the geotechnical design, maintenance planning, and safety assessment of underground pipeline systems integrated within transportation infrastructure.]]></description>
      <pubDate>Fri, 28 Aug 2026 08:35:03 GMT</pubDate>
      <guid>https://trid.trb.org/View/2698848</guid>
    </item>
    <item>
      <title>Effects of Constant and Alternating Temperatures on Sealing Performance of Threaded Pipe Joints over a Broad Temperature Range</title>
      <link>https://trid.trb.org/View/2708249</link>
      <description><![CDATA[Due to improper assembly and varying work conditions, gas leakage frequently occurs in threaded pipe joints. This work investigates the degradation of sealing performance in threaded pipe joints in rail transit vehicles for a broad temperature range arising from ambient environmental variations. By combining experimental investigations with numerical simulations, the effects of constant temperatures on torque decay and leakage rates across five nominal sizes (DN8, DN10, DN15, DN20, DN25) were systematically examined, as well as the influence of alternating temperatures (−30°C to 70°C) on DN25 joints. Mechanical tests were conducted to characterize the silicone rubber gaskets, followed by long-term torque decay monitoring and sealing performance tests. The results indicate that alternating thermal cycles induce significantly more severe torque decay and sealing degradation than constant temperatures, and the degradation becomes more severe as the frequency of temperature fluctuation increases. Under the specified tightening torque, the DN8, DN10, and DN25 joints maintained leakage rates within the sealing requirements after 2 months at room temperature, whereas DN15 and DN20 exceeded the safety threshold at a medium pressure of 0.7 MPa. Both low (−30°C) and high (70°C) constant temperatures substantially reduced the service life of the joints. These findings underscore the critical importance of accounting for thermal cycling in joint design and operation and provide practical recommendations for enhancing sealing reliability in pneumatic systems.]]></description>
      <pubDate>Thu, 27 Aug 2026 16:32:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2708249</guid>
    </item>
    <item>
      <title>Mitigation of Dynamic Load-Induced Pipeline Displacements Using EPS Geofoam</title>
      <link>https://trid.trb.org/View/2767191</link>
      <description><![CDATA[Buried lifelines under transportation infrastructure, such as pipelines beneath highways and railways, are highly vulnerable to joint damage induced by cyclic surface traffic and foundation loading. This study presents a parametric numerical evaluation of Expanded Polystyrene (EPS) geofoam blocks as a protective compressible inclusion to mitigate pipeline displacements beneath dynamic surface loads. Finite element simulations utilizing an advanced small-strain stiffness soil model were systematically conducted to investigate the coupled effects of geofoam thickness (t = 0.25–1.0D), width (B = 1.0–3.0D), and spacing from the pipe crown (S = 0.2–1.0D). The numerical trajectories indicate that the geosynthetic inclusion enhances structural performance by mobilizing positive soil arching, trapping shear strains, and maximizing dynamic energy dissipation. The optimized geofoam configuration restricts cumulative pipe crown settlement by up to 50% and decreases the peak bending moment by 20%. A critical design threshold is identified at a block width of B = 2.5D, beyond which further stress reduction diminishes due to the over-expansion of the overlying soil prism. Additionally, maximizing geofoam proximity to the conduit crown is essential for optimal shielding. These insights provide practical subgrade design guidelines for resilient buried infrastructure in transportation corridors.]]></description>
      <pubDate>Wed, 26 Aug 2026 08:55:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2767191</guid>
    </item>
    <item>
      <title>Numerical Evaluation Analysis of Oil Pipe Hanger Installation Risk Based on T-S Fuzzy Fault Tree</title>
      <link>https://trid.trb.org/View/2729761</link>
      <description><![CDATA[Aiming at the potential risks in the installation process of oil pipe hangers, such as unstable connection, complex environmental factors, and construction equipment failure, which may cause major safety accidents, this paper proposes a risk numerical assessment method based on T-S fuzzy fault tree for quantitative analysis. Firstly, a fault tree model of tubing hanger installation is established to systematically represent various possible risk factors. Secondly, the traditional fault tree is integrated with fuzzy logic analysis in combination with the T-S (Takagi-Sugeno) fuzzy reasoning model to cope with the uncertainty and ambiguity in the tubing hanger installation process. Subsequently, the occurrence probability and impact of each fault event are quantified through the fuzzy comprehensive evaluation method. Finally, the accuracy and effectiveness of the proposed model are verified through experiments. The experimental results show that the probability of occurrence of the top event based on the T-S fuzzy fault tree model has an average value of 0.82 in 100 groups of samples, with a small fluctuation range and a standard deviation of 0.11. In addition, in the key risk factor identification experiment, lack of experience (accounting for 24%) and motor failure (accounting for 23%) are the main risk factors, further proving the advantages of the model in risk identification. Overall, the method based on T-S fuzzy fault tree shows significant accuracy and stability when dealing with complex uncertainty factors, and can effectively improve the safety risk assessment level during the installation process of oil pipe hangers.]]></description>
      <pubDate>Fri, 21 Aug 2026 17:00:58 GMT</pubDate>
      <guid>https://trid.trb.org/View/2729761</guid>
    </item>
    <item>
      <title> 
Developing a Web Interface for Pipe Deterioration Models
</title>
      <link>https://trid.trb.org/View/2762052</link>
      <description><![CDATA[Pipeline infrastructure is critical to energy transportation and urban utility systems, yet aging pipelines are increasingly vulnerable to corrosion, material degradation, and environmental damage. Traditional integrity assessment relies on periodic inspection and offline analysis, providing only discrete snapshots of system condition and failing to capture the continuous, uncertain evolution of deterioration, leaving maintenance and risk-mitigation decisions reactive rather than predictive.
This project develops a dynamic probabilistic deterioration model and an interactive web-based decision-support interface. The predictive engine is a Dynamic Bayesian Network (DBN) constructed in the GeNIe modeling environment, mapping causal dependencies among pipeline condition factors (coating degradation, soil corrosivity, operating parameters) and defining time-slice transitions to capture corrosion evolution. Conditional probability tables are parameterized from historical inspection records, empirical corrosion models, and structured expert elicitation. The DBN is exported and embedded in a backend inference module that applies Bayesian updating to user inputs and computes posterior risk probabilities in real time. An interactive frontend translates the probabilistic forecasts into intuitive time-series risk curves and visual dashboards supporting 'what-if' scenario analyses.
The result is a fully functional web-based framework bridging probabilistic engineering modeling and practical pipeline integrity management. Operators and field engineers can integrate inspection data, simulate risk trajectories, forecast deterioration trends, optimize maintenance schedules, and mitigate corrosion risk before structural failures occur — shifting asset management from reactive to proactive, reducing costly emergency repairs, extending infrastructure lifespan, and mitigating risks to public safety and ecological health. Deliverables include the calibrated DBN model, open-source web interface code, implementation guidelines, a technical report, and peer-reviewed publication.
]]></description>
      <pubDate>Wed, 19 Aug 2026 16:19:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/2762052</guid>
    </item>
    <item>
      <title>Time-of-Flight Estimation Using the Discrete Logarithmic Frequency
          Method</title>
      <link>https://trid.trb.org/View/2761645</link>
      <description><![CDATA[Conventional measurement instruments such as scales, thermocouples, and                     laser-based technologies present challenges when used on lengthy and winding                     underground pipelines. These methods are often not feasible because of physical                     constraints, the challenge of light traveling in curves, and the need for large,                     energy-intensive sensors. Ultrasonic and microwave techniques both face                     challenges in making long-distance measurements because of rapid signal                     weakening and high energy requirements, which make them impractical for small                     pipes. This study introduces an original technique for Time-of-Flight (ToF)                     estimation using the Discrete Logarithmic Frequency (DLF) method to address                     these limitations. By analyzing the time–frequency correlations of signals                     transmitted through channels, the proposed technique enhances the precision and                     dependability of ToF measurements. By employing the DLF method, we are able to                     effectively gather and assess the signal’s performance as conduit lengths                     vary.]]></description>
      <pubDate>Wed, 19 Aug 2026 13:49:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2761645</guid>
    </item>
    <item>
      <title>Quantum Bayesian Networks for Cyber-Physical Threat Prediction in Pipeline SCADA Systems</title>
      <link>https://trid.trb.org/View/2762051</link>
      <description><![CDATA[Pipeline supervisory control and data acquisition (SCADA) systems are cyber-physical systems whose expanding connectivity to enterprise networks and remote services has broadened the cyber-attack surface. Intrusions can propagate beyond digital networks to manipulate physical processes, producing operational disruption, safety hazards, environmental damage, and financial loss. Predicting such cross-domain threats is difficult because attacks are rare and governed by complex causal dependencies, and classical sampling-based inference scales poorly under rare-evidence conditions.
This project constructs a Bayesian network representing causal relationships among cyber-attacks, physical impacts, and sensor observations in a pipeline SCADA environment, informed by a hardware-in-the-loop pipeline testbed with conditional probability tables derived from operational data and engineering judgment. After establishing a classical inference baseline for posterior estimation under normal and rare-evidence queries, the network is encoded as a quantum circuit that preserves its causal structure. Three quantum inference families are implemented and evaluated: quantum rejection sampling, quantum likelihood weighting, and a variational Born-machine approach for posterior attack-probability estimation. Methods are benchmarked on a noiseless simulator and on superconducting quantum hardware, with comparison across accuracy, sample efficiency, and circuit-depth requirements.
Expected outputs include a structured probabilistic model of cyber-physical threat propagation, a quantum-circuit implementation suited to near-term hardware, a comparative evaluation report, open-source code, and peer-reviewed publications. Findings will clarify where quantum inference can improve sampling efficiency for rare-event queries in critical infrastructure security and where current hardware constrains deployment, informing risk-assessment workflows for pipeline operators, the Pipeline and Hazardous Materials Safety Administration (PHMSA), and state DOTs, and laying groundwork for quantum-enhanced digital twin and resilience frameworks.
]]></description>
      <pubDate>Wed, 19 Aug 2026 16:17:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2762051</guid>
    </item>
    <item>
      <title>Numerical Simulation Study on Fire Prevention in Aero-Engine Fuel Tube</title>
      <link>https://trid.trb.org/View/2761686</link>
      <description><![CDATA[Transient gas-liquid two-phase flow in aero-engine fuel pipelines was examined using numerical simulations, focusing on the influence of flow rate on phase change behavior. Under low-flow conditions, phase change occurred repeatedly near the pipe wall, where vapor layers formed and collapsed in an intermittent manner. These processes introduced noticeable unsteadiness in the local mass flow and pressure fields. When the flow rate was increased, vapor generation was largely confined to a narrow region adjacent to the wall, and the overall flow exhibited a more stable character. The results suggest that flow-rate-dependent phase change plays an important role in determining the stability of fuel transport and should be considered in the fire safety assessment of aircraft fuel systems.]]></description>
      <pubDate>Wed, 19 Aug 2026 10:54:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2761686</guid>
    </item>
    <item>
      <title>Research on Flexible Positioning Technology for Airplane Pipe</title>
      <link>https://trid.trb.org/View/2761671</link>
      <description><![CDATA[Airplane pipe assembly is an important part of the aircraft manufacturing process. There are some limitations, such as poor adaptability and a long manufacturing cycle, in conventional clamps used for clamping pipes. To avoid these limitations, this paper developed a pipe clamping system with the capability of adapting pipes with different shapes and diameters. The least squares method was used to build a coordinate system for the pipe and pipe clamp system. The kinematical model of the pipe clamp system was analyzed. A method of finding the inverse solution of mechanical kinematical parameters was proposed, and was utilized to drive a mechanism performing a positioning function. The experiment, detailed in this paper, authenticated that the positioning precision of the pipe clamp system satisfies the requirements of airplane manufacture.]]></description>
      <pubDate>Wed, 19 Aug 2026 10:54:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2761671</guid>
    </item>
    <item>
      <title>Automatic Leak Detection in Pipelines Using Thermal Images from Fixed-Wing Drones and Convolutional Neural Networks</title>
      <link>https://trid.trb.org/View/2742205</link>
      <description><![CDATA[This study aims to develop and validate an automated approach for large-scale pipeline leak detection using fixed-wing unmanned aerial vehicles (UAVs) equipped with thermal imaging sensors and convolutional neural networks (CNNs). Pipeline leakages represent a critical challenge for energy infrastructure operators because of their environmental, economic, and safety implications, particularly in large and geographically distributed pipeline networks where ground-based inspections are costly and time-consuming. The proposed methodology integrates long-range thermal image acquisition from fixed-wing UAV flights with a deep-learning-based detection pipeline designed to identify and localize leakage events under real-world operating conditions. Unlike conventional approaches that predominantly rely on rotary-wing platforms or visible-spectrum imagery, the presented framework leverages the extended coverage capabilities of fixed-wing UAVs and the robustness of thermal imaging to improve monitoring efficiency across large areas. The main contributions of this work include the development of an integrated thermal-based leak detection framework tailored for fixed-wing UAV operations, the application of CNNs for automated leak identification and localization, and comprehensive validation under both simulated and real-world conditions. Quantitative evaluation demonstrates reliable performance, achieving a leak localization root mean square error of 0.8989 m on straight pipeline segments and an overall detection accuracy of 81%. The proposed approach is directly applicable for pipeline operators, infrastructure monitoring agencies, and energy companies by enabling early leak identification, reducing inspection costs, and supporting safer and more efficient maintenance planning. Furthermore, the presented framework provides a foundation for future research focused on larger annotated datasets and integration with predictive maintenance systems. All data generated or analysed during this study are included in this published article.]]></description>
      <pubDate>Thu, 06 Aug 2026 09:05:17 GMT</pubDate>
      <guid>https://trid.trb.org/View/2742205</guid>
    </item>
    <item>
      <title>Identification of gas-liquid flow patterns in horizontal pipes using phase fraction-integrated physics-guided neural network</title>
      <link>https://trid.trb.org/View/2737844</link>
      <description><![CDATA[Accurate identification of gas-liquid two-phase flow patterns in pipelines is a key challenge for optimizing offshore oil and gas transport, marine energy systems, and sustainable maritime operations. This paper integrates the gas-liquid flow pattern transition mechanism with a physics-guided neural network (PGNN) and proposes an identification model for gas-liquid flow patterns in horizontal pipes that combines data fitting with physical constraints. A database of horizontal gas-liquid flow patterns is developed with different pipe diameters (12.7 - 300 mm), gas superficial velocities (0.014 - 200.6 m/s), liquid superficial velocities (0.002 - 8.930 m/s), and liquid viscosities (1.002 - 166 mPa⸱s), comprising 5625 data points. Based on the visualization images of gas-liquid flow in a 65 mm ID horizontal pipe, the flow patterns are classified into annular flow, intermittent flow, dispersed bubble flow, and stratified flow, and the flow pattern data in the database are subsequently reclassified. The predictive abilities of 14 phase fraction correlations are evaluated using an existing flow pattern-phase fraction database, and the correlation proposed by Rouhani is found to have the best coefficient of determination and error control (RRMSE = 10.25%, R² = 0.9). As this correlation serves as the phase fraction physics-guided module, PGNN achieves 97.9% flow pattern identification accuracy on the independent test set, which is superior to other models. The effectiveness of the physics-guided module is quantitatively verified, showing high fitting accuracy (R² > 0.93) for physics-guided quantities. In cases where the flow pattern boundary is blurred and difficult to identify, PGNN maintains an accuracy of 96.88%, surpassing models such as random forest (95.3%) and multilayer perceptron (85.2%).]]></description>
      <pubDate>Wed, 05 Aug 2026 09:12:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/2737844</guid>
    </item>
    <item>
      <title>Advanced Predictive Modeling of Pipeline Settlement in Rectangular Pipe Jacking Tunneling using Hybrid Deep Learning Techniques: A PSO-LSTM-Self Attention Approach</title>
      <link>https://trid.trb.org/View/2742451</link>
      <description><![CDATA[Nowadays, as computer technology makes quick progress, innovative algorithms like deep learning are getting used more and more in underground engineering and lots of other fields. When working on rectangular pipe jacking tunnel projects, accurately predicting the magnitude of pipeline settlement is really key to keeping the work moving smoothly. But traditional ground settlement prediction methods mainly rely on empirical formulas and numerical simulation software. When applied to tunnels with complex geometries, though, these methods usually don’t work as well as needed. To fix this problem, our study came up with a new model called PSO-LSTM-Self-Attention Mechanism (shortened to PSO-LSTM-SAM), specifically designed to predict pipeline settlement caused by rectangular pipe jacking work. This model takes the data collected from construction monitoring and uses that as the input for time series modeling work. That allows for in-depth analysis of real-time settlement data, and as a result, it can make more precise predictions of long-term pipeline settlement. To verify the effectiveness of the PSO-LSTM-SAM algorithm, the researchers compared its prediction results with those from a conventional LSTM network, an LSTM-SAM network, and a PSO-SVR network. They also checked the model’s performance by looking at pipeline settlement predictions from different monitoring points, using data from the Changsha Railway Transit Line 6 project. The results show that the PSO-LSTM model, with the self-attention mechanism added in, greatly boosts how accurate tunnel settlement predictions are, and the model fits the data better, too. This proves that the PSO-LSTM-SAM model works well: by using the strengths of deep learning, it offers a new way to predict pipeline settlement when building rectangular pipe jacking tunnels.]]></description>
      <pubDate>Mon, 03 Aug 2026 15:57:02 GMT</pubDate>
      <guid>https://trid.trb.org/View/2742451</guid>
    </item>
    <item>
      <title>Hybrid Particle Swarm Optimization and Machine Learning Framework for Enhanced Prediction of Ground Settlement during Rectangular Pipe Jacking</title>
      <link>https://trid.trb.org/View/2742446</link>
      <description><![CDATA[Accurate prediction of ground settlement induced by rectangular pipe jacking, a                     prevalent trenchless technology in urban infrastructure development, remains a                     significant challenge. This study addresses this by developing and evaluating a                     robust machine learning (ML) framework. Leveraging 104 sets of field monitoring                     data from the Liuye Avenue West Extension rectangular pipe jacking project in                     Hunan, China, key construction parameters including jacking force, advance rate,                     and grouting pressure were utilized as inputs to predict ground settlement. A                     Particle Swarm Optimization (PSO) algorithm was integrated for automated                     hyperparameter tuning of six distinct ML models: standalone Least Squares                     Support Vector Machine (LSSVM), Backpropagation Neural Network (BPNN), Random                     Forest (RF), and their respective PSO-optimized counterparts. Comprehensive                     performance evaluation using Mean Squared Error (MSE), Mean Absolute Error                     (MAE), and Coefficient of Determination (R^2) revealed that the                     PSO-LSSVM hybrid model achieved superior predictive accuracy and generalization                     capability. Specifically, on the test dataset, the PSO-LSSVM model yielded an                     MSE of 0.367, MAE of 0.424, and an R^2 of 0.941. These findings                     demonstrate that the proposed PSO-enhanced LSSVM model significantly outperforms                     baseline models, offering a highly effective and reliable tool for predicting                     ground deformation in similar complex pipe jacking projects.]]></description>
      <pubDate>Mon, 03 Aug 2026 15:57:02 GMT</pubDate>
      <guid>https://trid.trb.org/View/2742446</guid>
    </item>
  </channel>
</rss>