<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=PHNlYXJjaD48cGFyYW1zPjxwYXJhbSBuYW1lPSJzdWJqZWN0bG9naWMiIHZhbHVlPSJvciIgLz48cGFyYW0gbmFtZT0idGVybXNsb2dpYyIgdmFsdWU9Im9yIiAvPjxwYXJhbSBuYW1lPSJsb2NhdGlvbiIgdmFsdWU9IjAiIC8+PC9wYXJhbXM+PGZpbHRlcnM+PGZpbHRlciBmaWVsZD0ic2VyaWFsIiB2YWx1ZT0iJnF1b3Q7ZVRyYW5zcG9ydGF0aW9uJnF1b3Q7IiBvcmlnaW5hbF92YWx1ZT0iJnF1b3Q7ZVRyYW5zcG9ydGF0aW9uJnF1b3Q7IiAvPjwvZmlsdGVycz48cmFuZ2VzIC8+PHNvcnRzPjxzb3J0IGZpZWxkPSJwdWJsaXNoZWQiIG9yZGVyPSJkZXNjIiAvPjwvc29ydHM+PHBlcnNpc3RzPjxwZXJzaXN0IG5hbWU9InJhbmdldHlwZSIgdmFsdWU9InB1Ymxpc2hlZGRhdGUiIC8+PC9wZXJzaXN0cz48L3NlYXJjaD4=" 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>Bidirectional charge transfer between modules of a high-voltage storage for autonomous state of health estimation and preconditioning in vehicle applications</title>
      <link>https://trid.trb.org/View/2736777</link>
      <description><![CDATA[Accurate state of health (SoH) estimation in high-voltage storage (HVS) systems for battery electric vehicles (BEVs) can significantly reduce production and ownership costs. This cost-reduction potential arises because more precise SoH information enables manufacturers to minimize excess aging reserves installed to compensate for underestimated SoH, while still meeting regulatory warranty obligations over vehicle lifetime. However, conventional SoH estimation methods require external power supplies and lengthy measurement procedures. This study proposes a reconfigurable HVS architecture concept that enables autonomous SoH estimation during BEV standby periods without external power sources. By conducting all measurements during vehicle standby periods, the vehicle executes scheduled, reproducible diagnostic events throughout the vehicle lifetime. This increases estimation frequency, reduces SoH changes between diagnostic events, and thereby improves estimation accuracy and numerical convergence. The proposed HVS architecture concept dynamically switches between series, parallel, and split-series–parallel configurations of high-voltage modules (HVMs) to generate controlled voltage gradients. Generated inter-module currents are used for SoH estimation, while a DC/DC converter regulates current amplitudes. A developed proof-of-concept hardware test bench validates autonomous capacity-based SoH (SoH[subscript C]) estimation using degradation mode analysis methods, as well as resistance-based SoH (SoH[subscript R]) estimation via hybrid pulse power characterization (HPPC) and electrochemical impedance spectroscopy (EIS). Results reveal strong agreement between the test bench and potentiostat reference measurements. SoH[subscript C] estimations at 100%, 85%, and 70% show a mean absolute error (MAE) difference of 0.24 percentage points between the two systems. Corresponding SoH[subscript R] estimations yield MAE deviations of 1.65 percentage points for HPPC and 2.55 percentage points for EIS. Beyond diagnostics, the proposed concept also enables battery heating and balancing. A cost analysis indicates economic plausibility. If affected hardware costs increase by 6.5% while the SoH estimation error decreases by 50%, total HVS costs may be reduced by roughly $190 per vehicle over 160,000km.]]></description>
      <pubDate>Wed, 12 Aug 2026 14:59:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2736777</guid>
    </item>
    <item>
      <title>Analysis of Multi-Modal Energy Supply and Power Systems Adaptability for eVTOL and UAV Applications in the Low-Altitude Economy</title>
      <link>https://trid.trb.org/View/2736774</link>
      <description><![CDATA[The rapid growth of the low-altitude economy (LAE), driven by urban air mobility, aerial logistics, and emerging aviation services, underscores an urgent need for diversified and flexible energy supply solutions. The unique, highly dynamic energy demands and pronounced spatiotemporal load fluctuations of LAE applications also present unprecedented challenges to existing power systems. In response, this paper systematically explores the necessity and feasibility of multi-modal energy supply strategies to support large-scale and sustainable deployment of heterogeneous LAE aircraft--specifically electric vertical takeoff and landing vehicles and unmanned aerial vehicles--and analyzes their implications for power system adaptability. The study first characterizes the energy consumption profiles and load distribution patterns of key LAE scenarios, based on representative operational models, highlighting the distinctive spatiotemporal variability and stringent reliability requirements that set LAE aircraft loads apart from conventional urban and transportation loads. It then examines the core principles and implementation pathways of major multi-modal supply technologies, including wireless charging, fast wired charging, and battery swapping, highlighting their respective advantages and application contexts. Through simulation analysis of representative city clusters, the impacts of different supply modes on battery performance and lifespan, grid load, and LAE operational efficiency are evaluated, demonstrating how the multi-modal energy supply framework optimizes social, economic, and environmental benefits compared to single-mode strategies. Finally, the paper identifies the main barriers to large-scale deployment of LAE applications, discusses the prospects for emerging technologies, and offers targeted recommendations, providing a multidimensional theoretical and practical reference for building a future-oriented energy ecosystem for the low-altitude economy.]]></description>
      <pubDate>Wed, 12 Aug 2026 14:59:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2736774</guid>
    </item>
    <item>
      <title>Vehicle-level modeling of internal resistance degradation and influential parameter analysis in lithium-ion battery packs using real-world data</title>
      <link>https://trid.trb.org/View/2742926</link>
      <description><![CDATA[Battery internal resistance degradation is a critical indicator of battery aging in battery electric vehicles (BEVs), yet its progression under real-world operating conditions is not sufficiently understood. This study presents a data-driven framework for quantifying and analyzing vehicle-level internal resistance degradation using one year of high-resolution (1 Hz) operational data collected from 54 BEVs. Using real-world operational data, the proposed framework models internal resistance degradation as a function of battery throughput and temperature. It also introduces the Internal Resistance Degradation Index (IRDI) to quantify degradation rates under varying operating conditions. The proposed internal resistance degradation model achieved a high goodness-of-fit (adjusted R² =0.951) that demonstrates its capability to accurately characterize vehicle-level degradation trends. A stepwise regression model also was developed to identify the vehicle-level factors associated with the IRDI, achieving an adjusted R² of 0.965. The results indicate that average internal resistance is the strongest predictor of IRDI, followed by throughput intensity, cumulative cycling condition, and average vehicle speed. These findings suggest that internal resistance degradation is governed not only by the current degradation state of the battery but also by the intensity of battery utilization and operating conditions. The proposed framework provides a practical tool for assessing vehicle-level battery health and degradation diagnostics using real-world operational data and will offer valuable insights for battery lifecycle management and usage-aware battery management systems.]]></description>
      <pubDate>Tue, 11 Aug 2026 16:35:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2742926</guid>
    </item>
    <item>
      <title>Representative battery load profiles require dynamic modeling beyond electrical power</title>
      <link>https://trid.trb.org/View/2728133</link>
      <description><![CDATA[During the development of battery electric vehicles, engineers subject battery systems to dynamic power input benchmark profiles to estimate their behavior within varying boundary conditions. However, existing approaches typically neglect the coupled dynamics of other critical stressors, particularly state-of-charge and temperature. As these variables strongly influence battery degradation, current benchmark profiles lack the ability to faithfully reproduce realistic system behavior and degradation responses. To address this limitation, this study proposes a methodology for the synthesis and evaluation of multivariate load profiles that jointly incorporate dynamic power, state-of-charge, and temperature characteristics. We assess their representativity by quantifying the replication of downstream battery reactions using industry-level electrothermal system response and cell degradation simulation models. The results show that accurate representation of voltage-related states is critical for reproducing degradation behavior. The proposed profiles achieve high-fidelity replication of statistical system states and enable up to 100% accuracy in full cycle equivalents, SoHR, or service life at SoHC=70% within the boundaries of simulation. These findings highlight the importance of multivariate, dynamically coupled benchmark profiles and provide a systematic framework for developing representative test procedures with improved real-world validity.]]></description>
      <pubDate>Tue, 28 Jul 2026 11:07:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728133</guid>
    </item>
    <item>
      <title>Advanced Inorganic Phase Change Materials for Thermal Protection Strategy of Lithium-ion Batteries: From Material Modification to System Application</title>
      <link>https://trid.trb.org/View/2728130</link>
      <description><![CDATA[The widespread application of lithium-ion batteries (LIBs) is constrained by thermal safety issues, particularly thermal runaway (TR), driving the demand for advanced thermal protection strategies. Inorganic phase change materials (IPCMs), recognized for their inherent nonflammability and high energy storage density, have emerged as a promising cooling medium with higher safety for battery thermal management (BTM) and TR mitigation. The rapid evolution of IPCMs has created a growing need for summarising and assessing the emerging strategies for IPCM-based battery thermal protection. To fill this gap, this work provides a comprehensive and focused review of IPCM-based strategies for LIB, spanning from material designs to battery system validation and practical application. It first introduces a series of material-level modification approaches, including encapsulation, structural support, additive enhancement, and functional flexible design. It focuses on their roles in improving various properties and stability of IPCM, as well as evaluating their applicable scenarios and limitations. Subsequently, the practical application of IPCM-based BTM systems during normal battery operation is reviewed, highlighting their cooling performance in battery temperature and temperature differences. Meanwhile, some horizontal comparisons are also conducted to explore the relative advantages of IPCM. After that, a dual-stage thermal storage mechanism of IPCMs is deeply analysed and discussed. Their impressive performances in suppressing TR initiation and propagation are further reviewed. Finally, current challenges and future directions of IPCM’s practical deployment and system selection are discussed to guide the development of next-generation IPCM material modification and advanced battery thermal protection systems.]]></description>
      <pubDate>Tue, 28 Jul 2026 11:07:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728130</guid>
    </item>
    <item>
      <title>Revealing hidden plating dynamics: High-fidelity modeling of lithium plating and stripping across operating regimes</title>
      <link>https://trid.trb.org/View/2728127</link>
      <description><![CDATA[High-fidelity electrochemical models enable accurate estimation of internal states as well as the simulation of complex Li plating and Li stripping behaviors of lithium-ion batteries, making them valuable tools for developing fast-charging strategies and optimizing operations. However, the reliability of the model and its adaptability to varying operating conditions heavily depend on the accuracy of its parameters, some of which are extremely difficult to determine precisely. To address this issue, we propose a novel modeling and parameterization framework that leverages electrical Li plating detection test data under diverse operating conditions to identify parameters strongly correlated with Li plating and Li stripping behavior. By utilizing electrical testing data, this approach constructs a multi-objective global optimization framework that minimizes the errors of terminal voltage, differential voltage peak position, and capacity loss, achieving accurate identification of the key parameters in the Li plating and Li stripping model. The proposed framework is validated using a commercial LCO/graphite cell under a wide range of operating conditions, including different ambient temperatures, Li-plating-provoking charging current rates, and Li stripping discharging current rates. The simulation results show good agreement with the experimental data, demonstrating the reliability and physical consistency of the identified parameters and the effectiveness of the proposed parameterization framework under the investigated operating conditions. Furthermore, this study quantitatively analyzes the relationship between lithium plating irreversibility and operating conditions such as ambient temperature and charging current rate, revealing that the irreversibility rate is more strongly correlated with the severity of lithium plating, while temperature mainly influences irreversibility indirectly through its impact on the amount of plated lithium formed during charging.]]></description>
      <pubDate>Tue, 28 Jul 2026 11:07:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728127</guid>
    </item>
    <item>
      <title>The potential of differential voltage analysis and electrochemical impedance spectroscopy for electric vehicles based on real-world data</title>
      <link>https://trid.trb.org/View/2728126</link>
      <description><![CDATA[As electric vehicles (EVs) become increasingly popular, battery status determination, specifically state of health (SoH), is becoming essential for monitoring aging, estimating residual value, and providing battery insurance. While onboard diagnostic methods such as electrochemical impedance spectroscopy (EIS) and differential voltage analysis (DVA) offer significant potential for in-situ SoH estimation, it remains unclear how frequently these measurements can be performed under real-world operating conditions. This study analyzes data from seven series-production vehicles, totaling 169760km, to evaluate idle periods and charging behavior. By modeling the SoH evolution, the study determines the achievable update intervals for each method, assessing their practical applicability for continuous battery monitoring. The results demonstrate that EIS can be effectively applied during idle periods, enabling frequent updates of the battery’s health state. DVA, in contrast, is more constrained by access to charging infrastructure, the state of charge (SoC) range, and the C-rate, but provides additional insights into specific degradation modes. The results show that EIS can be applied frequently enough during idle periods to resolve even the highest observed degradation rates at 1% SoH resolution, providing on average 412 diagnostic opportunities per 10000km, whereas DVA is substantially constrained by charging behavior and SoC range, yielding only 81, roughly a fivefold reduction. Based on these findings, a hybrid strategy is recommended that combines frequent impedance-based monitoring with intermittent DVA for in-depth degradation mode (DM) analysis.]]></description>
      <pubDate>Tue, 28 Jul 2026 11:07:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728126</guid>
    </item>
    <item>
      <title>A Rapid Sorting Framework for Retired Lithium-Ion Batteries via Electrode-Level Aging State Diagnosis</title>
      <link>https://trid.trb.org/View/2728124</link>
      <description><![CDATA[The second-life utilization of retired lithium-ion batteries (LIBs) is critical to achieving global sustainability goals, yet prevailing industrial sorting strategies suffer from inherent limitations. Specifically, current methods rely on full-cell features, causing poor electrode-level aging consistency in reassembled packs and lacking fast, low-cost testing for economic viability. This study proposes a rapid sorting method tailored to the electrode-level aging pathways of retired LIBs, with the aim of guiding rational sorting based on electrode-level aging diagnosis. Concretely, LIB aging pathways are determined by estimating full-cell capacity, lithium inventory, and cathode/anode capacity via voltage curve fitting. Also, a mapping model library consisting of 1,260 models correlates rapid-test resistance features with the four aforementioned capacity metrics. Experiments show mechanism-derived features play a dominant role in capacity estimation, yielding high precision with an average R² of 0.9 and an optimal R² exceeding 0.95. Furthermore, the method enables targeted and accurate diagnosis of cathode and anode aging states that are consistent with the actual operational conditions of LIBs. Compared with conventional sorting strategies, the proposed approach significantly improves the intra-pack capacity consistency, reducing the cell-to-cell capacity variation by 19.9%, 16.1%, and 13.2% at discharge rates of 0.2C, 1C, and 2C, respectively. This work realizes rapid and accurate estimation of the electrode-level aging states of retired LIBs, enhances the consistency and reliability of recombined battery packs, and thus provides technical support for the industrialization of LIB second-life utilization.]]></description>
      <pubDate>Tue, 28 Jul 2026 11:07:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728124</guid>
    </item>
    <item>
      <title>Explainable state of health estimation of lithium-ion batteries with extremely minimal labels via weakly supervised learning</title>
      <link>https://trid.trb.org/View/2728087</link>
      <description><![CDATA[Machine-learning-based state of health (SOH) estimation methods often suffer from poor generalization owing to the scarcity of labels from field data, leading to inaccurate results and improper management of battery health when implemented in a battery management system. To address this challenge, this study proposes a weakly supervised learning (WSL) framework for battery SOH estimation that requires only a minimal number of labels. First, numerous SOH-related weak labels are generated from unlabeled dQ/dV curves by employing an electrochemical feature that characterizes the intensity of the predominant electrochemical reaction. Next, a weakly supervised pre-training technique is conducted on a deep neural network (DNN) to learn the battery aging information existed in these weak labeled data. Finally, the DNN is fine-tuned by using a limited number of labeled data to achieve accurate and robust SOH estimation. The proposed WSL framework demonstrates superior generalization capability in SOH estimation using only six labeled samples across diverse scenarios, covering 176 batteries and 320 electric vehicles with variations in cathode materials, capacity configurations, and operating conditions. Experimental validation shows the average root mean squared errors (RMSEs) of SOH estimations in within- and cross-dataset scenarios range from 0.51% to 1.86% and 0.5% to 2.7%, respectively. These results underscore the strong potential of the proposed WSL to overcome labeling bottlenecks across a wide range of battery materials and operating conditions.]]></description>
      <pubDate>Tue, 28 Jul 2026 11:07:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728087</guid>
    </item>
    <item>
      <title>A synergistic sequence–feature fusion framework for robust battery SOH estimation across real-world random charging profiles</title>
      <link>https://trid.trb.org/View/2728094</link>
      <description><![CDATA[Accurate State-of-Health (SOH) estimation is critical for the safety and economic management of large-scale battery systems. However, random and incomplete charging behaviors in the field degrade the accuracy of conventional models, which typically require fixed voltage windows or full charging cycles. To resolve this limitation, we present a universal SOH estimation framework based on a synergistic sequence–feature fusion architecture, by integrating a boundary-independent feature extraction protocol with a dual-stream neural network. Evaluated on a diverse dataset comprising 320,000 operational segments across six commercial cathode chemistries, including LFP, NMC, and LCO, the proposed method achieves a mean absolute error (MAE) of 1.69% and a minimum error of 1.06%, outperforming all the representative baseline models. Moreover, the error variation across different datasets is less than 1.6%, demonstrating robust cross-chemistry adaptability. This methodology provides a potential solution for intelligent battery management in real-world environments.]]></description>
      <pubDate>Tue, 28 Jul 2026 11:07:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728094</guid>
    </item>
    <item>
      <title>Electrical short-circuit behavior and temporary localized overcharge conditions during thermal runaway in lithium-ion battery packs</title>
      <link>https://trid.trb.org/View/2732549</link>
      <description><![CDATA[Thermal propagation remains a safety challenge for lithium-ion traction batteries in the growing electric-vehicle market. While mitigation strategies have largely focused on limiting thermal interactions between cells, electrical coupling effects during and after cell failure have received comparatively less systematic attention. This study examines electrical cell-to-cell interactions during thermal runaway using a three-module assembly containing cylindrical 21700 cells. To characterize the electrical response, row voltages and selected cell surface temperatures were recorded during thermal runaway. The measured voltage response indicates internally driven electrical redistribution through the parallel network during thermal runaway, influenced by the effective short-circuit resistance established in the trigger cell. The three-module experiments further indicate temporary overcharge conditions in modules connected in series to the failing module, with the corresponding cell groups temporarily exceeding their normal operating window. Dedicated single-cell nail-penetration tests revealed substantial variation in the effective post-failure short-circuit resistance, resulting in a wide range of estimated short-circuit currents and electrical loading within the investigated assembly. A simplified electrical model of the three-module assembly reproduced the measured redistribution trends and provided insight into the electrical behavior of individual cells within the assembly. Overall, the results provide experimentally supported insight into topology-dependent electrical redistribution and temporary localized overcharge conditions during thermal runaway under representative local module-level boundary conditions.]]></description>
      <pubDate>Mon, 27 Jul 2026 09:46:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2732549</guid>
    </item>
    <item>
      <title>Thermally responsive variable thermal conductivity phase change material for full lifecycle thermal safety of lithium-ion batteries</title>
      <link>https://trid.trb.org/View/2717937</link>
      <description><![CDATA[The conflicting thermal requirements of lithium-ion batteries, namely efficient heat dissipation during normal operation and effective thermal insulation under abuse conditions, remain a fundamental challenge for thermal safety management. Here, we develop a thermally responsive variable thermal conductivity phase change material (VTPCM) that enables adaptive regulation of heat transport across the battery lifecycle. The VTPCM is constructed by integrating directionally aligned graphite flakes and thermally expandable microspheres into a hydrated salt matrix through directional freezing, thereby forming a conductive network that can be thermally disrupted. At ambient temperature, the VTPCM exhibits a high thermal conductivity of 7.2 W·m−1·K−1, which sharply decreases to 0.046 W·m−1·K−1 above the triggering temperature (∼110 °C), corresponding to a switching ratio of 156.5. Meanwhile, it delivers a phase change enthalpy of 200.8 J·g−1 and a total heat absorption capacity of 1238 J ·g−1, with only 5.8% degradation after 200 thermal cycles. When applied to a ternary lithium-ion battery module, a 2 mm-thick VTPCM layer effectively reduces the peak operating temperature from 58.1 °C to 49.6 °C during charge-discharge cycling and improves temperature uniformity. Under thermal runaway conditions, it induces a prolonged temperature plateau in the adjacent battery and blocks thermal runaway propagation by reducing the heat transfer power from 3811.98 W to 96.51 W, achieving a suppression efficiency of 97.47%. This work demonstrates a practical material strategy for mitigating the long-standing conflict between battery thermal management and thermal safety.]]></description>
      <pubDate>Mon, 27 Jul 2026 09:46:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717937</guid>
    </item>
    <item>
      <title>High-temperature airflow as the master switch of thermal runaway propagation in large-format cylindrical batteries</title>
      <link>https://trid.trb.org/View/2717931</link>
      <description><![CDATA[Lithium-ion batteries (LIBs) release large amounts of high-temperature flammable gases during thermal runaway (TR). However, the influence of high-temperature airflow on thermal runaway propagation (TRP) within confined environments has not been systematically investigated. To elucidate this effect, comparative experiments were conducted on 46,950 LIB modules (4 × 5 array) under standard and isolated exhaust packaging. Under standard exhaust packaging, the module featured a single exhaust channel that enabled high-temperature airflow to propagate freely throughout the module. In contrast, the isolated exhaust packaging utilized multiple exhaust channels to effectively mitigate the influence of high-temperature airflow on adjacent cells. Two significant findings were obtained: 1) The TRP velocities under standard and isolated exhaust configurations were 0.172 ± 0.026 and 0.098 ± 0.015 cells/min, respectively, corresponding to a 43.0% reduction. Moreover, the average maximum module temperature decreased from 720.1 ± 33.1 °C to 655.6 ± 29.5 °C, corresponding to a reduction of 64.5 °C. These results demonstrate that a multi-channel exhaust configuration effectively mitigates the influence of high-temperature airflow. 2) The diffusion pathway of high-temperature airflow exerts a pronounced influence on the TRP trajectory. Under standard exhaust packaging, high-temperature airflow spreads uniformly toward adjacent cells, thereby promoting diagonal TRP. Conversely, under isolated exhaust packaging, high-temperature airflow primarily affects cells within the same channel, thereby suppressing diagonal TRP. This study highlights the pivotal role of high-temperature airflow in governing TRP and provides valuable insights for the safe design of next-generation energy storage systems.]]></description>
      <pubDate>Mon, 27 Jul 2026 09:46:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717931</guid>
    </item>
    <item>
      <title>AgentEMS: Integrating DRL and LLM-refined rules for hierarchical energy management of multi-stack fuel cell vehicles</title>
      <link>https://trid.trb.org/View/2717866</link>
      <description><![CDATA[Fuel cell electric vehicles (FCEVs) offer a promising pathway for decarbonizing transportation. Multi-stack FCEVs, in particular, provide the enhanced flexibility, redundancy, and scalability required for heavy-duty applications. However, their complex architecture introduces significant challenges for energy management. This paper proposes AgentEMS, a hierarchical energy management framework that explicitly decouples high-level decision-making from low-level control execution. The upper-level decision layer employs a deep reinforcement learning (DRL) agent to adaptively select optimal operating modes based on real-time driving conditions. The lower-level control layer then executes interpretable, rule-based power allocation strategies across the fuel cell stacks. To overcome the bottleneck of manual rule design, this framework integrates a large language model (LLM) as an offline rule synthesizer. A novel prompt engineering mechanism extracts structured control knowledge from dynamic programming optimal trajectories, guiding the LLM to automatically generate degradation-aware and energy-efficient control rules. By combining DRL adaptability with rule-based stability, AgentEMS ensures safe, interpretable real-time operation. Experimental results demonstrate enhanced system efficiency and significantly reduced fuel cell degradation. The proposed approach reduces fuel-cell degradation by more than 45% compared with conventional end-to-end DRL methods, indicating substantial potential for extending system lifetime.]]></description>
      <pubDate>Mon, 27 Jul 2026 09:46:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717866</guid>
    </item>
    <item>
      <title>Online state estimation of lithium-ion batteries using nonlinear ultrasonics with LSTM-based deep learning model</title>
      <link>https://trid.trb.org/View/2717862</link>
      <description><![CDATA[Accurate state-of-charge (SOC) estimation is essential for ensuring the safe and reliable operation of lithium-ion batteries. Linear ultrasonic features such as time-of-flight and signal amplitude have been widely investigated as indicators for battery state monitoring. However, these features mainly depend on second-order elastic constants, which may limit estimation accuracy. This study presents a nonlinear ultrasonic framework for accurate battery state estimation by combining bispectral analysis with a long short-term memory (LSTM) network. First, a theoretical relationship between the ultrasonic nonlinearity parameter and battery state is established based on elasticity theory. Next, ultrasonic measurements are performed using a through-transmission configuration. A modified ultrasonic nonlinearity parameter is extracted by applying bispectral analysis to the signals reconstructed by the LSTM network. The proposed framework achieves a SOC estimation error below 3% and improves estimation accuracy by a factor of 3.06 compared with linear ultrasonic features. Under C/2, 1C and 2C conditions, root mean squared errors (RMSE) of 3.1%, 2.4% and 2.9% are obtained, respectively. The results demonstrate that the proposed nonlinear ultrasonic framework improves battery state estimation accuracy.]]></description>
      <pubDate>Mon, 27 Jul 2026 09:46:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717862</guid>
    </item>
  </channel>
</rss>