<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=PHNlYXJjaD48cGFyYW1zPjxwYXJhbSBuYW1lPSJkYXRlaW4iIHZhbHVlPSJhbGwiIC8+PHBhcmFtIG5hbWU9InN1YmplY3Rsb2dpYyIgdmFsdWU9Im9yIiAvPjxwYXJhbSBuYW1lPSJ0ZXJtc2xvZ2ljIiB2YWx1ZT0ib3IiIC8+PHBhcmFtIG5hbWU9ImxvY2F0aW9uIiB2YWx1ZT0iMCIgLz48L3BhcmFtcz48ZmlsdGVycz48ZmlsdGVyIGZpZWxkPSJpbmRleHRlcm1zIiB2YWx1ZT0iJnF1b3Q7TGl0aGl1bSZxdW90OyIgb3JpZ2luYWxfdmFsdWU9IiZxdW90O0xpdGhpdW0mcXVvdDsiIC8+PC9maWx0ZXJzPjxyYW5nZXMgLz48c29ydHM+PHNvcnQgZmllbGQ9InB1Ymxpc2hlZCIgb3JkZXI9ImRlc2MiIC8+PC9zb3J0cz48cGVyc2lzdHM+PHBlcnNpc3QgbmFtZT0icmFuZ2V0eXBlIiB2YWx1ZT0icHVibGlzaGVkZGF0ZSIgLz48L3BlcnNpc3RzPjwvc2VhcmNoPg==" 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>An Interpretable Physics-Constrained Deep Operator Network for Battery Internal Temperature Estimation With Limited Data</title>
      <link>https://trid.trb.org/View/2659194</link>
      <description><![CDATA[Accurate internal temperature estimation is crucial for developing effective safety management strategies in battery energy storage systems (BESSs) and electric vehicles (EVs). Traditional model-based methods often suffer from complexities in model parameters, while data-driven approaches heavily rely on large amounts of training data and lack theoretical interpretability. To address these challenges, this article proposes an interpretable physics-constrained deep operator network (PC-DeepONet) for internal temperature estimation of batteries. By integrating data loss from DeepONet with physical loss from a lumped-thermal model, the network offers strong theoretical interpretability, aligning better with the underlying thermal dynamics and significantly reducing data dependence. Additionally, battery thermal model parameters are innovatively embedded into the network as trainable components and optimized via backpropagation (BP), enhancing the network’s adherence to physical constraints. To address the imbalance between the losses, a log dynamic weight averaging (LDWA) method is employed to reduce the scale disparity and dynamically balance the weights. The experimental results demonstrate that, despite using limited training data at 25 °C, the proposed method exhibits enhanced stability and higher accuracy under various operating conditions and different temperatures. Compared to traditional methods, the estimated root-mean-square error (RMSE) can be reduced by 59.5% at 0 °C and 35.9% at 40 °C, respectively.]]></description>
      <pubDate>Thu, 30 Apr 2026 11:28:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659194</guid>
    </item>
    <item>
      <title>Comprehensive Analysis of Charging Profile Dynamics for Lithium-Ion Battery Capacity Estimation</title>
      <link>https://trid.trb.org/View/2659108</link>
      <description><![CDATA[Lithium-ion battery safety and reliability rely on accurately monitoring its State of Health (SOH). Due to the complex nature of battery degradation processes, data-driven methods offer promise as an alternative to electrochemical and empirical models. Analyzing factors such as constant current charging time, constant voltage charging time, temperature changes, and the voltage difference between charging start and end points provides a comprehensive understanding of a battery's health. Using machine learning regression techniques (GPR, ARDRegressor, XGBoost and ANN), with RMSE = 0.02 ampere hour (Ahr) for multiple batteries, the discussed health indicators offer insights into the effects of cycling on battery behaviour. Notably, this work introduces log (𝑽ᴍᴀx ―𝑽ᴍᴀx) as a capacity prediction feature, which considers the impact of partial discharges in previous cycles on subsequent charging patterns. This addition enhances the model's realism by reflecting real-world scenarios where batteries seldom undergo complete discharge-charge cycles.]]></description>
      <pubDate>Wed, 29 Apr 2026 09:10:07 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659108</guid>
    </item>
    <item>
      <title>Research on the Repeatability of Thermal Runaway of Lithium-Ion
     Batteries Triggered by Heating Wires</title>
      <link>https://trid.trb.org/View/2681210</link>
      <description><![CDATA[Due to limitations in available battery samples and testing costs, lithium-ion                     battery thermal runaway experiments are not practical to repeat multiple times,                     and the reliability of experimental results is frequently questioned. To                     systematically evaluate the repeatability of the heating wire-triggered method                     in thermal runaway tests, this study investigates two types of commercial 18650                     cylindrical batteries with NCM/graphite chemistry under different heating power                     levels and health conditions. The results indicate that under the same heating                     power, batteries of the same type exhibit good repeatability in thermal runaway                     onset time and onset temperature, with the consistency of onset time                     outperforming that of onset temperature. As the heating power increases, the                     onset time of thermal runaway decreases significantly, while the variation in                     onset temperature remains relatively small. Compared to fresh batteries, aged                     batteries show reduced variability in thermal runaway characteristics, with                     standard deviations in onset time generally below 7 s, the range is less than 15                     s, indicating improved repeatability. The heating wire-triggered method                     demonstrates stable and reliable repeatability under different power levels and                     aging states. This study provides critical data and technical references for the                     standardization of lithium-ion battery thermal runaway testing, offering                     valuable engineering guidance for battery safety assessment.]]></description>
      <pubDate>Mon, 27 Apr 2026 15:01:13 GMT</pubDate>
      <guid>https://trid.trb.org/View/2681210</guid>
    </item>
    <item>
      <title>Elucidating Internal Explosion Dynamics in Lithium-Ion Batteries: From Experimental Analysis to Theoretical Modeling</title>
      <link>https://trid.trb.org/View/2694684</link>
      <description><![CDATA[The explosion risk inherent in high-energy-density and large-scale batteries remains a significant barrier to their widespread deployment in energy storage and transportation systems. Within an individual cell, thermal runaway generates both solid and gaseous reaction fronts, the dynamic behaviors of which have been partially characterized in prior studies. The rapid propagation of these thermal runaway fronts through narrow gas channels between electrodes can trigger internal explosions. This study develops a comprehensive mathematical model to describe the internal dynamics of batteries during thermal runaway, derived from experimental observations and quantitative data, to establish boundary conditions for explosion initiation. Explosion phenomena were systematically examined in various types of cells, with experimentally measured gas explosion limits ranging from approximately 5.39% to 47.5%. By drawing an analogy with the deflagration-to-detonation transition, a hypothesis of thermal runaway front-induced detonation was proposed and mathematically formulated. A velocity expression for the thermal runaway gas front was derived, showing that its propagation speed is material-dependent—directly proportional to the gas generation rate and the velocity of the solid front, and inversely proportional to the width of the gas channel. Based on this formulation, boundary conditions for internal detonation were established. For high-energy-density and large-format batteries, the calculated Mach numbers of the solid front, gas front, and exhaust gas at the safety valve may exceed 1, indicating the potential for detonation. These results confirm the feasibility of internal detonation and provide a quantitative criterion for evaluating explosion risks. The proposed framework is applicable to various battery chemistries and offers theoretical guidance for the safety design of next generation high energy batteries.]]></description>
      <pubDate>Mon, 27 Apr 2026 14:58:15 GMT</pubDate>
      <guid>https://trid.trb.org/View/2694684</guid>
    </item>
    <item>
      <title>Simulation of Hybrid Fuel Cell-Battery Propulsion System Scrutinizing Multi-scheme Energy Management for a CTV Boat</title>
      <link>https://trid.trb.org/View/2580018</link>
      <description><![CDATA[This paper proposes a model of a hybrid fuel cell-battery propulsion system for a Crew Transfer Vessel (CTV). A multi-scheme energy management strategy is also applied to the Energy Management Strategies (EMS) block to optimize energy flow. A fuel cell-battery hybrid system was developed by integrating proton exchange membrane (PEM) fuel cells with Li-ion batteries to provide electricity to the propeller propulsion system, and hotel load. Accordingly, a hybrid battery/fuel cell propulsion system with the capability of both charging the battery at both stations and bunkering the fuel tanks will be proposed. During cruising, docking, stopping, accelerating, and loitering phases of a ship journey, power distribution will be carried out, and energy requirements will be investigated at different EMS strategies with the objective of maximising system efficiency. A simulation using MATLAB/Simulink software is conducted using operational profiles at different power load conditions. Simulation is conducted using four EMS schemes: state-based, equivalent fuel consumption minimization strategy (ECMS), a charge-depleting and charge-sustaining strategy (CDCS), and classical proportional-integral (PI) controller-based, which are all selected based on power mode and battery SOC. Results show proposed multi-scheme strategy can lead to significant energy and cost savings, with a maximum of 4% and 12% respectively.]]></description>
      <pubDate>Mon, 27 Apr 2026 14:55:47 GMT</pubDate>
      <guid>https://trid.trb.org/View/2580018</guid>
    </item>
    <item>
      <title>Intelligent Power Sharing by Battery and Ultracapacitor in Regular Routes of EV</title>
      <link>https://trid.trb.org/View/2659188</link>
      <description><![CDATA[Nowadays, hybrid energy storage system (HESS) is widely used in high-performance vehicles to fulfill the instant power requirement. Such kind of energy storage system (ESS) can become extremely useful for electric vehicles (EVs) driving in hilly regions. However, maintaining the state-of-charge (SoC) of the ultracapacitor (UC) during aggressive driving conditions is still a challenge and requires a reliable mechanism. In this context, this article employs artificial intelligence (AI) and its capability to predict the present and future requirements of the UC current. In the proposed method, the artificial neural network (ANN) model is trained using regular route driving data to generate a reference of transient current during EV traction. Further, the model charges the UC during the deceleration of the EV as per the predicted future current requirement. It has been modeled and simulated in MATLAB/Simulink considering the actual data of the vehicle. The hardware prototype consists of a 51.2 V, 86 Ah Li-ion battery, and 19.3 F, 51 V UC integrated with 48 V, 48 A, 3 kW IPMSM setup. In the developed driving cycle, velocity and road slope vary along the direction of traction and braking. The experimental results show that the battery energy utilization is 13.13% less in the ANN-based method as compared to the rule-based method. Additionally, the peak battery current is reduced by 26.6% and the battery power has a minimum standard deviation in the ANN-based method as compared to the battery-only method. As a result, the battery state-of-health (SoH) improves by 21.43% which leads to 2.71 years of battery lifetime enhancement in regular routes of driving.]]></description>
      <pubDate>Thu, 23 Apr 2026 13:54:25 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659188</guid>
    </item>
    <item>
      <title>Assessing Electrochemical Energy Storage Technologies for Waterborne Transport Systems</title>
      <link>https://trid.trb.org/View/2580012</link>
      <description><![CDATA[Electrochemical energy storage technologies play a key role in wide adoption of electric waterborne transport systems. Currently, lithium-ion (Li-ion) is the leading battery technology in electric and hybrid maritime applications. However, specific operational requirements such as power peaks and long sailing distances remain a concern with respect to typical Li-ion batteries, mainly due to the limitations in terms of energy and power density as well as safety. While batteries used in most of marine applications are based on established Li-ion technologies, other mature storage technologies such as supercapacitors could be suitable for waterborne applications. Additionally, the next generation battery technologies such as solid-state batteries show promise for addressing some limitations of Li-ion batteries. These alternative technologies have the potential to transform the landscape of electric marine transport systems. Focusing on waterborne transport systems, this paper provides a review and a comparative analysis of common Li-ion batteries. Additionally, the alternative electrochemical energy storage technologies including supercapacitor and solid-state batteries are investigated and compared to Li-ion batteries. This research provides valuable insights into the advancements and prospects of electrochemical energy storage system for waterborne transport systems.]]></description>
      <pubDate>Thu, 23 Apr 2026 09:11:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2580012</guid>
    </item>
    <item>
      <title>DCFC Strategies for Automotive Li-ion Cells: Non Disruptive Electrochemical Analysis and Post-mortem Raman Characterization</title>
      <link>https://trid.trb.org/View/2580001</link>
      <description><![CDATA[The shift towards E-mobility transportation represents an important step to guarantee an ecological and energetic transition. To have a good market penetration of electric vehicles, however, we must consider the needs of consumers, who demand short charging times and a long battery life. The study and design of DCFC (direct current fast charging) profiles is fundamental to achieve this goal. In a previous work, new DCFC profiles based on Multi Stage Constant Current (MSCC) charge step were proposed. The new profiles have been designed with the aim of providing a fast charge that avoids the conditions in which the cell incurs in lithium plating. In this work the results of two characterization techniques are presented: Electrochemical Impedance and Raman Spectroscopies. The first confirms the advantage of using the customized profiles, without dismantling the cell, while the second confirms the absence of Li plating on the anode surface, after the teardown.]]></description>
      <pubDate>Thu, 23 Apr 2026 09:11:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2580001</guid>
    </item>
    <item>
      <title>Enhanced Battery Health Estimation Using a Multikernel ARD-GPR Framework With Bayesian Optimization for Li-Ion Batteries</title>
      <link>https://trid.trb.org/View/2659185</link>
      <description><![CDATA[The estimation of battery aging plays a crucial role in electric vehicle applications. Currently, battery health status, including capacity estimation, has attracted extensive research and innovation. Gaussian process regression (GPR) is a prominent nonparametric modeling approach that can be used to evaluate battery degradation mechanisms while quantifying uncertainty. The kernel functions of GPR and their related length-scale parameters are relatively sensitive to the input distribution. However, they are often fixed during GPR applications, which may not be suitable for the battery’s dynamic circumstances. In this study, an automatic relevance determination (ARD)-based GPR with a constructed kernel function is proposed to ensure the estimation performs as promised, where the ARD is applied to capture five health indicators (HIs) during the battery charging–discharging process. Through Bayesian optimization (BO) for the parameter identifications for varying time windows, the estimated multiple-dimensional length scales of ARD-GPR show the dependence of the degradation process during the various phases. According to the cross-validation results under a complex environment, the proposed multikernel ARD-GPR can provide a precise estimation for experimental battery cells with an average root-mean-square error (RMSE) of 0.0195, which is 30.4% lower than the conventional methods. Moreover, the proposed multikernel ARD-GPR locates the degradation level by attributing the variation of ARD length scales under various battery degradation circumstances, which can offer an insight into the battery degradation mechanism.]]></description>
      <pubDate>Wed, 22 Apr 2026 14:04:05 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659185</guid>
    </item>
    <item>
      <title>A Novel High-Efficiency Multisource Inverter for Integrating Hybrid Energy Storage Systems in Electric Vehicle Applications</title>
      <link>https://trid.trb.org/View/2659180</link>
      <description><![CDATA[In this article, a novel multisource inverter (MSI) topology for hybrid energy storage systems (HESSs) in electric vehicle (EV) applications is proposed. An HESS in EV applications combines battery packs with ultracapacitors (UCs) to enhance the overall performance. This integration leverages the complementary characteristics of both technologies in which batteries provide high energy density for long-range operation, while UCs offer high power density for rapid charging and discharging during acceleration, regenerative braking, and other high-power events. The proposed topology enables the combination of all possible dc sources with fewer semiconductor components, thereby optimizing cost, weight, complexity, and power density due to the elimination of the magnetic elements from the circuit. Hence, an energy management system (EMS) is necessary to manage the energy between dc sources. Simulation and experimental results demonstrate that the proposed MSI topology achieves high efficiency, and the proposed EMS can control the system properly under various operating conditions. The proposed MSI offers higher efficiency in all modes of operations up to 1.85% compared with those existing MSIs that can produce all dc source combinations. Furthermore, the proposed topology can enhance the performance and reliability of the ac side loads by utilizing multiple energy storage sources simultaneously, thus improving energy utilization and reducing the dependence on a single energy source aiming to optimize energy efficiency, extend battery life, improve vehicle performance, and potentially reduce the overall size and cost if the energy storage system in EVs.]]></description>
      <pubDate>Wed, 22 Apr 2026 14:04:04 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659180</guid>
    </item>
    <item>
      <title>Developing Sulfide Based Solid State Battery with High Energy Density for Automotive Applications</title>
      <link>https://trid.trb.org/View/2579984</link>
      <description><![CDATA[The overall aim of the SUBLIME (Solid state sUlfide Based LI-MEtal batteries for electric vehicle (EV) applications) project is to respond to the further battery development challenges for EVs and produce next-generation solid-state batteries (SSB) with extreme high energy density of up to 450 Wh/kg as compared to 250–280 Wh/kg for conventional cells to double the driving range of electrical vehicles. The SUBLIME cell consists of a sulfide solid electrolyte (SE), Li metal anode and high nickel content cathode (NMC based). Up to now, we have overcome several challenges of this technology. The sulfide SE has been produced in kilogram scale with high ionic conductivity of 2.5 mS/cm at 25 ℃ and specific cathode and Li metal anode were developed for SSB application. The quality of the developed materials was confirmed in coin cell format, delivering a capacity of 195 mAh/g at 25 ℃. Next, we have been focusing on producing mono and multilayer pouch cells based on scalable process and optimizing the interfacial resistances between the cell components. For this purpose, coatings are applied on Li metal anode and cathode active material. The initial testing results of the pouch cells demonstrate the potential of this technology.]]></description>
      <pubDate>Tue, 21 Apr 2026 16:23:47 GMT</pubDate>
      <guid>https://trid.trb.org/View/2579984</guid>
    </item>
    <item>
      <title>State-of-Health Estimation of Lithium Titanate Batteries Under Locomotive Conditions With Meta-Learning Based on Long Short-Term Memory Network</title>
      <link>https://trid.trb.org/View/2659177</link>
      <description><![CDATA[Accurate state-of-health (SOH) estimation of lithium titanate batteries as power sources is essential for the safe operation of locomotives. The existing achievements few focus on the SOH of lithium titanate batteries under locomotive operating conditions. This article explores a novel meta-learning based on a long short-term memory (LSTM) network to estimate the SOH of lithium titanate batteries under locomotive varying conditions. First, the simulated operating condition of locomotives is designed. Then, among the various health indicators (HIs) that affect the accuracy of SOH estimation, three key indicators are selected. Further, the meta-learning based on LSTM (Meta-LSTM) network is proposed, where the meta-learning performance is independent of the similarity between the pretrained and target data. Experimental results reveal that the selected HIs are suitable for characterizing the decay of lithium titanate batteries. Based on the CALCE public dataset, designed 5C full charge–discharge experimental data and simulated locomotive operating condition data, the results show that the accuracy of SOH estimation is enhanced based on Meta-LSTM, especially in small sample scenarios, when the training set to test set ratio is 1:9 and 2:8, the root mean square error (RMSE) is 2.33% and 3.58%, respectively, demonstrating the effectiveness of Meta-LSTM for lithium titanate batteries under locomotive conditions.]]></description>
      <pubDate>Mon, 20 Apr 2026 09:24:40 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659177</guid>
    </item>
    <item>
      <title>A Federated Transfer Learning Framework for Lithium-Ion Battery State of Health Estimation Based on Fast-Charging Segments</title>
      <link>https://trid.trb.org/View/2659171</link>
      <description><![CDATA[Accurately estimating the state of health (SOH) of lithium-ion batteries (LIBs) using limited segments of fast-charging data is essential for effective battery management in electric vehicles (EVs). However, the task is complicated by two main challenges: insufficient training data from each target battery, requiring personalized models; and privacy risks associated with centralized data aggregation. To address these issues, this work proposes a two-stage federated transfer learning (TL) framework. In the first stage, federated learning (FL) enables multiple distributed batteries to collaboratively train a global model by sharing only model parameters, preserving privacy while learning generalized knowledge. In the second stage, this global model is fine-tuned using a small amount of local data from the target battery, resulting in a personalized model that captures individual battery characteristics. The framework is built on a lightweight convolutional neural network (CNN) enhanced with an efficient channel attention (ECA) mechanism, enabling accurate mapping from fast-charging segments to SOH values. Experimental results on a public fast-charging battery dataset show that the proposed method significantly outperforms both local-only models and conventional FL approaches without personalization. It achieves a root-mean-square error (RMSE) of just 1.13%, demonstrating its effectiveness in accurately predicting SOH, preserving privacy, and potential for real-world battery management systems.]]></description>
      <pubDate>Mon, 20 Apr 2026 09:24:40 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659171</guid>
    </item>
    <item>
      <title>ShotAdpt: Few-Shot Early Prediction of Battery Cycle Life With Adaptive Feature Reduction</title>
      <link>https://trid.trb.org/View/2659170</link>
      <description><![CDATA[Accurate cycle life prediction of lithium-ion batteries using early-cycle data significantly enhances the safety, manufacturing, utilization, and development of batteries. However, existing methods are data-intensive and, therefore, face the challenge of sample scarcity under unseen operating conditions. Additionally, these methods require an operating-condition-specific feature reduction step to train the predictor, which leads to a generalization gap across unseen conditions. To address these issues, ShotAdpt is proposed as the first few-shot learning (FSL) framework that employs task-oriented adaptive feature reduction for early prediction of battery cycle life under unseen conditions with limited samples. It employs a meta-learning method to jointly optimize both feature reduction and prediction tasks, which is compatible with any gradient-based learning model. Extensive experimental results on a real battery dataset demonstrate ShotAdpt’s effectiveness in early prediction under unseen conditions, using only data from the first 100 cycles. Compared to state-of-the-art methods, ShotAdpt reduces the mean testing means absolute percentage error (MAPE) and root mean square error (RMSE) by factors of 13.04 and 12.69, respectively. Meanwhile, it maintains robust generalization performance across different unseen conditions and selected feature numbers. Furthermore, ShotAdpt achieves comparable prediction performance using only the first five cycles of data, whereas state-of-the-art methods require 100 cycles, demonstrating its potential for practical applications.]]></description>
      <pubDate>Thu, 16 Apr 2026 13:54:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659170</guid>
    </item>
    <item>
      <title>Efficient physics-based modeling and experimental validation of parallel-connected battery cells enabled by the transmission line model</title>
      <link>https://trid.trb.org/View/2684268</link>
      <description><![CDATA[Battery modules composed of parallel-connected cells are commonly used as building blocks of battery packs, but their behavior is complex due to cell dynamics, as well as cell-to-cell heterogeneities and interactions. Furthermore, their simulation by means of empirical equivalent circuit models poses limitations because of lack of generalization, whereas electrochemical models lead to a challenging calculation of the current distribution. In this article, an electrically consistent method for the calculation of the equivalent voltage and resistance of a cell is presented according to the physically motivated discrete transmission line model. This enables the efficient computation of output voltage and current distribution for parallel-connected cells while providing interpretable physical information about the operation at each level. The presented approach is validated experimentally against a dataset of a 4P module in which interconnection resistance, ambient temperature, and the presence of an aged cell are considered as input parameters, with accurate and consistent results for module voltage (≤20 mV RMS) and current distribution (≤4.4% RMS). Moreover, the proposed framework exhibits higher computational efficiency and comparable scalability in relation to established approaches, while providing improved consistency between module-level behavior and cell-level dynamics. Therefore, the proposed method based on the transmission line model and hierarchical simplification is a suitable alternative for the physically motivated simulation and analysis of battery modules.]]></description>
      <pubDate>Wed, 15 Apr 2026 10:30:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2684268</guid>
    </item>
  </channel>
</rss>