CN107776613A - The flow-optimized control system of subway transportation - Google Patents

The flow-optimized control system of subway transportation Download PDF

Info

Publication number
CN107776613A
CN107776613A CN201710900137.6A CN201710900137A CN107776613A CN 107776613 A CN107776613 A CN 107776613A CN 201710900137 A CN201710900137 A CN 201710900137A CN 107776613 A CN107776613 A CN 107776613A
Authority
CN
China
Prior art keywords
train
mrow
track
msubsup
msub
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710900137.6A
Other languages
Chinese (zh)
Inventor
韩云祥
黄晓琼
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University of Technology
Original Assignee
Jiangsu University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu University of Technology filed Critical Jiangsu University of Technology
Priority to CN201710900137.6A priority Critical patent/CN107776613A/en
Publication of CN107776613A publication Critical patent/CN107776613A/en
Pending legal-status Critical Current

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
    • B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/30—Circuit design
    • G06F30/36—Circuit design at the analogue level
    • G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods

Abstract

The present invention relates to a kind of flow-optimized control system of subway transportation, the system generates the topology diagram of Rail traffic network first according to the plan operational factor of each train；Topology diagram is based on again, analyzes the controllability and sensitiveness of train flow；Further according to the plan operational factor of each train, more train Lothrus apterus running orbits are generated；Again in each sampling instant, based on the current running status of train and historical position observation sequence, the advanced positions at certain following moment of train are predicted, then establish from the continuous dynamic of train to the observer of discrete conflict logic, by the conflict situation that continuous dynamic mapping is the expression of discrete observation value；When system is possible to violate traffic control rule, to the Hybrid dynamics behavior implementing monitoring of subway transportation hybrid system, warning information is provided for control centre；Finally when warning information occurs, robust dual layer resist is carried out to train operation track using Adaptive Control Theory method, and program results is transferred to each train.

Description

The flow-optimized control system of subway transportation
The application is Application No.：201510150772.8 invention and created name is《The flow-optimized controlling party of subway transportation Method》, the applying date is：The divisional application of the application for a patent for invention on March 31st, 2015.
Technical field
The present invention relates to a kind of flow-optimized control method of subway transportation, more particularly to a kind of double-deck ground based on Robust Strategies Iron traffic flow Optimal Control System and its control method.
Background technology
With expanding day by day for China big and medium-sized cities scale, Traffic Systems are faced with the increasing pressure, energetically Feasibility of developing track transportation system turns into the important means for solving urban traffic congestion.National Eleventh Five-Year Plan guiding principle is it is to be noted, that there is bar The big city and group of cities area of part are using track traffic as Priority setting.China's just one unprecedented rail of experience Road transport development peak period, some cities have been turned to the construction of net by the construction of line, urban mass transit network progressively shape Into.In the complex region that Rail traffic network and train flow are intensive, still combined using train operation plan and be based on subjective experience Train interval dispensing mode gradually show its lag, be in particular in：(1) formulation of train operation plan timetable is simultaneously The influence of various enchancement factors is not considered, easily causes the safety that the management of traffic flow tactics is crowded, and reduction traffic system is run Property；(2) train scheduling work lays particular emphasis on the personal distance kept between single train, not yet rises to and carries out strategic pipe to train flow The macroscopic aspect of reason；(3) subjective experience of the train allocation process more dependent on a line dispatcher, the selection for allocating opportunity are random Property it is larger, lack scientific theory support；(4) the less shadow in view of external interference factor of allotment means that dispatcher is used Ring, the robustness and availability of train programs are poor.
The discussion object of existing documents and materials be directed to long-distance railway transportation more, and is directed to big flow, high density and closely-spaced The Scientific Regulation scheme of city underground traffic system under service condition still lacks system design.Under complicated road network service condition Train Coordinated Control Scheme needed on strategic level in region in transportation network the running status of single vehicles carry out calculate and Optimization, and collaborative planning is implemented in the traffic flow to being made up of multiple trains；Pass through effective monitoring mechanism on pre- tactical level The subregional critical operational parameters in transportation network top are adjusted to solve congestion problems, and ensure the fortune of all trains in the region Line efficiency；The running status of related train is then adjusted according to critical operational parameters on tactical level, obtains single-row wheel paths Prioritization scheme, the headway management of train is changed into from fixed manual type and considers train performance, scheduling rule and extraneous ring Variable " microcosmic-macroscopic view-middle sight-microcosmic " Separation control mode including the factors such as border.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of robustness and the flow-optimized control of the preferable subway transportation of availability System processed, the system can strengthen the subject of programs formulation and can effectively prevent subway train operation conflict.
Realize that the technical scheme of the object of the invention is to provide a kind of flow-optimized control system of subway transportation, including line topological Structural generation module, data transmission module, car-mounted terminal module, control terminal module and track monitoring module, track monitoring The status information of module collection train is simultaneously supplied to control terminal module；
The control terminal module includes following submodule：
Lothrus apterus Track Pick-up module before train operation：According to Train operation plan time of running table, train dynamicses are initially set up Model is learned, then train running conflict is established according to train running conflict Coupling point and allocates model in advance, ultimately produces Lothrus apterus row Car running orbit；
Train operation middle or short term Track Pick-up module：The train real time status information provided according to track monitoring module, profit With data mining model, thus it is speculated that the running orbit of train in future time period；
Train operation situation monitoring module：In each sampling instant t, the track estimation result based on train, when between train When being possible to be in the presence of violating safety regulation, warning information is provided to its dynamic behaviour implementing monitoring and for control terminal；
Train collision avoidance track optimizing module：When train operation situation monitoring module sends warning information, meeting train On the premise of physical property, region hold stream constraint and track traffic scheduling rule, by setting optimizing index function, use is adaptive Answer control theory method to carry out robust dual layer resist to train operation track by control terminal module, and pass through data transmission module Program results is transferred into car-mounted terminal module to perform；Train collision avoidance track optimizing module includes internal layer planning and outer layer planning two Class planning process.
Using the flow-optimized control method of subway transportation of the flow-optimized control system of above-mentioned subway transportation, comprise the following steps：
Step A, according to the plan operational factor of each train, the topology diagram of Rail traffic network is generated；
Step B, the topology diagram based on the Rail traffic network constructed by step A, analyze train flow controllability and The class feature of sensitiveness two；
Step C, according to the plan operational factor of each train, on the basis of Modeling Method for Train Dynamics is built, according to row Car operation conflict Coupling point establishes train running conflict and allocates model in advance, generates more train Lothrus apterus running orbits；
Step D, in each sampling instant t, based on the current running status of train and historical position observation sequence, to train The advanced positions at certain following moment are predicted；Its detailed process is as follows：
Step D1, train track data pre-process, using train initiating station stop position as the origin of coordinates, adopted each The sample moment, according to the acquired original discrete two-dimensional position sequence x=[x of train1,x2,...,xn] and y=[y1,y2,..., yn], processing is carried out to it using first-order difference method and obtains new train discrete location sequence △ x=[△ x1,△x2,...,△ xn-1] and △ y=[△ y1,△y2,...,△yn-1], wherein △ xi=xi+1-xi,△yi=yi+1-yi(i=1,2 ..., n-1)；
Step D2, train track data is clustered, to train discrete two-dimensional position sequence △ x and △ y new after processing, led to Setting cluster number M' is crossed, it is clustered respectively using genetic algorithm for clustering；
Step D3, parameter training is carried out using HMM to the train track data after cluster, by that will locate Train operation track data △ x and △ y after reason is considered as the aobvious observation of hidden Markov models, by setting hidden state number N' and parameter renewal period τ ', is rolled according to T' nearest position detection value and using B-W algorithms and obtains newest hidden Ma Erke Husband's model parameter λ '；Specifically：By the train track sets data length obtained is dynamic change, in order in real time with The state change of track train track, it is necessary to initial track HMM parameter lambda '=(π, A, B) on the basis of it is right It is readjusted, more accurately to speculate train in the position at certain following moment；Every period τ ', the T' according to newest acquisition Individual observation (o1,o2,...,oT') to track HMM parameter lambda '=(π, A, B) reevaluated；
Step D4, according to HMM parameter, obtained using Viterbi algorithm corresponding to current time observation Hidden state q；
Step D5, every the periodAccording to the HMM parameter lambda of newest acquisition '=(π, A, B) and nearest H Individual history observation (o1,o2,...,oH), the hidden state q based on train current time, in moment t, time domain is predicted by setting H', obtain the position prediction value O of future time period train；
Step E, establish from the continuous dynamic of train to the observer of discrete conflict logic, by the continuous of subway transportation system Dynamic mapping is the conflict situation of discrete observation value expression；When system is possible to violate traffic control rule, to subway transportation The Hybrid dynamics behavior implementing monitoring of hybrid system, timely warning information is provided for control centre；
Step F, when warning information occurs, meeting that train physical property, region hold stream constraint and track traffic is dispatched On the premise of rule, by setting optimizing index function, Shandong is carried out to train operation track using Adaptive Control Theory method Rod dual layer resist, and program results is transferred to each train, each train receives and performs train collision avoidance instruction until each train is equal Reach it and free terminal.
Further, step A detailed process is as follows：
Step A1, the website letter stopped in each train travelling process is extracted from the database of subway transportation control centre Breath；
Step A2, the site information stopped according to positive and negative two traffic directions to each train is classified, and will be same Same site on one traffic direction merges；
Step A3, according to website amalgamation result, multiple websites before and after being connected according to the space layout form of website with straight line.
Further, step B detailed process is as follows：
Step Bl, the Traffic flux detection model in single subsegment is built；Its detailed process is as follows：
Step Bl.1, state variable Ψ, input variable u are introduced and output variable Ω, wherein Ψ represent phase link between website Train quantity existing for certain moment in section, it includes single channel section and Multiple Sections two types, and u represents that track traffic dispatcher is directed to The Operation Measures that certain section is implemented, such as adjust train speed or change train in the station time, Ω represents certain section period On the train quantity left；
Step B1.2, by establishing time discretization shaped like Ψ (t+ △ t)=A1Ψ(t)+B1U (t) and Ω (t)=C1 Ψ(t)+D1Discrete time Traffic flux detection model in u (t) single subsegment, wherein △ t represent sampling interval, Ψ (t) tables Show the state vector of t, A1、B1、C1And D1The state-transition matrix, input matrix, output measurement square of t are represented respectively Battle array and direct transmission matrix；
Step B2, the Traffic flux detection model in more subsegments is built；Its detailed process is as follows：
Step B2.1, according to circuit space layout form and train flow historical statistical data, each son of cross link is obtained Flow proportional parameter beta in section；
Step B2.2, according to the discrete time Traffic flux detection model in flow proportional parameter and single subsegment, shape is built Such as Ψ (t+ △ t)=A1Ψ(t)+B1U (t) and Ω (t)=C1Ψ(t)+D1Discrete time traffic flow control in u (t) more subsegments Simulation；
Step B3, according to the controllable factor matrix [B of Controlling model1,A1B1,...,A1 n-1B1] order and numerical value n relation, Its controllability of qualitative analysis, according to the sensitivity coefficient matrix [C of Controlling model1(zI-A1)-1B1+D1], its input of quantitative analysis is defeated Go out sensitiveness, wherein n represents the dimension of state vector, and I represents unit matrix, and z is represented to original discrete time Traffic flux detection The element factor that model is changed.
Further, step C detailed process is as follows：
Step C1, train status transfer modeling, the process that train is run along track traffic road network are shown as between website Switching at runtime process, the website in train operation plan are set, and establish single train switched and transferred between different websites Petri net model：E=(g, G, Pre, Post, m) is train section metastasis model, and wherein g represents each sub- section between website, G tables Show the transfer point of train running speed state parameter, Pre and Post represent front and rear to connection between each sub- section and website respectively Relation,The operation section residing for train is represented, wherein m represents model identification, Z+Represent Positive Integer Set；
Step C2, the full operation profile hybrid system modeling of train, is considered as continuous process by operation of the train between website, from The stress situation of train is set out, and kinetics equation of the train in the different operation phase is derived according to energy model, dry with reference to the external world Factor is disturbed, is established on train in a certain operation phase speed vGMapping function vG=λ (T1,T2, H, R, α), wherein T1、T2、 H, R and α represents tractive force of train, braking force of train, train resistance, train gravity and train status random fluctuation parameter respectively；
Step C3, speculated by the way of emulation is mixed and solve train track, it is continuous using state by by time subdivision The characteristic Recursive Solution any time train of change in distance of a certain operation phase away from initial rest position point,Wherein J0For voyage of the initial time train away from initial rest position point, △ τ are the number of time window Value, J (τ) is τ moment distance of the train away from initial rest position point, thereby it is assumed that to obtain single-row wheel paths；
Step C4, train models in station time probability distribution function, for specific run circuit, by transferring train each The dwell time data at station, obtain the dwell time probability distribution of different circuit difference website condition Trains；
Step C5, the Lothrus apterus robust track allotment of more train couplings, the time of conflict point is reached according to each train, is passed through in advance Time segments division, it is discontented nearby to conflict point according to scheduling rule on the premise of random factor is incorporated in each sampling instant t Implement robust secondary planning in the train track of sufficient personal distance requirement.
Further, in step D, cluster number M' value is 4, and hidden state number N' value is 3, parameter renewal period τ ' For 30 seconds, T' 10,For 30 seconds, H 10, prediction time domain h' was 300 seconds.
Further, step E specific implementation process is as follows：
Step E1, the conflict hypersurface collection of functions based on regulation rule is constructed：Establish hypersurface collection of functions is to reflect The contention situation of system, wherein, the continuous function h related to single train in the hypersurface that conflictsIFor I type hypersurface, arranged with two The related continuous function h of carIIFor Type-II hypersurface；
Step E2, the observer by train continuous state to discrete conflict situation is established, structure train is in traffic network The safety regulation collection d that need to meet during operationij(t)≥dmin, wherein dij(t) represent train i and train j between the reality of t Every dminRepresent the minimum safety interval between train；
Step E3, based on person machine system's theory and complication system hierarchical control principle, according to train operation pattern, structure People ensures that the operation of system is in safe reachable set in the real-time monitoring mechanism of train of loop, designs and is solved from conflicting to conflicting The discrete monitor for section of slipping out of the hand, when the discrete observation vector of observer shows that safety regulation rally is breached, phase is sent at once The warning information answered.
Further, step F detailed process is as follows：
Step F1, the analysis result based on step B and step E, it is determined that the traffic flow regulation measure specifically taken, including Adjust the speed of service of train and/or adjust train in the station class measure of time two, and using above regulation measure specifically Point and opportunity；
Step F2, the termination reference point locations P, collision avoidance policy control time domain Θ, trajectory predictions of train collision avoidance planning are set Time domain γ；
Step F3, conflict Resolution process model building is run, the operation conflict Resolution in the above-listed workshop of Rail traffic network is considered as Inside and outside dual planning problem based on both macro and micro aspect, whereinRepresent outer layer plan model, i.e. rail Train flow flow-Density and distribution problem on road traffic network,Represent internal layer plan model, i.e. track traffic The state adjustment problem of single vehicles on section；F、x1And u1It is object function, state vector and the decision-making of outer layer planning problem respectively Vector, G (x1,u1)≤0 be outer layer planning constraints, f, x2And u2It is object function, the state of internal layer planning problem respectively Vector sum decision vector, g (x2,u2)≤0 is the constraints of internal layer planning, using the outer layer program results of macroscopic aspect as micro- The reference input of sight aspect internal layer planning；
Step F4, the modeling of conflict Resolution variable bound is run, structure includes adjustable train quantity a, train speed ω and row Both macro and micro constraints of the car including the variables such as station time γ：Wherein t need to implement the section k of conflict Resolution change Amount constraint can be described as：ak(t)≤aM、ωk(t)≤ωM、γk(t)≤γM, aM、ωM、γMRespectively maximum adjustable train number In the station time, such variable of freeing can be by traffic flow distribution, train thing for amount, maximum train running speed and most long train Rationality can be with the constraint of personal distance etc.；
Step F5, the optimal road network flow allocation plan of Multi-objective Robust solves：Based on cooperative collision avoidance trajectory planning thought, For different performance indications, by selecting different conflict Resolution object functions, base is solved in traffic flow operation macroscopic aspect In the multiple target traffic flow optimum flow allocation plan of Euler's network model and each control section in Rolling Planning interval it is only real Apply its first Optimal Control Strategy；
Step F6, the optimal section train operation state adjustment of Multi-objective Robust：According to each section or zone flow configuration knot Fruit, evolutionary model is mixed based on train operation and Lagrangian plan model obtains optimal single vehicles controlled quentity controlled variable, generation is optimal Single vehicles running orbit and each regulation and control train only implement its first Optimal Control Strategy in Rolling Planning interval；
Step F7, each train receives and performs train collision avoidance instruction；
Step F8, in next sampling instant, repeat step F5 to F7 is until each train reaches it and frees terminal.
Further, in step F2, next website that stops that reference point locations P is train is terminated, parameter Θ value is 300 seconds, γ value was 300 seconds.
Further, step F5 detailed process is as follows：Order
WhereinRepresent square of the distance between t train i present positions and next website, Pi(t)=(xit, yit) t train i two-dimensional coordinate value is represented,The next two-dimensional coordinate values for stopping website of train i are represented, So t train i priority index may be set to：
Wherein ntRepresent the train number of conflict on t section be present, from the implication of priority index, train away from Nearer from next website, its priority is higher；
Set optimizing index
Wherein i ∈ I (t) represent train code and I (t)=1,2 ..., nt, Pi(t+s △ t) represents train in moment (t + s △ t) position vector, Π represent control time, i.e., from current time Future Trajectory plan time span, uiExpression is treated The train i of optimization optimal control sequence, QitFor positive definite diagonal matrix, its diagonal element is that train i refers in the priority of t Number λit, and
The present invention has positive effect：(1) the flow-optimized control method of subway transportation of the invention is meeting track traffic On the premise of control personal distance, based on the real-time position information of train, maintenance data excavates means dynamic and speculates train Track；According to track traffic regulation rule, alarm is implemented to the conflict being likely to occur, according to train performance data and related constraint Condition gives each train planning conflict Resolution track；When being configured to train schedule, it is contemplated that influence train The probability distribution of all kinds of random factors and the robustness of train schedule, strengthen the availability of configuration result.
(2) controllability and sensitivity analysis result of the invention based on Rail traffic network topological structure, can be that subway is handed over Through-flow allotment time, allotment place and the selection offer scientific basis for allocating means, the randomness for avoiding regulation and control scheme from choosing.
(3) the scene monitoring mechanism of the invention based on constructed " people is in loop ", can be to train inside continuous variable Frequent interaction with external discrete event makes effecting reaction in time, the shortcomings that overcoming conventional open loop monitored off-line scheme.
(4) the dual layer resist scheme of train flow of the invention can not only reduce the solution dimension of Optimal Control Problem, also The practicality of regulation and control scheme can be strengthened, overcome the model in existing document and algorithm only focus on train AT STATION to hair when Between, and lack to train on specific railroad section run when control and prediction the defects of.
(5) present invention can be incorporated train in time and be transported in real time based on constructed train operation track rolling forecast scheme All kinds of disturbing factors in row, the accuracy of train trajectory predictions is improved, overcomes Conventional Off-line prediction scheme accuracy not high Shortcoming.
Brief description of the drawings
Fig. 1 is train flow analysis on Operating figure；
Fig. 2 is that Lothrus apterus 3D robusts track speculates figure；
Fig. 3 is that train operation state mixes monitoring figure；
Fig. 4 frees figure for train running conflict is optimal；
Fig. 5 is the schematic diagram of traffic flow bilayer allocation plan.
Embodiment
(embodiment 1)
A kind of flow-optimized control system of subway transportation, including it is wire topologies generation module, data transmission module, vehicle-mounted Terminal module, control terminal module and track monitoring module, track monitoring module are collected the status information of train and are supplied to Control terminal module.
The control terminal module includes following submodule：
Lothrus apterus Track Pick-up module before train operation：According to Train operation plan time of running table, train dynamicses are initially set up Model is learned, then train running conflict is established according to train running conflict Coupling point and allocates model in advance, ultimately produces Lothrus apterus row Car running orbit.
Train operation middle or short term Track Pick-up module：The train real time status information provided according to track monitoring module, profit With data mining model, thus it is speculated that the running orbit of train in future time period.
Train operation situation monitoring module：In each sampling instant t, the track estimation result based on train, when between train When being possible to be in the presence of violating safety regulation, warning information is provided to its dynamic behaviour implementing monitoring and for control terminal.
Train collision avoidance track optimizing module：When train operation situation monitoring module sends warning information, meeting train On the premise of physical property, region hold stream constraint and track traffic scheduling rule, by setting optimizing index function, use is adaptive Answer control theory method to carry out robust dual layer resist to train operation track by control terminal module, and pass through data transmission module Program results is transferred into car-mounted terminal module to perform.Train collision avoidance track optimizing module includes internal layer planning and outer layer planning two Class planning process.
Using the flow-optimized control method of subway transportation of the flow-optimized control system of above-mentioned subway transportation, comprise the following steps：
Step A, according to the plan operational factor of each train, the topology diagram of Rail traffic network is generated；Its is specific Process is as follows：
Step A1, the website letter stopped in each train travelling process is extracted from the database of subway transportation control centre Breath；
Step A2, the site information stopped according to positive and negative two traffic directions to each train is classified, and will be same Same site on one traffic direction merges；
Step A3, according to website amalgamation result, multiple websites before and after being connected according to the space layout form of website with straight line.
Step B, the topology diagram based on the Rail traffic network constructed by step A, analyze train flow controllability and The class feature of sensitiveness two；Its detailed process is as follows：
Step Bl, see Fig. 1, build the Traffic flux detection model in single subsegment；Its detailed process is as follows：
Step Bl.1, state variable Ψ, input variable u are introduced and output variable Ω, wherein Ψ represent phase link between website Train quantity existing for certain moment in section, it includes single channel section and Multiple Sections two types, and u represents that track traffic dispatcher is directed to The Operation Measures that certain section is implemented, such as adjust train speed or change train in the station time, Ω represents certain section period On the train quantity left；
Step B1.2, by establishing time discretization shaped like Ψ (t+ △ t)=A1Ψ(t)+B1U (t) and Ω (t)=C1 Ψ(t)+D1Discrete time Traffic flux detection model in u (t) single subsegment, wherein △ t represent sampling interval, Ψ (t) tables Show the state vector of t, A1、B1、C1And D1The state-transition matrix, input matrix, output measurement square of t are represented respectively Battle array and direct transmission matrix；
Step B2, the Traffic flux detection model in more subsegments is built；Its detailed process is as follows：
Step B2.1, according to circuit space layout form and train flow historical statistical data, each son of cross link is obtained Flow proportional parameter beta in section；
Step B2.2, according to the discrete time Traffic flux detection model in flow proportional parameter and single subsegment, shape is built Such as Ψ (t+ △ t)=A1Ψ(t)+B1U (t) and Ω (t)=C1Ψ(t)+D1Discrete time traffic flow control in u (t) more subsegments Simulation；
Step B3, according to the controllable factor matrix [B of Controlling model1,A1B1,...,A1 n-1B1] order and numerical value n relation, Its controllability of qualitative analysis, according to the sensitivity coefficient matrix [C of Controlling model1(zI-A1)-1B1+D1], its input of quantitative analysis is defeated Go out sensitiveness, wherein n represents the dimension of state vector, and I represents unit matrix, and z is represented to original discrete time Traffic flux detection The element factor that model is changed；
Step C, Fig. 2 is seen, according to the plan operational factor of each train, on the basis of Modeling Method for Train Dynamics is built, Train running conflict is established according to train running conflict Coupling point and allocates model in advance, generates more train Lothrus apterus running orbits；Its Detailed process is as follows：
Step C1, train status transfer modeling, the process that train is run along track traffic road network are shown as between website Switching at runtime process, the website in train operation plan are set, and establish single train switched and transferred between different websites Petri net model：E=(g, G, Pre, Post, m) is train section metastasis model, and wherein g represents each sub- section between website, G tables Show the transfer point of train running speed state parameter, Pre and Post represent front and rear to connection between each sub- section and website respectively Relation,The operation section residing for train is represented, wherein m represents model identification, Z+Represent Positive Integer Set；
Step C2, the full operation profile hybrid system modeling of train, is considered as continuous process by operation of the train between website, from The stress situation of train is set out, and kinetics equation of the train in the different operation phase is derived according to energy model, dry with reference to the external world Factor is disturbed, is established on train in a certain operation phase speed vGMapping function vG=λ (T1,T2, H, R, α), wherein T1、T2、 H, R and α represents tractive force of train, braking force of train, train resistance, train gravity and train status random fluctuation parameter respectively；
Step C3, speculated by the way of emulation is mixed and solve train track, it is continuous using state by by time subdivision The characteristic Recursive Solution any time train of change in distance of a certain operation phase away from initial rest position point,Wherein J0For voyage of the initial time train away from initial rest position point, △ τ are the number of time window Value, J (τ) is τ moment distance of the train away from initial rest position point, thereby it is assumed that to obtain single-row wheel paths；
Step C4, train models in station time probability distribution function, for specific run circuit, by transferring train each The dwell time data at station, obtain the dwell time probability distribution of different circuit difference website condition Trains；
Step C5, the Lothrus apterus robust track allotment of more train couplings, the time of conflict point is reached according to each train, is passed through in advance Time segments division, it is discontented nearby to conflict point according to scheduling rule on the premise of random factor is incorporated in each sampling instant t Implement robust secondary planning in the train track of sufficient personal distance requirement.
Step D, in each sampling instant t, based on the current running status of train and historical position observation sequence, to train The advanced positions at certain following moment are predicted；Its detailed process is as follows：
Step D1, train track data pre-process, using train initiating station stop position as the origin of coordinates, adopted each The sample moment, according to the acquired original discrete two-dimensional position sequence x=[x of train1,x2,...,xn] and y=[y1,y2,..., yn], processing is carried out to it using first-order difference method and obtains new train discrete location sequence △ x=[△ x1,△x2,...,△ xn-1] and △ y=[△ y1,△y2,...,△yn-1], wherein △ xi=xi+1-xi,△yi=yi+1-yi(i=1,2 ..., n-1)；
Step D2, train track data is clustered, to train discrete two-dimensional position sequence △ x and △ y new after processing, led to Setting cluster number M' is crossed, it is clustered respectively using genetic algorithm for clustering；
Step D3, parameter training is carried out using HMM to the train track data after cluster, by that will locate Train operation track data △ x and △ y after reason is considered as the aobvious observation of hidden Markov models, by setting hidden state number N' and parameter renewal period τ ', is rolled according to T' nearest position detection value and using B-W algorithms and obtains newest hidden Ma Erke Husband's model parameter λ '；Specifically：By the train track sets data length obtained is dynamic change, in order in real time with The state change of track train track, it is necessary to initial track HMM parameter lambda '=(π, A, B) on the basis of it is right It is readjusted, more accurately to speculate train in the position at certain following moment；Every period τ ', the T' according to newest acquisition Individual observation (o1,o2,...,oT') to track HMM parameter lambda '=(π, A, B) reevaluated；
Step D4, according to HMM parameter, obtained using Viterbi algorithm corresponding to current time observation Hidden state q；
Step D5, every the periodAccording to the HMM parameter lambda of newest acquisition '=(π, A, B) and nearest H Individual history observation (o1,o2,...,oH), the hidden state q based on train current time, in moment t, time domain is predicted by setting H', obtain the position prediction value O of future time period train；
Above-mentioned cluster number M' value is 4, and hidden state number N' value is 3, and parameter renewal period τ ' is 30 seconds, and T' is 10,For 30 seconds, H 10, prediction time domain h' was 300 seconds.
Step E, see Fig. 3, establish from the continuous dynamic of train to the observer of discrete conflict logic, by subway transportation system Continuous dynamic mapping be discrete observation value expression conflict situation；When system is possible to violate traffic control rule, over the ground The Hybrid dynamics behavior implementing monitoring of iron traffic hybrid system, timely warning information is provided for control centre；
The specific implementation process of the step E is as follows：
Step E1, the conflict hypersurface collection of functions based on regulation rule is constructed：Establish hypersurface collection of functions is to reflect The contention situation of system, wherein, the continuous function h related to single train in the hypersurface that conflictsIFor I type hypersurface, arranged with two The related continuous function h of carIIFor Type-II hypersurface；
Step E2, the observer by train continuous state to discrete conflict situation is established, structure train is in traffic network The safety regulation collection d that need to meet during operationij(t)≥dmin, wherein dij(t) represent train i and train j between the reality of t Every dminRepresent the minimum safety interval between train；
Step E3, based on person machine system's theory and complication system hierarchical control principle, according to train operation pattern, structure People ensures that the operation of system is in safe reachable set in the real-time monitoring mechanism of train of loop, designs and is solved from conflicting to conflicting The discrete monitor for section of slipping out of the hand, when the discrete observation vector of observer shows that safety regulation rally is breached, phase is sent at once The warning information answered.
Step F, see Fig. 4, when warning information occurs, meeting that train physical property, region hold stream constraint and track is handed over On the premise of logical scheduling rule, by setting optimizing index function, using Adaptive Control Theory method to train operation track Robust dual layer resist is carried out, and program results is transferred to each train, each train receives and performs train collision avoidance instruction until each Train reaches it and frees terminal；Its detailed process is as follows：
Step F1, the analysis result based on step B3 and step E3, it is determined that the traffic flow regulation measure specifically taken, bag Include the speed of service of adjustment train and/or adjust train in the station class measure of time two, and using the specific of above regulation measure Place and opportunity；
Step F2, the termination reference point locations P, collision avoidance policy control time domain Θ, trajectory predictions of train collision avoidance planning are set Time domain γ；
Next website that stops that reference point locations P is train is terminated, parameter Θ value is 300 seconds, and γ value is 300 Second；
Step F3, conflict Resolution process model building is run, the operation conflict Resolution in the above-listed workshop of Rail traffic network is considered as Inside and outside dual planning problem based on both macro and micro aspect, is shown in Fig. 5, whereinRepresent outer layer planning mould Type, i.e., train flow flow-Density and distribution problem on track traffic road network,Internal layer plan model is represented, i.e., The state adjustment problem of single vehicles on track traffic section；F、x1And u1Be respectively the object function of outer layer planning problem, state to Amount and decision vector, G (x1,u1)≤0 be outer layer planning constraints, f, x2And u2It is the target of internal layer planning problem respectively Function, state vector and decision vector, g (x2,u2)≤0 is the constraints of internal layer planning, and the outer layer of macroscopic aspect is planned into knot The reference input that fruit is planned as microcosmic point internal layer；
Step F4, the modeling of conflict Resolution variable bound is run, structure includes adjustable train quantity a, train speed ω and row Both macro and micro constraints of the car including the variables such as station time γ：Wherein t need to implement the section k of conflict Resolution change Amount constraint can be described as：ak(t)≤aM、ωk(t)≤ωM、γk(t)≤γM, aM、ωM、γMRespectively maximum adjustable train number In the station time, such variable of freeing can be by traffic flow distribution, train thing for amount, maximum train running speed and most long train Rationality can be with the constraint of personal distance etc.；
Step F5, the optimal road network flow allocation plan of Multi-objective Robust solves：Based on cooperative collision avoidance trajectory planning thought, For different performance indications, by selecting different conflict Resolution object functions, base is solved in traffic flow operation macroscopic aspect In the multiple target traffic flow optimum flow allocation plan of Euler's network model and each control section in Rolling Planning interval it is only real Apply its first Optimal Control Strategy；Its detailed process is as follows：Order
WhereinRepresent square of the distance between t train i present positions and next website, Pi(t)=(xit, yit) t train i two-dimensional coordinate value is represented,The next two-dimensional coordinate values for stopping website of train i are represented, So t train i priority index may be set to：
Wherein ntRepresent the train number of conflict on t section be present, from the implication of priority index, train away from Nearer from next website, its priority is higher；
Set optimizing index
Wherein i ∈ I (t) represent train code and I (t)=1,2 ..., nt, Pi(t+s △ t) represents train in moment (t + s △ t) position vector, Π represent control time, i.e., from current time Future Trajectory plan time span, uiExpression is treated The train i of optimization optimal control sequence, QitFor positive definite diagonal matrix, its diagonal element is that train i refers in the priority of t Number λit, and
Step F6, the optimal section train operation state adjustment of Multi-objective Robust：According to each section or zone flow configuration knot Fruit, evolutionary model is mixed based on train operation and Lagrangian plan model obtains optimal single vehicles controlled quentity controlled variable, generation is optimal Single vehicles running orbit and each regulation and control train only implement its first Optimal Control Strategy in Rolling Planning interval；
Step F7, each train receives and performs train collision avoidance instruction；
Step F8, in next sampling instant, repeat step F5 to F7 is until each train reaches it and frees terminal.

Claims (4)

  1. A kind of 1. flow-optimized control system of subway transportation, it is characterised in that：Including wire topologies generation module, data transfer Module, car-mounted terminal module, control terminal module and track monitoring module, track monitoring module collect the status information of train And it is supplied to control terminal module；
    The control terminal module includes following submodule：
    Lothrus apterus Track Pick-up module before train operation：According to Train operation plan time of running table, train dynamics mould is initially set up Type, then establish train running conflict according to train running conflict Coupling point and allocate model in advance, ultimately produce Lothrus apterus train fortune Row track；
    Train operation middle or short term Track Pick-up module：The train real time status information provided according to track monitoring module, utilizes number According to mining model, thus it is speculated that the running orbit of train in future time period；
    Train operation situation monitoring module：In each sampling instant t, the track estimation result based on train can when having between train When can be in the presence of violating safety regulation, warning information is provided to its dynamic behaviour implementing monitoring and for control terminal；
    Train collision avoidance track optimizing module：When train operation situation monitoring module sends warning information, meeting train physics On the premise of performance, region hold stream constraint and track traffic scheduling rule, by setting optimizing index function, use is self-adaptive controlled Theoretical method processed carries out robust dual layer resist to train operation track by control terminal module, and will be advised by data transmission module Check off fruit is transferred to the execution of car-mounted terminal module；Train collision avoidance track optimizing module includes internal layer planning and outer layer plans two classes rule Streak journey；
    Using the flow-optimized control method of subway transportation of the flow-optimized control system of above-mentioned subway transportation, comprise the following steps：
    Step A, according to the plan operational factor of each train, the topology diagram of Rail traffic network is generated；
    Step B, the topology diagram based on the Rail traffic network constructed by step A, the controllability and sensitivity of train flow are analyzed Two class features of property；
    Step C, according to the plan operational factor of each train, on the basis of Modeling Method for Train Dynamics is built, transported according to train Row conflict Coupling point establishes train running conflict and allocates model in advance, generates more train Lothrus apterus running orbits；
    Step D, in each sampling instant t, based on the current running status of train and historical position observation sequence, to train future The advanced positions at certain moment are predicted；Its detailed process is as follows：
    Step D1, train track data pre-process, using train initiating station stop position as the origin of coordinates, in each sampling Carve, according to the acquired original discrete two-dimensional position sequence x=[x of train1,x2,...,xn] and y=[y1,y2,...,yn], adopt Processing is carried out to it with first-order difference method and obtains new train discrete location sequence Δ x=[Δ x1,Δx2,...,Δxn-1] and Δ y=[Δ y1,Δy2,...,Δyn-1], wherein Δ xi=xi+1-xi,Δyi=yi+1-yi(i=1,2 ..., n-1)；
    Step D2, train track data is clustered, to train discrete two-dimensional position sequence Δ x and Δ y new after processing, by setting Surely number M' is clustered, it is clustered respectively using genetic algorithm for clustering；
    Step D3, parameter training is carried out using HMM to the train track data after cluster, after it will handle Train operation track data Δ x and Δ y be considered as the aobvious observations of hidden Markov models, by set hidden state number N' and Parameter updates period τ ', is rolled according to T' nearest position detection value and using B-W algorithms and obtains newest Hidden Markov mould Shape parameter λ '；Specifically：By the train track sets data length obtained is dynamic change, in order to which real-time tracking arranges The state change of wheel paths, it is necessary to initial track HMM parameter lambda '=(π, A, B) on the basis of it is heavy to its New adjustment, more accurately to speculate train in the position at certain following moment；Every period τ ', the T' sight according to newest acquisition Measured value (o1,o2,...,oT') to track HMM parameter lambda '=(π, A, B) reevaluated；
    Step D4, according to HMM parameter, obtained using Viterbi algorithm hidden corresponding to current time observation State q；
    Step D5, every the periodAccording to the HMM parameter lambda of newest acquisition '=(π, A, B) and nearest H history Observation (o1,o2,...,oH), the hidden state q based on train current time, in moment t, time domain h' is predicted by setting, is obtained The position prediction value O of future time period train；
    Step E, establish from the continuous dynamic of train to the observer of discrete conflict logic, by the continuous dynamic of subway transportation system It is mapped as the conflict situation of discrete observation value expression；When system is possible to violate traffic control rule, subway transportation is mixed The Hybrid dynamics behavior implementing monitoring of system, timely warning information is provided for control centre；
    Step F, when warning information occurs, constraint and track traffic scheduling rule are flowed meeting that train physical property, region are held On the premise of, by setting optimizing index function, it is double that robust is carried out to train operation track using Adaptive Control Theory method Layer planning, and program results is transferred to each train, each train receives and performs train collision avoidance instruction until each train reaches It frees terminal；Detailed process is as follows：
    Step F1, the analysis result based on step B and step E, it is determined that the traffic flow regulation measure specifically taken, including adjustment The speed of service of train and/or adjustment train in the station class measure of time two, and using above regulation measure specified place and Opportunity；
    Step F2, the termination reference point locations P, collision avoidance policy control time domain Θ, trajectory predictions time domain of train collision avoidance planning are set Υ；
    Step F3, conflict Resolution process model building is run, the operation conflict Resolution in the above-listed workshop of Rail traffic network is considered as and is based on The inside and outside dual planning problem of both macro and micro aspect, whereinOuter layer plan model is represented, i.e. track is handed over The online train flow flow-Density and distribution problem of path,Represent internal layer plan model, i.e. track traffic section The state adjustment problem of upper single vehicles；F、x1And u1Be respectively outer layer planning problem object function, state vector and decision-making to Amount, G (x1,u1)≤0 be outer layer planning constraints, f, x2And u2Be respectively the object function of internal layer planning problem, state to Amount and decision vector, g (x2,u2)≤0 is the constraints of internal layer planning, using the outer layer program results of macroscopic aspect as microcosmic The reference input of aspect internal layer planning；
    Step F4, the modeling of conflict Resolution variable bound is run, structure exists comprising adjustable train quantity a, train speed ω and train The both macro and micro constraints stood including the variables such as time γ：Wherein t need to implement the section k of conflict Resolution variable about Beam can be described as：ak(t)≤aM、ωk(t)≤ωM、γk(t)≤γM, aM、ωM、γMRespectively maximum adjustable train quantity, most In the time of standing, such variable of freeing can be physical by traffic flow distribution, train for big train running speed and most long train Can be with the constraint of personal distance etc.；
    Step F5, the optimal road network flow allocation plan of Multi-objective Robust solves：Based on cooperative collision avoidance trajectory planning thought, for Different performance indications, by selecting different conflict Resolution object functions, solved in traffic flow operation macroscopic aspect and be based on Europe The multiple target traffic flow optimum flow allocation plan of pull-up network model and it is only implemented in each control section in Rolling Planning interval First Optimal Control Strategy；
    Step F6, the optimal section train operation state adjustment of Multi-objective Robust：According to each section or zone flow configuration result, base Mix evolutionary model and Lagrangian plan model in train operation and obtain optimal single vehicles controlled quentity controlled variable, generate optimal single-row Car running orbit and each regulation and control train only implements its first Optimal Control Strategy in Rolling Planning interval；
    Step F7, each train receives and performs train collision avoidance instruction；
    Step F8, in next sampling instant, repeat step F5 to F7 is until each train reaches it and frees terminal.
  2. 2. the flow-optimized control system of subway transportation according to claim 1, it is characterised in that：In step F2, reference is terminated Point position P is next website that stops of train, and parameter Θ value is 300 seconds, and Υ value is 300 seconds.
  3. 3. the flow-optimized control system of subway transportation according to claim 1 or 2, it is characterised in that：Step F5 specific mistake Journey is as follows：Order
    <mrow> <msubsup> <mi>d</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> <mn>2</mn> </msubsup> <mo>=</mo> <mo>|</mo> <mo>|</mo> <msub> <mi>P</mi> <mi>i</mi> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msubsup> <mi>P</mi> <mi>i</mi> <mi>f</mi> </msubsup> <mo>|</mo> <msubsup> <mo>|</mo> <mn>2</mn> <mn>2</mn> </msubsup> <mo>=</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> </msub> <mo>-</mo> <msubsup> <mi>x</mi> <mi>i</mi> <mi>f</mi> </msubsup> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>+</mo> <msup> <mrow> <mo>(</mo> <msub> <mi>y</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> </msub> <mo>-</mo> <msubsup> <mi>y</mi> <mi>i</mi> <mi>f</mi> </msubsup> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>,</mo> </mrow>
    WhereinRepresent square of the distance between t train i present positions and next website, Pi(t)=(xit,yit) table Show t train i two-dimensional coordinate value,Represent the next two-dimensional coordinate values for stopping website of train i, then during t The priority index for carving train i may be set to：
    <mrow> <msub> <mi>&amp;lambda;</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> </msub> <mo>=</mo> <mn>100</mn> <mfrac> <msubsup> <mi>d</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> <mrow> <mo>-</mo> <mn>2</mn> </mrow> </msubsup> <mrow> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>n</mi> <mi>t</mi> </msub> </munderover> <msubsup> <mi>d</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> <mrow> <mo>-</mo> <mn>2</mn> </mrow> </msubsup> </mrow> </mfrac> <mo>,</mo> </mrow>
    Wherein ntRepresent the train number of conflict on t section be present, from the implication of priority index, train is under One website is nearer, and its priority is higher；
    Set optimizing index
    <mrow> <mtable> <mtr> <mtd> <mrow> <msup> <mi>J</mi> <mo>*</mo> </msup> <mrow> <mo>(</mo> <msubsup> <mi>u</mi> <mn>1</mn> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </msubsup> <mo>,</mo> <msubsup> <mi>u</mi> <mn>1</mn> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </msubsup> <mo>,</mo> <mn>...</mn> <mo>,</mo> <msubsup> <mi>u</mi> <mn>1</mn> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mi>p</mi> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </msubsup> <mo>,</mo> <mn>...</mn> <mo>,</mo> <msubsup> <mi>u</mi> <msub> <mi>n</mi> <mi>t</mi> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </msubsup> <mo>,</mo> <msubsup> <mi>u</mi> <msub> <mi>n</mi> <mi>t</mi> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </msubsup> <mo>,</mo> <mn>...</mn> <mo>,</mo> <msubsup> <mi>u</mi> <msub> <mi>n</mi> <mi>t</mi> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mo>&amp;Pi;</mo> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> </msubsup> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>s</mi> <mo>=</mo> <mn>1</mn> </mrow> <mo>&amp;Pi;</mo> </munderover> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>n</mi> <mi>t</mi> </msub> </munderover> <msub> <mi>&amp;lambda;</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> </msub> <mo>|</mo> <mo>|</mo> <msub> <mi>P</mi> <mi>i</mi> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mi>s</mi> <mi>&amp;Delta;</mi> <mi>t</mi> <mo>)</mo> </mrow> <mo>-</mo> <msubsup> <mi>P</mi> <mi>i</mi> <mi>f</mi> </msubsup> <mo>|</mo> <msubsup> <mo>|</mo> <mn>2</mn> <mn>2</mn> </msubsup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>s</mi> <mo>=</mo> <mn>1</mn> </mrow> <mo>&amp;Pi;</mo> </munderover> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <msub> <mi>n</mi> <mi>t</mi> </msub> </munderover> <msup> <mrow> <mo>(</mo> <msub> <mi>P</mi> <mi>i</mi> </msub> <mo>(</mo> <mrow> <mi>t</mi> <mo>+</mo> <mi>s</mi> <mi>&amp;Delta;</mi> <mi>t</mi> </mrow> <mo>)</mo> <mo>-</mo> <msubsup> <mi>P</mi> <mi>i</mi> <mi>f</mi> </msubsup> <mo>)</mo> </mrow> <mi>T</mi> </msup> <msub> <mi>Q</mi> <mrow> <mi>i</mi> <mi>t</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>P</mi> <mi>i</mi> </msub> <mo>(</mo> <mrow> <mi>t</mi> <mo>+</mo> <mi>s</mi> <mi>&amp;Delta;</mi> <mi>t</mi> </mrow> <mo>)</mo> <mo>-</mo> <msubsup> <mi>P</mi> <mi>i</mi> <mi>f</mi> </msubsup> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> <mo>,</mo> </mrow>
    Wherein i ∈ I (t) represent train code and I (t)=1,2 ..., nt, Pi(t+s Δs t) represents train in moment (t+s Δs T) position vector, Π represent control time, i.e., the time span that Future Trajectory is planned from current time, uiRepresent to be optimized Train i optimal control sequence, QitFor positive definite diagonal matrix, its diagonal element is priority index of the train i in t λit, and
  4. 4. a kind of flow-optimized control method of double-deck subway transportation, it is characterised in that comprise the following steps：
    Step A, according to the plan operational factor of each train, the topology diagram of Rail traffic network is generated；
    Step B, the topology diagram based on the Rail traffic network constructed by step A, the controllability and sensitivity of train flow are analyzed Two class features of property；
    Step C, according to the plan operational factor of each train, on the basis of Modeling Method for Train Dynamics is built, transported according to train Row conflict Coupling point establishes train running conflict and allocates model in advance, generates more train Lothrus apterus running orbits；
    Step D, in each sampling instant t, based on the current running status of train and historical position observation sequence, to train future The advanced positions at certain moment are predicted；Its detailed process is as follows：
    Step D1, train track data pre-process, using train initiating station stop position as the origin of coordinates, in each sampling Carve, according to the acquired original discrete two-dimensional position sequence x=[x of train1,x2,...,xn] and y=[y1,y2,...,yn], adopt Processing is carried out to it with first-order difference method and obtains new train discrete location sequence Δ x=[Δ x1,Δx2,...,Δxn-1] and Δ y=[Δ y1,Δy2,...,Δyn-1], wherein Δ xi=xi+1-xi,Δyi=yi+1-yi(i=1,2 ..., n-1)；
    Step D2, train track data is clustered, to train discrete two-dimensional position sequence Δ x and Δ y new after processing, by setting Surely number M' is clustered, it is clustered respectively using genetic algorithm for clustering；
    Step D3, parameter training is carried out using HMM to the train track data after cluster, after it will handle Train operation track data Δ x and Δ y be considered as the aobvious observations of hidden Markov models, by set hidden state number N' and Parameter updates period τ ', is rolled according to T' nearest position detection value and using B-W algorithms and obtains newest Hidden Markov mould Shape parameter λ '；Specifically：By the train track sets data length obtained is dynamic change, in order to which real-time tracking arranges The state change of wheel paths, it is necessary to initial track HMM parameter lambda '=(π, A, B) on the basis of it is heavy to its New adjustment, more accurately to speculate train in the position at certain following moment；Every period τ ', the T' sight according to newest acquisition Measured value (o1,o2,...,oT') to track HMM parameter lambda '=(π, A, B) reevaluated；
    Step D4, according to HMM parameter, obtained using Viterbi algorithm hidden corresponding to current time observation State q；
    Step D5, every the periodAccording to the HMM parameter lambda of newest acquisition '=(π, A, B) and nearest H history Observation (o1,o2,...,oH), the hidden state q based on train current time, in moment t, time domain h' is predicted by setting, is obtained The position prediction value O of future time period train；
    Step E, establish from the continuous dynamic of train to the observer of discrete conflict logic, by the continuous dynamic of subway transportation system It is mapped as the conflict situation of discrete observation value expression；When system is possible to violate traffic control rule, subway transportation is mixed The Hybrid dynamics behavior implementing monitoring of system, timely warning information is provided for control centre；
    Step F, when warning information occurs, constraint and track traffic scheduling rule are flowed meeting that train physical property, region are held On the premise of, by setting optimizing index function, it is double that robust is carried out to train operation track using Adaptive Control Theory method Layer planning, and program results is transferred to each train, each train receives and performs train collision avoidance instruction until each train reaches It frees terminal；Detailed process is as follows：
    Step F1, the analysis result based on step B and step E, it is determined that the traffic flow regulation measure specifically taken, including adjustment The speed of service of train and/or adjustment train in the station class measure of time two, and using above regulation measure specified place and Opportunity；
    Step F2, the termination reference point locations P, collision avoidance policy control time domain Θ, trajectory predictions time domain of train collision avoidance planning are set Υ；
    Step F3, conflict Resolution process model building is run, the operation conflict Resolution in the above-listed workshop of Rail traffic network is considered as and is based on The inside and outside dual planning problem of both macro and micro aspect, whereinOuter layer plan model is represented, i.e. track is handed over The online train flow flow-Density and distribution problem of path,Represent internal layer plan model, i.e. track traffic section The state adjustment problem of upper single vehicles；F、x1And u1Be respectively outer layer planning problem object function, state vector and decision-making to Amount, G (x1,u1)≤0 be outer layer planning constraints, f, x2And u2Be respectively the object function of internal layer planning problem, state to Amount and decision vector, g (x2,u2)≤0 is the constraints of internal layer planning, using the outer layer program results of macroscopic aspect as microcosmic The reference input of aspect internal layer planning；
    Step F4, the modeling of conflict Resolution variable bound is run, structure exists comprising adjustable train quantity a, train speed ω and train The both macro and micro constraints stood including the variables such as time γ：Wherein t need to implement the section k of conflict Resolution variable about Beam can be described as：ak(t)≤aM、ωk(t)≤ωM、γk(t)≤γM, aM、ωM、γMRespectively maximum adjustable train quantity, most In the time of standing, such variable of freeing can be physical by traffic flow distribution, train for big train running speed and most long train Can be with the constraint of personal distance etc.；
    Step F5, the optimal road network flow allocation plan of Multi-objective Robust solves：Based on cooperative collision avoidance trajectory planning thought, for Different performance indications, by selecting different conflict Resolution object functions, solved in traffic flow operation macroscopic aspect and be based on Europe The multiple target traffic flow optimum flow allocation plan of pull-up network model and it is only implemented in each control section in Rolling Planning interval First Optimal Control Strategy；
    Step F6, the optimal section train operation state adjustment of Multi-objective Robust：According to each section or zone flow configuration result, base Mix evolutionary model and Lagrangian plan model in train operation and obtain optimal single vehicles controlled quentity controlled variable, generate optimal single-row Car running orbit and each regulation and control train only implements its first Optimal Control Strategy in Rolling Planning interval；
    Step F7, each train receives and performs train collision avoidance instruction；
    Step F8, in next sampling instant, repeat step F5 to F7 is until each train reaches it and frees terminal.
CN201710900137.6A 2015-03-31 2015-03-31 The flow-optimized control system of subway transportation Pending CN107776613A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710900137.6A CN107776613A (en) 2015-03-31 2015-03-31 The flow-optimized control system of subway transportation

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710900137.6A CN107776613A (en) 2015-03-31 2015-03-31 The flow-optimized control system of subway transportation
CN201510150772.8A CN105083335B (en) 2015-03-31 2015-03-31 The flow-optimized control method of subway transportation

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201510150772.8A Division CN105083335B (en) 2015-03-31 2015-03-31 The flow-optimized control method of subway transportation

Publications (1)

Publication Number Publication Date
CN107776613A true CN107776613A (en) 2018-03-09

Family

ID=54564893

Family Applications (3)

Application Number Title Priority Date Filing Date
CN201510150772.8A Active CN105083335B (en) 2015-03-31 2015-03-31 The flow-optimized control method of subway transportation
CN201710900165.8A Pending CN107826146A (en) 2015-03-31 2015-03-31 The flow-optimized control method of subway transportation based on Robust Strategies
CN201710900137.6A Pending CN107776613A (en) 2015-03-31 2015-03-31 The flow-optimized control system of subway transportation

Family Applications Before (2)

Application Number Title Priority Date Filing Date
CN201510150772.8A Active CN105083335B (en) 2015-03-31 2015-03-31 The flow-optimized control method of subway transportation
CN201710900165.8A Pending CN107826146A (en) 2015-03-31 2015-03-31 The flow-optimized control method of subway transportation based on Robust Strategies

Country Status (1)

Country Link
CN (3) CN105083335B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110798802A (en) * 2019-11-04 2020-02-14 北京理工大学 Method for extracting shared bicycle skeleton network
CN116080413A (en) * 2023-04-11 2023-05-09 西南交通大学 Vehicle running system and method based on rail transit

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109703606B (en) * 2019-01-16 2020-12-15 北京交通大学 High-speed train intelligent driving control method based on historical operation data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103171596A (en) * 2013-03-11 2013-06-26 同济大学 Anti-collision early warning method of rail transit train
CN103310118A (en) * 2013-07-04 2013-09-18 文超 Method for predicting train operation conflicts on high speed railways
CN104462856A (en) * 2014-12-30 2015-03-25 江苏理工学院 Ship conflict early warning method

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8812227B2 (en) * 2011-05-19 2014-08-19 Metrom Rail, Llc Collision avoidance system for rail line vehicles
CN102336204A (en) * 2011-07-31 2012-02-01 宁波市镇海西门专利技术开发有限公司 Anti-collision system for trains
CN102700570A (en) * 2012-05-22 2012-10-03 西南交通大学 Anti-collision and early-warning system of railway vehicles
CN104192177B (en) * 2014-08-07 2016-05-25 国电南瑞科技股份有限公司 A kind of automatic adjusting method of the operation of the urban railway transit train based on Discrete Event Models
CN104192171B (en) * 2014-08-28 2017-01-11 同济大学 Rail transit train detecting method and device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103171596A (en) * 2013-03-11 2013-06-26 同济大学 Anti-collision early warning method of rail transit train
CN103310118A (en) * 2013-07-04 2013-09-18 文超 Method for predicting train operation conflicts on high speed railways
CN104462856A (en) * 2014-12-30 2015-03-25 江苏理工学院 Ship conflict early warning method

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110798802A (en) * 2019-11-04 2020-02-14 北京理工大学 Method for extracting shared bicycle skeleton network
CN110798802B (en) * 2019-11-04 2020-10-02 北京理工大学 Method for extracting shared bicycle skeleton network
CN116080413A (en) * 2023-04-11 2023-05-09 西南交通大学 Vehicle running system and method based on rail transit
CN116080413B (en) * 2023-04-11 2023-06-13 西南交通大学 Vehicle running system and method based on rail transit

Also Published As

Publication number Publication date
CN105083335A (en) 2015-11-25
CN107826146A (en) 2018-03-23
CN105083335B (en) 2017-09-29

Similar Documents

Publication Publication Date Title
CN105083333B (en) A kind of flow-optimized control method of subway transportation
CN105095984B (en) A kind of real-time predicting method of subway train track
CN105083334B (en) Subway train conflict method for early warning
CN105083322B (en) A kind of subway train conflict method for early warning
Liu et al. A real-time queue length estimation method based on probe vehicles in CV environment
CN105083335B (en) The flow-optimized control method of subway transportation
Ma et al. Signal timing at an isolated intersection under mixed traffic environment with self‐organizing connected and automated vehicles
Rakha et al. Traffic signal control enhancements under vehicle infrastructure integration systems.
Yin et al. Balise arrangement optimization for train station parking via expert knowledge and genetic algorithm
Xiong et al. Parallel bus rapid transit (BRT) operation management system based on ACP approach
CN105095983B (en) The real-time predicting method of subway train track
CN105093929B (en) The planing method of subway train conflict Resolution
Alwan et al. Scheduling algorithm for adaptive traffic light under VANET scenario
Hajbabaie et al. Center for Advanced Multimodal Mobility Solutions and Education
Haoya Cooperative Vehicle-Signal Control Considering Energy and Mobility in Connected Environment
Kunicina et al. Traffic Route Modelling and Assignment with Intelligent Transport System
Zhu et al. Modeling and control method of connected and autonomous vehicles (CAVs) in urban traffic network based on PC algorithm

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180309