Abstract:Discretionary lane-changing (DLC) is a complex and safety-critical maneuver in highway driving that presents substantial challenges to traffic safety and operational stability. Accurately modeling DLC decisions remains difficult. Many existing approaches have limitations. They often fail to capture dynamic risk interactions with surrounding vehicles. They also inadequately model the temporal evolution of driver intent. These limitations often lead to limited prediction accuracy and generalizability. To address these gaps, we propose a new model, the Spatiotemporal Risk Field-integrated DLC (SRF-DLC) model. This model integrates time-sequential vehicle kinematics, driving behavior, and risk representation using an Attention-based LSTM network. The model was trained on trajectories from the highD dataset. We used 5,631 trajectories, each lasting 1 to 4 seconds. The model forecasts three maneuvers: lane-keeping, overtaking, and fold-down. Results show that the model trained on 3-second trajectories performs best. It achieves a peak accuracy of 96.74%. This optimal history length aligns with natural human decision-making timelines. Ablation studies were also conducted. By that we confirm the critical role of the Spatiotemporal Risk Field. Excluding this component caused a significant drop in accuracy. The highest accuracy decrease reached 47%. In comparisons, the SRF-DLC model outperformed some existing methods. This demonstrates that explicit spatiotemporal risk contextualization and appropriate history length selection is crucial in accurate DLC prediction.

Abstract:This study proposes a maintenance task decision-making method that integrates FMEA, RCM, and PHM. An FMEA failure risk assessment model is established in accordance with EN 50126 to quantify failure risks and determine risk grades across three dimensions: failure severity, occurrence frequency, and detectability. Reliability-centered maintenance analysis is implemented to screen critical maintenance items, analyze functional failures, classify failure impacts, and make logical decisions about maintenance tasks, thereby forming standardized maintenance tasks. Combined with PHM technology, maintenance strategies are optimized based on a matrix of failure impact and occurrence frequency; candidate items for PHM construction are selected with priority defined; and an integrated maintenance decision-making system covering risk assessment, reliability decision, and intelligent health management is ultimately established. Full-process verification is performed with the IGBT module, the core component of traction systems, as the research object. The results reveal that the proposed method reduces the risk level of IGBT modules from unacceptable to acceptable and extends the tertiary maintenance mileage from 1.2 million km to 1.6 million km, effectively improving the economic efficiency and intelligence of equipment operation and maintenance. The hybrid-driven decision-making methodology establishes a progressive closed-loop framework of FMEA - RCM - PHM - RCM. By leveraging a unified risk quantification value as the linking bridge, it achieves the integrated fusion of the three approaches. This provides both theoretical support and practical engineering reference for optimizing maintenance systems and constructing intelligent operation and maintenance frameworks for railway vehicle traction systems.

Abstract:As environmental concerns caused by waste polyethylene terephthalate (PET) become increasingly severe, utilizing it as a resource for asphalt modification has emerged as an important direction in road engineering. However, existing studies have predominantly focused on PET-modified SBS or rubber asphalt individually, leaving the effects of PET-derived additives on SBS/CR composite modified systems inadequately understood. In this study, a PET chemical depolymerization product (PET EA) was prepared via aminolysis and incorporated into both low content (3% SBS + 5% CR) and high content (7% SBS + 10% CR) composite modified asphalts at various dosages. The influence of PET EA content on asphalt properties was systematically investigated, and fluorescence microscopy was employed to elucidate the modification mechanism. The results show that PET EA increases the softening point and viscosity of the SBS/CR modified asphalt systems, while adversely affecting ductility; these effects are more pronounced in the high content system. Specifically, at 7% PET EA, the softening point increases by 4.8?°C, the viscosity at 135?°C rises by approximately 185%, and the maximum tensile stress during ductility testing increases by 85%, whereas ductility decreases from 19.7?cm to 6.4?cm. Furthermore, PET EA acts as a stabilizer in the composite system, inhibiting sedimentation and phase separation of the modifiers during high temperature storage, thereby improving storage stability. The amide groups present in PET EA promote the migration of light components from the asphalt into the SBS phase, facilitating further swelling of SBS, which in turn affects macroscopic properties such as the three conventional indices and viscosity. Overall, PET EA can serve as an effective additive for SBS/CR composite modified asphalt, offering both performance enhancement and stabilization. The findings provide a theoretical reference for the preparation of PET SBS CR composite modified asphalt.

Abstract:To achieve rapid and accurate prediction of the natural carbonation depth of in-service bridge concrete under ordinary atmospheric environments, a dataset consisting of 496 groups of field-measured concrete carbonation samples from bridges is first established. Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Forest (RF) algorithms are adopted to screen and optimize feature combinations. Regression trees and four tree-based ensemble learning (EL) algorithms are separately applied to develop prediction models for the natural carbonation depth of bridge concrete, followed by interpretability-based machine learning analysis. The results show that: the semi-empirical semi-theoretical model specified in relevant current Chinese standard produces highly scattered predictions for natural carbonation depth of bridge concrete, while the EL model built with the Gradient Boosting Regression Tree (GBRT) algorithm delivers outstanding performance and enables fast and precise prediction results. Among the factors affecting natural carbonation of bridge concrete, concrete compressive strength and curing age stand out as the two most dominant features, negatively and positively correlated with carbonation depth respectively. The carbon dioxide concentration and annual average ambient temperature at the bridge site also exert considerable positive impacts on carbonation depth, while the remaining factors impose marginal effects.

Abstract:To address control inaccuracies caused by nonlinear dynamics, friction disturbances, and response lag in an integrated electro-hydraulic brake system, this paper proposes a four-closed-loop pressure control strategy integrating enhanced sliding mode control, fuzzy active disturbance rejection control, and compensation techniques. A dynamic model of the IEHB system is established. The four-loop architecture (pressure, position, speed, current) is designed: the pressure loop uses an improved sliding mode controller for high-precision tracking; the position loop combines feedforward with a discrete PI controller to reduce lag; the speed loop employs Fuzzy-ADRC with a LuGre friction compensator to suppress nonlinear disturbances; and the current loop uses a discrete PI controller with parameter feedforward for rapid response. Co-simulation results show that the proposed strategy limits the master cylinder pressure steady-state error to ±0.5 bar, reduces position tracking deviation below 0.5 rad, and shortens pressure settling time after step commands to less than 0.05 s. The strategy significantly improves accuracy, dynamic response, and robustness of IEHB pressure buildup, providing technical support for high-performance braking control.

Abstract:【Objective】To achieve safe and efficient autonomous driving of high-speed trains, this paper proposes a compensated model predictive control (MPC) algorithm based on recursive KalmanNet (RKN).【Method】 The method adopts RKN, which combines data-driven and physical modeling, for dynamics modeling, and employs dual gated recurrent units (GRU) to directly learn the Kalman gain and covariance matrices, enabling efficient and accurate state prediction. Furthermore, a proportional compensation module (PCM) is designed to correct the MPC output, while the RKN covariance update is used to adaptively adjust the compensation gain, ensuring the control input approaches the optimum. The stability of the algorithm is proved via Lyapunov theory, and its effectiveness is validated on a hardware-in-the-loop simulation platform. Experimental results.【Result】show that, compared with MPC based on the extended autoregressive integrated moving average model, tracking performance and comfort improve by 64% and 65.8%, respectively; compared with LSTM-based MPC, the improvements are 80.4% and 42.5%, respectively, confirming the superiority of the proposed algorithm.

Abstract:Orthotropic steel bridge deck rib-to-deck (RD) joints are susceptible to fatigue cracking under coupled vehicle and temperature loading. To address the high computational cost of finite element analysis and the lack of physical constraints in purely data-driven models, this study proposes a data–physics dual-driven fatigue life prediction model based on a Physics-Informed Temporal Convolutional Network (PI-TCN). An RD-joint local model containing a semi-elliptical surface crack is established using ABAQUS–FRANC3D co-simulation and the submodeling technique to simulate crack propagation under coupled vehicle–temperature loading. A fatigue life dataset incorporating crack dimensions, equivalent load, temperature, and coupled stress ratio is subsequently constructed. The model employs dilated causal convolutions to extract temporal features and combines the Paris-law residual with the supervised loss to form a joint loss function, thereby constraining the monotonicity and physical consistency of crack propagation. The results show that PI-TCN achieves lower prediction errors than the purely data-driven TCN model and can mitigate non-physical fluctuations, such as decreases in crack depth. In independent tests, the model successfully tracks fatigue lives ranging from 0.5 to 2.5 million cycles. The absolute errors of most samples are within 100,000 cycles, and the mean absolute percentage error of representative samples is approximately 2.85%. The proposed method improves the accuracy and stability of fatigue life prediction for RD joints.

Abstract:Abstract: Tactical route correction for low-altitude logistics and public low-altitude route networks must balance interpretability, online latency, adaptive congestion avoidance, and safety fallback. Static shortest-path methods cannot perceive segment capacity variation and local congestion. Incremental search methods such as dynamic Dijkstra, D* Lite and LPA* respond to edge-weight changes but still rely mainly on deterministic global or incremental replanning, whereas end-to-end reinforcement learning suffers from limited interpretability and difficult safety certification. This paper models the low-altitude route network as a three-dimensional directed graph with time-varying non-negative weights that incorporate free-flow travel time, capacity utilization, altitude-transition cost, risk exposure and temporary restrictions. An event-triggered hybrid Dijkstra-DQN framework is then developed. Dijkstra provides an interpretable global backbone route, while a DQN agent is activated only within a bounded local subgraph when a rolling monitoring window detects excessive congestion or abrupt edge-weight changes. Action masking, anchor-node reconnection, local-step limits and dynamic-Dijkstra fallback are embedded to keep the learning policy bounded, auditable and recoverable. Controlled simulations using synthetic urban scenarios and simulated-realistic data show that the proposed method reduces average flight time and congestion exposure under local disruptions while maintaining lower online latency than repeated global replanning. The findings should be interpreted as mechanism-level evidence under controlled simulation settings rather than proof of operational effectiveness in real-world complex airspace.

Abstract:Localized corrosion of steel pipe piles in the splash zone poses a critical threat to structural safety, necessitating urgent underwater reinforcement technologies. This study proposes a duplex stainless steel jacket grouting reinforcement method for locally corroded underwater steel pipe piles. Axial compression tests were conducted on nine specimens: one uncorroded specimen, three corroded specimens, and five corroded-reinforced specimens. Load-axial deformation curves, load-strain curves, and failure modes were obtained to investigate the influence of corrosion rate and stainless steel jacket thickness on bearing capacity and ductility. The experimental results indicate:1) The failure mode of unreinforced specimens was characterized by "elephant-foot-shaped" buckling failure at the bottom of the corroded region, while reinforced specimens showed inward buckling at the interface between reinforced and unreinforced zones, with no significant deformation in the grout or stainless steel jackets. 2) With an increase in the corrosion rate, the load-bearing capacity of steel pipe piles declines at an accelerating rate. 3) For specimens with corrosion rates of 10%, 20%, and 30%, the bearing capacities of reinforced piles recovered to 95%, 81.5%, and 64.8% of uncorroded levels, respectively. Notably, only the 10% corroded specimen exhibited restored ductility surpassing that of the uncorroded specimen, indicating a gradual decline in reinforcement effectiveness with higher corrosion severity. 4) Regarding jacket thickness, specimens with thicknesses of 1.8 mm, 2.4 mm, and 3.0 mm recovered to 80.7%, 81.5%, and 81.1% of the uncorroded bearing capacity, respectively, revealing minimal influence of jacket thickness on both bearing capacity and ductility under identical corrosion conditions. 5)The duplex stainless steel jacket grouting system enhances resistance to local buckling by effectively increasing the wall thickness of corroded piles, thereby mitigating strength degradation caused by corrosion-induced thinning and defects. However, the reinforcement efficacy is highly dependent on corrosion severity, emphasizing the need for tailored strategies based on specific corrosion levels in engineering practice.

Abstract:To address the issues in existing electric vehicle charging path planning methods, namely the neglect of queuing randomness and the difficulty in balancing real-time performance with global optimality, this paper proposes a path optimization method based on Generalized Total Cost (TGC) and a hierarchical Deep Q-Network (DQN). First, an M/M/c queuing model is introduced to quantify the randomness of charging waiting time. The TGC framework assists the Deep Q-Network in unifying nonlinear queuing time, travel time, and time-of-use electricity price into a single scalar reward. Second, a Top-M pre-screening mechanism combined with an action validity mask is employed to resolve convergence difficulties caused by large action spaces, and experience replay is utilized to break data correlations. The method""s performance is evaluated in a constructed high-fidelity simulation environment. When the Top-M parameter is set to 10, the proposed strategy achieves a global optimal solution hit rate of 89.5%, an average relative regret value converging to 0.0122, and a single inference time reduced to 0.35 ms.