Current Issue

2023, Volume 41,  Issue 6

Display Method:
2023, 41(6): .
Abstract(103) HTML (87) PDF(21)
An Analysis and Prospects of Hot Topics on Maritime Autonomous Surface Ship Safety Research
ZHANG Di, LI Zhihong, WAN Chengpeng
2023, 41(6): 1-11. doi: 10.3963/j.jssn.1674-4861.2023.06.001
Abstract(109) HTML (80) PDF(8)
In recent years, the maturation of technologies such as autonomous navigation, sensors, communication, and networking has spurred rapid advancements in Maritime Autonomous Surface Ship (MASS) research. In September 2023, the 33rd European Safety and Reliability Conference was successfully held in Southampton, UK. The conference them centered on building a safe future in an interconnected world, with a particular emphasis on the safety of MASS. Based on a comprehensive analysis of 514 conference papers (including 19 papers related to intelligent ship safety topics), combined with the previous two conference proceedings and relevant research from the past decade both domestically and internationally, four hot topics in the field of MASS safety research are summarized: ①Autonomy level and related regulations: As the autonomy of MASS increases, the current legal frameworks need updating to accommodate new technologies, with research focusing on defining the autonomy levels of MASS and exploring the corresponding legal and regulatory frameworks. ② Human factors in remote operations: Remote operation of MASS introduces new challenges related to human factors. Research is oriented towards designing remote operation systems to reduce the psychological burden on operators, enhance communication efficiency, and provide effective decision support to ensure safety. ③ Risk assessment of MASS: This field aims to use advanced technologies for more accurate safety and risk evaluations, incorporating the use of multi-dimensional sensor data, real-time monitoring, and diversified data analysis models. ④ Applications of artificial intelligence and machine learning in MASS: Both technologies are regarded as innovative directions in the field of MASS safety, with research primarily focusing on their application in fault prediction, route optimization, and automated safety monitoring. Through a survey of existing literature, future research directions for MASS safety are prospectively discussed from four critical perspectives. ① By adopting Model-based Systems Engineering approach for ship safety analysis, potential safety threats can be identified and eliminated from the design phase, promoting interdisciplinary collaboration, and enhancing the accuracy of safety and reliability analysis. ② In terms of human factor risk analysis, the Functional Resonance Analysis Method is considered more suitable for complex systems like MASS. By evaluating the interactions between system functions, failures can be identified, and preventive measures can be formulated. ③ To improve efficiency in emergency situations, research needs to develop support systems that assist operators in making rapid and accurate decisions, considering the psychological and physiological states of operators. ④ The application of artificial intelligence and machine learning to deepen theoretical research involves developing autonomous decision-making models capable of making accurate decisions in complex maritime environments and advanced algorithms that integrate multiple data sources for accurate weather forecasting and route optimization.
A Suspension Stiffness Optimization for Driving System in High-speed Train with the Built-in Axle Box Based on Orthogonal Test
WANG Jiaxin, ZHANG Hanchen, WU Zhiqiang, LIU Yuqing, CHEN Zaigang
2023, 41(6): 12-19. doi: 10.3963/j.jssn.1674-4861.2023.06.002
Abstract(101) HTML (82) PDF(8)
As the core subsystem of the power bogie of high-speed trains, the drive system is an important guarantee for the safe operation of high-speed trains. However, with the continuous increase in operating speed, the reliable and safe operation of high-speed trains is seriously challenged. To reduce the dynamic loads on the suspension nodes of the axle box built-in high-speed dynamic vehicle driving system and to reduce the vibration level of the key components of the driving system, this paper carries out an optimization study on the suspension stiffness of the driving system. To reduce the dynamic loads and the vibration levels of components in the driving system, an optimization analysis of the suspension stiffness is performed in this study. Based on the multi-body system dynamics theory, the axle box built-in high-speed locomotive dynamics model is established by comprehensively considering the effects of track random uneven excitation, traction power transmission and gear meshing. Using the orthogonal test design method, with the optimization objective of reducing the suspension load at the traction motor lifting point and the vertical load at the axle articulation point of the gearbox, the influence of the suspension stiffness of the traction motor lifting point, the gearbox boom lifting point, and the motor-gearbox connection point on the vibration acceleration of the key components of the vehicle and the dynamic load at the suspension nodes of the driving system are investigated. The influence law is also analyzed by using the extreme difference analysis method to obtain the optimal matching combination of the suspension stiffness of the driving system. The results show that the maximum longitudinal, lateral, and vertical suspension loads of the motor with optimized parameters are reduced by 22.3%, 37.9%, and 9.8%, respectively. Meanwhile, the vertical load between the gearbox and wheel axle is reduced by 9.1%. The lateral vibration accelerations of the motor, gearbox, and axle box are significantly reduced.
An Investigation on Vehicle Trajectory Characteristics at Exit and Entrance of High-density Interchanges Based on Naturalistic Driving Data
XU Jin, YANG Xuemin, ZHANG Xueyu, ZHANG Jie, KONG Fanxing, JIAO Chengwu
2023, 41(6): 20-31. doi: 10.3963/j.jssn.1674-4861.2023.06.003
Abstract(93) HTML (94) PDF(4)
Interchange is an important node of the road traffic network, and as the spacing between neighboring interchanges continues to shrink, a high-density cluster of interchanges is gradually formed, which is prone to traffic congestion, increasing driving load and accident risk. To clarify the operational risks and safety hazards in the entrance and exit sections of high-density interchanges, the field driving test is conducted on the Inner Ring Road of Chongqing. This test takes a cluster of high-density interchanges as the research object. Using onboard instruments, vehicle trajectory data are collected under natural driving conditions. The vehicle trajectory data includes speed, real-time driving position, and lateral distance between the vehicle center and the lane markings on both sides. By analyzing the measured data, the vehicle trajectory pattern of the interchange entrances and exits as well as the relation-ship between the behavioral characteristics of lane selection and the influence of the driver's gender on the trajectory pattern are clarified. The lane-changing behavioral characteristics and driving risk influencing factors in the process of vehicles leaving (merging into) the mainline are explored. The results reveal the following conclusions: ①The type of entrance or exit has a significant influence on lane selection and trajectory shape. Compared to parallel-type exits, direct-type exits have smoother trajectories and fewer lane changing numbers. ②When entering and exiting two adjacent interchanges with a short clearance, drivers tend to choose the auxiliary lane or the outermost lane on the mainline to reduce the number of lane changing. ③The number of mainline lanes near the entrance and exit affect drivers' lane selection behavior. ④When drivers leave the mainline, the lane-changing duration of the parallel-type exit is higher than that of the direct-type exit. The entrance type does not have a significant impact on lane-changing time. The lane-changing time for 78% of drivers is between 5 to 10 seconds. ⑤The operational risks in the exit section are higher than in the entrance section. It is recommended to use solid white lane line to prohibit crossing same-direction lane markings on the left side of the rightmost lane of the exit section. The length should cover from the beginning of the taper section to the diverging point, extending 50 meters forward from the start of the taper section.
A Personalized Lane Change Decision Method Based on Driver's Psychological Risk Field Model
LI Ke, HAN Tongqun, YANG Zhengcai, GAO Fei, WU Haoran
2023, 41(6): 32-41. doi: 10.3963/j.jssn.1674-4861.2023.06.004
Abstract(114) HTML (36) PDF(7)
In driving environments, the motion behavior of interacting vehicles can stimulate the psychological and mental state of drivers, subsequently influencing their lane-changing decision behavior. In response to this, a personalized lane-changing decision method based on a driver's psychological risk field model is investigated. Focusing on a three-lane expressway traffic scenario, the vehicles' lateral speed and lateral offset are analyzed by interacting multiple models. Variable lateral speed-related transition probability matrices are introduced to predict the target lane selection of interacting vehicles. A model is established to quantify the impact of the driving environment and interacting vehicles' motion behavior on drivers' psychological risk. The experiment is conducted by establishing mixed traffic scenarios in a SUMO-based driving simulator, and 287 cases of lane-change datasets are collected. Two characteristic parameters, average collision time and driver psychological risk factor, are selected. The K-means algorithm is used for driver style clustering, categorizing drivers into conservative, normal, and aggressive styles. Furthermore, different thresholds for psychological risk at the initial moment of lane-changing are determined for drivers with different styles. Then personalized safe lane-changing decisions for vehicles are implemented. Experimental results show that, for conservative, normal, and aggressive drivers, the actual minimum lane-changing decision times are 3.48, 6.29, and 11.33 s, respectively. The actual maximum lane-changing decision times are 4.65, 7.45, and 12.52 s, respectively. The theoretical lane-changing decision times are 4.09, 6.83, and 11.95 s, respectively. The prediction errors of the personalized lane-changing decision model are all less than 0.62 seconds. This approach accurately assesses the psychological risk of drivers with different styles and achieves personalized lane-changing decisions.
Coupling Failure Mode and Risk Modeling of Typical Aircrafts Runway Excursion
WANG Feiyin, YUAN Jintong, WANG Lei
2023, 41(6): 42-50. doi: 10.3963/j.jssn.1674-4861.2023.06.005
Abstract(56) HTML (33) PDF(3)
Runway excursion is identified as high-risk event by the International Air Transport Association. To explore the pattern of runway excursion incidents in global civil aviation and to explore the influencing factors and their coupling characteristics, the investigation reports of 57 runway excursion incidents of typical aircraft types from 2007 to 2018 are analyzed from the perspectives of number of casualties, aircraft types and causes of the incidents. The HFACS model and SHELL model are used to compensate for the limitations of using a single method considering the diversity and complexity of influencing factors of runway excursion incidents. Specifically, the HFACS model is optimized and adopted to vertically analyze the influence of human factors in the runway excursion event, change the traditional method of the SHELL model to analyze the coupling influence of multiple factors in the runway excursion event systematically and comprehensively and use the FMEA method to explore the coupling effect of multiple influencing factors in the runway excursion event and find 18 multifactor coupling failure modes that induce the runway excursion. The results showed that the risk priority of the failure modes is quantified by identifying the occurrence, severity, and detection of the failure modes. The results showed that 91.2% of the runway excursion events occurred in the landing phase, and 87.7% of the runway excursion events were related to the crew human influence, among which insufficient control of the aircraft occurred most frequently, accounting for 31.1%. Multi-factor coupling caused 78.9% of the events, and the risk priority value of failure mode F2-1 crew factors and meteorological factors in multi-factor coupling failure mode is the highest at 364.8, with an occurrence rate of 21.05%, which is the object that needs to be focused on prevention and control, indicating that pilots need to strengthen the simulation training of runway excursion under complex weather conditions.
A Method of Ship Trajectory Prediction Based on a C-Informer Model
CHEN Lijia, ZHOU Naiqi, LI Shigang, LIU Kezhong, WANG Kai, ZHOU Yang
2023, 41(6): 51-60. doi: 10.3963/j.jssn.1674-4861.2023.06.006
Abstract(52) HTML (25) PDF(4)
The navigation of ships in complex environments is influenced by various uncertain factors, such as wind, waves, water depth, and ship performance, etc. It is challenging to precisely define and reflect the dynamic patterns of ship trajectories simply using mathematical models. To address this issue, a multi-step prediction method for ship trajectories based on feature engineering and neural networks is studied. The task of trajectory prediction is divided into two parts: data processing and model prediction. The data processing module preprocesses AIS trajecto-ry data using feature engineering methods. It starts by cleaning the raw AIS data, then uses the maximal information coefficient to select features highly correlated with the position prediction task. Additionally, a variable time interval information is introduced to address the problem of existing models only being able to select fixed time interval data for training and prediction. This module ultimately reconstructs high-quality ship trajectory sequences. The model prediction module constructs a ship trajectory prediction model based on C-Informer. It utilizes the multi-head Prob-Sparse self-attention mechanism of the Informer model to reduce the time complexity of the network model. Simul-taneously, it enhances prediction speed by generative decoding. By introducing a causal convolution module, the sensitivity of the model to neighboring time trajectory features is increased to compensate for the deficiencies of the Informer model in extracting local information. This adaption makes the model more suitable for ship trajectory prediction tasks. The experimental results based on Automatic Identification System (AIS) data near Nanjing port show that the C-Informer model for trajectory prediction has an overall mean square error (MSE) of 1.72×10-7 and a mean absolute error (MAE) of 2.43×10-4. Compared to the original Informer model, this represents a reduction of 28.6% and 31.9%, respectively. When training the C-Informer model with the selected feature combinations, the MSE and MAE are decreased by 57.7% and 42.1%, respectively, compared to using only latitude and longitude fea-tures. In predicting trajectories at different time steps, the C-Informer model reduces prediction time by up to 69.6% compared to the long short-term memory network model, with a maximum loss reduction of 75.8%.
Path Tracking and Lateral Stability Control for Distributed Drive Vehicles with Low Adhesion
YANG Wei, TAN Liang, DU Yafeng, SUN Xue, ZHANG Yujie
2023, 41(6): 61-70. doi: 10.3963/j.jssn.1674-4861.2023.06.007
Abstract(50) HTML (27) PDF(2)
Due to the coupling relationship between tracking and lateral stability of vehicles under low adhesion conditions (such as snow and moisture), it is difficult to control both tracking accuracy and good stability simultaneously. Therefore, a joint control model of path tracking and lateral stability is proposed based on distributed independent drive electric vehicle platform. The transverse and longitudinal decoupling control is adopted for the path tracking problem. Besides, the model predictive control (MPC) method based on Frenet coordinate system is adopted for the horizontal tracking control problem, and angle compensation strategy is introduced to improve the accuracy of path tracking. For the longitudinal speed control problem, the model uses MPC to solve the expected acceleration, and determines the motor torque output according to the driving balance equation and the maximum utilization rate of road adhesion, so as to achieve the longitudinal speed control. For lateral stability control, a yaw torque control model based on stability augmentation system (STA) is proposed. After additional torque is obtained, it is effectively distributed to each wheel by quadratic programming method, thus enhancing the lateral stability of the vehicle. Moreover, the CarSim/Simulink co-simulation platform is used to simulate and verify the double-shift road conditions. The results show that under the condition of snow-covered pavement, the maximum lateral deflection angle of the improved model is reduced by 83.1% compared with the traditional MPC under the condition that the lateral error is close. Under wet road conditions, the maximum lateral error and the maximum lateral deflection angle of the improved model are reduced by 52.2% and 83.3%, respectively, compared with the traditional MPC model. Compared with the traditional synovial model, this model can effectively suppress the oscillation phenomenon when the tracking error and the side deflection angle of the center of mass are dominant. Through the joint control, the stability and safety of the vehicle on the low adhesion road surface can be enhanced.
Multi-Stage Optimization Method for Dispatch of Ground-Service Vehicles at the Airports During Peak Flight Period
QI Xinyue, ZHANG Jian, JIANG Han
2023, 41(6): 71-81. doi: 10.3963/j.jssn.1674-4861.2023.06.008
Abstract(44) HTML (27) PDF(1)
During the peak hours of flights, the demand for ground service is more concentrated. Plus, the limited number of available handing vehicles for dispatching at the airport, flights delay occurs, which have caused losses to the airport in many aspects. Aiming at this issue, a multi-stage optimization method for dispatch of ground-services vehicles is proposed, with a focus on considering the routing and time window constraints of shuttle buses and refueling vehicles. The flight punctuality rate and delay time are used as evaluation indexes to dispatch-optimization. A capacity-cost network G1 with four types of nodes and five types of arcs is developed. By setting appropriate arc capacity and cost parameters, the planning model of the minimum cost flow is determined, and Lagrangian relaxation heuristic algorithm is used to solve the problem. Through continuous optimization, the initial value of the dual gap, the allowable error, and the maximum number of iterations are set, and the prediction results are output. The flight operation status during peak hour is deeply analyzed, and an integer linear programming model is proposed based on a time-space network, in which the total delay of unserved flights is optimized in the first stage. Combined with the minimum-maximum theorem, a delay model for a single flight is developed to minimize the loss. Finally, based on the real flight data, simulation experiments and the method validation are carried out combing with the apron layout. The results shown that: ① the maximum number of flights served on-time by refueling and shuttle vehicles are 30 and 131, respectively; ② the minimum total delay of flights to be served are 223 and 542 min, respectively; ③ the total flight delay decreased by 21.56%, significantly shortening the flight delay and improving the overall operational efficiency at the airport.
Ship Trajectory Prediction Method of Gated Recurrent Unit Based on Spatial-temporal Attention Mechanism
HUANG Min, YANG Yadong, WU Xinpeng
2023, 41(6): 82-89. doi: 10.3963/j.jssn.1674-4861.2023.06.009
Abstract(45) HTML (22) PDF(0)
The accuracy of ship trajectory prediction is crucial for the intelligence level of ship's navigation. Addressing the insufficient capability of the gated recurrent unit (GRU) in capturing spatial-temporal information from ship data, which leads to poor accuracy in trajectory prediction, a method of GRU ship trajectory prediction based on spatial-temporal attention mechanism (STA-GRU) is investigated. The traditional activation function in GRU is improved by a weighted activation function set to retain more comprehensive ship trajectory data. A spatial attention mechanism module is introduced to extract spatial location features of ships using latitude, longitude, relative latitude, and relative longitude as input sequences. This module computes spatial-temporal weight attention factors to obtain spatial feature vectors. The resulting vectors serve as the training dataset for the STA-GRU model used for ship trajectory prediction. Experimental validation is conducted using AIS data from Qingdao Port, with an input duration of 20 minutes and a sampling frequency of 2 min. A ship navigation trajectory dataset is constructed under these conditions. Results indicate that, compared to LSTM, AT-GRU, and Bi-GRU algorithms, the STA-GRU model not only converges faster during training but also significantly reduces the root mean square error, mean absolute error, and final displacement error. The average reductions of the aforementioned indexes for trajectory prediction are 50.2%, 38.7%, and 48.3%, respectively. For longitude prediction, the average reductions are 43.8%, 50.5%, and 49.5%, respectively. For latitude prediction, the average reductions are 52.4%, 48.4%, and 50.5%, respectively. Therefore, the proposed STA-GRU model exhibits significantly improved accuracy in ship trajectory prediction and meets the real-time requirements for trajectory prediction.
Crack Segmentation of Asphalt Pavement Images Based on Improved U-net
ZHANG Tao, WANG Jin, LIU Bin, XU Niuqi
2023, 41(6): 90-99. doi: 10.3963/j.jssn.1674-4861.2023.06.010
Abstract(43) HTML (25) PDF(0)
To improve the segmentation accuracy of image-based asphalt pavement cracks, this paper proposes a strip-attention-u-net (SAU) network based on U-net. The network uses ResNeSt50 as a core feature learning struc-ture to effectively capture semantic information and local details. A channel enhanced strip pooling (CESP) module in the encode-decode skip connection is investigated to enhance the ability of learning crack features and better utilize residual connections. A convolutional block attention (CBA) module in the up sampling stage of the decoder is developed to mitigate feature losses caused by channel compression and preserve crack features. A loss function comprised by a Dice Loss and a Focal Loss function is performed to attract thin and small crack features. A publicly available EdmCrack600 dataset and an experimental BJCrack600 dataset (600 asphalt pavement images collected in an experiment) are used to evaluate the performance of the SAU network. Ablation experiments are conducted and the SAU network is compared with state-of-the-art networks (FCN, PSPNet, DeepLabv3, U-net, Attention U-net, and U-net++). For EdmCrack600 dataset, the proposed SAU network outperforms the state-of-the-art networks, with intersection over union (IoU) and F1 score of 50.89% and 83.59%, respectively. Regarding the BJCrack600 dataset, the SAU network demonstrates the best performance among the state-of-the-art networks, achieving IoU and F1 score of 69.69% and 90.90%, respectively. The study findings could provide more intelligent and efficient supports in making advanced decisions of road maintenance.
A Model of Rationally Inattentive Travel Mode Choice Behavior Considering the Influence of Information
ZHAO Chuanlin, SUN Shumin, HE Shaosong, WANG Yuhan
2023, 41(6): 100-106. doi: 10.3963/j.jssn.1674-4861.2023.06.011
Abstract(49) HTML (20) PDF(3)
Most travel mode choice models are developed based on rational assumptions, but in the current era of information explosion, various types of information bring both convenience and interference to travel decisions. Previous studies have not fully revealed the impact of human's limited information processing capacity on travel mode choice behavior. This research is conducted from both experimental and theoretical perspectives. A travel mode choice behavior experiment is designed including a decision-making process involving multiple types of information. After thirty rounds of repeated experiments, the rational inattention characteristic of traveler decision-making was verified, that is, the subjects did not pay attention to all travel information. It was found that the subjects paid higher attention to the number of people choosing each travel mode in the previous round, but lower attention to the predictive information in the next round. Considering the randomness of transportation status and the limited information processing capacity of travelers, a travel cost function for each travel mode is defined, and a travel mode choice model is established for individual traveler with the goal of minimizing the sum of information cost and expected travel cost. Shannon entropy is used to describe the amount of information and introduces unit information cost to represent the information processing capacity of travelers. Furthermore, the equilibrium conditions of the multiplayer game for travel mode choice were provided, and the model was solved using the method of successive averages (MSA). Numerical examples further demonstrated the properties of the model. The results indicate that travelers pay more attention to empirical information than to predictive information; When the unit information cost is infinite, travelers travel without information, and their choice of mode tends to be based on initial preferences; As the unit information cost decreases, the difference in the probability of choosing two modes becomes larger, and the tendency of mode choice becomes more clear; When the probability of a certain traffic state occurring is smaller or higher, the cost for travelers to obtain information is relatively small.
Crowd Count Neural Network Based on Attention Mechanism in Traffic Scenes
WANG Liyuan, YAO Yuntao, JIA Yang, XIAO Jinsheng, LI Bijun
2023, 41(6): 107-113. doi: 10.3963/j.jssn.1674-4861.2023.06.012
Abstract(49) HTML (24) PDF(2)
Crowd count is an important task in computer vision. Crowd count task in traffic scenes plays a significant role in maintaining public traffic safety and achieving traffic intelligence. However, crowd count in public traffic scenes faces difficulties due to pedestrian occlusion and complex background. In order to achieve high accuracy crowd count, an attention-based crowd density estimation network is proposed. The network consists of three parts: a feature extraction module is designed to generate multi-scale feature maps, which can enhance the feature representation capability and improve the robustness to pedestrian scale variation of the network; an attention module is designed to suppress the background noise response and enhance the crowd feature response, generate the probability distribution of the crowd region in the feature map, which can enhance the ability of the network to distinguish the crowd region from the background region; a density estimation module is designed that guides the network to regress a high-resolution crowd density map under the constraint of attention mechanism, which can improve the sensitivity of the network to crowd regions. In addition, a background-aware structure loss function is designed to reduce the model false recognition rate and improve the model counting accuracy; meanwhile, a multi-level super-vision mechanism is adopted to guide the network for learning, which can help gradient back-propagation and reduce over-fitting, further improving the network's crowd count accuracy. Experiments are carried out on public dataset ShanghaiTech. Compared with the state-of-the-art algorithms, on ShanghaiTechA and ShanghaiTechB datasets, the mean absolute error (MAE) improves by 2.4% and 1.5%, and the mean square error (MSE) improves by 3.3% and 0.9%, respectively, which demonstrates the superior accuracy and robustness of the proposed algorithm in both crowded and sparse scenes. Experiments are also conducted on real scene dataset with MAE=7.7 and MSE=12.6, which proves the good applicability of the proposed algorithm.
An Assessment of Road Conditions and Traffic Situations Impact on Multi-type Single and Chain Conflicts
ZHONG Hao, MA Wanjing, WANG Ling
2023, 41(6): 114-123. doi: 10.3963/j.jssn.1674-4861.2023.06.013
Abstract(54) HTML (25) PDF(2)
Traffic conflict is the underlying state before a traffic crash occurs. Understanding the impact of static road attributes and dynamic characteristics of traffic flow on traffic crashes is crucial. However, existing research primarily focuses on the hazardous states between two vehicles, neglecting events involving multiple traffic entities. To effectively extract various types of traffic conflicts, including both single and chain conflicts, this study utilizes drone-acquired vehicle trajectory data to identify single conflicts between vehicles and subsequently identifies chain conflicts through association matching. In addition, a chain conflict can be divided into three patterns, i.e., Longitudinal Risk-Decrease Pattern, Longitudinal Risk-Increase Pattern, and Comprehensive High-Risk-Persistent Pattern. Subsequently, a nested Logit model is developed to explore the influence of macroscopic traffic attributes and road conditions on various types of single and chain conflicts. The findings reveal that merging segments and basic segments of roads are high-risk regions for single conflicts, while diverging segments and weaving segments are prone to happen chain conflicts, particularly those of comprehensive high-risk persistent pattern. Interestingly, an increase in the number of lanes helps mitigate severe chain conflicts. Additionally, as the traffic density in mainlines rises, the probability of chain conflicts increases. The volume ratio of ramp to mainline correlates positively with chain conflict occurrence in which the Longitudinal Risk Increase Pattern being the most sensitive. The traffic flow conditions under which each type of conflict occurs, combined with the analysis of macroscopic fundamental diagrams, indicate that conflict occurrences exhibit peaks. Moreover, the critical density at which conflicts are the most frequent on road segments exceeds the critical density indicated by the macroscopic fundamental diagram for the same segment. These conclusions hold substantial importance for understanding the macro causes of multi-vehicle chain conflicts, and for effectively preventing their evolution into chain collisions.
A Two-stage Capacity Control Method for Air-rail Passenger Choice Behavior
YANG Wendong, PENG Jiyuan, JIANG Yu
2023, 41(6): 124-131. doi: 10.3963/j.jssn.1674-4861.2023.06.014
Abstract(41) HTML (22) PDF(1)
To address the inadequacy of theories and the complexity of passenger choice behavior, a two-stage capacity control model is established for air-rail intermodal capacity control. In the first stage, an air-rail intermodal passenger choice model is established. The shadow attraction value is introduced to address the shortcomings of existing choice models that overlook competition and limit passengers'choices. Then, the proposed choice model is verified based on the nested Logit model. In the second stage, a network capacity control model is established by maximizing intermodal expected revenue. The algorithm is proposed based on the branch and bound method, which is used to rationalize product offerings. The case study is carried out by a flight with 150 seats. A comparative analysis is also conducted to verify the expected revenue under different levels of competition. The results indicate that 91 seats are allocated to passengers in the aviation market and 59 seats to passengers in the intermodal market. The total expected revenue is 160 600 RMB. To airlines, products with lower price but stronger competitiveness are more valuable when considering product competition. By introducing shadow attraction value, the two-stage model captures the demand between the basic attraction model and independent demand model. Compared to the independent demand model, the model can increase the expected revenue by around 4%. The study illustrates that airlines can effectively cope with the impact of competition by maintaining the total number of seats for non-intermodal products and intermodal products.
Coordinated Optimization Method for Feeder Container Ship Route Planning and Stowage Based on DQN Algorithm
LI Jun, XIAO Di, WEN Xiang, ZHAO Yajie
2023, 41(6): 132-141. doi: 10.3963/j.jssn.1674-4861.2023.06.015
Abstract(52) HTML (30) PDF(4)
Given the unique features of feeder container shipping, including varying feeder port numbers and inconsistent berthing conditions, as well as the divers' types of container fleets, this research investigates the coordinated optimization for route planning and stowage in feeder container shipping considering their close connection in the actual transportation process. A two-stage hierarchical method is employed to study the route planning and container stowage problems. Multiple ports, different ship types with their respective bays and stack combinations, and containers of various sizes are included in the study. The fundamental relationships among these elements are established to achieve integrity and continuity of the two-stage optimization process. The first stage involves establishing a ship route planning model with the objective of minimizing the total operational cost. The second stage focuses on optimizing the stowage from the perspective of primary bay planning. The correspondence between containers and stacks is determined, and a ship stowage model is developed with the objective of minimizing the number of mixed container stacks. The stowage model ensures that the ship's stability meets the requirements throughout the route, while reducing the number of mixed stacks to improve port operation efficiency. To efficiently solve the proposed models, a Markov process corresponding to route planning and stowage decision-making is designed based on the Deep Q-learning Network (DQN) algorithm from deep reinforcement learning. The intelligent agent's state space, action space, and reward function are designed based on the problem's characteristics to construct the two-stage hierarchical DQN algorithm. Experimental results demonstrate that as the number of ships and the ship loading rate increase, the time required for accurate model solution significantly rises. Some cases cannot be solved within 600 seconds, while the DQN algorithm achieves rapid solutions in all examples. Compared with traditional models and the Particle Swarm Optimization (PSO) algorithm, the DQN algorithm efficiently solves cases of different scales. The maximum solving time for large-scale cases is 31.40 s, with an average time of less than 30 s, indicating good solution efficiency. Further calculations indicate that under different feeder port numbers, the average standard deviation of solving time for the DQN algorithm is only 1.74, showing better robustness compared to the average standard deviation of 11.20 for the PSO algorithm. Overall, the DQN algorithm exhibits less fluctuation in solving time with changing problem scales, showcasing stable solving performance and efficient optimization capabilities.
An Entropy Weighting-improved TOPSIS Method for Sector Complexity Evaluation
JIANG Wei, LI Yinfeng
2023, 41(6): 142-151. doi: 10.3963/j.jssn.1674-4861.2023.06.016
Abstract(44) HTML (23) PDF(2)
Sector complexity evaluation is the key and foundation for airspace planning and airspace resource allocation strategy. To solve the problems of multi-factor coupling and the issue of simplicity and subjectivity of existing evaluation methods, a sector complexity evaluation method based on entropy weight improvement-TOPSIS method is proposed. According to the operation characteristics of airspace sector, eight specific quantitative indicators are developed from three aspects of airspace static structure, traffic operation state and dynamic restriction, including route structure, aircraft potential conflict and bad weather, to establish a multidimensional evaluation index system that comprehensively reflects the complexity of airspace sector. A Gaussian distribution outlier detection method is used to eliminate the influence of extreme outliers on the evaluation. Combined with objective weight calculation of entropy weight method, a sector complexity evaluation method is proposed based on entropy weighting improved TOPSIS method, which is closer to the actual operation of the sector and conforms to the subjective cognition. This study takes Beijing regional sectors as an example for verification analysis, based on the standard of balanced sector complexity, the sector complexity is evaluated and analyzed from two scenarios: horizontal comparison between multiple sectors and comparison of single sector at different time periods, and compared with the expert evaluation results. The results show that the complexity of the two scenarios is unbalanced, indicating that the current allocation of airspace resources in Beijing area is unbalanced in both time and space. According to the evaluation results, airspace structure adjustment and traffic flow optimization can be carried out. Compared with the evaluation results of expert experience, the evaluation results of this method agree with the subjective cognition of experts as high as 80%, which verifies the feasibility, accuracy and effectiveness of this method. This method outperforms the expert evaluation method with the advantages of quantification, strong objectivity and convenient calculation.
An Analysis of Tripartite Evolutionary Game on Carbon Emission Reduction by Shipping Enterprises under the Goals of Carbon Peaking and Carbon Neutralization
JIANG Jun, YANG Chen, CHEN Lixuan, MA Zhiming, LIN Li, FU Xiaona
2023, 41(6): 152-160. doi: 10.3963/j.jssn.1674-4861.2023.06.017
Abstract(46) HTML (22) PDF(3)
Currently, the evolutionary game studies on carbon emission reduction in waterway transportation primarily focus on the interaction between enterprises and government, overlooking the impact of market consumers in the carbon reduction process. From the perspective of market consumers and by introducing shippers as game entities, the study of the tripartite game process involving shipping enterprises, regulatory government bodies, and shippers can provide a more comprehensive view of the carbon emission reduction pathways within the shipping industry. To balance the conflicting interests of shipping enterprises, regulatory government bodies, and shippers in the carbon reduction process, an evolutionary game model and dynamic replication equations among the three entities are constructed based on evolutionary game theory. The model is developed with sets of behavioral actions, probability combinations, and game behavior of the involved entities. Using MATLAB simulation tools, 12 equilibrium points of the model are solved, and a systematic analysis of their local stability is conducted. Through numerical simulation and analysis of the interactions and evolutionary processes among the three game entities, the influencing factors and mechanisms during the evolution are investigated. The study aims to explore the impacts of various parameters on the system's evolutionary outcomes. The simulation results indicate: ① As the benefits generated by low-carbon shipping technologies significantly surpass traditional technologies, the government begins to adopt more proactive regulatory strategies; ② During the evolutionary game, the strategy choices of participants are closely related to the probabilities of their initial strategy choices, suggesting that the initial strategies play a crucial guiding role in strategy evolution; ③ Under the dual influence of the government and shipping enterprises, shippers become a critical factor driving carbon emission reduction in the shipping industry; ④ The attitude of shipping enterprises towards new technology development is related to their benefits and government subsidies, challenging the traditional notion that associates it sorely with costs. The findings can provide valuable insights for strategy optimization in carbon emission reduction for shipping enterprises.
An Analysis of the Influence Factors on Using Intention of Vehicle Idle Start-stop System with a Structural Equation Model
YAN Yunzhu, FU Zhongning, YUE Jintian
2023, 41(6): 161-170. doi: 10.3963/j.jssn.1674-4861.2023.06.018
Abstract(49) HTML (24) PDF(2)
The vehicle idle start-stop system can significantly reduce fuel consumption and exhaust emissions. This study examines drivers' socio-economic attributes and subjective attitudes towards vehicle idle start-stop system to investigate their usage intention. A questionnaire of behavioral intention is designed with the Likert scale, and 520 valid observations are collected. The stability and reliability of the sample data are examined using common method bias test, reliability, and validity test. Under the framework of the technology acceptance model and the theory of planned behavior, a new latent variable, i.e., driver's trust in the idle start-stop system is added. The final structural equation model about usage intention of the system is established by optimizing the fitness value. From the tests of the model path hypotheses and mediation effect, the influence of each subjective factor is sorted out. Groups are divided according to socio-economic characteristics, and multiple-group models are established to analyze the specific influence of individual differences on the intention to use the system. The results found that: ① the most significant factor affecting the intention of drivers to use the vehicle idle start-stop system is their behavioral attitude; ② trust and perceived behavioral control also have a significant effect, while perceived usefulness is not a significant factor; ③ subjective norm and perceived ease of use have a significant positive effect on trust, which in turn affects the usage intention; 4) the higher-educated group is more likely to be influenced by perceived ease of use and trust, and the older and miniature-vehicle groups are more influenced by subjective norms while the oversized-vehicle group is more influenced by perceived behavioral control.
2023, 41(6): 171-172.
Abstract(41) HTML (50) PDF(0)