交通运输工程学报

Cover and Contents of Vol.26, No.4, 2026

Cover Contents

2026, 26(4): .

FullText HTML (42) PDF (278KB) (30)

Supernetwork optimization method for low-altitude emergency supply scheduling considering extreme weather impacts

SHI Yun, WU Wei-wei, ZHANG Hao-yu, XIA Han-qing

Abstract: More> To improve the delivery efficiency of emergency supplies in disaster-stricken areas under extreme weather while balancing scheduling costs and risk control, the optimization of low-altitude flight paths and the collaboration of multi-platform resources were taken as key focal points, and a multi-objective optimization method for low-altitude emergency supply scheduling based on an improved supernetwork was studied. By considering the heterogeneity of air-ground networks and the collaborative characteristics of multi-level nodes under extreme weather, a supernetwork planning model for low-altitude emergency supply scheduling was constructed, with the selection of supply transportation paths, flight platform configuration, and transit node selection as decision variables, and the minimizations of total transportation cost, average response time, and system risk as three objective functions. In view of the difficulty in quantifying the vulnerability of transportation networks and the impact of extreme weather, an improved parameter calculation method was developed and combined with the extreme weather risk index to achieve an accurate evaluation of the supernetwork model. After the parameters were embedded into the model, the selections of emergency scheduling paths, transportation volumes, and transportation modes were optimized through collaborative computing capabilities. Based on the complexity of multi-level decision-making, a variational inequality transformation mechanism and an improved projection algorithm were designed for the model. The feasibility of the model was verified through a numerical example in an urban extreme weather scenario, and the optimal transportation paths, platform allocations, and supply flow schemes were output. Research results show that the model framework can effectively integrate multiple types of supplies, heterogeneous platforms, and multi-level node resources, and the improved projection algorithm can efficiently solve the supernetwork optimization problem. The output results of the numerical example show the optimal transportation volume allocation schemes for different supply categories corresponding to various platforms and links. On the premise of satisfying capacity and operational constraints, the optimization of cost, time, and risk objectives can be achieved, which confirms that the method possesses rapid response capability and practical application potential under extreme weather conditions.

2026, 26(4): 1-14. doi: 10.19818/j.cnki.1671-1637.2026.160

FullText HTML (121) PDF (6939KB) (117)

Cooperative traffic monitoring path optimization for multiple unmanned aerial vehicles based on multi-agent reinforcement learning

LIU Xiao-bo, XUANYUAN Jing-yi, XIE Yuan-zhi, ZHENG Fang-fang

Abstract: More> To optimize the multiple unmanned aerial vehicles (multi-UAVs) cooperative traffic monitoring path planning with battery replacement station constraints, a mixed-integer linear programming model based on the UAV team orienteering problem was constructed, and a clustering method was adopted to determine the battery replacement stations' locations to achieve uniform distribution. A multi-agent Transformer-based reinforcement learning (MTRL) algorithm framework was proposed, in which a centralized Transformer architecture was adopted. The encoder was used to learn the global graph-structured representation of the scenario via multi-head attention mechanism, and the decoder was used to generate collaborative path planning. A reward function based on the number of visited target nodes was designed to optimize the UAV visiting sequence and battery replacement strategy. A structured masking mechanism was introduced to eliminate subcircuits, repeated visits, and path conflicts, ensuring solution feasibility. Numerical experiments were conducted in scenarios of 9 types of scale with varying numbers of target nodes, battery replacement stations, and UAVs. The results show that MTRL obtains high-quality feasible solutions in all 9 types of scenarios with stable training convergence. Compared with the commercial solver, the average cumulative reward increases by 9.77%-28.77% in small- and medium-scale scenarios and by 9.34%-14.84% in large-scale scenarios, while that of the genetic algorithm and tabu search decreases by 28%-41% in large-scale scenarios. The inference time remains at the millisecond level. In 18 groups of cross-distribution generalization experiments, the relative error is controlled within 1%. The proposed framework provides an efficient solution for UAV swarm mission planning, intelligent transportation path optimization, and logistics distribution scheduling. In addition, it offers a methodological reference for the application of multi-agent reinforcement learning to complex constrained optimization problems.

2026, 26(4): 15-32. doi: 10.19818/j.cnki.1671-1637.2026.161

FullText HTML (90) PDF (8221KB) (88)

End-to-end two-layer planning and optimization method for UAV swarm spider web-inspired coverage search

DING Peng-chong, SHANGGUAN Wei, CHEN Jun-jie, CHAI Lin-guo, PENG Jia-li

Abstract: More> To address the challenges of balanced optimization between resource allocation and search execution in unmanned aerial vehicle (UAV) swarm collaborative coverage search, and to improve the balance, flexibility, and response speed of regional coverage while reducing resource consumption, an end-to-end two-layer planning and optimization method for UAV swarm spider web-inspired coverage search was proposed. The first layer focused on UAV resource allocation optimization for multi-target regions. A multi-target balanced UAV resource allocation optimization model was constructed, and a deep learning-based end-to-end network was built. The search region features and UAV parameter encoding served as the input matrix, and the optimal collaborative quantity scheme of UAV swarms for multiple regions was directly output, to ensure the coverage task requirements under reliability constraints. The second layer achieved spider web-inspired coverage path optimization. Based on the maximum resource quota from the first layer's quantity allocation result, using the structure of radial threads and capture threads in spider webs, an arbitrary convex quadrilateral region was divided into adaptive sub-regions. Through the combination of radial and parallel paths, coverage optimization was realized and parallel search of UAV swarms was supported. The results demonstrate that the objective optimization performance of the proposed deep learning-based resource allocation network is comparable to the genetic algorithm (GA), and outperforms the deep learning network with linear loss combination of the same structure and the hybrid-loss single-step reinforcement learning method. Its strategic equilibrium is improved by 84.62% compared with GA, and the solution time is greatly reduced. The planning and optimization method for UAV swarm spider web-inspired coverage search is superior to its counterpart methods in terms of the association degree between base stations and sub-regions and the flexibility of search paths. The path equilibrium of sub-regions is increased by more than 75.45%, and the larger the UAV swarm scale, the more significant the optimization effect. The UAV swarm collaborative coverage search framework considers both resource and path optimization. It can improve resource utilization rate and task reliability in urban inspection, emergency rescue, and other scenarios.

2026, 26(4): 33-49. doi: 10.19818/j.cnki.1671-1637.2026.162

FullText HTML (85) PDF (22161KB) (60)

Planning method for three-dimensional air route network of urban low-altitude logistics drones

LI Shan, ZHANG Hong-hai, LI Zhuo-lun

Abstract: More> To regulate the large-scale operational order of urban low-altitude logistics drones, a planning method for the three-dimensional air route network of urban low-altitude logistics drones was proposed. Based on the urban low-altitude layered airspace structure, the grid method was adopted for the discretization modeling of urban low-altitude airspace. Combined with the "one-network, two-layer, and three-node" route network architecture, a transfer node location model and a route network planning model were established. An algorithm framework based on a self-organizing map neural network and multi-objective simulated annealing was developed to optimize the spatial layout of transfer nodes and network topology. A simulation experiment was conducted in a certain area of Nanjing City. The results show that when the number of demand nodes is fixed, the average node degree of the transfer network is greater than that of the delivery network due to the cargo circulation function undertaken by the transfer layer. Compared with the genetic algorithm and grey wolf optimization algorithm, the proposed multi-objective simulated annealing algorithm can better balance the relationship among objectives, and the comprehensive score increases by over 17%. As the scale of demand nodes expands, the number of transfer nodes shows an increasing trend, which activates more optional route nodes and expands the dimension of drone route selection. Compared with the single-layer network, the proposed route network reduces the non-linear coefficient by 14.09% and the average route flow by 52.43%, which can effectively disperse route loads. The proposed method enables route network planning in scenarios with dense user demands and improves the operational feasibility of logistics drones in complex urban environments.

2026, 26(4): 50-67. doi: 10.19818/j.cnki.1671-1637.2026.163

FullText HTML (119) PDF (14638KB) (50)

Dynamic safety separation calculation method for low-altitude logistics UAVs considering wind disturbance effects

ZHAO Gu-hao, CAO Yu-long, ZHOU Zhi-chong, XIE Han-chen

Abstract: More> When low-altitude logistics unmanned aerial vehicles (UAVs) operate in complex wind field environments, wind disturbance significantly affects flight trajectories, making traditional fixed safety separation methods difficult to meet actual operational requirements. Therefore, a dynamic safety separation calculation method considering wind disturbance effects was proposed. A wind disturbance attitude angle coupling model was established. By analyzing the influence mechanism of wind speed on UAV attitude angles, the coupling relationships of yaw angle, pitch angle, and roll angle with wind speed components were derived. A position deviation prediction model under wind disturbance was constructed. Global Positioning System (GPS) and inertial measurement unit data were employed for parameter fitting to establish quantitative relationships of lateral, longitudinal, and vertical position deviations with wind speed. A dynamic safety separation calculation method was proposed to dynamically adjust horizontal and vertical safety separations according to real-time wind field information and flight parameters. The result shows that the standard deviations of lateral, longitudinal, and vertical position deviations are 0.88, 1.32, and 0.91 m, respectively, with all model prediction errors within 1.5 m. Under the same traffic flow conditions, compared with the traditional fixed separation methods, the dynamic safety separation calculation method reduces the number of potential conflicts by approximately 37% while maintaining a safety margin above 95%. This method can effectively respond to the impact of wind disturbance on UAV flight trajectories, significantly improving the operational safety and airspace utilization efficiency of low-altitude logistics UAVs. It can provide theoretical support for trajectory planning, conflict detection, and airspace management.

2026, 26(4): 68-78. doi: 10.19818/j.cnki.1671-1637.2026.164

FullText HTML (88) PDF (5706KB) (41)

Hub-and-spoke UAM network design model considering service quality

JIANG Yu, LONG Ying, XUE Qing-wen, YUAN Ye, YUAN Li

Abstract: More> With the rapid development of the urban low-altitude economy, scientific layout of vertical take-off and landing (VTOL) facilities and the construction of an efficiently operated urban air mobility (UAM) network constitute the key and core of UAM development. Differentiating VTOL facilities by capacity and function into vertiports and vertistops, this study established a non-strict multi-allocation two-level hub-and-spoke UAM network that incorporates capacity constraints. A multi-objective optimization model was established with the objectives of minimizing VTOL facility construction cost and network transportation cost, minimizing total travel time, and minimizing the average service quality penalty score. The model was solved using a hybrid framework based on the non-dominated sorting genetic algorithm Ⅲ, enhanced by an embedded variable neighborhood search to co-optimize the location decisions for VTOL facilities and the network allocation scheme. Ground traffic travel data of Beijing was taken as a case study. UAM travel demand was predicted and a candidate VTOL facility set was generated. Based on this, model validity was verified and parameter sensitivity experiments were conducted. Research results show that, compared to traditional two-level network structures, the two-level hub-and-spoke network reduces total cost by 0.9%, reduces total travel time by 12.1%, shortens the average travel time per unit demand by 4.12 minutes, and delivers superior service quality. The number of VTOL facilities significantly affects objective function values and network congestion. An optimal trade-off among all objectives is achieved when deploying 3 vertiports and 8 vertistops. The proposed model thus enhances both economic benefits and transportation efficiency while improving UAM service quality, offering scientific decision support for the planning of hub-and-spoke UAM networks.

2026, 26(4): 79-89. doi: 10.19818/j.cnki.1671-1637.2026.165

FullText HTML (92) PDF (10399KB) (44)

Real-time track anomaly detection and prediction correction model for low-altitude traffic control platform

ZHANG Jian-ping, LUO Chuang, ZHANG Guang-yuan, WANG Zhi-yuan, CHEN Yun-xiang

Abstract: More> An end-to-end integrated model of track anomaly detection and correction for low-altitude traffic control platforms was developed. Four types of behavioral components, such as, statistical outliers, physical envelopes, morphological patterns, and sequence residuals, were fused to form a unified anomaly score, and anomaly identification was achieved by combining a feature fusion module, adaptive thresholding, and weight optimization. A unidirectional two-layer long short-term memory prediction network combined with an attention mechanism was employed as the temporal backbone, and a differentiable physical integrator, adaptive noise estimation, and Kalman update were incorporated to obtain predicted reconstruction sequences. A back-propagatable loss function was designed, and consistency distillation was adopted to align the outputs of different branches, ultimately forming an end-to-end physics-aware Kalman long short-term memory network model. The results show that in the anomaly detection task, compared with deep baseline models, the harmonic mean score (F1), area under the average precision-recall curve (AUPRC), and area under the ROC curve (AUROC) of the developed model under a fixed threshold increase by 5.95%, 4.16%, and 2.38%, respectively. In the prediction correction task, compared with a filtering-only method and a prediction-only model, the root mean square error (RMSE) decreases by 15.2% and 21.7%, respectively. In terms of real-time deployment, when the optimal window size is 32, the computational latency decreases by 76.9% compared with the window size of 64 corresponding to the best F1 value, while the F1 value decreases by only 0.57%. The model can balance the anomaly detection reliability and real-time trajectory correction ability under millisecond-level latency constraints and can provide effective methodological support for the development of real-time trajectory anomaly detection and prediction correction functions of low-altitude traffic control platforms.

2026, 26(4): 90-107. doi: 10.19818/j.cnki.1671-1637.2026.166

FullText HTML (60) PDF (21249KB) (15)

Drone-vehicle collaborative routing optimization with transfer operations in mountainous environments

QIN Ya-qin, DENG Qin-yuan, LEI Ji-lin, QIAN Zheng-fu, ZHAO Shi-lin

Abstract: More> To address the core issues of poor vehicle accessibility and insufficient scenario adaptability in logistics systems in mountainous areas and urban fringe environments, a novel collaborative scheduling model for transfer-based drones-vehicle systems is proposed. A freight transportation system consisting of multiple drones carried by mainline distribution vehicles is considered, allowing the simultaneous takeoff of multiple drones from vehicles, where each drone can provide simultaneous pickup and delivery services for one or more customers per flight. The fulfillment of system orders involves three stages: clustering pickup and delivery demands, designing mainline vehicle routes, and determining transfer-based drone routes. Based on the above system, a mixed-integer linear programming model considering time windows and multi-drone-vehicle collaborative operations with transfers is constructed to minimize the total system cost, and an improved artificial bee colony algorithm with cross-neighborhood search is designed to solve large-scale cases. Numerical experiments at different scales were designed based on the high-altitude mountainous areas of Yunnan Province to validate the effectiveness of the model and algorithm. Research results show that, compared with the classical drone-truck parallel collaboration model, the proposed model exhibits superior performance in scenario adaptability and cost efficiency, and reduces costs by 8.0% to 46.7%. Furthermore, the improved artificial bee colony algorithm outperforms the CPLEX solver and other comparative algorithms in both solution efficiency and cost. Particularly for large-scale problems, the solution cost is reduced by 1.4% to 4.3% compared with CPLEX. Finally, sensitivity experiments demonstrate that the model has strong robustness and confirm that adopting a relaxed time window strategy and increasing drone endurance in mountainous environments can effectively improve the efficiency and cost-effectiveness of distribution operations.

2026, 26(4): 108-120. doi: 10.19818/j.cnki.1671-1637.2026.167

FullText HTML (62) PDF (2312KB) (30)

Method for UAV adaptive cruising trajectory planning for high-risk road sections of forest roads

CHEN De-qi, ZHANG Shu-hui, ZHANG Wen-hui, JIANG Xian-cai

Abstract: More> To mitigate forest road traffic accident risks caused by canopy obstruction, a deep reinforcement learning (DRL)-based adaptive cruising model for UAVs that accounts for state uncertainty was proposed. At the perception stage, an adaptive unscented Kalman filter (UKF) tailored to forest road scenarios was designed to address global positioning system (GPS) signal loss. At the decision-making stage, a state uncertainty-aware soft actor-critic (SUA-SAC) algorithm was developed, where UKF-derived state estimates and their covariance were used as network inputs, enabling SUA-SAC to learn control strategies that are more robust to state estimation. The results show that, in terms of training efficiency, the convergence speed of SUA-SAC is improved by approximately 50% and 60% compared with the baseline SAC algorithm and proximal policy optimization algorithm. In multi-scenario tests, compared with the SAC algorithm, SUA-SAC reduces the average tracking error by 67%, 61%, and 66% in scenarios without interference, dynamic occlusion, and strong wind interference, respectively. In tests involving positioning signal loss lasting up to 20 s, the tracking error of SUA-SAC is less affected. Overall, SUA-SAC improves UAV trajectory tracking accuracy, flight stability, and mission success rate under complex forest road conditions, contributing to the enhancement of traffic safety on forest roads.

2026, 26(4): 121-133. doi: 10.19818/j.cnki.1671-1637.2026.168

FullText HTML (50) PDF (5020KB) (17)

Optimization model of medical UAV transportation network for biological sample leakage risk

ZHAO Jia-hong, ZHANG Jian-ping, HU Peng, ZHANG Long-fei, ZHANG Guang-yuan

Abstract: More> To ensure the safety of low-altitude transportation of biological samples, a multi-objective optimization model and a solution procedure are developed for the medical UAV transportation system. Considering the randomness of UAV transportation accidents, as well as the risk of biological sample leakage, a risk measurement model for medical UAV transportation is established. A medical UAV transportation network optimization model is built with the objectives of minimizing total cost and total risk. Considering the computational complexity of the proposed model, a modified NSGA-Ⅱ algorithm is adopted to design the solution procedure. Finally, a real-life case in Shenzhen, China, and several test cases are used to demonstrate the effectiveness of the proposed model and algorithm. The results show that the proposed model provides 165 effective transportation network optimization schemes for biological sample transportation in Shenzhen within 3 023.51 s. Compared with traditional risk models, the proposed risk measurement model quantitatively evaluates the transportation risk of cargo-carrying medical UAVs, and the obtained solutions reduce the total cost by an average of 18.32% and increase the degree of risk sharing by an average of 1.3 times. When solving optimization problems of different scales, the improved algorithm provides multiple non-dominated solutions within limited solution time and maintains a certain level of computational stability. The proposed model and solution algorithm provide medical UAV transportation network planning schemes and risk control methods for low-altitude transportation and emergency safety management of biological samples.

2026, 26(4): 134-143. doi: 10.19818/j.cnki.1671-1637.2026.169

FullText HTML (42) PDF (2791KB) (13)

District-level layout planning of UAV takeoff and landing sites based on the NSGA-Ⅱ algorithm: A case study of Nanshan District, Shenzhen

HUANG Qi-xiang, JIANG Zhi-bin, ZHANG Hong, LI Ya-ying

Abstract: More> Aiming at the multi-objective coordination challenges in the layout planning of unmanned aerial vehicles (UAV) takeoff and landing sites in high-density urban areas, including coverage efficiency, construction cost, airspace risk, and environmental noise, an optimization model integrating the multi-dimensional objectives above was proposed. An improved non-dominated sorting genetic algorithm (NSGA-Ⅱ) was adopted for the solution. Taking Nanshan District, Shenzhen as an example, a hybrid planning model covering three functions of passenger transport, freight, and urban governance was constructed. In the algorithm design, a hierarchical chromosome encoding scheme was proposed, including latitude and longitude coordinates, functional types, and scale levels. A dynamic constraint handling mechanism was applied to coordinate complex constraints such as airspace safety, land use compatibility, and noise sensitivity. Specifically, for freight takeoff and landing sites, a hierarchical connection rule was introduced to ensure the integrity of the urban logistics network. The analysis of typical schemes shows that, in core business districts, the passenger-oriented scheme has relatively high service coverage efficiency yet with higher airspace management pressure; freight optimization scheme can significantly improve logistics efficiency in logistics hubs, but the noise impact range rises by 25%; the balanced scheme is the most applicable in mixed-function areas like university towns; minimalist scheme provides feasible pathways for areas with budget constraints or ecological sensitivity. Meanwhile, further parameter analysis indicates that reducing the distance between first- and second-level freight hubs from 5 km to 4 km can improve freight efficiency by 12% but increase airspace conflict risks by 18%. The installation of noise barriers can reduce residential area noise by 4 dB yet with an additional cost of 100 000–200 000 RMB per site. A differentiated layout strategy is ultimately proposed: business districts such as the technology park adopt passenger-oriented layouts, and areas such as Mawan Port are equipped with a complete three-level freight network. The areas surrounding the Shenzhen Bay Nature Reserve are restricted to micro takeoff and landing sites. The multi-objective optimization framework and improved solution algorithm constructed in this paper provide a complete and quantifiable decision-support tool for the planning of UAV takeoff and landing sites in high-density urban areas, from modeling, solving, to scheme comparison.

2026, 26(4): 144-166. doi: 10.19818/j.cnki.1671-1637.2026.170

FullText HTML (52) PDF (6559KB) (12)

Automated detection and analysis technology for traffic conflicts based on unmanned aerial vehicle video data

GUO Yan-yong, LUO Yuan-wei, DAI Shuai, LIU Pan

Abstract: More> To achieve rapid and automated extraction of traffic conflicts, a traffic conflict detection and extraction method based on unmanned aerial vehicle (UAV) video was proposed. A video stabilization method integrating feature point extraction and matching algorithms was developed to eliminate frame-to-frame translation and rotation caused by UAV flight jitter and to ensure stable vehicle trajectory extraction. A rotated vehicle detection algorithm based on the YOLOv8-OBB model was developed and combined with the ByteTrack tracking method, where high- and low-confidence detection boxes were fused to enable continuous extraction of vehicle trajectories. The Savitzky-Golay filter was adopted to denoise and smooth the trajectories, thus retaining the original features of the trajectories and eliminating noise. A traffic conflict detection and classification method based on vehicle trajectories was developed, using bounding box-based approaches to calculate TTC, PET, and MTTC indicators and improve detection accuracy. Invalid conflicts were eliminated through a rationality verification mechanism, and angular conflicts, lateral conflicts, and rear-end conflicts were distinguished according to the vehicle heading angle and the predicted collision position at the time of conflict. A case study was conducted at three signalized intersections in Nanjing. The results show that traffic conflicts can be extracted rapidly and accurately from videos by the automatic traffic conflict detection method, with a detection accuracy of 92%. The average processing speeds of the video stabilization algorithm, trajectory extraction algorithm, and conflict extraction algorithm are 3.64 frames per second, 5.38 frames per second, and 250 frames per second, respectively, which meet the requirements for rapid analysis of large-scale video data. The results help improve the quality of traffic conflict data and provide reliable data support for traffic safety research based on traffic conflicts, demonstrating broad application potential.

2026, 26(4): 167-183. doi: 10.19818/j.cnki.1671-1637.2026.038

FullText HTML (48) PDF (8992KB) (21)

Progress in software-defined intelligent ship navigation control for the new generation of waterborne transportation system

MA Yong, WANG Wen-qi, HAN Meng-ru, ZHAO Yu-jiao, YAN Xin-ping

Abstract: More> To meet the development needs of the new generation of waterborne transportation systems and intelligent ships, the current status of software-defined technology and its application in intelligent ship navigation control were reviewed. A centralized software-defined intelligent ship navigation control architecture was constructed, featuring a four-end, three-layer structure, composed of user, cloud-control, ship, and shore-based terminals, as well as application, control, and device layers. This architecture migrates decision-making and control functions to software modules deployed on a cloud-control terminal or a local server, thus enabling software-based, modular, and service-oriented implementation of these functions. The results indicate that this architecture offers significant advantages. At the system level, the architecture achieves high structural flexibility, reconfigurability, and scalability, which substantially reduce system maintenance costs. At the functional level, the architecture supports rapid iteration of control algorithms, online upgrades, and on-demand deployment. At the operational level, the architecture supports flexible switching among multiple control modes, including assisted driving, remote control, and autonomous navigation. A case study of an intelligent navigation control system for an unmanned surface vehicle validated the architecture's ability to effectively support navigation tasks ranging from basic to complex, demonstrating comprehensive capabilities in high-precision control, scalable formation collaboration, and network-resilience defense. The proposed software-defined intelligent ship navigation control framework provides an open, intelligent, and sustainably evolving paradigm, offering critical support for a new-generation shipping system to realize an operating model where shore-based control serves as the primary mode, supplemented by onboard watchkeeping.

2026, 26(4): 184-199. doi: 10.19818/j.cnki.1671-1637.2026.209

FullText HTML (31) PDF (7589KB) (10)

Research progress, key technologies, and prospects of digital twin technology for inland waterway

LIANG Cai, LI Wen-yong, WANG Chang-hai, SHEN Wei, ZHOU Xiao-qin, LUO Ren-tong

Abstract: More> To clarify the conceptual connotation, key technologies, and development trends of digital twins for waterways and to promote the transformation and upgrading of inland waterways towards refined and intelligent management throughout the full lifecycle, a research method combining bibliometrics and text mining was adopted. Relevant Chinese and English literatures from 2000 to 2025 were systematically reviewed. The research status and key characteristics of digital twins in the waterway field were summarized and analyzed, and the definition and related concepts of waterway digital twins were discriminated and compared. In view of the characteristics of inland waterway projects, a full lifecycle management paradigm for inland waterways driven by digital twin technology as the core was established, and the data of the whole process from waterway design and construction to operation, maintenance, management, and service were connected. Furthermore, a cross-stage data mapping mechanism based on engineering breakdown structure (EBS) and a digital twin system architecture for inland waterways oriented to the full lifecycle were proposed, covering core elements such as data foundation, basic support platform, algorithm model platform, and application service platform. The application case of the Pinglu Canal project was introduced. The application status, challenges, and future development prospects of waterway digital twins were discussed. Research results show that current waterway digital twins face many challenges, such as the unformed comprehensive and precise perception system, difficult multi-source data fusion and governance, insufficient model simulation and interaction capabilities, and insufficient application effectiveness and intelligence level. In the future, it will develop towards the directions of space-air-ground-water integrated intelligent perception, full lifecycle management and control, real-time computing and simulation deduction, AI autonomous decision-making and intelligent control, and multi-industry integration. Through the construction of digital twin systems and technology applications, the whole-process construction management and control of waterways and the transformation of all-round intelligent operation and maintenance business are driven, supporting the smarter and more efficient transformation and upgrading of waterway management.

2026, 26(4): 200-229. doi: 10.19818/j.cnki.1671-1637.2026.083

FullText HTML (44) PDF (9059KB) (13)

Review of urban resilient transportation systems: Assessment methods and optimization improvements

WEI Ya-xin, LI Kun, MU Chen, LI Ying, TENG Jing, MA Xiao-lei, WANG Jian, AN Yi-sheng, DU Yu-chuan, ZHAO Xiang-mo

Abstract: More> To systematically review the assessment methods and optimization strategies of urban resilient transportation systems, an analytical framework centered on robustness and recoverability was constructed, and existing studies were synthesized and reviewed based on this. Regarding resilience assessment, four types of mainstream methods were systematically analyzed: graph theory and complex networks, probability statistical models, data-driven approaches, and multi-indicator assessment. Regarding resilience optimization, from single- and multi-dimensional perspectives, preventive strategies represented by network structure reinforcement and responsive strategies represented by emergency resource dispatching were investigated. By analyzing decision variables and objective functions, a theoretical mapping mechanism between assessment indicators and optimization strategies was constructed. The analysis results show that existing assessment methods are transforming from single physical topology measurement to intelligent assessment integrating spatiotemporal causal inference. Meanwhile, optimization strategies are evolving from static equilibrium of local road networks to dynamic games of cross-system coupling. The study clarifies the synergistic mechanism between assessment and optimization, and the identification of robustness boundaries and vulnerable nodes directly defines the solution space constraints for preventive optimization. In addition, the recoverability curve and performance loss quantification provide standardized benchmarks for constructing the objective functions of responsive optimization. Future research needs to focus on the deep integrated design of assessment and optimization, establishing closed-loop decision-making models capable of dynamic feedback and self-adjustment. Simultaneously, the integration of physical models and artificial intelligence methods should be strengthened to develop predictive assessment and proactive optimization technologies for complex scenarios, thus providing key theoretical and technical support for constructing intelligent and highly resilient urban transportation systems.

2026, 26(4): 230-258. doi: 10.19818/j.cnki.1671-1637.2026.210

FullText HTML (48) PDF (14625KB) (19)

Review of wireless communication channel characteristics and modeling research for intelligent transportation scenarios

LI Chang-zhen, LUO Su-su, ZHANG Zi-jian, YU Fa-yong, ZENG Xu-ming, CHEN Wei

Abstract: More> To promote mobile communication technologies to further empower the construction of intelligent transportation systems, the research status of communication channels in various transportation scenarios in China and abroad was reviewed from three aspects: wireless channel measurement, channel characteristics, and channel modeling. According to the application and technical requirements of different transportation systems, the relevant channel measurement and models results for road transportation, rail transportation, waterway transportation, and low-altitude scenarios were summarized respectively. In terms of channel measurement, the selection principles of typical measurement scenarios were elucidated from the perspective of the influence mechanism of communication environments on radio wave propagation; the common factors affecting radio wave propagation were summarized. In terms of channel characteristics, the influence of environmental factors on channel characteristics was analyzed, and the typical channel characteristics under different transportation scenarios were summarized and sorted out. In terms of channel models, the construction methods of channel models for different transportation scenarios were introduced, and the established reliable channel models were summarized. The results indicate that in the road transportation scenario, the wireless channel characteristics are significantly affected by the surrounding environments, such as buildings and vehicles on both sides of the road. Due to the rich dynamic scenarios, radio wave propagation frequently switches between line-of-sight and non-line-of-sight, and the resulting multipath effect and Doppler effect are obvious, which puts forward an urgent demand for low-latency and high-reliability communications; in the rail transportation scenario, the channel characteristics and models in environments such as viaducts, cuttings, stations, and tunnels are emphatically analyzed, pointing out that there is an urgent need for communication technologies to realize the highly informatized whole process of train operation (including trains and surrounding environments); in the waterway transportation scenario, the channel characteristics and models under marine and inland river environments are mainly analyzed; the time-varying non-stationarity of the channel caused by special factors such as ocean wave movement and sea surface evaporation duct in marine communications is analyzed, and the influence mechanism of multidimensional complex factors such as changeable scenarios, dynamic interference, diverse propagation, and land-water mixture on radio wave propagation in inland river communications is revealed; in the low-altitude scenario, the demands for reliable transmission of flight control and image transmission data of communication channels in complex urban environments and low-altitude dynamic airspaces are expounded. The research is helpful to deeply understand the wireless channel characteristics of different transportation scenarios and provides more reliable and efficient communication technology support for modern integrated intelligent transportation systems.

2026, 26(4): 259-275. doi: 10.19818/j.cnki.1671-1637.2026.077

FullText HTML (32) PDF (8672KB) (18)

Design of grounding system of propulsion coils for low-vacuum tube maglev train

LI Qiu-jun, HU Dao-yu, GAO Tian-yu, ZHANG Zhi-hua

Abstract: More> To study the grounding system of propulsion coils and the distribution of overvoltage characteristics for low-vacuum tube maglev train, a dual-port equivalent circuit model including ground propulsion coils, a metal low-vacuum tube, and distributed grounded devices was established. The accuracy of the equivalent circuit model was verified with data from published literature. Based on this model, the voltage response distribution characteristics of propulsion coils under lightning overvoltage were analyzed. The grounding system design was optimized from two dimensions: the number of ground points of propulsion coils as well as the insulation resistance between longitudinal grounded lines and the metal low-vacuum tube. Analysis results show that when lightning strikes the propulsion coils, local overvoltage is induced, but the overvoltage of other propulsion coils is suppressed by grounding. Between two ground points, the voltage changes with the distance from the ground points. The voltage shows a trend of first rising and then falling. The metal low-vacuum tube acts as a lightning protection strip to ensure that lightning cannot strike the propulsion coils directly. Meanwhile, insulation resistance exists between the longitudinal grounded lines (connected to the propulsion coils) and the metal low-vacuum tube, which effectively ensures that the overvoltage is suppressed to less than 1.0. The insulation resistance value between longitudinal grounded lines and the metal low-vacuum tube significantly affects the overvoltage level in propulsion coils. When the resistance value is greater than 10 kΩ, the overvoltage of all propulsion coils along the line can be guaranteed to be less than 1.0. Therefore, the configuration can be optimized with two parameters, namely, the number of ground points and the resistance between longitudinal grounded lines and the metal low-vacuum tube. Thus, the engineering implementation cost can be reduced while ensuring system safety. A theoretical basis and technical support is provided for the engineering application of ultra-high-speed low-vacuum tube maglev trains.

2026, 26(4): 276-285. doi: 10.19818/j.cnki.1671-1637.2026.019

FullText HTML (24) PDF (6335KB) (7)

Adaptive sliding mode acceleration slip regulation control based on road identification for distributed electric drive buses

YANG Bing, FU Rui, SUN Qin-yu, JIANG Si-yang, WANG Chang

Abstract: More> To solve the problem of excessive slippage of the driving wheels when distributed electric drive buses start on low-adhesion roads, an acceleration slip regulation (ASR) control strategy based on road identification and adaptive sliding mode control (ASMC) was proposed. A nonlinear vehicle dynamics model and a Dugoff tire model were established. A road adhesion coefficient estimation method was designed based on the high-degree cubature Kalman filter algorithm with singular value decomposition. Combined with the tire parameters of the target vehicle model, the tire test module in TruckSim was utilized to test tire characteristics and determine the optimal slip ratios under different road surfaces, based on which an ASR trigger and exit mechanism was designed. An anti-slip control algorithm based on ASMC was designed, into the reaching law of which an exponential adaptive gain was introduced to adaptively adjust the control force according to the error size, accelerate the slip ratio tracking speed, and suppress overshoot. Test maneuvers were set combined with the collected real-vehicle starting data. Based on the joint simulation platform of MATLAB/Simulink and TruckSim, the performance of the proposed ASR control strategy was verified under different starting maneuvers and loads and compared with the traditional model predictive control (MPC), first-order sliding mode control (FOSMC), and integral sliding mode control (ISMC) methods. Analysis results indicate that under four typical test maneuvers, the ASR control strategy based on ASMC minimizes both the average absolute error and root mean square error of slip ratio tracking; it increases the bus speed by 30.45%, 10.01%, 24.55%, and 13.45% compared with MPC, by 5.62%, 5.08%, 5.38%, and 6.35% compared with FOSMC, and by 4.09%, 2.74%, 3.21%, and 4.64% compared with ISMC, respectively. The proposed ASR control strategy can improve the longitudinal stability and driving performance of distributed electric drive buses, providing an important reference for the torque control system design of distributed electric drive buses.

2026, 26(4): 286-302. doi: 10.19818/j.cnki.1671-1637.2026.020

FullText HTML (37) PDF (6248KB) (10)

Trajectory tracking control technology for autonomous vehicles based on dynamic Kalman polynomial networks

CAI Ying-feng, ZHANG Yu-hang, SUN Xiao-qiang, ZHANG Xiao-dong, WANG Hai, CHEN Long

Abstract: More> To achieve high-reliability and high-precision trajectory tracking control for autonomous vehicles in complex dynamic scenarios, a predictive control framework based on a dynamic Kalman polynomial network was proposed. The dynamic characteristics of vehicles were captured by utilizing time-series memory capabilities, and the adaptive adjustment of Kalman filter was integrated to achieve the optimal correction of real-time control errors. By utilizing the nonlinear feature extension of polynomial networks, the modeling capability of the system was further enhanced. Dynamic perception, error correction, and nonlinear modeling were integrated into the method, significantly enhancing the adaptability and precision of the system to vehicle dynamics variations. Furthermore, a feedback controller based on lateral and heading deviations was incorporated to work synergistically with the predictive module, thereby achieving more accurate path tracking error correction. The co-simulation verification of CarSim and Simulink shows that the predictive-feedback controller exhibits obvious advantages under extreme conditions of low-adhesion surfaces and high-speed emergency lane changes. Specifically, under the condition of high-speed emergency lane changes, compared with ILQR and NMPC controllers, the root mean square value of the lateral deviation of path tracking is reduced by 32.5% and 38.4%, respectively; the root mean square value of heading deviation is reduced by 37.8% and 40.0%, respectively. The proposed method can provide an innovative and effective solution for the high-precision and high-reliability trajectory tracking control in autonomous driving systems.

2026, 26(4): 303-318. doi: 10.19818/j.cnki.1671-1637.2026.021

FullText HTML (42) PDF (7643KB) (13)

Impact of seat stiffness and angle on frontal crash injuries for elderly occupants in face-to-face seating configurations

WU He-quan, MI Hai-lin, CAI Jin-jue, LI Qi-qi

Abstract: More> To explore the impact of seat backrest rotational stiffness and angle on the injuries of elderly occupants in face-to-face scenarios during frontal collisions, a frontal crash simulation model at 56 km·h^-1 was constructed, incorporating a seat system with the THUMS elderly human body finite element model. By comparing the results with frontal full-vehicle crash tests, the coupling effectiveness between the occupant restraint system and the dummy model was validated. The study focused on investigating the influence of the front seat backrest at the standard 100° angle and the semi-reclined 125° angle, combined with rigid and flexible stiffness characteristics, on kinematic responses and injuries to multiple body regions, including the head, neck, chest, internal organs, and lower extremities, of both front- and rear-row elderly occupants. The results indicate that, in the frontal crash simulation tests, for front-row occupants under both seat angles, the injury probabilities for various body regions in the flexible seat condition were significantly higher than those in the rigid seat condition. In particular, under the 100° flexible seat condition, the head injury values all exceeded the thresholds, indicating a severe risk of head injury. Under the 125° flexible seat condition, the injury risks for various body regions were lower than those under the 100° flexible seat condition. For rear-row occupants, the injury index values for various body regions were generally high, with four rib fractures occurring in the chest, and the strain values of the lungs, heart, and liver exceeding the thresholds by nearly two times. Lower extremity contact occurred for both front- and rear-row occupants but did not exceed the thresholds. Across the four sets of tests, the differences in injury values for various body regions of rear-row occupants were minimal, indicating that the motion of front-row occupants had a limited impact on rear-row occupant injuries. Future seat design needs to consider both rigid structural optimization and angle adjustment to balance safety and comfort, while strengthening the rear restraint system to disperse impact energy.

2026, 26(4): 319-332. doi: 10.19818/j.cnki.1671-1637.2026.069

FullText HTML (28) PDF (27600KB) (8)

User Center

Journal Info

Index byMore>

Current Issue
2026, Volume 26, Issue 4

Search Type

Search Journal

LinksMore>