2014 No. 2

  Previous Issue | Next Issue 
Display Method:
2014, (2): .
Abstract(334) PDF(0)
Abstract:
Fast Pedestrian Detection and Localization Based on the Improved Adaboost Algorithm
YOU Feng, LI Fuliang, FENG Qiongying, ZHANG Ronghui, PEI Yulong, XU Jianmin
2014, (2): 1-5. doi: 10.3963/j.issn.1674-4861.2014.02.001
Abstract(366) PDF(1)
Abstract:
With the development of the intelligent transportation system (ITS) ,proactive pedestrian safety protec-tion has become increasingly significant and attracted the attention from many research institutions around the world .A fast pedestrian detection and location method based on the improved Adaboost Algorithm is introduced in this paper .The Haar-like features are selected and integral image is utilized to compute the features .An optimization method of updating the weights is put forward to improve the traditional Adaboost Algorithm .The experimental results show that the fast pedestrian detection and localization method has a better performance in accuracy and robustness .
Evaluating Safety Impact of Countdown Signal Timers at Signalized Intersections
YU Hao, LIU Pan, YANG Zhao, CHEN Yuguang
2014, (2): 6-10. doi: 10.3963/j.issn.1674-4861.2014.02.002
Abstract(377) PDF(1)
Abstract:
The primary objective of this study is to evaluate the impact of countdown signal timers on the safety of signalized intersections .Data were collected at 13 approaches of 9 signalized intersections .A cross-sectional analysis was conducted to compare the safety performance of signalized intersections with and without countdown timers .Various sur-rogate safety measures ,such as the red-yellow running violation ratio and traffic conflicts ,were used for safety assess-ment .It is found out that the countdown signal timers significantly increase the red-yellow running violation and traffic conflicts at signalized intersections for both through and protected left-turn movements .The study results of this paper suggest that the countdown signal timers negatively affect the safety performance of the signalized intersections and there-fore ,should be used more cautiously .
Typical Choice Behavior of Park and Ride in Shanghai
LIU Li, DU Yuchuan, LIU Xin
2014, (2): 11-16. doi: 10.3963/j.issn.1674-4861.2014.02.003
Abstract(407) PDF(1)
Abstract:
The paper conducts an investigation of the typical choice behavior for the unbalanced operation of Park and Ride in Shanghai .According to the results of the preliminary investigation ,travel time is the most important impact factor and the second most important impact factor is the travel cost .In order to verify the universality of the conclusion , this paper investigated the travel costs of typical travel routes at the peak time by network observation supplemented by actual travel time data .The study finds that :(1) P+R facilities in Shanghai can be divided into urban and suburban lots , and many users are derived from the public transportation and other motorized travel modes ;(2) drivers value travel time the most ,whose time value is higher in traffic jams than in free-flow road conditions ;(3) public transportation passen-gers are abstracted by the travel time savings while taxi users tempted by the travel cost ;(4) P+ R can promote multi-model travel mode ,and residents with imperfect bus transit services have higher demand for P+R facilities .
Algorithm for Predicting Bus Travel Time between Stops Based on Markov Chain
HU Jihua, LI Guoyuan, CHENG Zhifeng
2014, (2): 17-22. doi: 10.3963/j.issn.1674-4861.2014.02.004
Abstract(364) PDF(1)
Abstract:
Bus travel time between stops has obvious period distribution characteristics .The buses ,with the char-acteristic of state transition ,have a typical space-time process .In order to predict the bus travel time between stops in the future period of time accurately ,an improved algorithm based on the basic Markov chain is proposed .The algorithm can be divided into two steps .The first step is to set up the first-order Markov transition matrix for a specific bus route dur-ing different period of time with the bus GPS data and then to predict the bus travel time between stops based on the ma-trix .The second step is to improve the basic Markov chain algorithm by leading up the compensation of moving error . The algorithm was tested and validated by using the data taken from the bus route B1 of Guangzhou BRT .The test result shows that the improved algorithm with the compensation of moving error provides better predicting accuracy than both basic Markov chain algorithm and the BP neural network algorithm and that the improved algorithm is simple in imple-mentation .
Traffic Congestion Identification Method for Urban Expressway
WANG Yao, SHAO Changqiao, LIU Yang
2014, (2): 23-27. doi: 10.3963/j.issn.1674-4861.2014.02.005
Abstract(389) PDF(9)
Abstract:
In order to make up inadequate research on traffic congestion identification by single detector ,this study focuses on using actual single detector data to recognize congestion .Based on analyzing the field traffic data ,critical occu-pancy can divide the state of traffic flow into congested and uncongested flow .Speed to occupancy ratio and speed differ-ence can design a multiple indicator identification method to determine the time of congestion occurrence and end time .Fi-nally ,after three indicators threshold are calibrated ,this identification method is applied to Beijing urban expressway . The result shows that this method can identify congestion effectively in starting time ,duration ,and finishing time .
Traffic Accident Data Analysis of Third-class Urban Roadways Using Logistic Regression Models
DENG Yaowang, LI Lingyu, CHEN Yuren
2014, (2): 28-33. doi: 10.3963/j.issn.1674-4861.2014.02.006
Abstract(324) PDF(3)
Abstract:
According to the statistical data of Urumqi City from 2006 to 2010 ,nine different crash types of traffic accidents on urban roadways were selected respectively as the dependent variables .Furthermore ,nine factors were select-ed as the independent variables ,in aspects of road facilities and road environment .Based on Binary Logistic Regression model ,this paper established linear correlative models between crash types and nine affecting factors ,evaluated the model parameters ,analyzed the reliability and fitting degree of the model ,and investigated the impact that different independent variables combination have on the dependent variables .The paper also predicted the risk of each crash types under various conditions by using a multi-Logistic model ,and compared the prediction with the actual cases ,and tested the fitting effi-ciency of the model used .
Shared Parking Allocation Method for Mixed Land Use Development
RAN Jiangyu, GUO Xiucheng
2014, (2): 34-40. doi: 10.3963/j.issn.1674-4861.2014.02.007
Abstract(325) PDF(1)
Abstract:
In order to adapt to the mixed land use development trend in domestic big cities ,two key parts of suita-bility and demand analysis in shared parking allocation method are discussed .The research shows that ,the shared parking allocation measure for a single mixed land use block is suited in the core area of the first class parking zone and area of other classes in the parking space allocation standard for architectures ,while the shared parking allocation measure for mixed land use blocks is adaptive for the core area of every class parking zones .The analysis models and steps are ad-vanced for the total parking space demand calculation of mixed land use development when shared parking allocation meas-ure is taken ,in which the calculation of analysis period and dynamic parking space demand ratio is clarified .The whole method advanced is applied in the mixed developing blocks in the planned developed area of Jiangning District in Nanjing . It is found out that the total parking space demand ratio can be reduced by 25 .7% .
A Prediction Model of Short-term Passenger Flow for Urban Transit Hubs
LIU Jie, HENG Yuming, ZHAO Hui, GAO Xuejin, WANG Pu
2014, (2): 41-44,49. doi: 10.3963/j.issn.1674-4861.2014.02.008
Abstract(373) PDF(2)
Abstract:
Accurate prediction of the passenger flow plays a very important role in preparing advanced organization schemes and contingency plans for urban transit hubs .Therefore ,a combinational prediction model based on BP neural network and Least Squares Support Vector Machine (LSSVM ) is proposed in this paper .First ,a BP neural network is a-dopted to present an initial prediction based on the historical passenger volume .Then ,the LSSVM model is used to refine the "initial prediction"to reach the final predicted passenger volumes at urban transit hubs .The experiment results of this paper show that the proposed model can improve the prediction accuracy of the passenger flows at urban transit hubs by 1% ,which shows that the model in this paper can overcome the uncertainty caused by a single model .
Simulation Analysis of Reasonable Corridor Scale in Passenger Transport Terminal
ZHANG Jingshan, LUO Qingyu, LI Qiang
2014, (2): 45-49. doi: 10.3963/j.issn.1674-4861.2014.02.009
Abstract(333) PDF(1)
Abstract:
This paper studied the reasonable corridor scale which connects service facilities in passenger transport terminal .Based on the influence of corridor length and width on pedestrian flow ,the simulation schemes were designed u-sing simulation software .By using pedestrian flow data output from the simulation software ,the trend curves of pedestri-an flow data were established .On the one hand ,the differences of those curves were analyzed ;on the other hand ,the K-W tests of the statistical data were given in order to analyze the differences of the pedestrian flow data .Based on analysis results of the curves comparison and K-W test ,the divergent role of corridor length and width on pedestrian flow were an-alyzed .On this basis ,the reasonable width of unidirectional corridor is 4 meters ;the reasonable width of bi-directional corridor is 8 meters ;and the reasonable corridor length is 50 meters .
Convenience Evaluation for Urban Public Transportation Based on Vague Matter-Element
REN Qiliang, XIAO Qiurui, YANG Yun, LUO Chao, ZHAI Feifei, HE Nanzhu
2014, (2): 50-56. doi: 10.3963/j.issn.1674-4861.2014.02.010
Abstract(225) PDF(1)
Abstract:
The convenience of urban public traffic is an important manifestation of the level of public transport serv-ices .In order to give a scientific evaluation on the convenience index of urban public traffic ,12 evaluation indexes are se-lected including transfer distance ,transfer coefficient ,bus stops service rate ,transit network density ,etc ,to build an ur-ban public traffic convenience evaluation index system based on four cardinal points including O-D points ,public transpor-tation capacity ,routes and auxiliary facilities ,which influence the convenience indexes of urban public traffic .This paper gives a Vague matter-element model on the public traffic convenience of Chongqing ,and reaches "level 2"as the evalua-tion consequence .The results show that the new evaluation index system is a more helpful way to give an evaluation on the convenience index of urban public traffic ,and the difference between the closeness degree of the actual data and the closeness degree of "level 2"is 0 .0117 ,which gives the optimal evaluation results .
Bus Travel Willingness under the Condition of Bus Information
ZUO Yigang, LI Wenquan, CHEN Qian, LI Jie, GUO Shiyong
2014, (2): 57-62,67. doi: 10.3963/j.issn.1674-4861.2014.02.011
Abstract(268) PDF(1)
Abstract:
In-depth analysis of influencing mechanism of bus information on the residents travel mode choice is the theoretical basis of rational planning of urban bus travel information environment ,which has important significance for ur-ban traffic management and congestion mitigation .Based on the theory of planned behavior ,at the basis of three basic variables of behavior attitude ,subjective norm ,perceived behavioral control in the theory of planned behavior ,variables of transit information ,personal attributes and travel experience are added to improve the theory of planned behavior .An improved theory of planned behavior is used to build a bus travel willingness model under the condition of bus Informa-tion .With the Nanjing residents as research object ,a structural equation model is used to verify the survey data in order to determine the interaction between various factors and their impact on the willingness of bus travel .The results show that the bus information has significant and positive impact on bus travel variables of attitude ,subjective norm and per-ceived behavioral control with the influencing coefficients of 0 .533 ,0 .451 and 0 .576 respectively ,and that the bus infor-mation has indirect influence on bus travel willingness and the total effect is 0 .92 ,which shows that high quality of the in-formation can improve the appeal of bus and enhance bus travel willingness of residents .
Separate BRT Corridor Stop Spacing Optimization Model Based on the Travel Time of Walking-to-Stop Passengers
CHEN Bing, JIN Wenzhou, LUO Yunhui
2014, (2): 63-67. doi: 10.3963/j.issn.1674-4861.2014.02.012
Abstract(191) PDF(1)
Abstract:
The spacing between bus rapid transit (BRT ) stops influences the average travel time that the passengers spent for getting to BRT Stops .This effect is greater for the passengers who walk to the BRT Stops .First ,this paper analyzed the area affected by the BRT corridor ,and studied the average walking-to-stop time affected significantly by the stop spacing .The functional relationship between the average walking-to-stop time and the stop spacing based on the studies was obtained .Based on the functional relationship ,the balance between the walking-to-stop time reduction and bus travel time increase caused by the increase of the number of BRT stops was taken as an objective function ,and a BRT stop spacing optimization model was developed .Meanwhile ,the paper proposed a parameter calibration method .The model reflects more realistic condition ,which can provide a certain reference for the establishment of BRT stops .
An Evaluation System of the Parking Operation Index
ZHENG Shujian, ZHENG Xishuang, WEI Qingbo, ZHAO Yuhua
2014, (2): 68-71. doi: 10.3963/j.issn.1674-4861.2014.02.013
Abstract(330) PDF(10)
Abstract:
With the increasingly difficult urban parking problem ,city traffic managers need a systematic evaluation system for a comprehensive analysis of the operation of parking facilities in support of parking management decision mak-ing .Based on the properties of the data uploaded from parking facilities ,a parking operation evaluation index is estab-lished by considering parking efficiency ,traffic impact ,operating income and other indicators .In this system ,the utiliza-tion ,turnover rate and parking time are used to reflect parking efficiency whereas the flow rates at the entrance and the exit are used to measure the effect .In addition ,the parking price and average income show the financial conditions while the flexible and monthly parking proportions reflect parking demand distribution .The paper describes how to calculate all the indices .Finally ,based on the actual parking data from an example ,all the calculation results and various indicators are illustrated and verified .
Urban Expressway Exit Numbering Setting Method and Effect Evaluation:a Case Study of Wuxi City
ZU Yongchang, WANG Jianqiang, LU Jian
2014, (2): 72-76. doi: 10.3963/j.issn.1674-4861.2014.02.014
Abstract(226) PDF(0)
Abstract:
To ensure the driver to quickly determine export position ,urban expressway exit numbering is gradually used in many cities .However ,many problems still exist including non-uniqueness and disunity in exit numbering and its style in that there is no standard rule at state level .This paper ,on the basis of investigation and research ,proposes an exit numbering setting method that can reflect the features of road ,the flow characteristics to ensure the uniqueness of the exit numbers by illustrating the example of Wuxi Inner-ring West Expressway .Finally ,through contrast test ,the change of driver recognition time between before and after setting exit numbering is compared .It is found out that the legibility of 50% of the examinees is promoted in some degree ,which proves the feasibility and effectiveness of the method .
Optimization Strategy of City Logistics Distribution System Based on Time Reliability
ZHANG Hongda, JI Xiaofeng, JI Xuan, ZHOU Fei
2014, (2): 77-81. doi: 10.3963/j.issn.1674-4861.2014.02.015
Abstract(240) PDF(3)
Abstract:
Distribution time reliability has become a significant factor affecting urban logistics distribution system ef-ficiency .To scientifically evaluate the distribution time reliability ,based on summarizing and defining the connotation of city logistics distribution time reliability ,the impact factors of distribution time reliability have been revealed by road traf-fic situation ,distribution time windows ,distribution routing and spatial difference of distribution demand .Then ,the e-valuation model of distribution time reliability has been established based on logistics distribution section ,routing and net-work .On this basis ,an optimization model has been established ,whose aim is to maximize the logistics distribution time reliability .Finally ,the optimization strategies have been proposed from arranging distribution time ,choosing distribution route ,optimizing time window and improving logistics information .
Performance Evaluation of BRT System with Analytic Network Process
WANG Xiaohong, WENG Xiaoxiong, HAN Huilong, XIE Kai
2014, (2): 82-85,94. doi: 10.3963/j.issn.1674-4861.2014.02.016
Abstract(287) PDF(1)
Abstract:
For the need of performance evaluation of the government public transport financial investment projects , a performance evaluation index system of BRT System is proposed by using the principle of Network Analysis Process with the fares preferential policies .First ,the paper analyzes the performance of influencing factors and the urban public transport fares preferential policies .Second ,a comprehensive evaluation model is build through the analysis report . Third ,the super decisions software is adopted to calculate the model .Finally ,the model is applied to evaluating the per-formance of urban traffic fares policy of Guangzhou ,which was carried out in 2011 .The results indicate that the calcula-tion results are consistent with those of citizens'satisfaction analysis ,which shows that analytic network process (ANP) is feasible .
Big Data Technology-based Online Urban Transportation System Laboratory Environment Design
XIN Kejun, LIANG Biao, GUO Jianhua
2014, (2): 86-89. doi: 10.3963/j.issn.1674-4861.2014.02.017
Abstract(268) PDF(1)
Abstract:
The development and validation of urban intelligent transportation system (ITS) solution is one of the factors holding back the real world application of such urban ITS solutions .Targeting the need for validating the urban ITS solutions ,a big data technology based online urban transportation system laboratory environment is proposed in this paper through applying the techniques of big data theory and method ,with its main requirements and characteristics de-scribed and its functional architecture and physical architecture presented .In addition ,based on the current mainstream open source architecture of Hadoop ,software implementation architecture of the proposed environment is presented by u-sing the HDFS data storage method and the MapReduce parallel data processing mechanism .Through this environment , users can create user-specific virtual urban ITS analysis lab ,realizing the rapid development and validation of urban ITS solutions and hence promoting the development and construction of real world urban intelligent transportation systems .
Highway Surface Crack Image Identifying Algorithm
MA Ronggui, XU Kun, LIU Feifei
2014, (2): 90-94. doi: 10.3963/j.issn.1674-4861.2014.02.018
Abstract(268) PDF(3)
Abstract:
An algorithm to automatically detect and classify pavement cracks is presented in this paper .First ,the multi-window median filter is used ,which can not only remove the noises but also reserve crack information .Second ,the background subset interpolation method is applied to dealing with non-uniform illumination in the post-segmentation step . After that ,the otsu threshold segmentation method ,morphologic method ,and connected components marking method are used sequentially to segment the crack image .Furthermore ,the number of connected components ,projection feature , and distribution density are selected to classify the cracks .Finally ,the main parameters for crack ,such as length ,width , and area ,etc .,are calculated .The results show that the classification can be as accurate as 94% ,with the crack's length error of 7 .2% ,width error of 11 .3% ,and area error of 9 .6% ,which demonstrates that the mehod is effective and relia-ble .
Short-term Traffic Prediction Theory-based Method for Discriminating Highway Abnormal Traffic Status
TANG Xi ru, CHEN Yanyan, ZHAO Yuan
2014, (2): 95-99. doi: 10.3963/j.issn.1674-4861.2014.02.019
Abstract(265) PDF(1)
Abstract:
Because of the deficiency of monitoring facilities ,the efficiency of identifying traffic abnormal status of ordinary road is lower ,and the error is higher than that of highway using traditional auto-recognized method .This paper provides a new discriminated method to accelerate the processing time of traffic accidents ,which is based on the short-term traffic prediction theory and the general definition of abnormal traffic status .This method excludes self-healing situ-ations ,like recurrent congestion and Phantom traffic jams .Experiments indicate that the deviation of this method would be controlled within 0 .2 ,which means that it could identify abnormal traffic status efficiently and accurately .
Design and Test of a Bluetooth-based Road Travel Time Detector
LIU Xingliang, LI Menghui, XIONG Ziyu
2014, (2): 100-103. doi: 10.3963/j.issn.1674-4861.2014.02.020
Abstract(208) PDF(1)
Abstract:
A Bluetooth-based travel time detector is designed by using serial communication and embedded technolo-gy .The device can automatically collect the Bluetooth MAC addresses and corresponding time stamps and then save the data on a local storage device .Laboratory studies are used to study the relationship between average undetected rate and vehicle speed as well as the locations of first-time monitoring sites .The detection accuracy of the device is also tested through field trips against the following factors :average speed ,detection rate and number of the paired devices .The T-test ,Mann Whitney U-test and W-W test carried out all indicate that the device is reliable for travel time detection .In ad-dition ,the shortcomings of the device and the recommended improvements are also summarized at the end of the paper , which provides basis for further research on Bluetooth detector .
Simulation of hydroplaning phenomenon Based on the FLUENT software
WU Qi, YANG Jun
2014, (2): 104-109. doi: 10.3963/j.issn.1674-4861.2014.02.021
Abstract(299) PDF(6)
Abstract:
In this paper ,FLUENT software is utilized to simulate the hydroplaning process of three kinds of differ-ent vehicle tires ,i .e .tires with the longitudinal texture ,horizontal texture and multi texture ;the relative parameters such as the dynamic water pressure ,the vehicle speed and the water film thickness are calculated .The results of simula-tion show that :(a) Among the three different kinds of tires ,one with the multi texture has the best hydroplaning resist-ant property while one with longitudinal texture has the worst anti-hydroplaning performance ;(b) The dynamic water pressure increases with the increasing vehicle speed when the water thickness remains stable ,and the increasing rate of dynamic water pressure increases with the driving speed as well ;(c) The dynamic water pressure increases with the thickness of water on condition that the vehicle speed remains stable .Based on the principle that the hydroplaning phe-nomenon occurs while the dynamic water pressure is equal to the internal pressure of vehicle tires ,the relationship be-tween the critical hydroplaning speed and the thickness of water film is established in this paper .Then ,based on the ex-isting equation of water film thickness ,the relationship between the critical hydroplaning speed and the precipitation is al-so calculated .
2014, (2): 109-109.
Abstract(176) PDF(0)
Abstract:
Causation Analysis of Human Error Related Marine Accidents Using Apriori Algorithm
LI Lingling, QIU Lei
2014, (2): 110-114. doi: 10.3963/j.issn.1674-4861.2014.02.022
Abstract(261) PDF(1)
Abstract:
A high number of maritime accidents are caused due to human errors ,which are further influenced by personal factors ,environmental factors ,ship factors and management factors .A general statistical approach can only link maritime accidents to simple human behavior problem ;however ,it cannot further establish the relationship between the human error and other real influencing factors .It is very challenging for researchers to set up the relationship between the human fault and other influencing factors that cause the human error due to the insufficient data ,improper research meth-od ,and limited research which is only confined to the relationship between human error and a single factor .In this paper a model is established by using data mining association rules to analyze the relationship between the human fault and its environment influencing factors .This paper collects 100 domestic and international maritime accident investigation re-ports ,and uses data mining association rules to explore the relationships between human factor and environmental factor . Practices prove that human factor and environmental factor are the major factors causing maritime accidents .
An AIS-based Safety Control System for the Construction of Deepwater Channel
XU Haichao, WANG Xingchao, LIN Chuixing, DONG Chaoming
2014, (2): 115-119,126. doi: 10.3963/j.issn.1674-4861.2014.02.023
Abstract(238) PDF(1)
Abstract:
The safety of the constructions above water has become a hot research topic .According to the character-istics and requirements of the constructions above water ,a safety control system for the construction of a deepwater chan-nel in Tongzhousha is developed based on Automatic Identification System (AIS) .This paper presents AIS ,the structure of the system and the function of each component .In addition ,several key technologies involved ,including the communi-cation technologies of AIS receiver ,server and the design of weather and tide tables ,are also studied .The system can greatly improve the safety of the constructions above water .
Transport Capacity Bottlenecks Identification of Urban Rail Transit
KOU Chunge, HE Shiwei, HE Bisheng
2014, (2): 120-126. doi: 10.3963/j.issn.1674-4861.2014.02.024
Abstract(252) PDF(1)
Abstract:
The huge passenger flow makes transport capacity bottleneck problems becoming increasingly prominent , and has a bad impact on the system operating efficiency .In order to better analyze the problem ,this paper puts forward a recognition model on station static bottleneck ,and studies on station dynamic bottleneck by making use of capability utili-zation formulas as well as AnyLogic simulation software .Then this paper establishes a kind of line bottleneck analysis method based on passenger flow .Furthermore ,this paper also analyzes the dynamic transmission rules of bottlenecks . Finally ,the case study results show that the station bottleneck of FUXINGM EN Station emerges in the transfer stairs , while the Line 2 interval capacity utilization is balanced ,and its line bottleneck is generated between JIANGUOMEN Sta-tion and CHAOYANGMEN Station .Considering the characteristics of station and line ,this method puts forward corre-sponding bottleneck identification thoughts ,and it proves to be of practical value .
Grey Model-based Railway Bridge Crack Deterioration Prediction
QIN Xianguo, MA Hongkui
2014, (2): 127-129,134. doi: 10.3963/j.issn.1674-4861.2014.02.025
Abstract(246) PDF(1)
Abstract:
The concrete cracks on railway bridges are common problems ,which have serious impact on the service life of the railway bridge .A non-equal interval GM (1 ,1) prediction model based on grey system theory is proposed to pre-dict the crack width of the railway concrete bridge .According to the predicted deterioration of bridge conditions ,the ma-intenance plan of BICS can be developed to improve the bridge conditions and train safety .The prediction model was vali-dated by using the crack data of Beiniuchuan Super-large Bridge of Shenshuo Railway from 1996 to 2012 .The results show that the prediction model can accurately predict the crack width of the bridge .The paper also analyzes the effect of BICS injection method applied in Beiniuchuan Super-large Bridge of Shenshuo Railway .Its repair effect on the concrete crack is significant .
Train Operation Adjustment Based on Immune Genetic Algorithm
LI Rongna, ZHANG Xi
2014, (2): 130-134. doi: 10.3963/j.issn.1674-4861.2014.02.026
Abstract(274) PDF(1)
Abstract:
The adjustments to train operation is the key research topic for benefiting the railway dispatching profes-sionals ,and the automatic adjustments has become the "core measure"of the level of automation of the railway dispatc-hing .In this paper ,a train operation adjustment model is developed with the target of minimizing the deviation from train travelling diagram ,and 6 constraint conditions are taken into account ,including train running in a section ,tracing time of trains in a section ,station stop time ,train departure time ,track number ,and overtaking time .An immune genetic algo-rithm is used in this paper to solve the above model ,which is known to be free from the defects of traditional genetic algo-rithms including slow convergent speed and premature convergence .Efforts are also made to improve the algorithm by re-designing its encoding scheme ,fitness function ,antibody concentration and mutation operator .Simulation results show that ,when compared with the traditional GA ,the proposed algorithm shows more superior characteristics in convergence speed ,optimal values ,and success rates and therefore it can be used to provide better adjustment schemes for train dis-patching personnel .

Copyright Editorial Office of Transport Information and Safety鄂ICP备05003336号-2

Address：No. 1178，Heping Avenue, Wuchang, Wuhan, CHINA (430063)

Tel：027-86580355 Email：jtjsj@vip.163.com

Supported by: Beijing Renhe Information Technology Co. Ltd