Browse Topic: Electrical, Electronics, and Avionics

Items (60,824)
Find
Cooperative Control of Two Free-Piston Engine-Generators for Vibration Reduction2026-01-5088To be published on 11/16/2026
The free-piston engine-generator (FPEG) is a promising power unit in vehicle-mounted energy conversion systems. However, inertial-force excitation caused by free-piston reciprocating motion remains a major constraint on its practical application. To address this issue, a hierarchical control architecture consisting of a single-engine motion control layer and a two-engine synchronization control layer is proposed for an opposed two-engine FPEG system. The single-engine motion control layer combines iterative learning control with displacement feedback and adaptive compensation with velocity feedback to regulate dead-center positions. The two-engine synchronization control layer introduces a Combustion State Observer (CSO) to estimate cycle-to-cycle indicated-work variations caused by stochastic combustion fluctuations and guide differential fuel-injection compensation. A simulation verification framework is established to evaluate the proposed strategy under compound disturbances. Relative to the single-engine case, the cooperative scheme achieves a 99.6% mean-square force reduction while maintaining 43.3% indicated thermal efficiency. The residual RMS inertial force is further reduced by 38.1% compared with the master–slave baseline. These results demonstrate that the CSO-based cooperative synchronization strategy is effective in reducing inertial-force excitation in two-engine FPEG systems.
Zhao, Bowen, Ren, Boyao, Xu, Zhaoping
Analysis of Competition and Cooperation Relationship between Ride-Hailing and Subway2026-99-201411/13/2026
Due to the rapid growth in ride-hailing services and the steady expansion of urban rail transit networks, understanding the complex interaction between the two is important. Most existing studies only focus on the overall competition and cooperation effects. Few scholars discuss local spatial differences and how the built environment works in detail. To investigate the spatial heterogeneity of built environment factors between the ride-hailing and the subway systems by situation and location, our study categorizes 3.71 million ride-hailing trips into three types: Proximal-to-Station Trip (PST), Medial-to-Station Trip (MST), and Distal-to-Station Trip (DST). We employed the values of built environment factors per grid as independent variables, and the grid-based volume of each ride-hailing trip category (PST, MST, DST) as the dependent variable. Additionally, we conducted analysis mainly with the multi-scale geographically weighted regression model (MGWR). We found that ride-hailing trips and subway trips have competition, cooperation, or complementarity relationships, which depend on trip purposes and public transit accessibility. Besides, we think that this relationship relies on the built environment, and it also shows clear spatial heterogeneity. The impact of different built environment factors has significant variation and spatial heterogeneity: Catering, Shop, and Bus Stop continuously trigger the demand for ride-hailing services, while Residence generally reduces the use. In PST, Enterprise, Medical, and Residence inhibit ride-hailing due to the high subway accessibility. In DST, these functions conversely boost ride-hailing usage due to limited bus coverage. These findings provide crucial insights for smart transportation management, multi-modal, and location-specific strategies to boost sustainable urban transportation development.
Zhao, Shiya, Xiao, Lingling
ST-ParFusion: Spatio-Temporal Parallel Fusion Network for Traffic Flow Prediction Based on Multi-Relation Driving2026-99-201311/13/2026
Accurate and real-time traffic state prediction is fundamental to optimizing urban traffic control and improving the service quality of online mapping platforms. While data-driven deep learning methods have shown promise in handling large-scale data, most existing approaches suffer from limitations due to their reliance on simplistic modeling components that cannot fully capture complex and multi-scale spatiotemporal dependencies. Unlike prior studies that predominantly utilize static graph structures or sequential processing, this research addresses the challenge of modeling dynamic correlations by proposing a Spatiotemporal Parallel Fusion Network. The theoretical framework of this study integrates graph spectral theory with advanced attention mechanisms to model both the physical and semantic topology of traffic networks. The proposed methodology features a multi-source spatial modeling framework that fuses a static connectivity graph, an inverse distance weighted graph, and a flow similarity graph via multi-relational graph convolution. This approach allows for the simultaneous capture of physical connectivity and dynamic traffic patterns. Furthermore, utilizing a parallel architecture, the temporal modeling component integrates multi-head self-attention with two-dimensional causal dilated convolutions. A cross-attention fusion module is further introduced to dynamically regulate spatiotemporal interactions. Comprehensive tests conducted on four practical traffic datasets indicate that the introduced model significantly outperforms thirteen cutting-edge benchmark methods. The study confirms that the proposed multi-graph strategies and parallel architectures effectively reduce mean absolute error and root mean square error, validating the efficacy of the proposed solution for the advancement of intelligent transportation systems.
Chen, Lulu
Vision-Based Structural Displacement Measurement Using a Ground-Fixed Laser Reference under UAV Observation2026-99-201711/13/2026
Structural displacement is an important quantity in Structural Health Monitoring (SHM), as it directly reflects the condition and safety of structures. Vision-based measurement methods have been widely studied in recent years, mainly because they allow non-contact sensing and can cover relatively large areas. When these methods are applied to Unmanned Aerial Vehicle (UAV) platforms, however, additional challenges arise. In practical operation, platform motion and attitude changes tend to introduce drift into the measurements, which can noticeably affect the final results. In this study, a displacement measurement approach that combines vision sensing with a laser reference is investigated for both UAV-based and fixed-camera scenarios. A laser source installed on the ground projects a reference spot onto the structural surface, placed close to a multi-circle target. This setup provides a stable reference point that is less affected by platform movement. The displacement is then estimated by tracking the relative motion between the target and the laser spot, instead of relying directly on absolute measurements. With this design, a large part of the motion caused by the platform can be separated, allowing the structural displacement to be expressed in a ground-based coordinate system. The implementation includes several practical steps, such as adaptively selecting regions of interest, performing basic image processing, refining feature locations at the subpixel level, and updating scale factors during operation. Experiments with both UAV and stationary camera setups show that conventional measurements are strongly affected by low-frequency drift, while the laser-referenced results remain relatively stable across different measurement points. According to the Root Mean Square (RMS) analysis, about 77%–95% of the drift caused by platform motion can be reduced under UAV conditions. These results indicate that the method can serve as a practical option for displacement monitoring in UAV-based vision applications.
Li, Zheng, Xu, Junhao, Hua, Yuansheng
Beyond Static Graphs: A Dynamic Spatiotemporal Transformer Framework for Real-Time Traffic Signal Optimization in Smart City Networks2026-99-202211/13/2026
2222
Lin, Ziyu
Multi-Factory Production–Transport Collaborative Scheduling Under Time-Varying Traffic: Traffic Parameterization Embedding and Order-Level Multi-Agent Proximal Policy Optimization (MAPPO) Joint Decision-Making2026-99-202411/13/2026
Multi-factory scheduling presents notable challenges when road congestion exhibits temporal variability, as transport lead times deviate from predefined production plans and schedules deemed feasible at the planning stage may become unfeasible upon dispatch initiation. This study, therefore, addresses the problem through an integrated pipeline of traffic prediction, traffic parameterization, and joint scheduling, which links traffic prediction with scheduling within a unified decision framework rather than treating them as two separate tasks. Link-speed data from the Q-Traffic dataset are utilized to train a Light Gradient Boosting Machine (LightGBM) short-horizon predictor; the predicted speeds are converted into a bounded congestion factor, and a route-wise aggregation method is applied to derive the traffic correction coefficient at the factory-customer-route-time level. Traffic information is incorporated into the scheduler via transport-time adjustments and delivery-related penalty terms, thereby incorporating traffic information without substantially changing the original scheduling structure. At the decision layer, each order is treated as an independent agent, and each scheduling action is defined by the ternary set (factory, route, dispatch time window). The decision layer is trained under the framework of Centralized Training with Decentralized Execution (CTDE) by adopting Multi-Agent Proximal Policy Optimization (MAPPO), a method that mitigates the weak local optima commonly generated by stage-wise planning strategies. Comprehensive experiments, including main performance tests, ablation studies, and robustness analyses, are conducted on small, medium, and large problem instances as well as on low, medium, and high congestion groups. Across all experimental settings, the integration of parameterization and MAPPO joint decision-making achieves a favorable trade-off among total cost, on-time delivery rate (OTD), and average delivery delay, while maintaining stable performance amid traffic congestion fluctuations. Predictor accuracy, reproducible experimental configurations, and summarized results are also reported to support the replication and reuse of the proposed method in traffic-aware production-transport coordination scenarios. In comparison with stage-wise planning and heuristic Earliest Due Date (EDD)-based baselines, the augmented MAPPO policy yields lower overall costs and higher OTD values on large-scale instances. Ablation results further demonstrate that it modulates the learned preferences for routes and time windows in scheduling decisions. Decentralized inference of the proposed model remains in the millisecond range across all tested problem scales, which validates the practicality of the model for rolling-horizon decision support in real-world operations.
Cai, Jiayu
A Deep Reinforcement Learning-Based Multi-Section Coordinated Variable Speed Limit Control Method for Expressways2026-99-200911/13/2026
This paper proposes a reinforcement learning-based multi-section, coordinated variable speed limit control approach for expressways. The method handles joint speed-limited decision-making at coupled spatiotemporal traffic dynamics across multiple sections and lanes. The traffic state space is constructed based on indicators: lane flow, speed, occupancy rate, number of slow-moving vehicles, and minimum Time-to-collision (TTC). Lane-level speed limits for each control unit are defined as action variables. A weighted reward function is designed to consider operational efficiency, safety, rationality of speed gradient, and control response. The model integrates Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs) to capture spatial correlations and time-varying properties in traffic-state information. In addition, a risk-aware dual-policy output mechanism is introduced to adaptively balance safety-oriented and efficiency-oriented control objectives. Using the Houjie-Xinlian section of the Guangshen Expressway as an example, three control strategies are simulated on the SUMO platform: CGDQN, FCDQN, and an uncontrolled scenario. Experimental results show that the total reward for CGDQN exceeds that of FCDQN. CGDQN reduces vehicle queueing and slow-moving traffic across various scenarios, thereby decreasing the likelihood of traffic accidents. The results demonstrate that the proposed method achieves coordinated multi-section variable speed limit control on expressways under different conditions, and is both feasible and effective.
Zhang, Yuping, Xu, Tian, Ma, Lin, Lin, Siyu, He, Runjing, Yuan, Chenwei
Analysis of Industrial Agglomeration Characteristics in Air-Rail Dual-Hub Regions Based on POI Big Data: Case of Guangzhou2026-99-200811/13/2026
In order to reveal the industrial agglomeration pattern, multi-scale characteristics, and driving mechanism of the air-rail dual-hub regions, this study takes Guangzhou as an example to extract the universal patterns of this region type. Based on POI big data of 9 different types of industries, this study uses kernel density analysis, average nearest neighbor analysis, Ripley’s K function analysis, and spatial autocorrelation analysis to explore the agglomeration characteristics of various industries in the air-rail dual-hub regions. The results show that the industries have a “core-edge” spatial distribution pattern: high-value areas are mainly concentrated around Guangzhoubei Railway Station and Huadu Central Business District, and extend in a belt and bead chain along rail transit and main roads. The overall industries show significant agglomeration, and the intensity is gradient. The consumption-oriented industries are stronger (food and beverage service 0.306, accommodation service 0.331, shopping service 0.338); Culture and education services, enterprises, and sports and recreation services are relatively weak (0.433-0.489); The agglomeration is hierarchical in scale, and the dominant scale is between 1.92 km and 4.48 km, forming a multi-scale structure with the coexistence of “node attachment-mesoscale composite service circle-regionalized cluster superposition”; Industrial POI density is positively correlated with road network density, night light index and population density as a whole, showing the composite driving characteristics of “population support-traffic guidance-vitality enhancement”. The results show that the hub effect of the air-rail dual-hub regions has expanded from the agglomeration around the station to the multi-type composite organization mode of “circle-corridor-group”. The study provides a basis for the guidance of spatial planning in different types and scales of the air-rail dual-hub regions.
Zhang, Ruijie, Ouyang, Jie, Shen, Ziran, Xue, Weining
Influence of Low Stability on Turning Safety of Ro-Ro Passenger Ship2026-99-202311/13/2026
To investigate the safety margin of the Ro-Ro passenger ship (ROPAX) with low stability during turning operations, a four-degree-of-freedom coupled mathematical model was established. The results indicate that during turning maneuvers, the maximum heel angle of the ROPAX vessel significantly exceeds the steady state values specified and calculated by the International Code on Intact Stability 2008 (2008 IS Code). It is noteworthy that this excessive transient heel angle, which exceeds the steady state assessment framework adopted in conventional IMO regulations, often receives insufficient attention in practical engineering and operational evaluations. Nevertheless, its impact on safety is critical. This study provides crucial evidence for evaluating the maneuvering safety margin of the ROPAX vessel and offers a valuable reference for refining stability criteria and operational guidelines for actual navigation.
Wang, Honggui, Li, Yunting, Li, Jinge, Yang, Yong, Wang, Biao, Wang, Xinjian
Cooperative Control for Connected Automated Vehicle Platoon under Cut-In Scenarios: A Topology Reconfiguration Approach2026-99-201811/13/2026
This paper proposes a distributed cooperative control framework to address the stability control problem of connected and automated vehicle (CAV) platoons encountering external cut-in vehicles. To maintain platoon cohesion under cut-in scenarios, an active topology reconfiguration approach based on both the predecessor-following (PF) topology and the leader-following (LF) topology is first designed. By designating the first vehicle behind the cut-in vehicle as the new leader and combining with the LF topology, it is ensured that vehicles ahead of the cut-in can access the state information of those behind it, thereby maintaining platoon cohesion. Secondly, a model predictive control system is developed to adapt to the topology changes. Its prediction model, optimization objectives, and safety constraints can all be switched according to the topology, ensuring both platoon cohesion and operational safety. Simulation results demonstrate that the proposed strategy effectively suppresses oscillations in inter-vehicle spacing and speed fluctuations caused by the cut-in vehicle, enabling rapid recovery and smooth control of the platoon, and performs significantly better than static topology strategies. This provides a reliable solution for cooperative platoon control in dynamic traffic environments.
Yao, Yuan, Yang, Lei, Liu, Yafei, Liu, Fan, Sun, Zhanbo
Comprehensive Evaluation and Optimization of Traffic Organization Schemes for Highway Reconstruction and Expansion Based on Traffic Simulation2026-99-203311/13/2026
To address the difficulty in quantitatively evaluating the effectiveness of traffic organization schemes in highway reconstruction and expansion projects, this study proposes an evaluation system integrating traffic safety and operation efficiency. By combining VISSIM simulation with SSAM conflict analysis, this study verifies the effectiveness of the proposed evaluation method through a case study of the Guihua Interchange on the Chengnan Highway. For traffic safety evaluation, a safety risk assessment model is constructed, consisting of four first-level indicators (road, traffic, facilities, and management) and fifteen second-level indicators, along with a four-level risk classification standard. For operational efficiency evaluation, the Level of Service (LOS) and average delay are adopted for quantitative assessment. Simulation experiments are conducted on the three-stage traffic organization scheme for the Guihua Interchange in the Chengnan Highway reconstruction and expansion project. The results show that the comprehensive risk scores of the three-stage scheme are 12, 12, and 13, respectively, all classified as general risk. The peak-hour delay rates of the first and second stages are both lower than 6 s/(veh·km), verifying the feasibility of the temporary ramp and truck diversion strategy. The third-stage simulation indicates that the conflict rate of the east-south ramp reaches 0.58 conflicts/(veh·km) (93.5% of which are lane-changing conflicts). It is suggested to add graphical path indication traffic signs, paint no-lane-changing markings on the inner lanes, and guide ramp traffic flow in advance. The research demonstrates that the proposed evaluation system can effectively support the feasibility judgment, optimization path identification, and dynamic evaluation verification of traffic organization schemes, significantly improving the safety and approval efficiency of reconstruction and expansion projects.
Qin, Lang, Wang, Yue, Chen, Qingyu, Liu, Gang
Feasibility-Repair Adaptive Large Neighborhood Search for EVRPTW-SPD with Time Windows and Full Recharge2026-99-214511/13/2026
Optimizing electric vehicle route planning with time windows and simultaneous pick-up and delivery (EVRPTW-SPD) remains challenging due to the complex interactions among routing, dynamic cargo loads, charging behavior, and time windows. Under a full-recharge policy in which vehicles are fully recharged whenever they visit a charging station, a hybrid heuristic framework is proposed. We first build a complete customer assignment by inserting unrouted customers one by one. Energy infeasibility is handled by a hierarchical charging-station repair module (CRM), which combines a greedy algorithm with a parallel evolutionary algorithm to identify the best repair plan while minimizing total detour cost. The repaired solution is then further improved through adaptive large neighborhood search (ALNS) with dynamic operator selection and simulated annealing (SA) acceptance. Load, time-window, and battery violations are penalized adaptively during the search, and a restart rule is used when the search stays trapped for too long. Experiments on the Akbay benchmark indicate that the method consistently finds feasible solutions and converges within acceptable computing time, demonstrating the effectiveness of feasibility-oriented repair and adaptive exploration of infeasible solutions for the full-recharge EVRPTW-SPD problem.
Liu, Jingtong
Method for Identifying Typical Vehicle Operation Scenes Applied to Energy-Saving Driving of New Energy Vehicles2026-99-214111/13/2026
Aiming at the problems that existing energy-saving technologies for new energy vehicles highly rely on high-cost, high-precision sensors such as radars and cameras, and suffer from high implementation costs, this paper studies vehicle operation scene recognition methods for energy-saving driving of new energy vehicles, aiming to develop a low-cost scene recognition model and provide corresponding technical support for energy-saving driving of such vehicles. Firstly, actual road driving data of new energy vehicles with comprehensive scene coverage are collected via real-vehicle tests, with the total test mileage exceeding 126,000 km. Secondly, a data-driven recognition method for typical vehicle operation scenes combining Principal Component Analysis (PCA) and the K-means clustering algorithm is proposed, which classifies three typical operation scenes: congested, urban free-flow, and suburban scenes. Finally, a set of scene-specific driving assistance control strategies is designed, and the potential energy-saving effects of the strategies based on vehicle operation scene recognition are investigated based on a mature powertrain energy consumption simulation model for new energy vehicles. The research shows that under the China Light-Duty Vehicle Test Cycle (CLTC), the energy consumption of new energy vehicles can be reduced by approximately 4.5% through anticipatory perception of vehicle operation scenes and adaptive switching of scene-specific energy-saving control strategies. Moreover, the proposed technology can realize accurate scene recognition without relying on high-cost, high-precision sensors such as radars and cameras, and it can meet the application requirements of low-cost new energy vehicles, including logistics vehicles.
Liu, Yu, Guo, Yijing, Zhang, Hao, Yu, Hanzhengnan, Yuan, Xiaohui
Research and Analysis of Civil Aircraft Air Data Systems Malfunction2026-99-214211/13/2026
As a core subsystem of civil aircraft avionics, the Air Data Systems’ (ADS) output parameter accuracy directly determines the normal operation of the flight control system, navigation system, and display control panels. Inconsistencies in air data can easily lead to abnormal flight parameters and deviations in control commands, posing a serious threat to flight safety. It is a high-frequency and high-risk type of fault in route maintenance. This article focuses on this type of fault and explains the functions, components, and the entire workflow of data acquisition, calculation, and transmission of ADS on civil aircraft. Based on actual flight failure cases of relevant aircraft, this paper analyzes the causes of failures from dimensions such as hardware and circuits, and constructs a complete system of failure causes. The paper proposes effective solutions, including standardized fault localization processes, precise testing methods, and differentiated elimination strategies, forming a closed-loop solution of ‘diagnosis-localization-testing-verification,’ for failure characteristics caused by different reasons. This research can offer technical support for improving the operational reliability of civil aircraft ADS and reducing the recurrence of failures.
Song, Mingming, Mi, Yujie
Research on Dual-Safety Collaborative Testing and Risk Assessment Framework for Vehicles2026-99-214311/13/2026
In order to solve the problems of incomplete risk assessment and blind areas of test coverage caused by the separation of functional safety and cybersecurity of intelligent connected vehicles, this paper proposes a dual-safety collaborative test and risk assessment framework. The framework builds an attack-hazard correlation model by integrating Hazard Analysis and Risk Assessment (HARA) and Threat Analysis and Risk Assessment (TARA) to accurately identify high-priority 'attack-hazard' scenarios, and then relies on the test environment that integrates functional safety and cybersecurity tools to generate and execute collaborative test cases. Finally, the strategy of the design and test will be optimized through quantitative evaluation feedback. Taking the intelligent cockpit controller as a case, the results show that this framework can find out deep security vulnerabilities missed by traditional independent testing, achieve more comprehensive risk identification and accurate assessment, and provide effective guidance for the practice of intelligent connected vehicle safety engineering. The framework achieves a 42% improvement in defect detection rate for cross-domain security vulnerabilities, and the test coverage rate of attack-hazard coupling scenarios reaches 96%, which is significantly higher than the 61% coverage rate of traditional testing methods.
Cai, Han, Zeng, Jie, Liao, Wei, Liu, Ke
Research on Model-Driven Test Case Generation Method for Train Operation and Control System2026-99-214611/13/2026
The train operation and control system is a safety-critical system whose software correctness directly affects railway operational safety. Traditional test case design relies on expert experience, leading to low coverage, poor repeatability, and insufficient completeness. To address these challenges, we propose a model-driven automatic test case generation method for the train operation and control system. A multi-view modeling framework is established, including the system function model, the environment model, the operational scenario model, and the line data model. Test cases are automatically generated by traversing the model space based on the predefined coverage criteria. To overcome the limitations of conventional open-loop modeling, a closed-loop modeling approach is proposed, where the environment constraints, the scenario sequences, and the line data constraints are integrated as additional solvable conditions. A constraint-satisfaction-based line data solver is proposed to select test data that meet the specific scenario requirements. The proposed method is applied to the Chinese Train Control System Level 3(CTCS-3 )level train operation and control system for functional validation. Experimental results show that the proposed approach achieves 100% state coverage and 96% transition coverage on a typical station scenario, and reduces manual test case design effort by 65%.
Zhu, Linfu, Zhao, Jialiang, Xiao, Zhongliang, Xia, Yunchao, Yang, Xiaoxu
Research on the Test and Evaluation Method of Vehicle Automatic Emergency Steering Systems2026-99-210211/13/2026
As global vehicle numbers rise, traffic accidents pose significant threats to life and property, with approximately 1.3 million casualties annually. To mitigate accidents, automotive Original Equipment Manufacturers and suppliers are prioritizing active safety technologies like the automatic emergency steering (AES) system, which proactively intervenes in vehicle dynamics to avoid collisions. The AES system, as an important component of active safety, lacks systematic testing and evaluation methods. We aim to conduct a more comprehensive and scientific pre-evaluation of the AES system, which realizes its functions through onboard sensors, decision control systems, and actuators. The environmental awareness system uses sensors such as a camera, millimeter wave radar, and laser radar to collect surrounding information. Based on the perceived data, the decision control system generates the optimal steering strategy through hazard identification and risk assessment. This study addresses these gaps by analyzing AES performance indices and existing regulations (e.g., UN R79, ISO 23375, IIHS, E-NCAP) to design a comprehensive test framework. Four high-coverage scenarios were developed: longitudinal scooter conflicts, vehicle cut-ins, pedestrian crossings, static cone bucket, and misoperation validation, ensuring evaluation under diverse conditions. It has important practical significance for improving China’s automotive safety technology level and reducing road traffic accident casualties. With the rapid development of autonomous driving technology, this research achievement will also provide technical support for the development of higher-level intelligent driving systems.
Shen, Liangyi, Gao, Zong, Kong, Lingming, Wang, Zhiyu, Zhang, Xiao
Functional Resilience Assessment of Urban Rail Transit Stations from a Network Perspective--A Case Study of Shenzhen2026-99-200411/13/2026
This study explores challenges in maintaining operational resilience for urban rail transit networks during emergencies. It develops a comprehensive evaluation system based on resilience triangle theory, covering pre-event, during-event, and post-event stages to assess station functional resilience across the full event cycle. By integrating complex network theory with dynamic passenger flow simulation, the research analyzes transportation system topological features and passenger adaptive behaviors during incidents. Key methodological innovations include a dual-constraint feasible path criterion that combines time flexibility thresholds and transfer tolerance parameters to evaluate passenger preferences for efficiency and comfort simultaneously, and a spatiotemporally extended recovery efficiency model using time-varying passenger load factors to overcome limitations of traditional static assessments. Empirical analysis of Shenzhen’s rail transit network verifies the framework’s ability to accurately identify and quantify the resilience performance of critical vulnerable nodes. Findings reveal terminal stations like Buji and Mucunwan reduce the largest connected subnetwork ratio to approximately 90%, significantly degrading overall network connectivity; over 85% of passengers at stations within Futian District’s central loop can switch routes, indicating high structural redundancy; and during morning peak hours, stations like Wuhe and Minzhi exhibit recovery efficiencies below 1% with recovery times exceeding 120 minutes, demonstrating substantial spatiotemporal resilience differences. The research provides a quantifiable, stage-specific, and behavior-integrated evaluation tool for rail transit resilience assessment, offering theoretical and practical insights for enhancing resilience evaluation systems through network-passenger interaction analysis.
Kang, Zhiping, Peng, Wenxiang, Xue, Zhaojie, Zhang, Ying, Wang, Guocong
Modeling and Interpreting Accident Severity in Autonomous Vehicles: A ROSE-LightGBM-SHAP Framework2026-99-201211/13/2026
Although autonomous vehicle (AV) technology is regarded as a transformative force for enhancing road safety, collisions remain inevitable during the transition phase toward large-scale commercial deployment, making it crucial to investigate the causal mechanisms of accident severity for optimizing AV systems and improving transportation infrastructure. To address the dual challenges of extreme class imbalance and the lack of interpretability in existing studies utilizing real-world data, this paper proposes an interpretable accident severity analysis model integrating Random Over-Sampling Examples (ROSE) with the LightGBM algorithm and SHAP (SHapley Additive exPlanations) framework. Utilizing real-world testing data from the California Department of Motor Vehicles (DMV), this study first establishes a rigorous “Split-then-Sample” strategy to effectively mitigate class imbalance while eliminating data leakage risks, and subsequently constructs the ROSE-LightGBM classifier. Experimental results demonstrate the model’s superior robustness in identifying minority class (injury) accidents, significantly outperforming baseline models such as Random Forest and XGBoost with a Recall of 80.00% and an F1-score of 77.42%. SHAP-based multi-dimensional analysis further reveals that severe vehicle damage, high point-of-interest (POI) complexity, and collisions involving vulnerable road users (VRUs) are dominant factors escalating accident severity, whereas high-level sensor configurations equipped with LiDAR and physically separated roads exhibit significant risk-mitigating effects; additionally, the study quantifies the non-linear threshold relationships between environmental features and accident risks. The analytical framework proposed in this paper not only provides an effective paradigm for modeling imbalanced data but also offers actionable, scientifically interpretable insights for the formulation of AV safety strategies.
Hou, Yi, Wu, Shaoping, Dong, Chunjiao, Ma, Jihui, Lu, Zhenzhen, Liu, Zhe, Sun, Dongyuan
A Study on Road Accessibility Based on Space Syntax and POI Data: A Case Study of the Inner Second Ring Road Area in Xi’an2026-99-203611/13/2026
With the continuous advancement of big data technology, the application scenarios of Point of Interest (POI) data have been steadily expanding. This study focuses on the area within the Second Ring Road of Xi’an. First, a road network map of the study area was generated using AutoCAD and then imported into Depthmap to construct an axial model for spatial syntax analysis. Subsequently, a comparative analysis of key road network indicators was conducted, including global integration, local integration, synergy, and choice. The results indicate that the road network within the Second Ring Road of Xi’an still retains the typical checkerboard layout inherited from the Ming Dynasty, with North-South Street and East-West Street serving as the core structure. Arterial roads exhibit high integration levels, and there is a strong correlation between global integration and local integration, suggesting a relatively complete road network structure. Furthermore, multi-category POI data closely related to daily life were collected from Amap (Gaode Maps), covering catering services, daily life services, science, education, culture, as well as sports and leisure. A visual comparative analysis reveals that the spatial distribution of POI data is generally consistent with road integration: road segments with high POI density correspond to higher integration values. Meanwhile, the development of the northern and southern parts of the study area is relatively unbalanced, with POI data distributed more sparsely in the northern region. Incorporating POI data into road accessibility analysis enhances the visualization of research results and renders the analysis more intuitive and convincing. Ultimately, this study aims to provide valuable references and decision support for the optimization and development of the road network within the Second Ring Road of Xi’an.
Zhang, Xinxin
Optimization of Pilot Fatigue Evaluation Method for Tunnel Sections Based on Attention Mechanism2026-99-201511/13/2026
To investigate pilot fatigue during tunnel navigation, we developed a simulated experimental platform based on a large-scale ship maneuvering simulator (LSSM). EEG data were collected from 12 pilots while they navigated the tunnel using a saline-electrode wireless portable EEG device (EMOTIV FLEX). We processed the pilot’s EEG signal data using the toolbox, which was EEGLAB (via MATLAB), to extract the wave characteristics that reflect the fatigue/multi-branch longitudinal short memory (LSTM) performance (i.e., Alpha to Delta waves). We developed a multi-branch LSTM model on the foundation of an optimized attention mechanism. The conventional machine-learning models showed limited performance, with random forest achieving an accuracy of 82.75% and an AUC of 0.75, and SVM achieving an accuracy of 75.00% and an AUC of 0.70. The experiment findings revealed that using EEG temporal features in conjunction with the task performance of pilots in the LSTM model delivered an accuracy of 91.67% and an AUC of 0.95, and precision/recall levels above 89. The study offers an efficient and accurate technical solution to check the fatigue of pilots in tunnel navigation and will substantially contribute to the safety of the cargo shipments with the help of the inland waterways.
Yang, Yichen, Xu, Yanmin, Guan, Hongxu
Design and Application of UAV-Based Intelligent Inspection Technology for Highways2026-99-200511/13/2026
Manual highway inspection in conventional practice suffers from low operational efficiency, elevated safety risks for field personnel, and unavoidable inspection blind spots across key infrastructure sections. To address these prominent challenges, this research develops an integrated intelligent UAV inspection system that synergizes flight control technology, Beidou positioning, machine vision, and artificial intelligence algorithms. The system enables rapid detection and accurate identification of structural defects on highway pavements, bridges, slopes, and other critical infrastructure components. We conduct targeted optimizations on both the YOLOv7-RDD object detection algorithm and the DeepLabV3+ segmentation algorithm, optimizations that markedly boost the accuracy and environmental robustness of defect recognition in complex highway scenarios. A dedicated deployment scheme featuring automatic UAV airports and intelligent route planning is also proposed to underpin fully automated, high-frequency inspection operations. Field engineering applications have validated the system’s practical effectiveness: defect recognition accuracy surpasses 95% in real-world highway environments, while overall inspection efficiency is improved by approximately 80%. This research delivers pivotal technical support for the intelligent maintenance and refined management of transportation infrastructure networks.
Bai, Xing, Xie, Yaoxuan
A Tunnel Deformation Monitoring Method Based on Line-Structured Light and Swin Transformer2026-99-200711/13/2026
Tunnel deformation monitoring is essential for tunnel safety assessment and early warning. As vital components of transportation infrastructure, tunnels require continuous and reliable structural health monitoring to ensure the efficiency of traffic systems. Traditional tunnel deformation monitoring methods, such as total stations and settlement gauges, typically rely on discrete point measurements. These approaches struggle to capture continuous, full-field deformation of the entire tunnel cross-section, which is essential for identifying localized damage and non-uniform settlement. To overcome this limitation, we propose a tunnel deformation monitoring method based on line-structured light. By projecting line-structured light with a laser emitter, the proposed method enables full-field deformation measurement of the tunnel cross-section. This approach provides continuous and dense deformation measurement rather than discrete point measurements. Accurate extraction of the line-structured light from captured images is a key step in the proposed method. To address the difficulties caused by intricate backgrounds in tunnel environments, we propose a background segmentation approach based on the Swin Transformer. The proposed model improves the separation of the line-structured light from the surrounding background interference. It remains effective under conditions such as dust, surface texture variation, and uneven illumination. Across 30 measurement trials, the proposed method achieved a mean error of 0.5834 mm, demonstrating sub-millimeter accuracy, as well as good stability and reliability under non-ideal imaging conditions.
Xiao, Zhiwen, Li, Zheng, Xu, Junhao, Zhu, Jiasong, Hua, Yuansheng
A Deformation Monitoring Method Based on UAV Multi-Source Data Fusion2026-99-201911/13/2026
Water conservancy and transportation infrastructure are traditionally monitored using techniques including total stations, sensor networks, or global navigation satellite systems (GNSS). Although these techniques offer high accuracy at discrete points, they are unable to identify deformations outside of monitored locations, and increasing point density significantly increases costs. Growing interest has been shown in the recently developed unmanned aerial vehicle (UAV)–based remote sensing; nonetheless, most studies rely on single data sources, which results in poor accuracy and low robustness in complex situations. To overcome these drawbacks, this study proposes a deformation monitoring method based on UAV multisource data fusion. A high-precision fused model is created by combining high-resolution oblique imagery with airborne LiDAR point clouds. During aerial triangulation, preprocessed LiDAR point clouds serve as geometric constraints. This combines extensive texture information with high geometric accuracy to enable accurate registration within a single coordinate system. A two-stage registration strategy, comprising feature-based singular value decomposition (SVD) and the iterative closest point (ICP) algorithm, is employed for multi-period models. Surface displacements are measured using cloud-to-cloud (C2C) distances, which are then broken down into orthogonal X-, Y-, and Z-components to meet technical requirements. Validation on a reservoir dam shows that the proposed strategy greatly improves monitoring accuracy and reliability when compared to single-source approaches. The automated workflow provides a practical solution for long-term infrastructure monitoring by facilitating efficient data processing and the detection of subtle surface deformations.
Xu, Junhao, Ni, Guizhu, Li, Zheng, Hua, Yuansheng
Development of a Driving Behavior Scoring Model for Electric Vehicles Oriented to Energy Consumption2026-99-212211/13/2026
Considering the huge influence of personal driving habits on the actual driving mileage of electric vehicles (EVs), together with the weak interpretability of most existing evaluation models, this research combines logistic regression and scorecard methods to build a new assessment model that focuses on energy consumption and driving behavior, and a complete closed-loop technical framework has been set up in the research process, covering key steps such as raw data preprocessing, feature mining and screening, model design and construction, as well as final score output. Taking real collected vehicle operation data as the basic research material, we extracted 17 feature indicators from three major dimensions, including driver pedal operation habits, real-time vehicle operating state, and actual energy consumption performance, and adopted the mutual information (MI) calculation method to select eight core features with strong differentiation for 100-kilometer power consumption. Since obvious nonlinear correlations exist between these core indicators and vehicle energy consumption, we adopted decision tree-based grouping processing, weight of evidence (WOE) encoding, and information value (IV) quantitative analysis to realize feature discretization and optimization, and then constructed a scoring model relying on a logistic regression algorithm. The verification results demonstrate that the proposed model has an Area Under the Curve (AUC) value of 0.83 when identifying driving behaviors with high or low energy consumption, proving its excellent differentiation ability. This model turns complicated driving behaviors into intuitive quantitative scores, effectively making up for the defects of traditional black-box models that cannot offer practical guidance for energy-saving optimization, and it can also provide solid theoretical reference and practical application support for promoting energy-saving driving behavior among EV users.
Deng, Shuxiang, Guan, Di, Wu, Yunzhu, Liang, Yongkai, Ma, Kunqi, Xu, Hang
Spatially Differentiated Reliability Modeling for Smart AtoN Networks during Offshore Wind Farm Construction2026-99-215211/13/2026
The construction of large-scale offshore wind farms significantly increases the complexity of surrounding navigable waters, posing new challenges to the reliability assessment of aids to navigation (AtoN) systems. Traditional evaluation methods often assume uniform risk conditions, which may oversimplify the non-uniform navigational environment during the construction phase. To address this issue, this paper proposes a spatially differentiated reliability assessment framework for smart AtoN networks. The construction area is divided into several spatial zones according to navigational characteristics and traffic intensity. Based on this spatial partitioning, a binary decoupling mechanism of node failure risk is established by separating the impacts of external hazards and internal engineering activities. The hardware degradation process of AtoN nodes is modeled using the Weibull distribution, and an environmental acceleration factor (EAF) is introduced to characterize the spatial variation of physical stress levels. Monte Carlo simulation is then employed to analyze the reliability evolution of the smart AtoN networks over the entire construction cycle. The results reveal pronounced spatial non-uniformity in the degradation trajectories of AtoN nodes across different zones. Compared with conventional models based on uniform assumptions, the proposed approach can more accurately capture early-stage risk concentration and the long-tail resilience effect of low-risk nodes. These findings provide quantitative support for spatially differentiated maintenance strategies and inspection planning, thereby improving navigation safety management in offshore wind farm construction areas.
Xu, Ruqing, Zeng, Fanping
Research on Driving Style Recognition Method Based on Generalized Regression Neural Network2026-99-212111/13/2026
Accurate identification of driving styles serves as a critical foundation for realizing customized driving experiences, optimizing autonomous driving systems, constructing efficient intelligent traffic management systems, and guiding the design of energy-efficient vehicles. This study aims to achieve efficient, stable, and accurate recognition of diverse driving styles. To this end, an improved driving style recognition method based on the Generalized Regression Neural Network (GRNN) is proposed. This method takes real-time vehicle driving data as the core input, enabling effective classification and precise identification of driving styles. First, the raw collected vehicle driving data were systematically preprocessed to eliminate redundant data and outliers, and three typical driving styles were classified and defined using the classic K-means clustering algorithm. Second, the standardized preprocessed dataset was rationally divided into a training set, an independent test set, and a validation set: the training set was used to optimize and train the GRNN recognition model, while the test set was adopted to quantitatively assess the overall recognition accuracy of the constructed model. Finally, the validation set was employed to comprehensively verify the generalization ability and stability of the model across different driving scenarios. Experimental results demonstrate that the proposed GRNN-based method achieves a driving style recognition accuracy exceeding 96%, with favorable generalization ability and stable performance. The research findings can provide reliable technical support and critical decision-making references for adaptive autonomous driving scenario application, intelligent traffic system optimization, and low-energy-consumption vehicle development.
Zhou, Weichen, Zhao, Shuang, He, Wenhao, Liu, Hai, Zhang, Hao
Vulnerability Analysis of Urban Road Networks Considering Cascading Failures with Intersection Turning Movements2026-99-215611/13/2026
Traditional studies of cascading failures in urban road networks mainly focus on the road segment failures, often neglecting the bottleneck effect of intersections on traffic flow. This study proposes a cascading failure model that considers the coupling between road segments and intersection turning movements. An urban road network model was constructed using Python, and a single-segment attack strategy was applied to simulate cascading failures under emergency conditions. Using average system travel time, network efficiency, and Origin-Destination (OD) demand loss as urban road network vulnerability assessment indicators, we compare the changes under different cascading failure models in the event of failures on different road segments. The results show that after considering the intersection turning movements, the propagation range of cascading failures significantly expands, the average system travel time increases, network efficiency decreases, and OD demand loss increases. If only the cascading failure process of road segments is considered, ignoring intersection effects may substantially underestimate the impact of disruptions on network performance. Therefore, accounting for intersection turning movements in cascading failure modeling more accurately captures the propagation characteristics of traffic flows, enhances the precision of vulnerability assessments, and provides theoretical support for urban road network vulnerability analysis and traffic emergency management.
Liang, Jin, Gao, Mingxia, Mo, Junwen
Research on the Grading Diagnosis Method for Wheel Tred Faults of EMU Based on Envelope Demodulation2026-99-215511/13/2026
To address the issues of low noise resistance and complex engineering implementation in traditional methods for diagnosing wheel tread faults in high-speed trains, a hierarchical diagnostic method based on envelope demodulation is proposed. This method collects axle box vibration signals and synchronized speed signals, calculates the tread fault characteristic frequency based on wheel diameter, and, after signal preprocessing and Hilbert envelope demodulation, locates the maximum amplitude at the 1x frequency corresponding to the characteristic frequency in the envelope spectrum. After conversion to dB, fault level is determined by using fixed three-level thresholds of 13 dB (preliminary warning), 18 dB (alarm), and 23 dB (alarm). The results of the simulation and field experiment show that this method can accurately extract fault features even in a strong noise environment with a signal-to-noise ratio as low as -3 dB, and the diagnosis accuracy rate reaches 93.3%. Additionally, the process is simple, computationally light, and easy to implement in engineering, providing an efficient and reliable solution for online monitoring of wheel tread faults in high-speed trains.
Li, Hailong, Hong, Zhi, Wang, Peng
Numerical Simulation of Green Water on Fixed Structures Based on OpenFOAM2026-99-213511/13/2026
To analyze wave loads on fixed offshore structures during green water events, this study employs the open-source CFD software OpenFOAM to conduct numerical simulations of green water on fixed structural decks. A numerical wave tank is first established by developing wave generation models based on both the piston-type wavemaker method and the velocity-inlet method, and by implementing a damping wave-absorption model through modification of the two-phase flow solver interFoam. On this basis, an overset grid technique is adopted to represent the fixed structure, enabling the simulation of green water on the fixed structure. The results show that the second-order Stokes waves generated by both wave-making methods converge with mesh refinement, with the velocity-inlet method exhibiting higher accuracy. Under second-order Stokes wave action, the simulated wave loads on the fixed structure agree well with analytical solutions. The present work provides a reliable numerical approach for safety design and load evaluation of marine structures.
Bai, Chunpu, Sun, Xiaofeng
Research on Multi-Train Cooperative Energy-Saving Optimization Based on Regenerative Braking Energy Recovery2026-99-213411/13/2026
With the acceleration of urbanization, passenger traffic on urban rail transit has proliferated rapidly, emerging as a significant source of urban energy consumption and impacting the efficient operation and sustainable development of urban rail transit systems. In the field of multi-train cooperative energy-saving operation for urban rail transit, previous research has faced two main challenges: First, studies often indirectly represent regenerative braking energy recovery rate through the overlap time of “traction-braking” phases, neglecting to account for intuitively demonstrating energy-saving effects. Second, research has predominantly centered on mathematical formulation and algorithmic development, neglecting practical engineering constraints and failing to adequately assess the viability of implementing operational plans in real-world scenarios. To bridge these identified gaps, this study fully integrates the characteristics of power supply sections with the spatiotemporal coupling of train operations. It analyzes the interaction scenarios of regenerative braking energy among all up- and down-bound trains within the same power supply zone that influence each other. Employing the spatiotemporal network modeling method, a three-dimensional space-time-speed grid network framework is constructed. The global train operation time and state are discretized, and the objective function is formulated to minimize the net energy consumption of train operations. A mixed-integer programming (MIP) model is developed subject to various constraints such as departure intervals, stop durations, safety tracking, and additional operational constraints. The resulting solution is an energy-optimized urban rail train timetable and operational diagram. Numerical experiments are conducted in engineering scenarios to verify the efficacy of this approach, thereby establishing a generalized framework for energy-saving optimization in actual urban rail transit lines. Two solution methods based on the constructed model are proposed for different engineering applications, ensuring safety, operational efficiency, and energy sustainability of urban rail transit operations.
Chen, Yuefeng, Lao, Ziyao, Jiang, Jiahui, Jiang, Yangsheng, Huang, Jingyang
Fault Diagnosis for Rolling Bearings Based on RCMDE and GG2026-99-213011/13/2026
Given the nonlinear and nonstationary nature of fault signals in rotating machinery, this paper proposes a fault feature extraction and identification method based on refined composite multiscale dispersion entropy (RCMDE) and Gath–Geva (GG) clustering. In the proposed approach, RCMDE is first employed to extract feature sets from the vibration signals. Principal component analysis (PCA) is then applied for dimensionality reduction, and the resulting low-dimensional features are fed into the GG clustering algorithm to achieve fault diagnosis. The effectiveness of the proposed method is validated on a typical bearing fault dataset, with classification performance evaluated using the classification coefficient and partition entropy. Experimental results demonstrate that the proposed RCMDE-GG achieves superior performance in fault feature extraction and exhibits excellent classification capability.
Wang, Guohui, Wang, Haiming, Wang, Tiecheng, Liu, Yongqiang
A Three-Dimensional Multi-Vehicle Bin Packing Method Based on VDN2026-99-213211/13/2026
With the rapid development of e-commerce and on-demand logistics, distribution centers are confronted with the dual challenge of surging cargo volumes and insufficient loading efficiency. In scenarios involving the parallel transportation of multiple vehicles, loading decisions across different vehicles exhibit mutual coupling characteristics. Without coordinated global planning, such unregulated decision-making not only diminishes the overall space utilization rate of the fleet but also gives rise to risks of uneven load distribution and compromised transportation stability. Existing research in this field, however, remains primarily focused on single-vehicle loading optimization, a limitation that renders it unable to meet the practical operational demands of modern logistics systems. To address these issues, this paper investigates the three-dimensional cargo loading problem from a multi-vehicle collaborative perspective and proposes a multi-agent reinforcement learning (RL) method based on Value Decomposition Networks (VDN), which is designed to realize the joint optimization of transportation efficiency and vehicle operational safety. Specifically, the paper models the multi-vehicle loading process as a Partially Observable Optimal Multi-Agent Markov Decision Process (OPOMDP). By adopting a centralized training and distributed execution framework, each vehicle is enabled to generate a globally coordinated loading strategy solely on the basis of its local observation data. On this foundational framework, two key mechanisms are devised to enhance the performance of the loading strategy. First, a stability cost metric, which is constructed based on dynamic shifts in the vehicle’s center of gravity, is introduced to quantify the rollover risk of the vehicle; this metric is then integrated into the reward signal of the RL model, thereby guiding the strategy to maintain transportation safety while improving the cargo loading rate. Second, a specialized placement reward mechanism is proposed to incentivize each agent to proactively explore optimal cargo rotation methods and compact spatial packing structures, which in turn reduces intra-layer voids and elevates the overall volume utilization rate of the cargo compartment. Experimental results demonstrate that the proposed method outperforms traditional heuristic algorithms and mainstream RL baseline algorithms by a significant margin in terms of loading success rate, volume utilization rate, and weight utilization rate. Meanwhile, the stability constraint mechanism embedded in the model effectively mitigates the vehicle rollover risk, ultimately achieving the synergistic optimization of loading efficiency and transportation safety.
Meng, Xiancheng, Xue, Guixiang, Yin, Haiyang, Sun, Yunjun
Adaptability Analysis of Green Technologies for Plateau Railways Based on Game Theory Combination Weighting2026-99-212611/13/2026
This study suggests a unified evaluation framework to evaluate the adaptability of green design technologies for plateau railway initiatives. We build an evaluation system that looks at four areas: External Environmental, Resource & Environmental, Socio-environmental, and Technical Feasibility. This system is needed because of the unique problems that come with high altitude, hypoxia, and ecological fragility. A new method for combining weights based on Game Theory uses both subjective (Analytic Hierarchy Process (AHP) and objective (Entropy Weight, Grey Relational Analysis) inputs to find strong indicator weights. The final ranking is done using a TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) model that uses these weights. The results show that the system is very adaptable overall, with Technical Feasibility and Resource & Environmental Adaptability being the best. Subsystem analysis shows that the Labor-saving and Environmental Protection systems are the most flexible. The framework does a good job of finding specific technologies that need to be improved because they are not very adaptable. Boxplots, line charts, and heatmaps are examples of visualizations that can help you understand performance distribution and find areas for improvement. This study provides a pragmatic, scientifically validated decision-support instrument for the selection and enhancement of sustainable technologies in extreme-environment railway engineering.
Zhang, Chi, Yang, Xinfeng
Adaptation Analysis of 643-t-Class Modular Roll-On/Roll-Off Transportation Equipment Based on SPMT for High-Temperature Gas-Cooled Reactors2026-99-213611/13/2026
Modular construction is crucial for the development of fourth-generation nuclear technology, particularly high-temperature gas-cooled reactors (HTGRs). Owing to its heavy weight, complex center of gravity, and sensitivity to dynamic disturbances during transport, the 643-t core module presents a major safety and accuracy challenge for roll-on/roll-off (Ro-Ro) transportation. Traditional static self-propelled modular transporter (SPMT) load-distribution algorithms are not adequate for the transportation of nuclear power modules because of dynamic response lag. Accordingly, a dynamic load adaptive balancing (DALEA) algorithm is proposed, integrating dynamic center-of-gravity prediction and hydraulic-suspension adaptation into a closed-loop control system. A 0.01 s sampling interval is used in the control model, while the co-simulation results show convergence within 0.08-0.09 s and a steady-state load-balance error within +/-2.5%. Using MATLAB/Simulink and ANSYS co-simulation platforms, DALEA, genetic algorithm (GA), static load allocation (SLA), and particle swarm optimization (PSO) were compared. Under uniform Ro-Ro operation, DALEA achieves a load-balancing error of 1.8%, corresponding to a 41.9% reduction relative to GA (3.1%), and reduces convergence time by 61.9% relative to GA (0.21 s to 0.08 s). The maximum platform deflection is 2.3 mm, the initial hydraulic-pressure deviation is 3.2% and then stabilizes within approximately 2.1%, the tire ground-pressure deviation is <=8%, and the total supported-load fluctuation is <=2.1%. Under the co-simulation conditions considered in this study, the 66-axis SPMT adaptive scheme indicates feasibility for 643-t module Ro-Ro transportation and provides a technical reference for modular HTGR transport.
Wang, Zhe, Qin, Yujie
Hybrid-Powered Tracked Vehicle Integrated Energy Management Strategy2026-99-212311/13/2026
To address the energy management strategy of hybrid tracked vehicles, and in order to achieve a more rational power distribution among the engine-generator set and the power battery, thereby improving overall fuel economy and system operating efficiency, this paper proposes an integrated energy management control strategy based on a rule-based strategy and deep Q-networks (DQN). Considering the structural characteristics and operating features of the series-hybrid tracked vehicle power system, a relatively comprehensive vehicle dynamics and energy management simulation model is established on the MATLAB/Simulink platform. We introduce a deep reinforcement learning method. The agent’s observation inputs are the vehicle’s operating state and power demand, whereas fuel consumption, battery limits, and various system operating restrictions are folded into the optimization objective. By continuously interacting with the model environment, the agent can continuously learn energy allocation strategies for the powertrain. After training is completed, the trained agent is tested under specific operating conditions, and the proposed integrated control strategy is compared with traditional constant-voltage control and a multi-point speed control strategy. Simulation results show that, under the same test conditions, the integrated control method can optimally adjust engine speed, thereby reducing the number of operating points in the low-efficiency range. While ensuring vehicle dynamic performance and system stability, this strategy can reduce fuel consumption by at least 3.66%, thereby demonstrating its feasibility and effectiveness in energy management for series-hybrid tracked vehicles.
Yan, Zhipeng, Shi, Feina, Zhao, Zhiying, Niu, Liye, Geng, Jiangbo
Neural Network-Based Rollover Early Warning for Multi-Axle Special Vehicles2026-99-215311/13/2026
To address the issues that multi-axle special vehicles are prone to rollover accidents during high-speed maneuvers due to their high load capacity and elevated center of mass (CoM), and that the traditional Time-To-Rollover (TTR) rollover early warning algorithm based on state estimation suffers from misjudgment and false alarm problems, this study takes a specific five-axle special vehicle as the research object to investigate rollover early warning algorithms. First, a vehicle dynamic rollover index accounting for unsprung mass was established, the index was validated via multi-condition simulations, and a rollover early warning threshold of 0.8 was determined in conjunction with the dynamic characteristics of multi-axle special vehicles. Subsequently, integrating vehicle state estimation results, a TTR rollover early warning algorithm based on state estimation was developed, and its early warning performance as well as inherent limitations were verified via simulations. Finally, a neural network-corrected TTR rollover early warning algorithm (NN-C-TTR) was proposed, the overall architecture of the algorithm and the neural network module were designed, and the algorithm was validated through both simulation tests and real-vehicle tests. The results demonstrate that the proposed algorithm effectively addresses the misjudgment and false alarm issues of the traditional TTR early warning algorithm, achieves accurate advance warning of rollover risks for multi-axle special vehicles, and exhibits outstanding reliability and engineering practicality.
Yin, Yongqi, Liu, Qiang, Yang, Yuxue, Zhu, Chengyong, Jiang, Xinhao, Zhang, Chunchao, Zhang, Zhengyi, Shu, Hongbin
Scheduling Optimization for Automated Container Terminals Using Discrete Artificial Protozoa Optimization2026-99-212911/13/2026
As container terminals advance toward intelligent automation, collaborative scheduling of quay cranes (QCs), automated guided vehicles (AGVs), and automated stacking cranes (ASCs) becomes increasingly complex due to task release times, resource exclusivity, limited transfer-buffer capacity, and battery charging constraints, which induce waiting and blocking and increase makespan. This paper develops a SimPy-based discrete-event simulation model for the QC–AGV–ASC system and formulates a makespan minimization problem under fixed charging rules. Candidate solutions comprise a task sequence and offline assignments for yard-side and transportation resources, which are decoded into executable plans via simulation. Multiple metaheuristics are implemented on a unified evaluation interface and compared across different task scales and resource configurations.
Yang, Miaofei
Research on Optimising Traffic Management for the Demolition of Zicai Bridge on Pinglu Canal Based on VISSIM Simulation Evaluation2026-99-210611/13/2026
With the ongoing construction of the Pinglu Canal, the Zicai Bridge requires demolition and reconstruction to comply with the specified navigation clearance standards. This study focuses on optimizing traffic organization during the bridge’s construction period to alleviate the pressure on the urban traffic system. Based on a review of domestic and foreign research on traffic management for road-occupying construction, we employed a literature review, field investigation, and a combination of qualitative and quantitative analysis methods to characterize the traffic conditions in the construction area. By integrating bridge engineering codes, surrounding road network data, and on-site traffic information, we conducted traffic flow planning, formulated routes for pedestrians and non-motorized vehicles, and optimized the layout of road intersections and traffic signs. Two traffic management schemes were developed, and their performance was evaluated using VISSIM simulation tests. The results indicate that Scheme Two can effectively reduce vehicle queue length, traffic delay, and the number of vehicle stops, achieving orderly traffic operation during the construction period. Its lane adjustment strategy and traffic route design can maintain the operability of urban traffic while ensuring the smooth progress of construction work, and thus provide a valuable reference for similar engineering projects.
Liao, Xiyan, Zheng, Youfu, Zhang, Lanfang
Study on the Selection of SB-Level Low Wind Resistance Metal Beam-Post Guardrail Structures2026-99-211711/13/2026
Both concrete guardrails and corrugated beam guardrails have certain wind resistance that can easily hinder wind speed in sections with severe wind-blown sand and snow. This can further cause sand and snow particles to accumulate on the road surface, thereby reducing the friction coefficient of the road surface and having adverse effects on the safety of operating road traffic. The study analyzed the formation mechanism of wind-blown sand and snow, analyzed the functional characteristics of guardrail structure, and explored the SB-level low wind resistance metal beam-post guardrail structure from the perspective of reducing wind resistance area and considering the characteristics of protective vehicles. The main conclusions are as follows: (1) In areas with high wind speed and abundant sand and snow, the roadbed guardrail will have a blocking effect on the wind due to its cross-sectional size, causing wind-blown sand and snow on the road surface. The low wind resistance guardrail can be adopted in key areas, and the metal beam-post guardrail type can be adopted. (2) Considering the types of vehicles protected by SB-level guardrails, the guardrail structure adopts the form of upper and lower beams, with the upper beam mainly protecting large vehicles (buses and trucks) and the lower beam protecting cars. (3) The connection type between beams and posts varies depending on the cross-sectional shape of the tube. Considering the low wind resistance characteristics and structural protection capabilities, circular pipe beams with good wind resistance and square pipe beams with better cross-sectional bending resistance can be used as a beam structure. Circular pipe beams are connected to posts using channel-shaped, while square pipe beams are connected to posts using C-shaped connectors.
Lu, Jian, Zheng, Ping, Jia, Ning, Zhang, Fei, Yao, Yao
Topology Modeling of Inland Traffic Based on Vessel Trajectory Turning Points2026-99-211811/13/2026
The inland waterway system features numerous tributaries and varied channel structures, forming a highly coupled traffic network that results in diverse and complex vessel encounters at river intersections. To investigate the vessel traffic flow conditions at waterway intersections, data were collected at the confluence of the Yangtze River and Xiangjiang River, which represents a typical and strategically important inland navigation hub with intensive traffic activities. Based on high-resolution AIS data, vessel trajectory turning points were identified by using the Douglas–Peucker algorithm, and the topological structure of intersection traffic networks was constructed through OPTICS clustering, thereby extracting turning patterns and navigation paths. Given the complexity of inland vessel traffic flows, the trajectories are classified into four categories according to whether they enter tributaries and their navigation directions. For each trajectory category, representative turning points were identified and treated as network nodes. The node weights were assigned based on the normalized vessel traffic density, which reflects the relative importance of different navigation behaviors. These elements were integrated into a unified topological network that captures both spatial structure and traffic intensity. The topology result reveals the distinct turning patterns and dominant navigation paths associated with vessel traffic flows at inland waterway intersections. The present findings provide a methodological basis for inland waterway planning and maritime safety management.
Wang, Ding, Chu, Xiao, Li, Jia, Wang, Junxian, Jiang, Zhonglian
Design and Implementation of an Automatic Tractor-Container Binding Identification System Based on Multi-Source Perception Fusion2026-99-203411/13/2026
To address the tractor-container binding problem in drop-and-pull transportation scenarios, this paper proposes an automatic tractor-container binding identification method based on multi-source perception fusion and implements a corresponding application system. The system integrates RFID, Bluetooth, and container positioning devices to determine whether a tractor and a container are bound, enabling automatic identification and dynamic management of binding relationships throughout the entire transportation process. In terms of identification strategy, a hierarchical decision-making and fusion verification mechanism is adopted. Through cross-validation of multi-source data, the reliability of identification results is significantly improved. When the reader fails to return data or is offline, the system can perform identification based on the trajectories of tractors and containers, thereby ensuring continuity and stability of the identification process. This approach effectively reduces the impact of complex environmental factors and wireless network fluctuations on identification results, improves binding identification accuracy, and enhances logistics transportation efficiency. A one-month large-scale test was conducted in real-world drop-and-pull transportation scenarios. The system achieved a binding record accuracy rate of 98.04%, according to the test, demonstrating the system’s feasibility and usefulness in actual engineering applications. The system offers dependable technical assistance for sophisticated, data-driven drop-and-pull transportation management.
Deng, Shiwei, Luo, Sen, Zhang, Xiang, Hu, Junjie, Wang, Zhi
Meso-Scale Freeze–Thaw Damage Characteristics of Low-Dose SBS Modified Asphalt Stabilized Macadam2026-99-210411/13/2026
To elucidate the freeze–thaw damage mechanism of asphalt-stabilized macadam from a mesoscopic perspective and to quantify the deterioration of internal parameters, this study examines the effect of adding 2% SBS to cold-region ATB-25. Specimens subjected to 0 to 25 freeze–thaw cycles were scanned using X-ray computed tomography (CT), and image-based morphometric analysis was conducted to track the evolution of key meso-scale indices, including porosity, void number, equivalent void diameter, and void fractal dimension. The results show that the porosity increase in modified ATB-25 (3.06% to 3.71%, approximately 21%) is markedly lower than that in conventional ATB-25 (3.31% to 4.31%, approximately 30%). Similarly, the increase in void number for the modified mixture (2,898 to 4,452, approximately 54%) is smaller than that for the conventional mixture (3,364 to 5,813, approximately 73%). The equivalent void diameter initially decreases and subsequently increases, whereas the void fractal dimension initially increases and then decreases, indicating early closure of small defects followed by void coalescence under cumulative freeze–thaw loading. These CT-based results demonstrate that incorporation of 2% SBS effectively restrains void growth and suppresses the formation of new voids, likely due to enhanced binder elasticity, improved aggregate–mastic bonding, and reduced moisture susceptibility. Consequently, the SBS-modified ATB-25 exhibits superior resistance to freeze–thaw damage. This study provides quantitative mesostructural evidence supporting the use of SBS-modified asphalt-stabilized macadam in cold regions and informs the optimization of mixture design to improve durability under cyclic freezing and thawing.
Zhao, Zhenguo, Shang, Yunfei, He, Yongnan, Ma, Lianxia, Liu, Bo
Design and Optimization of Electrical/Electronic Architecture for Autonomous Racing Cars Based on Central Gateway and Domain Controllers2026-99-211111/13/2026
Within the Formula Student China championship context, the electronic and electrical system of the race car is subject to exceptionally stringent performance requirements under conventional distributed architectures. However, persistent limitations remain, most notably, wiring harness layouts that become overly intricate and computing resources that are dispersed across units rather than coherently organized. Against this practical engineering backdrop, the present paper advances a domain-oriented architecture built around a “central gateway + domain controller” configuration, through which a hybrid in-vehicle network integrating CAN with Flexible Data-Rate (CAN FD) with automotive Ethernet is constructed. By design, the power domain, execution domain, and information domain are explicitly partitioned, with dual-core redundancy and hardware-level safety loops deployed inside each domain. This architecture increases bandwidth, reduces CPU loading, and improves both system security and scalability, thereby offering a strong engineering reference for autonomous racing vehicles.
Zhou, Heng, Ma, Wei
Analysis of Factors Affecting the Path Selection of Stranded Passengers in Urban Rail Transit Public Health Emergencies2026-99-211611/13/2026
In recent years, passenger stranding incidents induced by public health emergencies in urban rail transit have become increasingly prevalent. There are multidimensional factors influencing the path selection behaviors of passengers. This study takes sudden health incidents as an example and employs a pre-trial survey questionnaire to collect data on path selections made by stranded passengers under various influencing factors during sudden health-related emergencies. Furthermore, the role of travel characteristics, physical and mental health status, risk perception, and decision preferences in path selection by stranded passengers under various influencing factors is systematically analyzed. Finally, a path selection model based on the Logit model is constructed to provide scientific and actionable support for rail transit emergency management and enhance the resilience of urban transportation systems.
Han, Xue, Ruan, Xingyu, Xu, Lulu, Xue, Shantao, Cao, Youting
Integration of Commuter Carpooling Pricing and Multi-Objective Matching for Optimization Using an Improved Genetic Algorithm Based on Open-Ended Mileage Initialization2026-99-211311/13/2026
This study addresses the multiconstraint matching problem in commuter carpooling systems and develops a multi-objective optimization model that incorporates capacity limits, time window deviations, and detour tolerance constraints. An improved genetic algorithm based on the concept of open-ended saving-mileage, referred to as GAOSA, is proposed. In the mathematical modeling stage, the spatial positions of commuters are represented through two-dimensional coordinates, and feasible matching relations are established by combining arrival times with time window constraints. The fitness function is designed to reduce total driving distance and increase the matching rate. To enhance search efficiency and avoid premature convergence caused by random initialization in traditional genetic algorithms, GAOSA constructs a heuristic initial solution according to saving potential and then performs selection, crossover, and mutation to iteratively improve the matching solution. Small-scale randomly generated instances are used for experimental validation. The results show that GAOSA reduces average travel distance and accelerates convergence while maintaining the same matching rate. The method establishes an executable matching framework under spatial, temporal, and behavioral constraints and provides a computational strategy for scheduling and resource coordination in commuter carpooling systems.
Wang, Zhennan, Sha, Junlin, Wang, Yunhan, Liu, Yilin, Wang, Sikai, Wang, Hao
Quantitative and Interpretable Analysis of the Influencing Mechanisms of Ship Pilot Fatigue Based on LightGBM and SHAP2026-99-202111/13/2026
To quantify how waterborne traffic environments influence vessel operators’ fatigue and to support the development of fatigue prevention measures, a framework comprising 30 features across four major categories was constructed based on EEG-based fatigue recognition results. A LightGBM algorithm was employed to establish a quantitative model, with histogram acceleration, GOSS, and EFB strategies used to improve the processing efficiency of multi-source heterogeneous data. Combined with the SHAP method, the model’s decision-making process was analyzed from three perspectives: feature importance, single-feature effects, and interaction effects. The results indicate that LightGBM achieved the best predictive performance, with a test-set MAE of 0.04293, MSE of 0.00398, and R2 of 0.90134. Traffic flow, vessel density, and the proximity factor were identified as the three most important factors, with a cumulative contribution of 45.2%, and high traffic flow combined with high vessel density increased fatigue levels by 42.3%. This study quantifies the relative importance and influence patterns of each factor, providing practical support for maritime authorities to optimize crew scheduling and improve waterway design.
Chuan, Dingkai, Xu, Yanmin, Guan, Hongxu
Comparative Analysis of Lateral Stability of A-Double Vehicle Combinations with Different Configurations2026-99-211911/13/2026
This study investigates the lateral stability of A-double vehicle combinations, focusing on the rearward amplification effect—a critical phenomenon where dynamic responses amplify toward the rear units in multi-trailer configurations. Utilizing TruckSim simulation, a validated multi-body dynamics model of an A-double combination (a vehicle combination consisting of a tractor, a dolly, and two semitrailers) was established. Based on different semitrailer lengths, four configurations were analyzed using the model: 20 ft + 20 ft, 20 ft + 40 ft, 40 ft + 20 ft, and 40 ft + 40 ft. Simulations under a single sine-wave steering input assessed key stability metrics, including lateral acceleration, yaw rate, and their corresponding rear amplification factors (RAay and RAr). The results confirmed the presence of motion lag and rearward amplification (RA > 1) across all configurations. Stability was found to degrade with increasing speed, as both motion responses and RA factors increased. Among the configurations, the 40 + 40 combination demonstrated the best stability (lowest RA factors and highest critical speed), followed by 20 + 40, 40 + 20, and finally 20 + 20. The study also revealed that stability decreases when the payload center is positioned further from the hitch point or at a greater height. These simulation findings were substantiated by real-vehicle slalom tests conducted at the automobile test site, where the 20 + 40 configuration exhibited the best handling performance. The research concludes that, for a given total mass, A-double combinations with longer semi-trailer wheelbases offer superior stability, providing essential insights for optimizing configuration design and promoting the safe application of high-capacity vehicles in China.
Ou, Chuan-jin, Zhao, Jia-hao, Wang, Xiaoyou, Li, Yue, Zhan, Hao, Zhang, Hongwei, Huang, Baiyang, Huang, Chao-zhi
Mountainous Combined-Alignment Car-Following Model2026-99-214711/13/2026
Mountainous expressways are characterized by complex topography, resulting in extensive combined horizontal–vertical alignment sections where vehicle dynamics are more complex and the following risks are elevated. In such environments, vehicle car-following behavior is jointly influenced by inter-vehicle interactions and road geometric constraints, which limit the applicability of traditional car-following models. To address this issue, a Mountainous Combined-Alignment Car-Following Model (MCCM) is proposed based on driving risk field theory. The model constructs a vehicle kinetic energy field incorporating slope and curvature to describe the effects of combined alignments on vehicle motion, and integrates it with the road potential energy field and driver behavior field to form a unified driving risk field. The short-range interaction characteristics of the risk field are transformed into forces acting on the following vehicle, enabling simultaneous representation of vehicle dynamics, driver behavior, and inter-vehicle interactions. Measured trajectory data from a typical combined-alignment section of the Hangrui Expressway in Yunnan Province are used for model calibration and validation. Model performance is evaluated using the root mean square error (RMSE) and mean absolute percentage error (MAPE), and compared with the Intelligent Driver Model (IDM) and Safety Potential Field Model (SPFM). Results indicate that MCCM achieves higher accuracy in trajectory fitting, acceleration–deceleration response, and car-following stability, with significantly lower errors than the reference models. The proposed model provides effective support for driving safety analysis and microscopic traffic simulation on mountainous expressways.
Hu, Liwei, Ma, Siyue
A Functional Safety Decision-Making Method for Vehicles against Cyberattacks2026-99-212711/13/2026
While connected and autonomous vehicle (CAV) technology is rapidly maturing, it also introduces significant cyber-safety vulnerabilities. Various network injection attacks, typified by spoofing attacks, can tamper with on-board sensor data or manipulate control commands, thereby compromising the functional safety of vehicles. Although research on in-vehicle cyber-safety attack detection has become well-established, ensuring functional safety after an attack has been detected remains a critical unresolved challenge. Against this background, this paper proposes a novel vehicle functional safety decision-making framework that integrates cyber-safety threat assessment with functional safety protection mechanisms to maintain vehicle safety under cyberattacks. First, a game-theoretic model is adopted to perform dynamic trust evaluation on surrounding vehicles, enabling quantitative assessment of the risks posed by potentially compromised agents. Second, a safety controller based on trust-adaptive Control Barrier Function (CBF) is constructed, which adjusts safety constraints in real time according to the trustworthiness of neighboring vehicles to prevent collisions. Third, a real-time optimization layer generates safe control commands on the premise of satisfying the adaptive safety constraints. In this study, the Car Learning to Act (CARLA) autonomous driving simulation platform is used to build highway driving scenarios for validating the effectiveness of the proposed framework. The validation results demonstrate that vehicles equipped with the proposed framework can maintain a safe following distance and avoid collisions when traveling behind a cyberattacked vehicle. The proposed framework outperforms the baseline controller without trust-aware safety mechanisms and provides an important solution for preserving vehicle functional safety under cyber threats.
Liu, Ke, Zeng, Jie, Liao, Wei, Cai, Han
Items per page:
1 – 50 of 60824