Subjects: Traffic and Transportation Engineering >> Water Transportation submitted time 2024-03-31
Abstract： The ship motion perception approaches mainly use maritime radar, Automatic Identification System (AIS) and cameras. However, using either of these approaches alone may result in information inconsistency and insufficient data accuracy. Therefore, a multi-sensor fusion perception system is proposed in this study to monitor ship motion in inland waterways. Firstly, a hardware platform of multi-sensor fusion ship motion perception system composed of maritime radar, AIS, cameras and other accessories is constructed. Secondly, by utilizing the target detection and tracking algorithms, track association algorithms, the ship motion data collected from the three sensors are integrated. Finally, the performance of the ship motion perception system is verified by field experiments in day and night. The experimental results indicate that the integrated ship motion perception system with multiple sensors is able to improve the information consistency and data accuracy of ship motion apparently in inland waterway compared to other perception systems.
Subjects: Traffic and Transportation Engineering >> Water Transportation submitted time 2024-03-28
Abstract： Vessel recognition plays important role in ensuring navigation safety. However, existing methods are mainly based on a single sensor, such as automatic identification system (AIS), marine radar, closed-circuit television (CCTV), etc. To this end, this paper proposes a coarse-to-fine recognition method by fusing CCTV and marine radar, called multi-scale matching vessel recognition (MSM-VR). This method first proposes a novel calibration method that does not use any additional calibration target. The calibration is transformed to solve an N point registration model. Furthermore, marine radar image is used for coarse detection. A region of interest (ROI) area is computed for coarse detection results. Lastly, we design a novel convolutional neural network (CNN) called VesNet and transform the recognition into feature extraction. The VesNet is used to extract the vessel features. As a result, the MVM-VR method has been validated by using actual datasets collected along different waterways such as Nanjing waterway and Wuhan waterway, China, covering different times and weather conditions. Experimental results show that the MSM-VR method can adapt to different times, different weather conditions, and different waterways with good detection stability. The recognition accuracy is no less than 96%. Compared to other methods, the proposed method has high accuracy and great robustness.
Subjects: Traffic and Transportation Engineering >> Ship Engineering submitted time 2024-03-23
Abstract： In recent years, there has been an increasing demand for higher detection and classification accuracy of ship targets to enable safe ship navigation, driving the development of ship intelligence. However, the performance of deep learning-based ship target detection algorithms is affected by the optical imaging process of ship targets, which can be easily disrupted by environmental factors such as wind, current, rain, and fog. Additionally, the diverse range of ship types, morphologies, and sizes pose challenges for accurate detection and identification of ship targets. To address these challenges, this paper proposes a multi-scale neural network-based target detection method for improving the accuracy of ship target detection in optical images. The proposed method employs a Convolutional Neural Networks (CNN) to extract image features. The improved backbone of CSPDarkNet and multi-scale network is used to realize the accurate detection of the ship-borne optical camera on the water ship target, and the detection accuracy of the model for small targets and dense targets is improved. Furthermore, label smoothing to prevent overfitting, and non-maximum suppression to reduce repetitive detections. Experimental results demonstrate that the proposed model achieves accurate detection of ship targets on water and can be used for the detection of small and intensive targets. The mean average precision (mAP) of the proposed method on the Ship-Detection dataset reaches 84.80, which outperforms previous research methods such as Faster-RCNN, DINO and offers greater potential for practical applications.
Peer Review Status:
Awaiting Review
Subjects: Traffic and Transportation Engineering >> Road Engineering submitted time 2024-02-07 Cooperative journals: 《应用力学学报》
Abstract：
A finite element model for train-dummy integrated passive safety simulation analysis was constructed based on the dummy model representing the male human characteristics of 50th percentile in China.The attitude changes of occupants during train collisions were analyzed,and the mechanical response characteristics of the head and neck of occupants were explored.The influence mechanism of seat alignment on occupants’ head and neck injury response was also revealed,and an injury risk prediction model based on head and neck biomechanical injury parameters was developed.The results show that the collision between the occupant’s face and the front seat may cause primary brain stem injury.The front and back curvature of the occupant’s neck will lead to the greater stress in the lower neck cervical spine,and it will also lead to the greater stress in the intervertebral disc of upper and lower necks,respectively.The Nij tolerance limit specified in the current standard will significantly underestimate the neck injuries suffered by occupants in rear-end train collisions.
Subjects: Traffic and Transportation Engineering >> Road Engineering submitted time 2024-02-07 Cooperative journals: 《应用力学学报》
Abstract：
In order to investigate the problem of frequent wheel flange crack damage in a high-power heavy haul locomotive operating on high-altitude multi-curved railway lines in China,a combined approach of theoretical analysis,numerical simulation,and field test is employed.First,based on multibody dynamics and stability theory,a vehicle dynamics model for the high-power heavy haul locomotive and a prediction model for wheel flange crack damage are respectively established.Next,the accuracy of the model is validated by comparing field test data with numerical simulation results.Finally,based on the characteristics of the operating route for the heavy haul locomotive,an analysis is conducted on the effects of curve radius,curve superelevation,curve gradient,and wheel flange lubrication on the damage pattern of wheel flange cracks.The research results indicate that continuous small radius curves are the main cause of wheel flange cracks in this heavy haul locomotive.In addition,wheel flange lubrication has a significant effect on the locomotive wheel flange crack damage.Therefore,the wheel-rail dynamic interaction can be reduced by setting appropriate route parameters and implementing effective wheel flange lubrication,and the occurrence of wheel flange cracks in the heavy haul locomotive can be minimized.
Subjects: Traffic and Transportation Engineering >> Railway Transportation submitted time 2024-02-07 Cooperative journals: 《应用力学学报》
Abstract：
A three-dimensional transient contact finite element model based on explicit time integration is developed for the rack railway suitable for mountain rail transit.The medium and high frequency coupling dynamic interaction between gear-rack meshing and wheel-rail rolling contact can be analyzed in time domain.Factors such as the true geometry of the wheelset and track,the ‘wheel paradox’ caused by the diameter difference between the gear and the wheel,and structural vibration are taken into account.The gear and rack meshing and wheel-rail contact are both solved by a surface-to-surface contact algorithm with the Coulomb friction integrated.Considering the zero and non-zero wheel-rail friction coefficients,the influence of the ‘wheel paradox’ on the gear-rack meshing and wheel-rail rolling contact can be deconstructed.Taking the Strub rack railway as an example,the dynamic contact phenomena under a running speed of 10 km/h and slopes of 0‰,240‰ and 480‰ are investigated.The results show that the contact forces of gear-rack and wheel-rail show periodic fluctuations due to gear meshing,but the vertical total force and total traction torque fluctuate near gravity load and traction torque,respectively.The wheel paradox makes the vertical contact force and normal stress of the rack decrease,while the vertical contact force and normal stress of the wheel-rail increase.In terms of the tangential contact solution,the tangential contact stress of the tooth surface and the slip area in the contact spot increase.Under the condition of slope 240‰,the wheel-rail friction coefficient increases from 0 to 0.2,the maximum normal contact stress of rack and wheel-rail increases from 248.69 and 752.66 MPa to 195.17 and 757.44 MPa,and the maximum tangential contact stress changes from 24.48 and 152.84 MPa to 21.31 and 2.14 MPa.The wheel-rail contact presents full sliding contact due to significant creep.Under the same speed and friction conditions,the increase of slope makes the vertical force and traction force of rack increase,the vertical force and traction force of wheel and rail decrease,and the contact stress has the same change.
Subjects: Traffic and Transportation Engineering >> Traffic and Transportation System Engineering submitted time 2020-10-28
Abstract： This paper introduces a unified hybrid metaheuristic algorithm for the transit bus and driver scheduling problems, such as the problem with fuel or electronic vehicles, the problem with single route or multiple routes, and the problem that arises from most transit companies in China where a driver should drive the same bus in the same day. The problems aim to minimize the fixed bus cost, the bus travel cost, the fixed driver cost and the allowance for drivers, while satisfying various operational rules on vehicles and drivers. The hybrid algorithm was implemented based on initial solution generation, local search improvement and the search strategies such as iterative local search (ILS), variable neighborhood decent (VND), and set partitioning. The performance of the proposed algorithm was tested on 62 single-route instances and 11 multi-route instances. There are three important findings for transit operations in China from the experimentation. First, electronic vehicles may replaces fuel buses by an increase of 0.8% and 1.6% vehicles for single-route instances and multi-route instances, respectively. Second, compared with the single-route scheduling, the multi-route scheduling has potentials to reduce 4.6% of vehicles and 2.4% of drivers. Third, if the drivers are allowed to change driving in their daily works, the number of vehicles required could be reduced significantly, especially for the single-route instances.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Geography Subjects: Traffic and Transportation Engineering >> Road Engineering submitted time 2019-03-31
Abstract： " Based on metacartography, this study establishes a model to convert the time distance of taking light rail to the spatial distance in meters. On this basis, this study uses the spatial transformation method of geographic information system (GIS) map projection to redefine the distance between two locations with the converted distance and transforms the original map into a time distance map. By spatializing the time distance, this study gives time distance a visual expression. The results show that the influence of light rail on urban form is affected by the distance between the station points and the selected center point; that is, that the transformation is greater when the station points are farther away from the center point, and vice versa. The impact of light rail on the layout of business centers is basically distributed in the shape of a circle. Time distance compresses the traditional urban form. There is still much room for the city to further compress the time distance, and the existing business centers should be upgraded.
Peer Review Status:Awaiting Review
Subjects: Traffic and Transportation Engineering >> Ship Engineering submitted time 2018-03-30
Abstract： The hydroelastic behavior of very large floating structures (VLFSs) is investigated based on the proposed multi-modules beam theory (MBT). To carry out the analysis, the VLFS is first divided into multiple sub-modules that are connected through their gravity center by a spatial beam with specific stiffness. The external force exerted on the sub-modules includes the wave hydrodynamic force as well as the beam bending force due to the relative displacements of different sub-modules. The wave hydrodynamic force is computed based on three-dimensional incompressible velocity potential theory, and the boundary element method with the free surface Green function as the integral kernel is adopted to numerically find the solution. The beam bending force is expressed in the form of a stiffness matrix. The coupled motion equation is established according to the continuous conditions of the displacement and force. The motion response defined at the gravity center of the sub-modules is solved by the multi-body hydrodynamic control equations, then both the displacement and the structure bending moment of the VLFS are determined from the stiffness matrix equations. To account for the moving point mass effects, the proposed method is extended to the time domain based on impulse response function (IRF) theory. The accuracy of the proposed method is verified by comparison with existing results. Detailed results through the displacement and bending moment of the VLFS are provided to show the influence of the number of the sub-modules, and the influence of the moving point mass.
Peer Review Status:Awaiting Review
Hits
YES
Hits
Downloads
Comment