Archive

15 March 2021, Volume 40 Issue 03 Previous Issue    Next Issue
---
Transport+Big Data and Artificial Intelligence
Transportation Infrastructure Engineering
Transportation Equipment


For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Transport+Big Data and Artificial Intelligence

Select

Taxi Time Prediction of Departure Aircraft LI Nan1, JIAO Qingyu1, ZHANG Liandong2, FAN Rui1 2021, 40(03): 1-6.  DOI: 10.3969/j.issn.1674-0696.2021.03.01 Abstract ( )   PDF (811KB) ( )   In order to accurately predict the taxi time of departing flights, combined with the actual operation condition of Beijing Capital International Airport, a multiple regression model was established according to the classification results obtained by using DBSCAN algorithm to classify the airport operation time according to the flight flow per hour. The impact of the taxiing distance of aircrafts, the number of taxiing aircrafts on the ground (departure and arrive), the runway operation mode on the taxiing time of flights was analyzed. And two methods, traditional statistics and machine learning (Lasso regression), were used to predict the taxiing time of departure aircraft. The results show that: compared with the traditional statistical multiple regression model, the prediction accuracy of the proposed model under machine learning crosstraining set is higher and 87% of errors between the predicted and actual values are within 5 minutes, which can be used to predict the actual flight taxiing time of large airports. References | Related Articles | Metrics

Select

Selection Problem of Search Ship at Sea WANG Jun, YU Anmin, YANG Chunlin 2021, 40(03): 7-15.  DOI: 10.3969/j.issn.1674-0696.2021.03.02 Abstract ( )   PDF (3940KB) ( )   In view of the urgency of the maritime search mission and the different probability distribution of the target in the sea area to be searched, the sea area to be searched was divided into several sub-areas according to the probability distribution, and the probability distribution of the target in different sea areas was also studied. Considering that the probability of different location of the target in the sea area was different, so the ships search priority for each sub-area was different, the optimal selection problem of dispatching ships to multiple regions was studied. The maritime search ship selection optimization model with the minimum expected time of each sub-region to finish the search was proposed, which fully considered the search ability and maximum speed of the search ship, the initial distance from each sub region and other factors, and designed the algorithm. The effectiveness of the proposed model was verified by an example. The research results show that: considering the probability of different sub-areas, choosing the right ship and designating the search ship to rush to the right sub-area can save the search task completion time. References | Related Articles | Metrics

Select

Conflict Identification between Pedestrian and Vehicle at Non-signalized Intersection Considering Visibility MA Yanli, ZHU Jieyu, ZHANG Sufeng, ZHANG Peng 2021, 40(03): 16-21.  DOI: 10.3969/j.issn.1674-0696.2021.03.03 Abstract ( )   PDF (1466KB) ( )   In order to reduce the traffic accidents of pedestrians and vehicles crossing the street at non-signalized intersections in low visibility, a study on the identification of vehicles and pedestrians crossing the street considering the impact of visibility was carried out. Combined with the relative position, velocity, acceleration, vehicle size and other information of vehicles and pedestrians, the conflict recognition model between pedestrians and vehicles was constructed. The visibility measurement method of traffic environment based on the distance between people and vehicle was determined, and the relationship model between vehicle speed and visibility was given. On this basis, the proposed model was modified, and the effectiveness of the proposed model was verified. The results show that the proposed conflict recognition model can effectively identify the conflicts between pedestrians and vehicles crossing the street, and the accuracy of conflict recognition is 82.4%. This study can provide decision-making for pedestrians and vehicles at non-signalized intersections with intelligent vehicle infrastructure cooperative systems, and thus improve the safety of pedestrian and vehicle in low visibility. References | Related Articles | Metrics

Select

Delay Calculation Model of Associated Intersections LIU Qingguang1, GU Yumu1, LIN Peiqun2 2021, 40(03): 22-26.  DOI: 10.3969/j.issn.1674-0696.2021.03.04 Abstract ( )   PDF (2064KB) ( )   In order to overcome the demerit that the traditional delay model only studied the isolated intersection, an “offset-delay” model for associated intersections was established to analyze the running condition of associated intersections quantitatively. Based on steady-state theory of traffic (Webster delay model), the proposed model considered the influential factors of the associated intersections, such as traffic volume, timing scheme, offset and link length, which could dynamically reflect the relationship between offset and delay of associated intersections. The specific case has been applied to illustrate the use of the formula and verify the proposed delay model for associated intersections. The results show that: compared with the simulation results of VISSIM software, the “offset-delay” model is more reliable. References | Related Articles | Metrics

Select

Anomaly Detection of Traffic Signal Lights in Network Based on Self-learning LIU Yongtao1, 2, FAN Yamin1, ZHANG Li1, LI Guan1 2021, 40(03): 27-33.  DOI: 10.3969/j.issn.1674-0696.2021.03.05 Abstract ( )   PDF (5407KB) ( )   With the development of intelligent traffic, signal lights have become the key equipment for the normal operation of urban roads. It is necessary for traffic departments to grasp the operation status of signal lights in real time to find out and eliminate the faults in time and reduce the incidence of traffic accidents. Aiming at the problems of complex hardware structure, high cost, difficult installation and construction, and inconvenient maintenance of existing research methods, a fault diagnosis method of networked signal lights based on self-learning was proposed. The system could quickly and accurately grasp the operation status of signal lights under normal conditions by one click learning. By means of dynamic threshold fuzzy reasoning and diagnosis method, the problem of threshold drift caused by system aging and temperature change was solved. The whole system adopted wireless networking mode and one-drag-three measurement structure. Through the edge computing distributed processing method, the construction difficulty was greatly reduced and the cost of hardware system was reduced by more than 50%, which effectively solved many problems existing in current design and installation. References | Related Articles | Metrics

Select

Influence Analysis of Pedestrian Active Safety System on Operation State of Traffic Flow HUA Jun1, SUN Zhicheng2, ZHAO Junwei1, ZHU Tong2, 3 2021, 40(03): 34-42.  DOI: 10.3969/j.issn.1674-0696.2021.03.06 Abstract ( )   PDF (2679KB) ( )   Pedestrian active safety system can effectively reduce the risk of collision between pedestrians and vehicles, but its impact on the long-term operation state of traffic flow remains to be explored. Net Logo software was used to set the motion modes of vehicle agents and pedestrian agents based on the idea of agent-based modeling. The average vehicle speed fluctuation, vehicle waiting time, pedestrian waiting time and pedestrian speed distribution were selected to evaluate the traffic flow stability and traffic efficiency while traditional vehicles, vehicles with pedestrian detection system and vehicles with pedestrian-vehicle communication system were running. The results show that the pedestrian active safety system has different performances under different road conditions. The use of pedestrian detection systems is not conducive to the traffic flow stability. The popularity of pedestrian-vehicle communication systems may affect traffic efficiency and increase urban congestion. The study provides ideas for driver training, automatic driving vehicle market access, road design and management. References | Related Articles | Metrics

Select

Real-Time Assessing the Personnel Exposed Risk of Hazardous Material Transport on Highway TAO Jian, WANG Wenjun, PANG Duofeng, YIN Chuanfeng 2021, 40(03): 43-48.  DOI: 10.3969/j.issn.1674-0696.2021.03.07 Abstract ( )   PDF (481KB) ( )   For more accurate real-time assessment of exposure risks of road transportation personnel of dangerous goods, a real-time evaluation model of exposure risks of highway transportation personnel of dangerous goods was proposed, which was based on the risk evaluation content, the vehicle speed and road information parameters collected by GPS vehicle monitoring system. The functional relationship between the average vehicle speed and the traffic density and the exposure of personnel in high-speed service area was focused when the dangerous goods were in highway transportation. The personnel exposure on roads and at densely populated areas was assessed in real time, and the correction of vehicle type to average speed was considered. The transportation risks were assessed by case study when vehicles were under different speed conditions and passing the service area. Results show that vehicle speed and population density exert significant effects on transportation personnel exposure risks. The proposed model can further decompose risk indicators and improve the accuracy of risk assessment, meanwhile, it can evaluate the dynamic risk of transportation in real time, which has practical significance to assist the intelligent supervision of dangerous goods transportation risk and reduce the transportation risk. References | Related Articles | Metrics

Select

Real-Time Abnormal Detection of Train Operation Speed of Urban Rail Transit Based on XGboost Model LIU Jie 2021, 40(03): 49-55.  DOI: 10.3969/j.issn.1674-0696.2021.03.08 Abstract ( )   PDF (2298KB) ( )   With the rapid development of urban rail transit, it is necessary to study the detection method of abnormal train speed in order to ensure the safe running of trains. Therefore, a train speed anomaly detection method combining extreme gradient boost (XGboost) and anomaly detection method was proposed. Firstly, the XGboost model was trained by using the data of train speed sampled on site. Then, cross validation and grid search method were used to determine the optimal parameters of XGboost model. Finally, the maximum likelihood estimation and Grubbs test were used to determine the anomaly of the prediction results. The experimental results show that: compared with the other four common models in the test set, F1 values are increased by 7.08%, 12.9%, 16.9% and 2.9% respectively. Moreover, the proposed method meets the real-time detection requirements of train operation in terms of time efficiency. References | Related Articles | Metrics

Select

Line Carrying Capacity of Urban Rail Transit Fast and Slow Train Scheme WANG Xiaochao1, ZHOU Lu1, JIN Hua2, TIAN Meng2 2021, 40(03): 56-63.  DOI: 10.3969/j.issn.1674-0696.2021.03.09 Abstract ( )   PDF (631KB) ( )   In view of the problem that the calculation method of the existing carrying capacity of urban rail transit was rough, the calculation formula of the line carrying capacity of urban rail transit under the fast and slow train schemes was given by using the easily available parameters through reasonable assumptions and classification discussion. Moreover, a case study was performed based on an operational line in Fuzhou Metro. The results show that it is the number of slow stations in the section divided by overtaking stations rather than the distance between overtaking stations is the main influencing factor of the line carrying capacity, and some suggestions on the setting of overtaking stations are given. References | Related Articles | Metrics

Select

Multi-attribute Decision-Making Model for Transportation Modes Selection of Commodity Vehicles WANG Haiyan, AN Kaimin 2021, 40(03): 64-71.  DOI: 10.3969/j.issn.1674-0696.2021.03.10 Abstract ( )   PDF (1338KB) ( )   In order to ensure the transportation timeliness, improve transportation efficiency and effectiveness of commodity vehicles, transportation time, price, safety and reliability were chosen as main factors to constitute attribute set for decision-making of transportation modes selection. Considering the “partial compensation” characteristics among the attributes, coupled with the shippers preference for different modes of transportation, a multi-attribute decision-making model of transportation modes selection was established, which was solved by improved ELECTRE-I algorithm. Then, the commodity vehicle transportation of “Wuhan-Guiyang” was carried out as an example to verify the effectiveness of the proposed model. The results indicate that the improved ELECTRE-I algorithm is feasible for vehicle transportation mode selection, which can provide theoretical support for the automobile manufacturer to select reasonable and effective transportation mode, save transportation time and reduce transportation cost. References | Related Articles | Metrics

Transportation Infrastructure Engineering

Select

Stress State of Straddle Monorail Steel Track Beam Based on ABAQUS LIN Cheng 2021, 40(03): 72-77.  DOI: 10.3969/j.issn.1674-0696.2021.03.11 Abstract ( )   PDF (3074KB) ( )   Aiming at the straddle type monorail steel track beam structure, the stress state of the steel track beam with different types of roof stiffeners was analyzed by using the finite element analysis software ABAQUS, and the stress system of the bridge deck was deeply analyzed. Results show that the top plate of steel track beam shows obvious stress characteristics of three basic systems, and the stress of the second and third system accounts for 30%~45%. Both longitudinal and transverse stiffeners on the top plate can reduce the stress of the second and third system of the roof. The effect of longitudinal stiffeners is better than that of transverse stiffeners, but it will reduce the welding space at the top of the track beam, which makes it difficult to be manufactured. Increasing the number of transverse stiffeners can significantly reduce the stress of the top plate, which is better than increasing the thickness of stiffeners. This study provides a theoretical basis for the design of straddle monorail steel track beam with transverse stiffener structure on the top plate. References | Related Articles | Metrics

Select

Validity Analysis of Bridge Health Monitoring Data Based on Deep Learning LIANG Zongbao 1, CHAI Jie1, NA Shouyong2, MA Tianli1, TANG Yu1 2021, 40(03): 78-83.  DOI: 10.3969/j.issn.1674-0696.2021.03.12 Abstract ( )   PDF (3426KB) ( )   As the cornerstone of bridge structural health monitoring system, the validity of monitoring data is very important. However, most of the current methods rely on statistical theory and require a lot of domain knowledge, which is not suitable for large-scale datasets. A method combining grey relation degree and deep learning was proposed. Data was preprocessed by grey relation analysis, and data labels were automatically given and validated. The validity of monitoring data was analyzed by deep learning models such as DNN and DBN. Experiments show that the proposed method improves the accuracy of monitoring data validity analysis to 94.47%, and has good prediction performance. It solves the problems of low efficiency and low accuracy existing in traditional manual analysis, and is suitable for structure health monitoring system of large-scale bridge. References | Related Articles | Metrics

Select

Composite Beam Fatigue Damage Law of Steel Bridge Deck Gussasphalt Pavement WANG Min1,2, SHANG Fei1, XIAO Li1, BAO Guangzhi3 2021, 40(03): 84-88.  DOI: 10.3969/j.issn.1674-0696.2021.03.13 Abstract ( )   PDF (1490KB) ( )   The gussasphalt mixture is one of the typical paving materials for steel bridge decks. The combined structure of gussasphalt mixture and orthotropic steel bridge deck bears the load of automobile. In order to investigate the influence of material parameters of gussasphalt mixture on the fatigue damage law of composite structure during service of steel bridge, the fatigue test of composite beam with three-point loading was adopted. Load and deformation parameters were collected during the test, and damage variables of composite beams were calculated. The influence degree of material modulus, pavement thickness and load level on fatigue damage of composite beam was analyzed. The results show that under the same deformation conditions, the material with higher modulus improves the pavement stiffness, but its decay speed is faster; the thickness change has a basically linear relationship with the fatigue damage rate of the composite beam, and the load change has a great influence on it. Especially when the initial deflection of the applied load increases from 0.6 mm to 0.8 mm, the fatigue damage rate of the composite beam increases by 180%. References | Related Articles | Metrics

Select

Adhesion of Lime Modified Asphalt Based on Surface Energy Theory DONG Shihao, HAN Sen, YIN Yuanyuan, WU Song, ZHANG Qixin 2021, 40(03): 89-97.  DOI: 10.3969/j.issn.1674-0696.2021.03.14 Abstract ( )   PDF (6843KB) ( )   In order to study the effect of lime ［Ca (OH) 2］ on the adhesion of asphalt, based on the surface energy theory, the change of adhesion work between the lime modified asphalt and granite was analyzed, and the influence of lime content and fineness on the adhesion of asphalt was studied. In order to further verify the correctness of the analysis results based on the surface energy theory, the pull-out test was carried out and the correlation analysis with the adhesion work was carried out. The results show that the addition of lime can improve the polarity of asphalt, increase the surface energy of asphalt, and then improve the adhesion by increasing the adhesion work between asphalt and aggregate. The adhesion of asphalt increases with the increase of the fineness of lime. When the content of lime is about 10% by the weight of asphalt, asphalt and granite have the best adhesion. The correlation coefficient between the results of pull-out test and the results of surface energy theory test is 0.900, which has a high correlation and shows that it is feasible to use surface energy theory to evaluate the effect of lime modified asphalt. References | Related Articles | Metrics

Select

Storage Stability of Anionic Emulsified Asphalt HUANG Weirong, MENG Qiao, ZHAO Ke, CUI Jindong 2021, 40(03): 98-102.  DOI: 10.3969/j.issn.1674-0696.2021.03.15 Abstract ( )   PDF (3352KB) ( )   In order to solve the problem of storage stability in anionic emulsified asphalt application, the test instruments such as optical microscope, laser particle size analyzer and storage stability tester were used to analyze the influence of raw materials, preparation process and storage environment on the storage stability of self-made anionic emulsified asphalt. The test results show that when the dosage of emulsifier, stabilizer and antifoaming agent are 3.0%, 0.1% and 0.1% respectively, the soaping temperature is 40 ℃, the asphalt temperature is 130 ℃ and the shearing time is 90s, the prepared emulsified asphalt has good storage stability. Microscopic analysis results show that the prepared emulsified asphalt has smaller particle size, more uniform distribution and better storage stability. References | Related Articles | Metrics

Select

Influence of Acquisition Methods on Segregation Evaluation of Digital Image of Asphalt Mixture LI Shenglian1, LIANG Naixing2, ZENG Sheng2 2021, 40(03): 103-107.  DOI: 10.3969/j.issn.1674-0696.2021.03.16 Abstract ( )   PDF (2230KB) ( )   In order to study the influence of the acquisition method on the evaluation results of the digital image processing technology asphalt mixture evaluation method, a reasonable image acquisition condition was proposed. Digital image preprocessing was carried out on the AC-13 and AC20 grade type mixture images, the asphalt mixture images under different light intensity as well as images of different acquisition heights. Image uniformity was evaluated by four-sided static moment variation coefficient, and the results of variation coefficients were compared and analyzed. The research results show that the results of the static moment variation coefficient of 500 images of the AC-13 and AC25 asphalt mixture are concentrated in the range of 0 to 1.5%. The lower layer of AC-25 asphalt mixture is more prone to segregation than the upper layer of AC-13. In the case of sufficient light intensity, the uniformity evaluation result is not affected, but when the illumination is insufficient at night, the result will deviate, so it is necessary to compensate the illumination for the image acquisition. When the image acquisition height is 60cm, the aggregate particle surface ratio is consistent with the actual condition. As the height of the acquisition increases, the adhesion particles with large size in the preprocessed image increase, which affects the accuracy of uniformity evaluation. References | Related Articles | Metrics

Select

Instability Criterion Method of Tunnel Engineering under Seismic Action TAN Xukai1,2, GAO Feng1,2, XU Wei1, LUO Xing1 2021, 40(03): 108-115.  DOI: 10.3969/j.issn.1674-0696.2021.03.17 Abstract ( )   PDF (541KB) ( )   In order to find a breakthrough in instability criterion method of tunnel engineering under seismic action, the principle, advantages and disadvantages and the application scope of the existing static and dynamic instability criterion methods of tunnel engineering were discussed, which strived to put forward practical and feasible criterion ideas. Firstly, the seismic response, damage mechanism, and the current overview of seven kinds of static instability criterion methods of tunnel engineering were described. Secondly, combined with the seismic response characteristics and the static instability criterion method of tunnel engineering, the development situation of dynamic instability criterion methods for tunnel engineering was elaborated from the qualitative judgment, theoretical inference, shaking table model test judgment. Then, the problems and shortcomings of the current dynamic instability criterion methods were summarized, such as lack of theoretical support for qualitative criterion method, the lack of research depth of the dynamic criterion theoretical method developed from the static criterion method, and the lack of special research on the shaking table failure test of the dynamic instability criterion method. Finally, the research prospect of the instability criterion method of tunnel engineering under seismic action were proposed, which provided a certain reference for researchers in this field. References | Related Articles | Metrics

Select

Application of PVC Pipe Cumulative Blasting Method in Horizontal Sandy Mudstone Tunnel ZHONG Yupei1, QI Yanjun2, LIU Shukui2 2021, 40(03): 116-120.  DOI: 10.3969/j.issn.1674-0696.2021.03.18 Abstract ( )   PDF (2812KB) ( )   Taking Duanjiaping tunnel of Menghua railway section as an example, the forming characteristics of horizontal sandy mudstone tunnel by blasting were analyzed. The PVC pipe cumulative blasting method was put forward and the PVC pipe cumulative blasting device was developed. The expected blasting and forming effect was achieved by using PVC pipe cumulative blasting method. When the direction of PVC pipe cumulative energy structure was basically perpendicular to the horizontal rock layer bedding structure, it was necessary to reduce the blasting hole spacing. The PVC pipe cumulative blasting method can better control the overbreak and underbreak amount of the tunnel in horizontal sandy mudstone stratum, and most of overbreak amount is controlled within 15 cm, and the maximum overbreak amount is reduced by 78.8%. At the same time, if the factory produces PVC pipe energy-accumulating structure in large scale, the time and materials will be saved better, and the work efficiency will be improved. References | Related Articles | Metrics

Transportation Equipment

Select

Influencing Factors of Structural Damage and Ship Impact Force in Ship-Bridge Collision ZHANG Aifeng, LIU Shaokang, YAO Miaomiao, ZHEN Chunbo 2021, 40(03): 121-127.  DOI: 10.3969/j.issn.1674-0696.2021.03.19 Abstract ( )   PDF (10165KB) ( )   With the rapid development of transportation industry, ship routes become more and more dense, the number of river-crossing and sea-crossing bridges increases year by year, and the probability of ship-bridge collision accidents increases. The collision process of 6600DWT vertical bow cargo ship and square pier collision was simulated by using nonlinear finite element method. The energy conversion relationship of ship-bridge collision was studied; the variation rule of dynamic responses of ship structures, such as ship speed, bow depth, ship stress and strain, changing with time was analyzed. Five factors, including ship speed, load, collision angle, lateral offset and pier section type, were selected to set up multiple working conditions. The effects of each factor on the impact force and contact time of ship-bridge collision were studied respectively. The research results show that: the ship-bridge collision accident may cause obvious plastic deformation in the contact area; the impact force is positively correlated with the speed and load of the ship, but negatively correlated with the collision angle and lateral offset, and it has a certain correlation with the cross-section form of the pier. The research results reproduce the whole process of ship-bridge collision and reveal the locality of ship-bridge collision damage and the difference of impact force under the influence of various factors. References | Related Articles | Metrics

Select

Design of IGBT Heat Dissipating Fin Structure Based on STAR-CCM+ LIU Zhen1,3, LIN Xin1,2, WU Huawei1,3, YE Congjin1,3, GENG Xiangyang4 2021, 40(03): 128-134.  DOI: 10.3969/j.issn.1674-0696.2021.03.20 Abstract ( )   PDF (7669KB) ( )   The IGBT component is the core component of the motor controller, and its heat dissipation performance directly affects the stability of the controller. According to the heat dissipation requirements of an IGBT component, on the basis of the traditional rectangular heat-dissipating fins, an isosceles triangular heat-dissipating fin with 3 mm bottom and 1 mm height and an isosceles trapezoidal heat-dissipating fin with 1 mm upper bottom, 3 mm lower bottom and 1 mm height were designed. Three-dimensional modeling and theoretical junction temperature calculations were performed respectively on the IGBT modules of the three kinds of heat radiators. And the computational fluid dynamics analysis software STAR-CCM+ was used to numerically simulate the IGBT modules of three kinds of heat dissipating fins with different fin heights, fin thicknesses and fin spacing. The temperature field and vector field of the IGBT module were analyzed. The results show that that the error between the simulation results and the theoretical calculation results is about 5%. And the heat dissipation performance of IGBT module of the three kinds of heat radiators is the best when the fin height is 34 mm, the fin thickness is 2.8 mm and the fin spacing is 2.8mm. References | Related Articles | Metrics

Select

Lithium Battery SOC Estimation Based on ABP-EKF Algorithm LI Jun, ZHANG Jun, ZHANG Shiyi 2021, 40(03): 135-140.  DOI: 10.3969/j.issn.1674-0696.2021.03.20 Abstract ( )   PDF (1510KB) ( )   Accurate estimation of battery SOC is a prerequisite and important basis for the rational implementation of battery management in electric vehicles. Aiming at the problem that the estimation accuracy of power battery SOC for electric vehicles is improving continuously, the joint estimation method was used to study the SOC of lithium battery. Based on the Thevenin battery model and the modified ampere-hour integration algorithm, the output equation and state space model of the lithium battery were derived. The parameters of the battery model were identified by collecting relevant data during the experiment and applying the recursive least square method. The principles of the extended Kalman filter (EKF) algorithm and the adaptive BP neural network algorithm were analyzed, and two algorithms were combined. On this basis, the self-adaptive BP-EKF algorithm (ABP-EKF) was proposed. The proposed algorithm was used to jointly estimate the lithium-ion battery SOC. Finally, the data of the lithium battery SOC was estimated by comparing the two algorithms of ABP-EKF and EKF. The research results show that compared with the EKF algorithm, the proposed ABP-EKF algorithm reduces the mean error term and root mean square error term by 3.9% and 3.79%, respectively. References | Related Articles | Metrics