<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>Inverse Topology Optimization of Sense-in-Energy Microdevices via Physics-Informed AI</title>
      <link>https://trid.trb.org/View/2732003</link>
      <description><![CDATA[For wide-threshold impact sensing, Sense-in-Energy (SiE) microdevices must simultaneously achieve reliable triggering, identifiable voltage output, and low energy loss under different loading conditions. However, a strong nonlinear relationship exists between cantilever-beam topology and the coupled electrochemical-fluid-solid response, making on-demand inverse generation difficult using conventional empirical design and parameter iteration. Here, the authors propose a physics-informed conditional variational autoencoder (PI-CVAE) framework for inverse cantilever-beam topology design. The cantilever topology is represented by an 11 x 18 binary matrix, and the loss function incorporates a BFS connectivity criterion, a span penalty, and a target-stiffness matching mechanism to reduce topology fracture, insufficient geometric span, and physical-property mismatch. In this study, the structural generation success rate is defined as the physically valid structural generation rate, namely the proportion of generated structures that simultaneously satisfy main-body connectivity, absence of isolated material cells, and the equivalent-stiffness interval required for the corresponding low-g, medium-g, or high-g scenario. In the low-g scenario, PI-CVAE improves this rate by approximately 18 percentage points compared with an ordinary CVAE without physics-informed components. After the equivalent-stiffness triggering intervals for low-g, medium-g, and high-g scenarios are established, the model can directly generate cantilever-beam topologies according to target threshold, voltage-amplitude, and energy-loss conditions. Simulation results show that the optimized structures increase voltage amplitude by up to 47% and reduce energy loss by up to 42%. Multi-g impact experiments show that the measured voltage waveforms of the optimized devices are consistent with simulation predictions in their main trends, with a maximum voltage-amplitude error of approximately 9%, and that ineffective energy consumption is reduced. This study provides an efficient intelligent design tool for the development of SiE devices and demonstrates the generalization capability and engineering potential of this intelligent design method under diverse operating conditions.]]></description>
      <pubDate>Fri, 21 Aug 2026 14:01:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2732003</guid>
    </item>
    <item>
      <title>Multi-Domain Physics-Informed Machine Learning Based Real-Time Digital-Twin Emulation for a Hydrogen-Powered Maglev Transportation System</title>
      <link>https://trid.trb.org/View/2720123</link>
      <description><![CDATA[Hydrogen-powered maglev trains (HPMLT) are increasingly regarded as promising candidates for next-generation clean rail transportation, owing to their low emissions, potentially reduced maintenance demands, and enhanced operational robustness. However, HPMLT systems exhibit strongly coupled dynamics across the electrical, mechanical, magnetic, and chemical domains, while also involving multi-time-scale behavior arising from the interaction between fast LIM electrical dynamics and comparatively slower magnetic, mechanical, and fuel-cell-related processes. Conventional electromagnetic transient simulations (EMT), predominantly based on numerical integration of detailed physics-based formulations, can become prohibitively time-consuming when confronted with nonlinear multi-domain interactions and fast transients, and may struggle to faithfully preserve cross-domain coupling effects under real-time constraints. To address these limitations, this paper develops a multi-domain, physics-informed real-time digital-twin for an HPMLT system. The proposed approach integrates multi-domain physical constraints grounded in high-fidelity simulation evidence from an Ansys Maxwell finite-element (FE) model and a MATLAB EMT model directly into a physics-informed neural network (PINN) architecture, and subsequently deploys the resulting model on a Xilinx® UltraScale+ VCU118 FPGA platform. Results show that the proposed framework reduces on-chip model-update latency by approximately 57% compared with conventional serial TZR-based approaches, achieving a full HPMLT update in 1.15 s for a 100 s simulation time step. The proposed PINN models maintain mean percentage absolute error below 2% across the considered subsystems, while the PEMFC model exhibits discrepancy below 1% over the investigated operating range. These results demonstrate that the proposed multi-domain PINN-based RTDT provides an effective balance among fidelity, robustness, and deterministic low-latency performance for real-time emulation of strongly coupled HPMLT systems.]]></description>
      <pubDate>Fri, 21 Aug 2026 14:01:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2720123</guid>
    </item>
    <item>
      <title>Integrated Framework for SOH Estimation of Lithium-Ion Batteries Under Capacity Heterogeneity in Real-World Fleets</title>
      <link>https://trid.trb.org/View/2717095</link>
      <description><![CDATA[In real-world driving conditions, onboard state-of-health (SOH) estimation for lithium-ion batteries faces three major challenges: (1) most operational data lack accurate capacity labels, limiting their usefulness for supervised learning; (2) labels derived from ampere-hour integration are highly sensitive to operating conditions and measurement errors; and (3) vehicle-side observable features often exhibit weak mechanistic relevance and limited comparability across battery platforms with different nominal capacities. To address these issues, this study proposes a unified SOH estimation framework tailored for low-confidence fleet data. The method first calibrates capacity labels through SOC linearization, temperature/current-rate correction, and robust constraints, converting low-confidence operational segments into more reliable supervision. A multi-level feature system is then constructed by coupling dimensionless statistical descriptors with mechanism-based indicators, including incremental capacity (IC) peaks and relaxation signatures, thereby strengthening feature–SOH associations and improving robustness under capacity heterogeneity. Because IC and relaxation information cannot be extracted for every charging event, explicit binary masks and time-since-last-measurement variables are introduced so that models can down-weight stale or missing mechanistic features while still utilizing them when available. Based on the calibrated labels and unified feature representation, multiple representative models, including Informer, Autoformer, TCN, LSTM, N-BEATS, CNN, MLP, SVR, and XGBoost, are systematically benchmarked under a common evaluation protocol. The outputs of selected base models are further combined through a simple averaging ensemble, which exploits complementary error patterns to improve prediction stability without increasing model complexity. Evaluation using a three-year dataset from 300 vehicles with 155 Ah batteries and a limited 180 Ah cross-capacity validation setting provides preliminary evidence of applicability under capacity heterogeneity. On the 155 Ah fleet, the ensemble model achieves a fleet-level MAE of 1.11% and a MAPE of 1.31%, while the predicted end-of-life SOH of the held-out 180 Ah test vehicle remains close to the measured value.]]></description>
      <pubDate>Fri, 21 Aug 2026 14:01:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717095</guid>
    </item>
    <item>
      <title>The application of perovskite-based tandem solar cells in near-space: A perspective</title>
      <link>https://trid.trb.org/View/2717093</link>
      <description><![CDATA[Near-space platforms operating at altitudes of 20∼100 km impose strict requirements on photovoltaic power systems, including lightweight, flexibility, and long-term stability under ultraviolet irradiation, high-energy particle flux, low pressure, and severe thermal cycling. Under these demanding conditions, perovskite-based tandem solar cells (Pero-based TSCs) have emerged as a highly promising solution, owing to their outstanding optoelectronic properties and record power conversion efficiencies (PCEs) approaching 35%. In this review, the authors first outline the near-space environmental conditions and corresponding performance requirements for photovoltaic devices. The authors then highlight the key advantages of Pero-based TSCs for near-space applications, including their high power-to-weight ratio (PWR, over 6 W/g), flexible design compatible with curved airframes, favorable performance at different temperatures, and inherent tolerance to radiation-induced defects. Subsequently, the major challenges are discussed, such as multiscale system optimization under near-space environments, thermal-cycling-induced degradation of tandem devices, the need for lightweight yet radiation-resistant encapsulation, and limited reverse-bias tolerance under nonuniform illumination. Finally, potential solutions are discussed, with emphasis on multi-physics simulation, suppression of defects and ion migration, advanced encapsulation, and reverse-bias mitigation. Overall, this review provides insights into the development of high-efficiency and stable Pero-based TSCs for reliable power systems for near-space applications.]]></description>
      <pubDate>Fri, 21 Aug 2026 14:01:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717093</guid>
    </item>
    <item>
      <title>A World Model-Based Architecture for Reasoning About Vehicle Reactions to Achieve Proactive Rear-End Collision Avoidance</title>
      <link>https://trid.trb.org/View/2711947</link>
      <description><![CDATA[Autonomous Vehicles (AVs) currently face a significantly higher risk of being rear-ended by Human-Driven Vehicles (HDVs) compared to conventional vehicles—approximately 1.6 times higher. This vulnerability largely stems from the prevailing unilateral decision-making paradigm, which predicts surrounding traffic behaviors independently of the AV’s actions, thereby neglecting the reciprocal interplay between the AV and following HDVs. Consequently, AVs may execute maneuvers that are technically feasible but unexpected or hazardous for nearby human drivers, which can increase rear-end collision risk in high-interaction scenarios. To bridge this gap, this study proposes a World Model-based architecture designed to explicitly reason about these reactive behaviors. First, a World Model is established to learn environmental dynamics, enabling continuous inference of how HDVs react to specific AV actions. Second, a planner based on the Actor-Critic architecture is developed and trained entirely within this World Model, facilitating the learning of farsighted, closed-loop interaction policies. This architecture is implemented in a novel longitudinal control method, named ThinkACC, and tested in high-interaction platoon scenarios. Compared to baseline Adaptive Cruise Control (ACC) system, ThinkACC achieves an 86.8% reduction in rear-end collisions while maintaining high levels of comfort and efficiency. In particular, the agent emerges with human-like defensive driving behaviors, such as proactively accelerating to mitigate risks of rearward collision. These findings demonstrate the capability of World Models to reason about bidirectional interactions, offering a viable path for enhancing AVs safety and generalization in mixed traffic environments.]]></description>
      <pubDate>Fri, 26 Jun 2026 13:59:51 GMT</pubDate>
      <guid>https://trid.trb.org/View/2711947</guid>
    </item>
    <item>
      <title>Learning Safety-Critical Scenarios from Real-World Pre-Crash Data for Autonomous Driving Safety Validation</title>
      <link>https://trid.trb.org/View/2711945</link>
      <description><![CDATA[A major challenge in Autonomous Vehicle (AV) safety validation is the scarcity of safety-critical interactions and the difficulty of modeling their underlying decision dynamics. The authors propose CrashGAIL, a conditional adversarial imitation learning framework that learns interaction-conditioned policies from real-world pre-crash trajectories and synthesizes high-risk two-vehicle scenarios under four interpretable motion-direction conditions. CrashGAIL combines (i) a dual-agent conditional policy architecture, (ii) a VAE warm-up for stabilizing latent representations, and (iii) an auxiliary condition-classification head to improve condition-behavior consistency, followed by PPO-based adversarial policy optimization. Experiments on 816 in-depth crash cases show improved kinematic fidelity while maintaining realistic geometric diversity compared with a strong time-series generative baseline. In counterfactual simulation with the Baidu Apollo stack, CrashGAIL-generated scenarios yield a higher overall crash involvement rate and expose failure modes that are less visible under replay-based testing.]]></description>
      <pubDate>Fri, 26 Jun 2026 13:59:51 GMT</pubDate>
      <guid>https://trid.trb.org/View/2711945</guid>
    </item>
    <item>
      <title>Cross-Domain Electrochemical Impedance Spectroscopy Reconstruction for PEMFC Aging Characterization: A Time-Frequency PINN Framework with ECM Priors</title>
      <link>https://trid.trb.org/View/2711943</link>
      <description><![CDATA[Proton exchange membrane fuel cells (PEMFCs) hold strong prospects due to their high efficiency and low emissions; however, in engineering operation, electrochemical impedance spectroscopy (EIS) is typically discretely acquired and data-scarce, and a reliable mapping from time-domain operational data to frequency-domain EIS is still lacking, which hinders characterization and tracking of the continuous spectral evolution with aging. To address this gap, the authors propose a time–frequency joint learning framework, termed Physics ECM Informed Neural Network (PEINN), which integrates an equivalent circuit model (ECM) to learn a cross-domain mapping from operational time-series representations to impedance spectra, enabling frequency-domain regression and reconstruction of EIS and comparative analysis of spectral evolution across aging stages. Using only 40% of the data for training, PEINN achieves R2>0.99, demonstrating strong potential for health-state assessment. Cross-dataset validation on additional PEMFC datasets further shows stable predictive performance, confirming good generalization and robustness. Moreover, within the proposed time–frequency aging characterization framework, the authors combine the frequency-domain evolution of the predicted EIS with peak-feature verification in the distribution of relaxation times (DRT) time-constant domain, enabling decoupled identification and interpretation of dominant processes such as charge-transfer deterioration and aggravated mass-transport limitation, thereby providing an explainable basis for health assessment and degradation inference.]]></description>
      <pubDate>Fri, 26 Jun 2026 13:59:51 GMT</pubDate>
      <guid>https://trid.trb.org/View/2711943</guid>
    </item>
    <item>
      <title>State of Charge Prediction for Electric Aircraft Lithium-Ion Batteries with Limited Data by Stochastic Quantization and Informer Network</title>
      <link>https://trid.trb.org/View/2711942</link>
      <description><![CDATA[With the ongoing global energy transition, new energy electric aircraft offer a promising technological pathway for achieving green aviation. As the core power source of electric aircraft, lithium-ion batteries have their state of charge (SOC) as one of the most critical parameters throughout the battery lifecycle. Accurate SOC estimation directly impacts flight endurance, performance, and operational safety. Since new energy electric aircraft are still in the research and development stage in China and have not yet achieved large-scale industrial deployment, the availability of real flight data is limited. This data scarcity hampers deep learning models from fully capturing the dynamic feature patterns of battery systems under diverse and complex operating scenarios, thereby directly affecting SOC estimation accuracy. To address the issue of limited real-flight monitoring data, this study proposes a battery SOC prediction method with stochastic quantization-based data augmentation and Informer network. The approach enhances the original training samples through a stochastic quantization (SQ) algorithm, thereby expanding the data distribution, while leveraging the Informer network's strengths in time-series modeling to improve prediction accuracy under small-sample conditions. Experimental results demonstrate that this method achieves significant advantages in both data augmentation effectiveness and model generalization capability, providing a feasible solution to the problem of scarce battery data.]]></description>
      <pubDate>Fri, 26 Jun 2026 13:59:51 GMT</pubDate>
      <guid>https://trid.trb.org/View/2711942</guid>
    </item>
    <item>
      <title>Barrier Costs-Embedded MPPI Control for Rollover-Safe Cooperative Payload Transport with All-Wheel-Steering Distributed Electric-Drive Carriers</title>
      <link>https://trid.trb.org/View/2706179</link>
      <description><![CDATA[Autonomous driving control of heavy-duty vehicles remains highly challenging, particularly for cooperative transport systems (CTSs) carrying oversized payloads with multiple vehicle carriers. A primary difficulty arises from the frequent occurrence of stability-related accidents, such as rollover, during critical maneuvers. In this paper, a novel rollover prevention control pipeline for CTSs equipped with all-wheel-steering (AWS) distributed-electric-drive carriers is proposed. The framework is built upon an innovative iterative model predictive path integration (i-MPPI) method, which exhibits distinct advantages over common model predictive control (MPC) in dealing with the complex, nonlinear, high-dimension coupled dynamics of CTSs. To ensure effective rollover prevention performance, a control-barrier-function (CBF)-inspired safety cost is embedded into the sampling-based trajectory evaluation process, and a one-step safety modification is further applied to the i-MPPI control command. Extensive simulation results demonstrate that the proposed pipeline successfully prevents rollover while outperforming multiple baseline approaches in typical critical situations. The maximum LTRs decrease 13.33% and 18.57% compared with applying the conventional ReLU cost in two testing scenarios, respectively, and the computation speed reaches 7 – 10 times faster than common MPC. Moreover, the results reveal that the AWS distributed-drive architecture enables flexible pose regulation of both the payload and the carriers, allowing rollover mitigation to be achieved without significant degradation of trajectory tracking accuracy. The path tracking error of carriers decreases more than 50% and 80% in the two scenarios compared with using front-wheel-steering-and-driving FWSD carriers.]]></description>
      <pubDate>Thu, 18 Jun 2026 17:03:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2706179</guid>
    </item>
    <item>
      <title>Mechanical response and crack propagation in Si/C composite electrodes during electrochemical cycling: The critical influence of polymeric binders</title>
      <link>https://trid.trb.org/View/2706175</link>
      <description><![CDATA[Silicon-carbon (Si/C) composite anodes are considered ideal replacements for traditional graphite anodes due to their high specific capacity. However, their significant volume changes during charge-discharge cycles readily lead to rapid capacity decay and mechanical failure of the electrodes, severely limiting their practical application. As a key component in electrodes, the binder is essential for preserving the mechanical integrity of the composite electrode and for constraining the expansion of active materials. This study, an in-situ curvature measurement system was utilized to evaluate the impact of binders, i.e. polyacrylic acid (PAA), carboxymethyl cellulose (CMC), and polyvinylidene fluoride (PVDF), on the bending deformation, modulus, partial molar volume and stress-strain behavior of Si/C composite electrodes during lithiation/delithiation cycles. Then, scanning electron microscopy was used for systematic characterization the changes of electrode surface and cross-sectional morphologies. The results indicated that the Si/C composite electrodes with PAA could maintain relatively best electrochemical performance and structural integrity, owing to its large Young's modulus and strong confinement capability and which can effectively suppress its volume changes. While, the electrode with PVDF binder showed significant cracking evolution and interfacial delamination due to its lower modulus and poor bonding strength. This study reveals the working mechanism of the binder’s influence on the electrode stability from a mechanical-electrochemical coupling perspective, which can provide crucial theoretical and experimental basis for the rational design and optimization of superior Si/C anode binders.]]></description>
      <pubDate>Thu, 18 Jun 2026 17:03:15 GMT</pubDate>
      <guid>https://trid.trb.org/View/2706175</guid>
    </item>
    <item>
      <title>Fine-Tuned Large Language Model Empowered State of Health Evaluation of Lithium-ion Batteries based on Charging Sequence Matching</title>
      <link>https://trid.trb.org/View/2703763</link>
      <description><![CDATA[Accurate, convenient, and reliable state of health evaluation is critical for safe and efficient operation of lithium-ion batteries in electric vehicles. However, complex operating conditions, stringent feature engineering, and data scarcity severely limit the applicability of conventional estimation methods in engineering practice. Here, the authors infuse classification into state evaluation, breaking the existing mindset for battery degradation identification. Considering the potential limitations of data-driven technologies, this work employs emerging large language models from natural language processing to replace smaller models. Over 80,300 cyclic samples from 311 cells across large-scale datasets underpin this investigation. Firstly, incomplete charging data is scanned, fused, and dimensionally reduced to transform into a lightweight charging sequence. Thereafter, the current charging sequence is combined with the truncated candidate sequences to empower sequence matching, bypassing inherent degradation feature extraction. Furthermore, the authors devise various model construction strategies to fine-tune the model, seamlessly integrating prior knowledge with domain-specific insights. The validation results demonstrate that the proposed paradigm reliably exhibits robust evaluation performance, with an overall accuracy exceeding 99%. This work highlights the potential of large language models in battery intelligent management without requiring additional sensors, opening avenues for further interdisciplinary exploration.]]></description>
      <pubDate>Thu, 04 Jun 2026 15:13:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2703763</guid>
    </item>
    <item>
      <title>Global Coordinated Control Framework for Advanced All-Wheel Steering and Driving Vehicles: Unleashing Potential through Tire Slip State Assessment</title>
      <link>https://trid.trb.org/View/2703762</link>
      <description><![CDATA[To address the challenge of efficient actuator coordination in all-wheel steering and driving vehicles, this paper proposes a global coordinated control framework based on tire slip state assessment. First, a hybrid feedforward control method comprising steady-state control, dynamic compensation, and oblique steering compensation is proposed to respond rapidly to the driver’s demands under various operating conditions. Then, considering different steering modes of four-wheel steering vehicles, a driver intention interpretation method that integrates conventional steering and oblique steering is developed. Subsequently, a sliding mode control algorithm is utilized to track the driver’s desired motion states, improving the vehicle’s robustness against system disturbances. Moreover, taking lateral acceleration and yaw rate as inputs, a coordinated strategy for the four-wheel steering angles and driving torques is established based on tire slip state assessment. Finally, hardware-in-the-loop test results show that, compared to the model predictive control (MPC) algorithm, the proposed control scheme increases the maximum speed in double lane-change maneuvers by 13%, significantly improving the vehicle handling performance under different operating conditions.]]></description>
      <pubDate>Thu, 04 Jun 2026 15:13:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2703762</guid>
    </item>
    <item>
      <title>Robust Mass Estimation for Heavy-duty Vehicles under Multi-source Disturbances</title>
      <link>https://trid.trb.org/View/2703761</link>
      <description><![CDATA[Vehicle mass estimation (VME) is a critical input for control and safety systems in heavy-duty vehicles (HDVs), with direct implications for transportation efficiency and driving safety. In real-world road transport, however, torque interruptions during gear shifting, stochastic sensor signal anomalies, and insufficient persistent excitation make conventional real-time estimation methods highly dependent on specific operating conditions and signal quality, both of which are difficult to sustain in practice. Leveraging the fact that the total vehicle mass remains time-invariant during a single transportation mission, this study reformulates the real-time VME problem into a one-shot estimation framework. The proposed approach integrates dynamic and kinematic vehicle models to decouple vehicle mass from road grade, incorporates an online data-screening strategy to retain only quality-assured samples, and performs one-shot parameter estimation using the M-estimator Sample Consensus (MSAC) algorithm once a predefined number of samples is reached. This design enables accurate mass estimation under representative driving conditions while inherently mitigating the adverse effects of gear-shift disturbances, stochastic sensor anomalies, and insufficient excitation. Sensitivity analysis demonstrates that a sampling frequency of 10 Hz combined with a dataset of 500 high-quality samples achieves maximum relative estimation errors within 5% under all tested loading conditions, while configurations of 10 Hz/400-point and 20 Hz/500-point offer alternative trade-offs between accuracy and data collection time. Simulation and real-vehicle experiments further demonstrate that the proposed method significantly outperforms conventional estimation methods across multiple cargo loading conditions and all tested scenarios. The proposed framework offers a practical and scalable solution for high-precision VME in real-world HDV operations, with potential applications in cargo monitoring, adaptive control, and active safety systems.]]></description>
      <pubDate>Thu, 04 Jun 2026 15:13:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2703761</guid>
    </item>
    <item>
      <title>Adaptive DDPG energy management strategy for hybrid electric vehicles based on online robust driving condition identification</title>
      <link>https://trid.trb.org/View/2703759</link>
      <description><![CDATA[Energy management under variable driving conditions is a critical aspect for improving the fuel efficiency of hybrid electric vehicles (HEVs). Addressing the issue that insufficient real-time accuracy and robustness in recognizing complex and variable driving conditions hinders the overall energy-saving performance of HEVs, this paper proposes an online robust driving condition identification method integrating a Temporal Convolutional Network (TCN) and a Kernel Extreme Learning Machine (KELM). Base on this basis, constructs an adaptive Deep Deterministic Policy Gradient (TCN-KELM-DDPG) energy management framework for HEVs. To balance the real-time requirement and robustness of driving-condition identification, this study adopts a cascaded TCN–KELM architecture: the TCN extracts temporal features from historical and current vehicle-speed sequences and produces short-horizon representations, which are then fed into the KELM to complete condition classification via Gaussian-kernel mapping into a high-dimensional space. Based on the results of robust condition identification, an adaptive DDPG is applied to address the continuous and complex action space under different driving conditions, enabling dynamic optimization of torque distribution in the HEV powertrain and improving the global energy efficiency of HEVs in complex driving scenarios. Hardware-in-the-loop experimental results based on typical standard driving cycles and real-world road tests demonstrate the effectiveness of the proposed TCN-KELM-DDPG strategy in improving condition identification performance and reducing the overall energy consumption cost of HEVs.]]></description>
      <pubDate>Thu, 04 Jun 2026 15:13:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2703759</guid>
    </item>
    <item>
      <title>Online Detection of Lithium Plating in Lithium-Ion Batteries Using Dynamic Electrochemical Impedance Spectroscopy and GRU Networks</title>
      <link>https://trid.trb.org/View/2703758</link>
      <description><![CDATA[Lithium plating compromises battery safety during fast charging, yet real-time detection remains challenging due to the entanglement of natural polarization and anomalous impedance drops. Here, the authors propose a physics-informed, data-driven framework for online plating detection using dynamic electrochemical impedance spectroscopy. The authors utilize the complex Morlet wavelet transform (CMWT) to robustly extract the 1 Hz real impedance (Z1 Hz), mitigating conventional boundary artifacts. A gated recurrent unit (GRU) network then continuously tracks the impedance evolution. The optimized GRU achieves an R2 of 0.99 and a root mean square error of 0.23% under standard conditions. Reducing parameters by about 30% and memory by about 15% relative to traditional recurrent architectures, it provides a pragmatic inference engine for resource-constrained battery management systems. Crucially, the authors introduce a phase-adaptive differential thresholding strategy based on the macroscopic impedance derivative (▽Z). Integrating a downsampled computational interval with an RMSE-bounded late-stage threshold, the framework physically decouples normal activation polarization from genuine structural collapse. This approach deliberately prioritizes false-positive suppression, ensuring reliable lithium plating detection across diverse thermodynamic environments without relying on rigid absolute baselines.]]></description>
      <pubDate>Thu, 04 Jun 2026 15:13:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2703758</guid>
    </item>
  </channel>
</rss>