Top Downloaded

Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

In last 2 years

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Collaborative Driving Decision-making Method of Unmanned Mining Trucks in Open-pit Mine Operation Areas NI Haoyuan, YU Guizhen, LI Han, CHEN Peng, LIU Xi, WANG Wenda Journal of Transportation Systems Engineering and Information Technology    2024, 24 (3): 277-289.   DOI: 10.16097/j.cnki.1009-6744.2024.03.027 Abstract （128）      PDF （3340KB）（961）       The long parking and waiting time of unmanned mining trucks in open-pit mines during transportation in the loading and unloading operation area is a bottleneck that restricts the efficiency improvement of unmanned transportation systems in open-pit mines. To improve the transportation efficiency of unmanned mining trucks, this paper combines the transportation operation process in the operation area and proposes a multi-vehicle collaborative driving decision-making method based on dynamic travelable distance. The decision-making model was formulated as a mixed integer linear programming (MILP) model to express the optimization objective and problem constraints. Considering the challenge of meeting real-time decision-making requirements in solving the MILP model, the multivehicle conflict resolution was implemented based on Monte Carlo tree search (MCTS). The core idea was to use the derivation capability of the search tree to conduct forward simulation of multi- vehicle driving, calculate the optimal driving priority of multi-vehicle, and thereby dynamically adjust the travelable distance of multi-vehicle. In addition, different MCTS node value functions were designed based on the operating characteristics of unmanned mining trucks in the operation area to achieve driving priority ranking that comprehensively considered transportation efficiency and operating characteristics. A multi- vehicle driving simulation experiment was designed in the scenario of 4, 8, and 12 parking spots in the operation area. Compared with the method based on first-come-first-served (FCFS), the throughput was increased by 22.03% to 28.00% and the average parking waiting time was shortened by 31.71% to 50.79% . In addition, a 6-parking spots operation area scenario experimental platform for miniature intelligent vehicles was built. The total multi-vehicle single-operation time was reduced by 18.84% compared to the FCFS. The results of simulation and miniature intelligent vehicles experiments indicated that the proposed method could enhance the efficiency of multi-vehicle transportation in open-pit mine operation areas.

Select

Prediction of Outbound Transportation Volume of Xinjiang Coal Railway by Integrating Sparrow Search with Long Short-Term Memory LI Haijun, ZHANG Xiaoyang , GAO Ruhu , WEI Dehua, CHEN Xiaoming Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 14-23.   DOI: 10.16097/j.cnki.1009-6744.2024.05.002 Abstract （199）      PDF （2275KB）（636）       To enhance the precision of predicting the Xinjiang's coal railway outbound volume transportation, a prediction model integrating the sparrow search algorithm and the long and short-term memory network (SSA-LSTM) is proposed. The model introduces the sparrow search algorithm to optimize the hyper-parameters of the LSTM model in order to improve the model prediction performance. Based on the data of Xinjiang coal rail outbound transportation volume from 2015 to 2022, the gray correlation analysis is employed to comprehensively evaluate the impact of factors, including economic and transportation aspects, ensuring that the selected factors exhibit a strong correlation with the prediction targets. Among the influencing factors, the GDP data is adjusted for Consumer Price Index (CPI) effects, and the refined data are then fed into the model for prediction. Finally, the model is applied to predict the Xinjiang's coal rail outbound transportation volume across short, medium, and long time horizons. The results demonstrate that the SSA-LSTM model outperforms both the BP neural network and the conventional LSTM model, achieving a Mean Absolute Percentage Error (MAPE) of 0.88% and a Root Mean Square Error (RMSE) of 49.9. Furthermore, incorporating CPI processing into the prediction process significantly reduces the prediction error, with MAPE and RMSE decreasing by 75.8% and 56.2%, respectively, compared to non-CPI-processed predictions. This study provides an effective approach for predicting Xinjiang's coal rail outbound transportation volume, offering important data insights that inform the strategic design of coal transportation routes out of Xinjiang.

Select

Prediction of Transportation Industry Carbon Peak in China LI Ninghai, CHEN Shuo, LIANG Xiao, TIAN Peining Journal of Transportation Systems Engineering and Information Technology    2024, 24 (1): 2-13.   DOI: 10.16097/j.cnki.1009-6744.2024.01.001 Abstract （513）      PDF （2327KB）（609）    PDF(English version) （684KB）（2）    Transportation industry faces a series of challenges under the strategy of "carbon peak" due to the high carbon emissions. This paper analyzes the current situation of the carbon emissions in passenger and freight transportation in China. Based on the statistical data and relevant research results, this study simulates the carbon emissions of the transportation industry including private cars. The carbon emission factors of each transportation mode are calculated. The trend of passenger and freight turnover in 2019 to 2040 is predicted based on the experience of some developed countries. Taking 2040 as the target year, the scenarios of future transportation structure and carbon emission factors were designed, and the time and value of carbon peak for transportation in China are estimated. The results show that the transportation carbon emission, including private cars, is 1.11 billion tons in 2020. It is predicted that the passenger transportation demand will be 8.2 to 8.7 trillion person-kilometers, and the freight transportation demand will be 27.3 to 28.7 trillion tonnage kilometers in 2040. It is verified that it would be difficult to achieve the carbon peak before 2040 only through improving the transportation structure, and it is also significantly important to promote the upgrading of clean transportation technology. The scenario analysis shows that the transportation industry is expected to achieve the carbon peak in 2031 to 2034 by encouraging the transformation of transportation structure such as "road to rail" and "road to water", and promoting the cleanliness of roadway transportation.

Select

Urban Road Traffic Accidents Prediction Based on Image Sequence Analysis HU Zhenghua, ZHOU Jibiao, MAO Xinhua, ZHANG Minjie Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 91-102.   DOI: 10.16097/j.cnki.1009-6744.2024.05.009 Abstract （202）      PDF （3453KB）（593）       To further improve the accuracy of traffic accident prediction in road networks, a short-term traffic accident prediction method based on sequential image analysis is proposed. First, an oversampling technique is applied to interpolate traffic accident data collected from a WeChat mini-program to mitigate the impact of extensive zero values within the data on model training accuracy. These data are then integrated with road network traffic flow and accidentrelated attributes to generate stable time series as input for the model. A Bidirectional ConvLSTM U-Net with densely connected convolutions (BCDU-Net) is constructed. In this model, bidirectional ConvLSTM structures are used to integrate the features from the encoder and decoder layers, comprehensively capturing spatiotemporal correlations in the sequential data. Additionally, densely connected convolutions are employed to concatenate feature maps in the depth dimension, ensuring that each layer can directly access gradients from the loss function. Finally, the performance of the proposed model is evaluated by comparing the predicted results with actual traffic accident data. The results show that, compared to the Fully Connected Long Short-Term Memory (FC-LSTM) model, the Convolutional LSTM (ConvLSTM) model, and the U-Net model, the proposed model achieves reductions in cross-entropy loss of 65.96%, 15.70%, and 3.47%, reductions in root mean square error of 21.48%, 3.13%, and 1.71%, and increases in precision of 75.06%, 11.82%, and 3.08%, respectively. It is demonstrated that the proposed method offers superior performance in predicting urban road traffic accidents.

Select

Calculation for Carbon Emission Reduction Effect of Urban Rail Transit Based on Carbon Recovery Period Theory YANG Yang, WANG Xue-chun, YUAN Zhen-zhou, CHEN Jin-jie, NA Yan-ling Journal of Transportation Systems Engineering and Information Technology    2023, 23 (5): 1-11.   DOI: 10.16097/j.cnki.1009-6744.2023.05.001 Abstract （514）      PDF （2003KB）（581）    PDF(English version) （1142KB）（33）    Reasonable quantification of the carbon emission reduction effect of urban rail transit has theoretical and practical significance to calculate the external cost of urban rail transit, enrich the theoretical system of carbon trading in the field of transportation, and even formulate subsidy policies for urban rail transit. This paper considered the passengers' travel behavior difference after the construction of urban rail transit, and established the carbon emission model of urban rail transit datum line and project activity from the perspective of life cycle. Furthermore, a theoretical model of carbon recovery period was established as a quantitative indicator of carbon emission reduction effect of urban rail transit. Carbon recovery period refers to the duration of carbon emission recovery toward the construction period through carbon emission reduction during the operation period, which is the time when the cumulative carbon footprint changes from positive to negative for the first time. Then, the urban rail transit data collection was completed in the datum line, project construction and activity period, and the model is calibrated. The Shijiazhuang Subway Line 3 was taken as a case study, the carbon emissions of its datum line, the project construction period and the project activity period were analyzed, and the carbon recovery period was calculated under the two models of future development. The results show that the carbon recovery period is respectively 27 years, 22 years and 29 years under normal, rapid, and slow growth scenarios. Under the scenario of normal development of energy structure and energy efficiency level, rapid development and slow development, the carbon recovery period is respectively 25 years, 24 years and 29 years. The conclusions indicate that large-scale passenger volume and efficient passenger transportation intensity are important elements for the positive impact of carbon emission reduction in urban rail transit. The systematic changes brought about by the adjustment of energy structure and the energy efficiency improvement can have a great positive impact on the carbon emission reduction of urban rail transit.

Select

Research on Energy Consumption and Carbon Emissions in the Whole Life Cycle of Beijing-Xiong'an Intercity Railway CAO Meng, YUAN Zhenzhou, YANG Yang, NIE Yingjie, NA Yanling, SUN Yunchao, CHEN Jinjie Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 37-44.   DOI: 10.16097/j.cnki.1009-6744.2024.05.004 Abstract （146）      PDF （1339KB）（572）       As the backbone of green transportation, intercity railways play a supporting role in reducing energy consumption and achieving the goal of "carbon peak and carbon neutrality". This paper analyzes the development trajectory and energy consumption patterns of intercity railways in China, with a particular focus on the entire lifecycle of planning, design, construction, and operation within the context of the "dual carbon" initiative. Utilizing the Beijing-Xiong'an intercity railway as a prototypical case, the paper examines energy consumption and carbon emissions across its lifecycle, incorporating the influence of energy-saving, emission-reduction strategies, and green carbon sink measures. The findings reveal that carbon emissions during the planning and design phases are negligible, whereas the energy consumption during the operation stage dominates, accounting for approximately 74.9% of the total annual lifecycle energy consumption. Additionally, the energy consumption attributed to building materials production (scaled to 100 years) constitutes roughly 22.4% of the total. Notably, the implementation of energy conservation, emission reduction, and green carbon sequestration measures has yielded substantial outcomes, achieving an average annual energy savings of approximately 12%. When compared with similar railway energy consumption indicators globally, the Beijing- Xiong'an intercity railway's unit transportation traction energy consumption of 6.42 tce per million person-kilometer aligns with expectations. Furthermore, its carbon reduction impact is significant in diverting highway passenger traffic, savings approximately 612.67 million yuan in carbon sink transactions and generating substantial societal benefits. This comprehensive analysis offers valuable insights and reference for the establishment of a green and low-carbon intercity railway carbon emission dual control indicator system.

Select

Analysis of Residents' Travel Mode Choice in Medium-sized City Based on Machine Learning LI Wenquan, DENGAnxin, ZHENGYan, YIN Zijuan, WANG Baifan Journal of Transportation Systems Engineering and Information Technology    2024, 24 (2): 13-23.   DOI: 10.16097/j.cnki.1009-6744.2024.02.002 Abstract （616）      PDF （3143KB）（567）       This paper aims to investigate the characteristics of travel behaviors and the influencing factors on travel mode choice in a medium-sized city. Utilizing travel data from a medium-sized city in China, a random forest model embedded with a particle swarm optimization algorithm adding a variation procedure (PSO-RF) was proposed for travel mode choice prediction, due to the distinctions in prediction accuracy and modeling rationality of discrete choice model and machine learning model, as well as the characteristics and efficiency of hyperparameter optimization algorithms. The predictive accuracy, predictive mode proportion's absolute deviation, and expected simulation error were used to statistically compare the predictive performance among PSO-RF, machine learning models, and the multinomial Logit model. The SHAP (SHapley additive exPlanation) model was employed to thoroughly analyze the nonlinear relationships among individual socio-economic attributes, travel attributes, mode attributes, and residents' travel mode choices. The results indicate that PSO-RF has the highest average overall prediction accuracy (0.856), and the lowest average predictive mode proportion's absolute deviation (0.062) and average expected simulation error (0.306). Statistically significant differences in models' predictions are observed. Distance has the most prominent impact on the choice of different travel modes. The modes of walking and private cars show higher sensitivity to distance, with probability changes exceeding 35% at different distances. Individuals under 30 years old exhibit greater variations in the probability of choosing different travel modes compared to other age groups. Gender, car ownership, and bus IC card ownership notably affect the probability of choosing a bus and a private car.

Select

Collaborative Lane Change Method for Autonomous Vehicles Based on Dynamic Trajectory Planning LIU Miaomiao, LIU Xiaochen, ZHU Mingyue, WEI Zeping, DENG Hui, YAO Mingkun, WU Silin, LI Ang, SHI Zan, GONG Xiaoyu Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 65-78.   DOI: 10.16097/j.cnki.1009-6744.2024.05.007 Abstract （282）      PDF （2891KB）（564）       Traditional multi-vehicle coordination lacks effective utilization of information about target platoons and lane-changing vehicles. To address the impact of dynamic information changes on the lane-changing process, this paper proposes a collaborative lane-changing control method for autonomous vehicles based on dynamic trajectory planning. First, focusing on the scenario of a single vehicle merging into vehicle platoons in autonomous driving environments, a collaborative lane change control framework based on real-time dynamic information is proposed. Considering the cooperation between the lane-changing vehicle and the target platoon vehicles, and the impact of the lane-changing behavior on the target platoon, longitudinal collaborative control models are established for both non-lane changing and lane-changing periods. Second, after the lane-changing vehicle sends a lane-change request and satisfies the lane-change triggering conditions, a dynamic lane-change trajectory planning method using a sinusoidal curve is employed to derive a safe and reliable trajectory. Vertical coordination goals are considered. And based on the dynamic planning of longitudinal speed changes, a sine-curve-based dynamic lane change trajectory planning approach is introduced to derive safe and reliable trajectories. Then, a model predictive control-based trajectory tracking control algorithm is used to achieve real-time trajectory tracking. Finally, by constructing a joint simulation platform of Prescan and Simulink, several sets of simulation experiments under different speed conditions are designed. And traditional control algorithms based on vehicle tracking strategies are compared with the proposed control strategy by analyzing three key indicators: lane change trigger time, train stabilization time, and speed fluctuation amplitude. This comprehensive analysis validates the effectiveness and feasibility of the proposed control strategy. Simulation results show that, compared with traditional methods, the average stable time of the platoon is reduced by 34%, and the speed fluctuation amplitude of the platoon remains stable. In addition, safe and efficient lane changes can be achieved under different relative speed conditions.

Select

Impact of Charging and Incentive Strategies on Commuting Mode Choice WANGDianhai, LIYiwen, CAI Zhengyi Journal of Transportation Systems Engineering and Information Technology    2024, 24 (2): 1-12.   DOI: 10.16097/j.cnki.1009-6744.2024.02.001 Abstract （592）      PDF （2668KB）（554）    PDF(English version) （436KB）（4）    This paper investigates the regulatory impact of two traffic demand management strategies, tolls and rewards, on travel mode choices, using the main urban area of Hangzhou as a case study. The stated preference (SP) and revealed preference (RP) surveys were performed to understand the intention of private car commuters' mode choice under parking charge and travel reward scenarios. The disaggregate theory was used to establish Nested Logit (NL) models for commuting mode selection under separate and joint implementation of parking fees and travel rewards. The results indicate that both parking fees and travel incentives can reduce private car travel demand and promote public transportation. Only when the parking price reaches a certain level can private car trips be effectively reduced, and appropriate incentives can actively encourage travelers to switch to other modes of travel. If charging and incentive strategies are implemented simultaneously, it will manifest a joint effect of charging as the main approach and incentive as a supplement. In all three scenarios, income is a significant factor influencing travel mode choices. The higher the income, the more likely the continuation of private car usage. In the scenario with only a parking fee, the elasticity of parking fees increases with the rate; there are limited elasticity when the rate is low. The elasticity of travel rewards initially raises and then drops with the increase in the reward amount; Small rewards also show elasticity.

Select

Path Optimization for Vertical Take-off and Landing Aircraft in Dynamic Urban Airspaces for Urban Air Mobility ZHOU Hang, ZHAO Fengyang, HU Xiaobing Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 295-308.   DOI: 10.16097/j.cnki.1009-6744.2024.05.027 Abstract （177）      PDF （4788KB）（554）       To address the current challenges of achieving optimality and computational efficiency in dynamic airspace route optimization for urban air mobility, as well as the inadequacy in addressing mixed urban and suburban operational scenarios, an innovative approach to constructing a combined urban-suburban network is initially proposed to support both urban and suburban operations seamlessly. Based on the flight dynamics model of electric vertical takeoff and landing (eVTOL) aircraft, an accurate eVTOL power consumption model is developed to optimize flight paths. A Dynamically Weighted Routing Network (RSA-DWRN) algorithm for dynamic airspace is introduced by leveraging the Ripple Spreading Algorithm. With a combined urban-suburban network framework that incorporates time-varying airflow patterns and obstacle zones, the optimization performance of the RSA-DWRN's is compared against the traditional DPO-A* algorithm across five scenarios through 600 experiments, considering path power consumption, flight time, computation time, and matching degree as key metrics. Simulation results show that RSA-DWRN algorithm performs best under the four indexes, especially as the complexity of dynamic airspace environmental factors increases. In scenarios with moving obstacles, the DPO- A* algorithm fails to predict their trajectories and requires frequent updates to the network state, significantly increasing the computational cost of path planning. In contrast, the RSA-DWRN algorithm co-evolves with changes in the dynamic environment, finally obtaining optimal solutions that simultaneously ensure optimization results and computational efficiency.

Select

A Train Group Control Method Based on Car Following Model Under Virtual Coupling SHUAI Bina, LUO Jianan, FENG Xinyan, HUANG Wencheng Journal of Transportation Systems Engineering and Information Technology    2024, 24 (3): 1-11.   DOI: 10.16097/j.cnki.1009-6744.2024.03.001 Abstract （410）      PDF （2282KB）（520）    PDF(English version) （1740KB）（1）    There remains a gap between transportation capacity and demand under the high-speed railway moving block mode, prompting the exploration of new approaches such as virtual coupling to enhance transportation capacity. With the concept of virtual coupling and inspired by car-following models utilized in road traffic, we propose a novel acceleration adjustment strategy by train dynamics and multi-agent methods for tracking trains based on the speed and distance relationship between adjacent trains, with the goal of ensuring train safety and passenger comfort while enabling virtual coupling within the train group. A corresponding virtual coupling acceleration adjustment model is established for train groups, aiming to achieve equal speed and distance between all trains in the group. The proposed model is validated using the CRH380A high-speed train as a case study. Simulation results demonstrate that the proposed acceleration adjustment strategies effectively realize the virtual coupling of train groups. Compared to the moving block method, adopting virtual coupling reduces the time required for train collaboration by 9.7% and decreases the distance between trains by 10.1% , thereby improving efficiency. Furthermore, the time required to achieve virtual coupling is shorter when considering the train group as a whole compared to when the group is separated into multiple groups.

Select

Multimodal Transportation Route Optimization for Long and Bulky Cargo Considering Carbon Emissions WANGJuan, CHENGYuli, YANGYuhan, ZHANGYinggui Journal of Transportation Systems Engineering and Information Technology    2024, 24 (4): 1-11.   DOI: 10.16097/j.cnki.1009-6744.2024.04.001 Abstract （478）      PDF （1887KB）（504）       Long and bulky cargo has the characteristics of large outline, overweight and high cost and cannot be disassembled during the transportation process. Multimodal transportation is becoming the first choice of long and bulky cargo transportation, the core of which is route decision problem. In this paper, an energy consumption factor is introduced, and calculation formulas of carbon emissions during the transportation and reconstruction and reloading process at the node for long and bulky cargo multimodal transportation are all proposed. Then, taking into consideration the following factors, i.e., loading outline, gauge, bridge bearing capacity and reloading capacity at the nodes, and road reconstruction, a multimodal transportation route optimization model for long and bulky cargo with carbon emissions is proposed with the objective of minimizing multimodal transportation cost and carbon emissions. In addition, an adaptive genetic algorithm with an elite retention strategy is designed for the multimodal route decision for long and bulky cargo considering carbon emissions. Numerical results show that, compared with the traditional genetic algorithm and the adaptive genetic algorithm, the objective value of the proposed method is 20% higher and its cost and carbon emissions are 12% and 22% lower, respectively. The route plan by the proposed method can consider transportation cost and carbon emissions simultaneously, which can provide support to solve the multimodal route decision problem for long and bulky cargo and also reduce the cost and increase the efficiency in logistics and achieve the "dual-carbon" target.

Select

Dynamic Spatiotemporal Priority Control of Connected Vehicles Public Transport System LI Zhe, GOU Yangyang, LI Zhenyao, LI Ao, CEN Wei, GAO Jianping Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 56-64.   DOI: 10.16097/j.cnki.1009-6744.2024.05.006 Abstract （186）      PDF （2303KB）（489）       To improve the utilization efficiency of bus lanes and reduce vehicle delays at intersections of continuous bus lanes, this paper investigates dynamic spatiotemporal priority control of connected public transport systems from spatial and temporal dimensions and analyzes the applicable traffic flow conditions. In the spatial dimension, intermittent bus entrance lanes are introduced and vehicle operation control strategies are formulated for four dynamic intervals, including clearance distance. In the temporal dimension, based on deep reinforcement learning, signal timing is dynamically adjusted through time extension of the green light and time interruption of the red light. A simulation verification platform is constructed using SUMO and Python, and comparative simulation experiments and three saturation scenarios are designed for four control schemes concluding the original scheme, spatial priority scheme, temporal scheme, and spatiotemporal collaborative priority scheme. The results show that at saturation levels of 0.2, 0.5, and 0.8, the spatiotemporal collaborative priority scheme reduces the average delay compared to the original scheme by respectively 40.96% , 39.93% , and 28.20% . At low saturation, the spatial priority effect is obvious; at medium saturation, the temporal effect is obvious. Using intermittent bus entrance lanes may lead to a slight increase in bus delays, but the average delay at the entire intersection is significantly reduced. The proposed dynamic spatiotemporal priority control method for connected vehicle bus systems can effectively improve intersection traffic efficiency while ensuring bus priority.

Select

Impact of "Star-Type" High-speed Railway Network on High-quality Development of Regional Social Economy YUE Guoyong, HU Hao Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 24-36.   DOI: 10.16097/j.cnki.1009-6744.2024.05.003 Abstract （163）      PDF （2915KB）（486）       This paper focuses on the first "Star-type" high-speed railway network in China and analyzes its impact on regional high-quality development from four dimensions: spatial pattern, economic development, social development and ecological environment. The study constructs a comprehensive impact evaluation model and establishes a multidimensional indicator system to evaluate the effects. It culminates in a detailed quantitative analysis of the outcomes to provide a nuanced understanding of the impacts. The result indicates that the opening of the "Star-type" high-speed railway network has significantly reduced the weighted average travel time between and within Henan province to 4.90 hours and 1.62 hours, with improvements rate of 65.6% and 37.8% . The intensity of regional connections has been significantly enhanced, gradually forming a "center-periphery" development structure which focuses on intra-provincial connections and steadily expands to the energy consumption optimization and comprehensive operational emission reduction of railway northeast and southeast. The primacy index of Zhengzhou high-speed railway hub has increased from 1.90 to 2.83, further consolidated its position as a core hub. The differencein-differences model is used to verify that the "Star-type" high-speed railway network has a positive promotion on economic and social development indicators of Henan，such as social fixed assets investment, foreign capital utilization, per capita Gross Domestic Product (GDP), urbanization rate, employment upgrading index, etc. The amount of optimized comprehensive energy consumption and comprehensive operational emission reduction in railway passenger transport has steadily increased, and industrial SO2 emissions reduced, with significant ecological environment effects.

Select

Signalized Intersection Eco-driving Strategy Based on Deep Reinforcement Learning LI Chuanyao, ZHANG Fan, WANG Tao, HUANG Dexin, TANG Tieqiao Journal of Transportation Systems Engineering and Information Technology    2024, 24 (1): 81-92.   DOI: 10.16097/j.cnki.1009-6744.2024.01.008 Abstract （510）      PDF （2473KB）（478）    PDF(English version) （2399KB）（2）    Eco-driving in a connected and autonomous driving environment has great potential to improve traffic efficiency, energy saving, and emission reduction. This paper proposes a prosocial eco-driving strategy based on the deep reinforcement learning algorithm that optimizes the longitudinal manipulation and lateral decision-making of the connected and automated vehicle (CAV). The state space is divided into the local variables related to dynamic vehicle characteristics and the global variables associated with signalized intersection to ensure adequate interaction between the CAV and the roadway environment. The designed reward function integrates the vehicle driving requirements, synergy with signals and global energy saving incentives. In addition, this study developed a typical urban road intersection scenario to train the model. The results show that the proposed strategy can achieve eco-driving of the CAV in collaboration with the signal and output lateral control to ensure the vehicle travels to the target lane. In addition, simulations in a dynamic traffic environment reveal that the proposed method can improve the capacity at the intersection by about 17.90% and reduce the traffic system's fuel consumption and pollutant emissions by approximately 8.76% through the control of multiple CAVs to guide the human-driven vehicles.

Select

Energy Saving and Emission Reduction Potential of Road Traffic in Coastal Urban Agglomerations Under Background of Carbon Peak ZHANG Lanyi , XU Yinuo, WANG Shuo, XIE Zhengyi, WENG Dawei, WANG Zhenhao, HU Xisheng, ZHENG Pingting Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 45-55.   DOI: 10.16097/j.cnki.1009-6744.2024.05.005 Abstract （154）      PDF （2617KB）（475）       In alignment with China's strategic "dual-carbon" goals, this paper aims to investigate the potential for energy saving and emission reduction in the road transportation system of coastal urban agglomerations. Taking the coastal urban agglomerations in Fujian Province as an example, a long-range energy alternatives planning system model (LEAP) has been constructed, three primary scenarios and four secondary sub-scenarios have been developed. The emission reduction potential and trend of regional road traffic were studied by adjusting the parameters of vehicle ownership and fuel economy. The study indicates that among all scenarios, the Modified Policy Scenario (MPS) demonstrates the most superior energy saving and emission reduction effects, with the greatest potential for energy conservation and emission reduction. Compared to the Business as Usual (BAU) scenario, the energy saving of the MPS is expected to be improved by 59.3% , by 2035. Under the MPS scenario, the trends in greenhouse gas and pollutant emissions both show a significant decline, with remarkable emission reduction effects. Looking specifically at the energy- saving and emission reduction potential of different vehicle types, under the MPS scenario, small- duty gasoline passenger vehicle (SGPV), heavy-duty diesel freight vehicle (HDFV), and light-duty gasoline freight vehicle (LGFV) have the greatest potential for energy conservation; carbon emissions from 8 types of vehicles can peak by 2025; and pollutant emissions can be effectively controlled, with the greatest potential for pollutant emission reduction found in HDFV. The research confirms that advancing the implementation of comprehensive policies, accelerating the phase-out of traditional fuel vehicles, and optimizing the structure of road vehicles will have a positive impact on the realization of the green and low-carbon goals. Through model simulation, it is anticipated that the road traffic system of the coastal urban agglomerations in Fujian Province will achieve significant energy-saving and emission-reduction effects before 2030.

Select

Intra-driver Heterogeneity Prediction and Modeling Based on Naturalistic Driving Experiment ZHANG Duo, RAO Hong-yu, LIU Jia-qi, WANG Jun-hua, SUN Jian Journal of Transportation Systems Engineering and Information Technology    2023, 23 (5): 33-44.   DOI: 10.16097/j.cnki.1009-6744.2023.05.004 Abstract （451）      PDF （2856KB）（459）       To provide reliable support for car-following behavior in traffic flow modeling research and advanced driving assistance systems, this study proposes a method for predicting and modeling the intrinsic heterogeneity of driver following behavior based on the Transformer deep learning model and considers individual driver's behavior changes in the car-following process. This study is based on a large-scale naturalistic driving experiment, which involved over 200000 kilometers of naturalistic driving records. First, the baseline models are developed using longterm behavioral observations of 41 drivers, and 3194 intra-driver heterogeneity events are identified and extracted according to the baseline model. Further, a deep learning predictor based on the Transformer multi-head self-attention mechanism is designed to accurately predict intra-driver heterogeneity events of drivers. The results show that the predictor performs better than the long short-term memory network in predicting the three-class time points of carfollowing intra-driver heterogeneity, with an F1 score of 87.13%. Based on prediction results, dynamic car-following parameter switching can reduce the driving behavior modeling error by 21.08%. The research results help to understand the behavioral response mechanism of drivers, and further improve the accuracy of traffic flow simulation and the design of personalized control strategies.

Select

Route and Speed Optimization for Green Intermodal Transportation Considering Emission Control Area WU Peng, LI Ze, JI Hai-tao Journal of Transportation Systems Engineering and Information Technology    2023, 23 (3): 20-29.   DOI: 10.16097/j.cnki.1009-6744.2023.03.003 Abstract （414）      PDF （5114KB）（458）       This study solves a new green high-seas multimodal transportation route and speed optimization problem considering emission control areas. This study first formulates a multi-objective mixed integer nonlinear programming model under different carbon emission policies and transforms the nonlinear model into an equivalent mixed-integer linear programming model according to the problem characteristics. To effectively solve the models, an improved adaptive genetic algorithm (IAGA) incorporating the characteristics of the problem is proposed, in which a customized multi-layer coding and decoding mechanism and an adaptive genetic evolution operator are proposed. Finally, a case study from the high-sea multimodal transportation system in China is conducted to demonstrate the viability of the proposed model and algorithm and a sensitivity analysis is also done for various time frames and low-sulfur fuel costs. The numerical experimental results show that: 1) Compared with a traditional genetic algorithm and the commercial solver Lingo, the improved adaptive genetic algorithm results in more satisfactory solutions and reduces total multimodal transportation costs by 5.2% and 3.7% . 2) Under the mandatory carbon emissions policy, changes in emission allowances typically do not affect the choice of the route made by an operator, but only affect whether the operator conducts transportation activities. Under the carbon tax policy, the overall cost of intermodal transportation is not significantly affected by the carbon tax price increase. Under the carbon trading policy, multimodal transport options with different emission allowances may be consistent. And 3) the shipping cost can lead to a direct proportion to the price of low- sulfur fuel, and adopting different ship speeds inside and outside the emission control areas can bring clear economic advantages.

Select

Cross-line Train Service Plan Optimization in Urban Rail Transit Network JIAN Min, CHEN Shaokuan, WANG Zhuo, LI Hao Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 116-127.   DOI: 10.16097/j.cnki.1009-6744.2024.05.011 Abstract （169）      PDF （3725KB）（458）       In order to improve the service quality of urban rail transit by reducing transfer times, a method for generating cross-line train routes and an optimization model for planning train routes with cross-line operation are proposed based on the characteristics of passenger flow in the network. First, with the developed inference method of passenger travel routes, the various passenger flows and proportions in the network are calculated to obtain the crossline times, thereby generating the set of alternative long cross-line train routes. Then, with the goal of minimizing passenger transfer times, an optimization model for the operation of long cross-line train routes in the network is constructed, which satisfies the constraints of basic operating conditions and cross-line capacity. An improved genetic algorithm with a frequency-based passenger flow assignment method is used to solve the problem to obtain the operating frequency of the mainline and cross-line train routes in the network. Finally, the effect of long cross-line train routes is analyzed based on an urban rail network. The results show that the optimized train service plan reduces the transfer times of all transfer passengers by 2.02% to 5.97% . Thus, the passenger transfer time and network transfer coefficient are reduced, and the direct passenger flow is increased by 1.58% to 4.58% with the operated long cross-line train routes. The operated long cross-line train routes play the role of short train routes in the connected line to supplement the sectional transportation capacity, thus reducing the total number of running trains on the line and the train kilometers on the main line. In addition, when the transfer passenger volume at the transfer station is high, the cross-line train route cannot be operated due to the high operating frequency of the main-line train on the connected line, and the effect of improving the operational services gradually decreases as the operating frequency of the crossline train route reaches the upper limit of the cross-line capacity

Select

Location-inventory-routing Optimization of Maritime Logistics Network in Remote Islands Under Demand Uncertainty WU Di, HAN Xinli, SHI Shuaijie, JI Xuejun, ZHENG Jianfeng, LIU Baoli Journal of Transportation Systems Engineering and Information Technology    2024, 24 (5): 268-282.   DOI: 10.16097/j.cnki.1009-6744.2024.05.025 Abstract （132）      PDF （2962KB）（457）       To reduce the effects of uncertain material demands on the stability of maritime logistics network in remote islands, this paper investigates the design problem of a three-level hub-and-spoke material distribution network consisting of a mainland supply port, central islands, and satellite islands. The problem is formulated as a locationinventory-routing model that includes decisions on the number of central island locations, aiming to minimize system costs. The model takes into account some practical factors such as heterogeneous fleets, transportation mode diversity, and inventory capacity constraints. An Integrated Genetic-Annealing Optimization Algorithm Embedded with Monte Carlo Simulation-Based Neighborhood Traversal Operators (GAAEMCNT) is developed to decompose the original problem into several sub-problems, including location and assignment, route grouping, and optimization of route and inventory. The integrated optimization of the problem is realized through the interaction and iteration of inner and outer layer of the GAAEMCNT algorithm. Experiments on islands in the South China Sea are conducted to analyze the effects of changes in the number of islands, density distributions and demand on the maritime network system. The results show that: (i) when the distribution of material demand on islands is unchanged and the number of islands is the same, the unit cost of logistics network in the aggregation distribution is lower than that in the discrete distribution; (ii) when the distribution of island material demand is unchanged and the distribution of island is the same, the change of island number has minimum influence on the unit cost of logistics network; (iii) the change of the mean value of the material demands in the islands has a significant impact on the cost of each part of the system, and the total cost is positively correlated with the mean value; (iv) the fluctuation of the demand has a more obvious impact on the cost of the storage system, but a smaller impact on the cost of the transportation system. These findings validate the applicability of the algorithm proposed in this study across various island scenarios, providing decision-making support for the construction and optimization of maritime logistics network in remote islands under demand uncertainty.