本申请是申请号为：201510150696.0，发明创造名称为《一种地铁交通流优化控制This application is the application number: 201510150696.0, and the name of the invention is "A Metro Traffic Flow Optimization Control"方法》，申请日为：2015年3月31日的发明专利申请的分案申请。Method", the filing date is: the divisional application of the invention patent application on March 31, 2015.
技术领域technical field
本发明涉及一种地铁交通流优化控制方法，尤其涉及一种基于鲁棒策略的双层地铁交通流优化控制方法。The invention relates to a subway traffic flow optimization control method, in particular to a robust strategy-based double-deck subway traffic flow optimization control method.
背景技术Background technique
随着我国大中城市规模的日益扩大，城市交通系统面临着越来越大的压力，大力发展轨道交通系统成为解决城市交通拥塞的重要手段。国家“十一五”规划纲要指出，有条件的大城市和城市群地区要把轨道交通作为优先发展领域。我国正经历一个前所未有的轨道交通发展高峰期，一些城市已由线的建设转向了网的建设，城市轨道交通网络已逐步形成。在轨道交通网络和列车流密集的复杂区域，仍然采用列车运行计划结合基于主观经验的列车间隔调配方式逐渐显示出其落后性，具体表现在：(1)列车运行计划时刻表的制定并未考虑到各种随机因素的影响，容易造成交通流战术管理拥挤，降低交通系统运行的安全性；(2)列车调度工作侧重于保持单个列车间的安全间隔，尚未上升到对列车流进行战略管理的宏观层面；(3)列车调配过程多依赖于一线调度人员的主观经验，调配时机的选择随意性较大，缺乏科学理论支撑；(4)调度人员所运用的调配手段较少考虑到外界干扰因素的影响，列车调配方案的鲁棒性和可用性较差。With the increasing scale of large and medium-sized cities in our country, the urban traffic system is facing more and more pressure, and vigorously developing the rail transit system has become an important means to solve urban traffic congestion. The national "Eleventh Five-Year Plan" outline pointed out that large cities and urban agglomerations where conditions permit should take rail transit as a priority area of development. my country is experiencing an unprecedented peak period of rail transit development. Some cities have shifted from line construction to network construction, and urban rail transit networks have gradually formed. In complex areas with dense rail transit network and train flow, the method of still adopting train operation plan combined with train interval allocation based on subjective experience gradually shows its backwardness. Due to the influence of various random factors, it is easy to cause congestion in traffic flow tactical management and reduce the safety of traffic system operation; (2) The train scheduling work focuses on maintaining the safe interval between individual trains, and has not yet risen to the strategic management of train flow. At the macro level; (3) The train deployment process mostly depends on the subjective experience of the front-line dispatchers, and the timing of the deployment is relatively random, lacking scientific theoretical support; (4) The deployment methods used by the dispatchers seldom take into account external interference factors The impact of the train allocation scheme is poor in robustness and availability.
已有文献资料的讨论对象多针对长途铁路运输，而针对大流量、高密度和小间隔运行条件下的城市地铁交通系统的科学调控方案尚缺乏系统设计。复杂路网运行条件下的列车协调控制方案在战略层面上需要对区域内交通网络上单列车的运行状态进行推算和优化，并对由多个列车构成的交通流实施协同规划；在预战术层面上通过有效的监控机制调整交通网络上部分区域的关键运行参数来解决拥塞问题，并保证该区域中所有列车的运行效率；在战术层面上则根据关键运行参数来调整相关列车的运行状态，获取单列车轨迹优化方案，将列车的间隔管理从固定的人工方式转变为考虑列车性能、调度规则和外界环境等因素在内的可变的“微观-宏观-中观-微观”间隔控制方式。The discussion objects of the existing literature are mostly for long-distance railway transportation, but there is still a lack of systematic design for the scientific regulation and control scheme of the urban subway transportation system under the conditions of large flow, high density and small interval operation. The train coordination control scheme under the complex road network operating conditions needs to calculate and optimize the operating status of a single train on the regional traffic network at the strategic level, and implement collaborative planning for the traffic flow composed of multiple trains; at the pre-tactical level On the one hand, the effective monitoring mechanism is used to adjust the key operating parameters of some areas on the traffic network to solve the congestion problem and ensure the operating efficiency of all trains in the area; on the tactical level, the operating status of the relevant trains is adjusted according to the key operating parameters to obtain The single-train trajectory optimization scheme transforms the train interval management from a fixed manual method to a variable "micro-macro-meso-micro" interval control method that considers factors such as train performance, dispatching rules, and external environment.
发明内容Contents of the invention
本发明要解决的技术问题是提供一种鲁棒性和可用性较好的基于鲁棒策略的地铁交通流优化控制方法，该方法可增强调配方案制定的学科性且可有效防止地铁列车运行冲突。The technical problem to be solved by the present invention is to provide a robust and usable subway traffic flow optimization control method based on a robust strategy, which can enhance the discipline of deployment plan formulation and can effectively prevent subway train operation conflicts.
实现本发明目的的技术方案是提供一种基于鲁棒策略的地铁交通流优化控制方法，包括如下步骤：The technical scheme that realizes the object of the present invention is to provide a kind of subway traffic flow optimization control method based on robust strategy, comprising the steps:
步骤A、根据各个列车的计划运行参数，生成轨道交通网络的拓扑结构图；Step A, according to the planned operation parameters of each train, generate the topology structure diagram of the rail transit network;
步骤B、基于步骤A所构建的轨道交通网络的拓扑结构图，分析列车流的可控性和敏感性二类特性；Step B, based on the topology diagram of the rail transit network built in step A, analyze the controllability and sensitivity of the train flow;
步骤C、根据各个列车的计划运行参数，在构建列车动力学模型的基础上，依据列车运行冲突耦合点建立列车运行冲突预调配模型，生成多列车无冲突运行轨迹；Step C, according to the planned operation parameters of each train, on the basis of constructing the train dynamics model, establish a train operation conflict pre-allocation model according to the train operation conflict coupling points, and generate multiple train conflict-free running trajectories;
步骤D、在每一采样时刻t，基于列车当前的运行状态和历史位置观测序列，对列车未来某时刻的行进位置进行预测；其具体过程如下：Step D. At each sampling time t, based on the current running state of the train and the historical position observation sequence, predict the traveling position of the train at a certain moment in the future; the specific process is as follows:
步骤D1、列车轨迹数据预处理，以列车在起始站的停靠位置为坐标原点，在每一采样时刻，依据所获取的列车原始离散二维位置序列x＝[x1,x2,...,xn]和y＝[y1,y2,...,yn]，采用一阶差分方法对其进行处理获取新的列车离散位置序列△x＝[△x1,△x2,...,△xn-1]和△y＝[△y1,△y2,...,△yn-1],其中△xi＝xi+1-xi,△yi＝yi+1-yi(i＝1,2,...,n-1)；Step D1, train track data preprocessing, take the stop position of the train at the starting station as the origin of coordinates, and at each sampling time, according to the acquired original discrete two-dimensional position sequence of the train x=[x1 ,x2 ,.. .,xn ] and y=[y1 ,y2 ,...,yn ], use the first-order difference method to process them to obtain a new train discrete position sequence △x=[△x1 ,△x2 ,...,△xn-1 ] and △y=[△y1 ,△y2 ,...,△yn-1 ], where △xi =xi+1 -xi ,△yi =yi+1 -yi (i=1,2,...,n-1);
步骤D2、对列车轨迹数据聚类，对处理后新的列车离散二维位置序列△x和△y，通过设定聚类个数M'，采用K-means聚类算法分别对其进行聚类；Step D2, clustering the train track data, clustering the new discrete two-dimensional position sequence △x and △y of the train after processing by setting the number of clusters M', using the K-means clustering algorithm to cluster them respectively ;
步骤D3、对聚类后的列车轨迹数据利用隐马尔科夫模型进行参数训练，通过将处理后的列车运行轨迹数据△x和△y视为隐马尔科夫过程的显观测值，通过设定隐状态数目N'和参数更新时段τ'，依据最近的T'个位置观测值并采用B-W算法滚动获取最新隐马尔科夫模型参数λ'；具体来讲：由于所获得的列车轨迹序列数据长度是动态变化的，为了实时跟踪列车轨迹的状态变化，有必要在初始轨迹隐马尔科夫模型参数λ'＝(π,A,B)的基础上对其重新调整，以便更精确地推测列车在未来某时刻的位置；每隔时段τ'，依据最新获得的T'个观测值(o1,o2,...,oT')对轨迹隐马尔科夫模型参数λ'＝(π,A,B)进行重新估计；Step D3. Use the Hidden Markov Model to perform parameter training on the clustered train trajectory data. By treating the processed train trajectory data △x and △y as the obvious observations of the hidden Markov process, by setting The number of hidden states N' and the parameter update period τ', according to the latest T' position observations and the BW algorithm to obtain the latest hidden Markov model parameters λ'; is dynamic. In order to track the state changes of the train trajectory in real time, it is necessary to readjust it on the basis of the initial trajectory hidden Markov model parameter λ'=(π,A,B), so as to more accurately speculate that the train is at The position at a certain moment in the future; every period τ', according to the latest T' observations (o1 ,o2 ,...,oT ') for the trajectory hidden Markov model parameter λ'=(π, A, B) re-estimate;
步骤D4、依据隐马尔科夫模型参数，采用Viterbi算法获取当前时刻观测值所对应的隐状态q；Step D4, according to the Hidden Markov Model parameters, use the Viterbi algorithm to obtain the hidden state q corresponding to the observed value at the current moment;
步骤D5、每隔时段根据最新获得的隐马尔科夫模型参数λ'＝(π,A,B)和最近H个历史观测值(o1,o2,...,oH)，基于列车当前时刻的隐状态q，在时刻t，通过设定预测时域h'，获取未来时段列车的位置预测值O；Step D5, every time period According to the latest hidden Markov model parameters λ'=(π,A,B) and the latest H historical observations (o1 ,o2 ,...,oH ), based on the hidden state q of the train at the current moment , at time t, by setting the prediction time domain h', the predicted position value O of the train in the future period is obtained;
步骤E、建立从列车的连续动态到离散冲突逻辑的观测器，将地铁交通系统的连续动态映射为离散观测值表达的冲突状态；当系统有可能违反交通管制规则时，对地铁交通混杂系统的混杂动态行为实施监控，为控制中心提供及时的告警信息；Step E, establish an observer from the continuous dynamics of the train to the discrete conflict logic, and map the continuous dynamics of the subway traffic system to the conflict state expressed by the discrete observation values; when the system may violate the traffic control rules, the mixed system of the subway traffic Mixed dynamic behaviors are monitored to provide timely alarm information for the control center;
步骤F、当告警信息出现时，在满足列车物理性能、区域容流约束和轨道交通调度规则的前提下，通过设定优化指标函数，采用自适应控制理论方法对列车运行轨迹进行鲁棒双层规划，并将规划结果传输给各列车，各列车接收并执行列车避撞指令直至各列车均到达其解脱终点。Step F. When the alarm information appears, under the premise of satisfying the physical performance of the train, the regional flow capacity constraints and the rail traffic dispatching rules, by setting the optimization index function, the adaptive control theory method is used to perform a robust double-layer train trajectory planning, and transmit the planning results to each train, and each train receives and executes the train collision avoidance instruction until each train reaches its release end point.
进一步的，步骤A的具体过程如下：Further, the specific process of step A is as follows:
步骤A1、从地铁交通控制中心的数据库提取各个列车运行过程中所停靠的站点信息；Step A1, from the database of the subway traffic control center, extract the site information that each train stops during operation;
步骤A2、按照正反两个运行方向对各个列车所停靠的站点信息进行分类，并将同一运行方向上的相同站点进行合并；Step A2, classify the station information where each train stops according to the positive and negative running directions, and merge the same stations in the same running direction;
步骤A3、根据站点合并结果，按照站点的空间布局形式用直线连接前后多个站点。Step A3, according to the site merging result, connect multiple sites before and after with straight lines according to the spatial layout of the sites.
进一步的，步骤B的具体过程如下：Further, the specific process of step B is as follows:
步骤Bl、构建单一子段上的交通流控制模型；其具体过程如下：Step B1, constructing a traffic flow control model on a single subsection; its specific process is as follows:
步骤Bl.1、引入状态变量Ψ、输入变量u和输出变量Ω，其中Ψ表示站点间相连路段上某时刻存在的列车数量，它包括单路段和多路段两种类型，u表示轨道交通调度员针对某路段所实施的调度措施，如调整列车速度或更改列车的在站时间等，Ω表示某时段路段上离开的列车数量；Step Bl.1. Introduce state variable Ψ, input variable u and output variable Ω, where Ψ represents the number of trains that exist at a certain moment on the connected section between stations, and it includes two types of single section and multi-section, and u indicates rail transit dispatcher The dispatching measures implemented for a certain road section, such as adjusting the speed of the train or changing the time of the train at the station, etc., Ω represents the number of trains leaving on the road section in a certain period of time;
步骤B1.2、通过将时间离散化，建立形如Ψ(t+△t)＝A1Ψ(t)+B1u(t)和Ω(t)＝C1Ψ(t)+D1u(t)的单一子段上的离散时间交通流控制模型,其中△t表示采样间隔，Ψ(t)表示t时刻的状态向量，A1、B1、C1和D1分别表示t时刻的状态转移矩阵、输入矩阵、输出测量矩阵和直接传输矩阵；Step B1.2, by discretizing the time, establish the form such as Ψ(t+△t)=A1 Ψ(t)+B1 u(t) and Ω(t)=C1 Ψ(t)+D1 u A discrete-time traffic flow control model on a single subsection of (t), where △t represents the sampling interval, Ψ(t) represents the state vector at time t, and A1 , B1 , C1 and D1 represent the State transition matrix, input matrix, output measurement matrix and direct transfer matrix;
步骤B2、构建多子段上的交通流控制模型；其具体过程如下：Step B2, constructing a traffic flow control model on multiple sub-sections; the specific process is as follows:
步骤B2.1、根据线路空间布局形式和列车流量历史统计数据，获取交叉线路各子段上的流量比例参数β；Step B2.1, according to the spatial layout form of the line and the historical statistical data of the train flow, obtain the traffic ratio parameter β on each sub-section of the crossing line;
步骤B2.2、根据流量比例参数和单一子段上的离散时间交通流控制模型，构建形如Ψ(t+△t)＝A1Ψ(t)+B1u(t)和Ω(t)＝C1Ψ(t)+D1u(t)的多子段上的离散时间交通流控制模型；Step B2.2. According to the traffic ratio parameter and the discrete-time traffic flow control model on a single subsection, construct a form such as Ψ(t+△t)=A1 Ψ(t)+B1 u(t) and Ω(t) = Discrete-time traffic flow control model on multi-subsections of C1 Ψ(t)+D1 u(t);
步骤B3、根据控制模型的可控系数矩阵[B1,A1B1,...,A1n-1B1]的秩与数值n的关系，定性分析其可控性，根据控制模型的敏感系数矩阵[C1(zI-A1)-1B1+D1]，定量分析其输入输出敏感性，其中n表示状态向量的维数，I表示单位矩阵，z表示对原始离散时间交通流控制模型进行转换的基本因子。Step B3, according to the relationship between the rank of the controllable coefficient matrix [B1 ,A1 B1 ,...,A1n-1 B1 ] of the control model and the value n, qualitatively analyze its controllability, according to the control model The sensitivity coefficient matrix [C1 (zI-A1 )-1 B1 +D1 ], quantitative analysis of its input and output sensitivity, where n represents the dimension of the state vector, I represents the identity matrix, z represents the original discrete time The basic factor for the transformation of the traffic flow control model.
进一步的，步骤C的具体过程如下：Further, the specific process of step C is as follows:
步骤C1、列车状态转移建模，列车沿轨道交通路网运行的过程表现为在站点间的动态切换过程，根据列车运行计划中的站点设置，建立单个列车在不同站点间切换转移的Petri网模型：E＝(g,G,Pre,Post,m)为列车路段转移模型，其中g表示站点间各子路段，G表示列车运行速度状态参数的转换点，Pre和Post分别表示各子路段和站点间的前后向连接关系，m:表示列车所处的运行路段，其中m表示模型标识，Z+表示正整数集合；Step C1, train state transfer modeling, the process of the train running along the rail transit network is a dynamic switching process between stations, according to the station settings in the train operation plan, a Petri net model for a single train switching between different stations is established : E=(g, G, Pre, Post, m) is the train section transfer model, where g represents each sub-section between stations, G represents the transition point of the train speed state parameter, Pre and Post represent each sub-section and station respectively The forward and backward connection relationship between, m: Indicates the running section of the train, where m represents the model identifier, and Z+ represents a set of positive integers;
步骤C2、列车全运行剖面混杂系统建模，将列车在站点间的运行视为连续过程，从列车的受力情形出发，依据能量模型推导列车在不同运行阶段的动力学方程，结合外界干扰因素，建立关于列车在某一运行阶段速度vG的映射函数vG＝λ(T1,T2,H,R,α)，其中T1、T2、H、R和α分别表示列车牵引力、列车制动力、列车阻力、列车重力和列车状态随机波动参数；Step C2: Modeling the hybrid system of the train's full running profile, considering the running of the train between stations as a continuous process, starting from the stress situation of the train, deriving the dynamic equation of the train at different running stages according to the energy model, and combining external disturbance factors , establish a mapping function vG = λ(T1 , T2 , H, R, α) about the speed vG of the train in a certain running stage, where T1 , T2 , H, R and α represent the traction force of the train, Random fluctuation parameters of train braking force, train resistance, train gravity and train state;
步骤C3、采用混杂仿真的方式推测求解列车轨迹，通过将时间细分，利用状态连续变化的特性递推求解任意时刻列车在某一运行阶段距初始停靠位置点的距离，其中J0为初始时刻列车距初始停靠位置点的航程，△τ为时间窗的数值，J(τ)为τ时刻列车距初始停靠位置点的路程，由此可以推测得到单列车轨迹；Step C3, guessing and solving the train trajectory by means of hybrid simulation, and recursively solving the distance between the train at a certain operation stage and the initial stop position point at any time by subdividing the time and using the characteristics of continuous state change, Where J0 is the voyage of the train from the initial stop point at the initial moment, △τ is the value of the time window, and J(τ) is the distance between the train and the initial stop point at the time τ, from which the trajectory of a single train can be inferred;
步骤C4、列车在站时间概率分布函数建模，针对特定运行线路，通过调取列车在各车站的停站时间数据，获取不同线路不同站点条件下列车的停站时间概率分布；Step C4, train station time probability distribution function modeling, for a specific operating line, by calling the train stop time data at each station, to obtain the train stop time probability distribution under the conditions of different lines and different stations;
步骤C5、多列车耦合的无冲突鲁棒轨迹调配，根据各列车预达冲突点的时间，通过时段划分，在每一采样时刻t，在融入随机因子的前提下，按照调度规则对冲突点附近不满足安全间隔要求的列车轨迹实施鲁棒二次规划。Step C5, conflict-free robust trajectory allocation of multi-train coupling, according to the time when each train arrives at the conflict point, through the time period division, at each sampling time t, under the premise of incorporating random factors, according to the scheduling rules Robust quadratic programming for train trajectories that do not meet safety interval requirements.
进一步的，步骤D中，聚类个数M'的值为4，隐状态数目N'的值为3，参数更新时段τ'为30秒，T'为10，为30秒，H为10，预测时域h'为300秒。Further, in step D, the value of the number of clusters M' is 4, the value of the number of hidden states N' is 3, the parameter update period τ' is 30 seconds, T' is 10, is 30 seconds, H is 10, and the prediction time domain h' is 300 seconds.
进一步的，步骤E的具体实施过程如下：Further, the specific implementation process of step E is as follows:
步骤E1、构造基于管制规则的冲突超曲面函数集：建立超曲面函数集用以反映系统的冲突状况，其中，冲突超曲面中与单一列车相关的连续函数hI为第I型超曲面，与两列车相关的连续函数hII为第II型超曲面；Step E1, constructing a conflict hypersurface function set based on control rules: establishing a hypersurface function set to reflect the conflict situation of the system, wherein, the continuous function hI related to a single train in the conflict hypersurface is a type I hypersurface, and The continuous function hII related to the two trains is the type II hypersurface;
步骤E2、建立由列车连续状态至离散冲突状态的观测器，构建列车在交通路网内运行时需满足的安全规则集dij(t)≥dmin，其中dij(t)表示列车i和列车j在t时刻的实际间隔，dmin表示列车间的最小安全间隔；Step E2, establish an observer from the continuous state of the train to the discrete conflict state, and construct the safety rule set dij (t)≥dmin that the train needs to satisfy when running in the traffic network, where dij (t) represents the train i and The actual interval of train j at time t, dmin represents the minimum safe interval between trains;
步骤E3、基于人-机系统理论和复杂系统递阶控制原理，根据列车运行模式，构建人在环路的列车实时监控机制，保证系统的运行处于安全可达集内，设计从冲突到冲突解脱手段的离散监控器，当观测器的离散观测向量表明安全规则集会被违反时，立刻发出相应的告警信息。Step E3. Based on the human-machine system theory and the hierarchical control principle of complex systems, and according to the train operation mode, build a real-time monitoring mechanism for trains with people in the loop, to ensure that the operation of the system is within the safe reachable set, and design from conflict to conflict relief The discrete monitor of the means, when the discrete observation vector of the observer indicates that the security rule set will be violated, it will immediately send out the corresponding alarm information.
进一步的，步骤F的具体过程如下：Further, the specific process of step F is as follows:
步骤F1、基于步骤B和步骤E的分析结果，确定具体所采取的交通流调控措施，包括调整列车的运行速度和/或调整列车在站时间两类措施，以及采用以上调控措施的具体地点和时机；Step F1, based on the analysis results of steps B and E, determine the specific traffic flow control measures to be taken, including two types of measures: adjusting the running speed of the train and/or adjusting the train’s time at the station, as well as the specific location and location of the above control measures opportunity;
步骤F2、设定列车避撞规划的终止参考点位置P、避撞策略控制时域Θ、轨迹预测时域Step F2, set the termination reference point position P of the train collision avoidance plan, the collision avoidance strategy control time domain Θ, and the trajectory prediction time domain
步骤F3、运行冲突解脱过程建模，将轨道交通网络上列车间的运行冲突解脱视为基于宏观和微观层面的内外双重规划问题，其中表示外层规划模型，即轨道交通路网上列车流流量-密度配置问题，表示内层规划模型，即轨道交通路段上单列车的状态调整问题；F、x1和u1分别是外层规划问题的目标函数、状态向量和决策向量，G(x1,u1)≤0是外层规划的约束条件，f、x2和u2分别是内层规划问题的目标函数、状态向量和决策向量，g(x2,u2)≤0是内层规划的约束条件，将宏观层面的外层规划结果作为微观层面内层规划的参考输入；Step F3, model the operation conflict resolution process, consider the operation conflict resolution between trains on the rail transit network as an internal and external dual programming problem based on the macro and micro levels, where Represents the outer planning model, that is, the train flow-density configuration problem on the rail transit network, Represents the inner planning model, that is, the state adjustment problem of a single train on a rail transit section; F, x1 and u1 are the objective function, state vector and decision vector of the outer planning problem, G(x1 ,u1 )≤ 0 is the constraint condition of the outer layer planning, f, x2 and u2 are the objective function, state vector and decision vector of the inner layer planning problem respectively, g(x2 , u2 )≤0 is the constraint condition of the inner layer planning, Use the macro-level outer-level planning results as the reference input for the micro-level inner-level planning;
步骤F4、运行冲突解脱变量约束建模，构建包含可调列车数量a、列车速度ω和列车在站时间γ等变量在内的宏观和微观约束条件：其中t时刻需实施冲突解脱的路段k的变量约束可描述为：ak(t)≤aM、ωk(t)≤ωM、γk(t)≤γM，aM、ωM、γM分别为最大可调列车数量、最大列车运行速度和最长列车在站时间，此类解脱变量会受到交通流分布状态、列车物理性能和安全间隔等方面的约束；Step F4, run conflict-relief variable constraint modeling, and construct macro- and micro-constraint conditions including variables such as adjustable train number a, train speed ω, and train on-station time γ: among them, the road section k that needs to implement conflict resolution at time t Variable constraints can be described as: ak (t)≤aM , ωk (t)≤ωM , γk (t)≤γM , aM , ωM , and γM are the maximum adjustable train number, the maximum The train running speed and the longest train station time, such release variables will be constrained by traffic flow distribution, train physical performance and safety interval;
步骤F5、多目标鲁棒最优路网流量配置方案求解：基于合作式避撞轨迹规划思想，针对不同的性能指标，通过选择不同的冲突解脱目标函数，在交通流运行宏观层面求解基于欧拉网络模型的多目标交通流最佳流量配置方案且各控制路段在滚动规划间隔内仅实施其第一个优化控制策略；Step F5, multi-objective robust optimal road network flow configuration solution solution: Based on the idea of cooperative collision avoidance trajectory planning, according to different performance indicators, by selecting different conflict resolution objective functions, solve the problem at the macro level of traffic flow operation based on Euler The network model's multi-objective traffic flow optimal flow allocation scheme and each control section only implements its first optimal control strategy within the rolling planning interval;
步骤F6、多目标鲁棒最优路段列车运行状态调整：依据各路段或区域流量配置结果，基于列车运行混杂演化模型和拉格朗日规划模型获取最优的单列车控制量，生成最优的单列车运行轨迹且各调控列车在滚动规划间隔内仅实施其第一个优化控制策略；Step F6, multi-objective robust optimal section train operation state adjustment: according to the traffic configuration results of each section or area, based on the hybrid evolution model of train operation and the Lagrangian programming model, the optimal single-train control quantity is obtained, and the optimal Single train running trajectory and each control train only implements its first optimal control strategy within the rolling planning interval;
步骤F7、各列车接收并执行列车避撞指令；Step F7, each train receives and executes the train collision avoidance instruction;
步骤F8、在下一采样时刻，重复步骤F5至F7直至各列车均到达其解脱终点。Step F8. At the next sampling time, repeat steps F5 to F7 until each train reaches its release end point.
进一步的，步骤F2中，终止参考点位置P为列车的下一个停站站点，参数Θ的值为300秒，的值为300秒。Further, in step F2, the termination reference point position P is the next stop site of the train, and the value of parameter Θ is 300 seconds, A value of 300 seconds.
进一步的，步骤F5的具体过程如下：令Further, the specific process of step F5 is as follows: make
其中表示t时刻列车i当前所在位置和下一站点间的距离的平方，Pi(t)＝(xit,yit)表示t时刻列车i的二维坐标值，表示列车i下一停靠站点的二维坐标值，那么t时刻列车i的优先级指数可设定为：in Indicates the square of the distance between the current position of train i and the next station at time t, Pi (t)=(xit , yit ) indicates the two-dimensional coordinate value of train i at time t, Indicates the two-dimensional coordinate value of the next stop of train i, then the priority index of train i at time t can be set as:
其中nt表示t时刻路段上存在冲突的列车数目，由优先级指数的含义可知，列车距离下一站点越近，其优先级越高；Where nt represents the number of conflicting trains on the road section at time t, from the meaning of the priority index, the closer the train is to the next station, the higher its priority;
设定优化指标Set Optimization Metrics
其中i∈I(t)表示列车代码且I(t)＝{1,2,...,nt}，Pi(t+s△t)表示列车在时刻(t+s△t)的位置向量，Π表示控制时段，即从当前时刻起未来轨迹规划的时间长度，ui表示待优化的列车i的最优控制序列，Qit为正定对角矩阵，其对角元素为列车i在t时刻的优先级指数λit，并且Where i∈I(t) represents the train code and I(t)={1,2,...,nt }, Pi (t+s△t) represents the train at time (t+s△t) Position vector, Π represents the control period, that is, the time length of future trajectory planning from the current moment, ui represents the optimal control sequence of train i to be optimized, Qit is a positive definite diagonal matrix, and its diagonal elements are train i in the priority index λit at time t, and
本发明具有积极的效果：(1)本发明的基于鲁棒策略的地铁交通流优化控制方法在满足轨道交通管制安全间隔的前提下，以列车的实时位置信息为基础，运用数据挖掘手段动态推测列车轨迹；依据轨道交通管制规则，对可能出现的冲突实施告警，依据列车性能数据和相关约束条件给各个列车规划冲突解脱轨迹；在对列车运行时刻表进行配置时，考虑了影响列车的各类随机因子的概率分布和列车运行时刻表的鲁棒性，增强配置结果的可用性。The present invention has positive effects: (1) the subway traffic flow optimization control method based on the robust strategy of the present invention satisfies the premise of rail traffic control safety interval, based on the real-time position information of the train, using data mining means to dynamically estimate Train trajectories: According to the rail traffic control rules, implement warnings for possible conflicts, and plan conflict-relief trajectories for each train based on train performance data and related constraints; The probability distribution of random factors and the robustness of the train schedule enhance the usability of configuration results.
(2)本发明基于轨道交通网络拓扑结构的可控性和敏感性分析结果，可为地铁交通流调配时间、调配地点和调配手段的选择提供科学依据，避免调控方案选取的随意性。(2) Based on the controllability and sensitivity analysis results of the rail transit network topology, the present invention can provide a scientific basis for the selection of subway traffic flow deployment time, deployment location and deployment means, and avoid randomness in the selection of control schemes.
(3)本发明基于所构建的“人在环路”的场面监控机制，可以对列车内部连续变量和外部离散事件的频繁交互及时做出有效反应，克服常规开环离线监控方案的缺点。(3) The present invention is based on the constructed "people in the loop" scene monitoring mechanism, which can respond effectively in time to the frequent interaction of train internal continuous variables and external discrete events, and overcome the shortcomings of conventional open-loop off-line monitoring solutions.
(4)本发明的列车流的双层规划方案不仅能够降低优化控制问题的求解维数，还能够增强调控方案的实用性，克服已有文献中的模型和算法只关注列车在车站的到发时间，而缺乏对列车在具体线路区间上运行时的控制与预测的缺陷。(4) The bi-level programming scheme of the train flow of the present invention can not only reduce the solution dimension of the optimal control problem, but also enhance the practicability of the control scheme, and overcome the models and algorithms in the existing literature that only pay attention to the arrival and departure of the train at the station Time, but lacks the defect of control and prediction when the train is running on the specific line section.
(5)本发明基于所构建的列车运行轨迹滚动预测方案，可以及时融入列车实时运行中的各类干扰因素，提高列车轨迹预测的准确性，克服常规离线预测方案精确度不高的缺点。(5) The present invention is based on the constructed train trajectory rolling prediction scheme, which can be timely integrated into various disturbance factors in the real-time operation of the train, improves the accuracy of train trajectory prediction, and overcomes the shortcomings of low accuracy of conventional offline prediction schemes.
附图说明Description of drawings
图1为列车流运行特性分析图；Figure 1 is an analysis diagram of train flow operation characteristics;
图2为无冲突3D鲁棒轨迹推测图；Figure 2 is a conflict-free 3D robust trajectory estimation diagram;
图3为列车运行状态混杂监控图；Fig. 3 is the mixed monitoring diagram of the train running state;
图4为列车运行冲突最优解脱图；Fig. 4 is the optimum relief figure of train operation conflict;
图5为交通流双层配置方案的示意图。FIG. 5 is a schematic diagram of a two-layer configuration scheme of traffic flow.
具体实施方式detailed description
(实施例1)(Example 1)
一种地铁交通流优化控制系统，包括线路拓扑结构生成模块、数据传输模块、车载终端模块、控制终端模块以及轨迹监视模块，轨迹监视模块收集列车的状态信息并提供给控制终端模块。A subway traffic flow optimization control system includes a line topology generation module, a data transmission module, a vehicle terminal module, a control terminal module, and a trajectory monitoring module. The trajectory monitoring module collects train status information and provides it to the control terminal module.
所述控制终端模块包括以下子模块：The control terminal module includes the following submodules:
列车运行前无冲突轨迹生成模块：根据列车计划运行时刻表，首先建立列车动力学模型，然后依据列车运行冲突耦合点建立列车运行冲突预调配模型，最后生成无冲突列车运行轨迹。Conflict-free trajectory generation module before train operation: According to the planned operation timetable of the train, the train dynamics model is established first, and then the train operation conflict pre-allocation model is established according to the train operation conflict coupling point, and finally the conflict-free train operation trajectory is generated.
列车运行中短期轨迹生成模块：依据轨迹监视模块提供的列车实时状态信息，利用数据挖掘模型，推测未来时段内列车的运行轨迹。Short-term trajectory generation module for train operation: According to the real-time status information of the train provided by the trajectory monitoring module, use the data mining model to predict the trajectory of the train in the future period.
列车运行态势监控模块：在每一采样时刻t，基于列车的轨迹推测结果，当列车间有可能出现违反安全规则的状况时,对其动态行为实施监控并为控制终端提供告警信息。Train operation status monitoring module: at each sampling time t, based on the train trajectory estimation results, when there may be a violation of safety rules between trains, monitor its dynamic behavior and provide alarm information to the control terminal.
列车避撞轨迹优化模块：当列车运行态势监控模块发出告警信息时，在满足列车物理性能、区域容流约束和轨道交通调度规则的前提下，通过设定优化指标函数，采用自适应控制理论方法由控制终端模块对列车运行轨迹进行鲁棒双层规划，并通过数据传输模块将规划结果传输给车载终端模块执行。列车避撞轨迹优化模块包含内层规划和外层规划两类规划过程。Train collision avoidance trajectory optimization module: when the train operation status monitoring module sends out an alarm message, on the premise of satisfying the physical performance of the train, the regional flow capacity constraints and the rail traffic dispatching rules, the adaptive control theory method is adopted by setting the optimization index function The control terminal module performs robust two-layer planning on the train trajectory, and transmits the planning results to the vehicle terminal module through the data transmission module for execution. The train collision avoidance trajectory optimization module includes two types of planning processes: inner planning and outer planning.
应用上述地铁交通流优化控制系统的基于鲁棒策略的地铁交通流优化控制方法，包括以下步骤：The subway traffic flow optimization control method based on the robust strategy using the above-mentioned subway traffic flow optimization control system includes the following steps:
步骤A、根据各个列车的计划运行参数，生成轨道交通网络的拓扑结构图；其具体过程如下：Step A, according to the planned operation parameters of each train, generate the topology structure diagram of the rail transit network; its specific process is as follows:
步骤A1、从地铁交通控制中心的数据库提取各个列车运行过程中所停靠的站点信息；Step A1, from the database of the subway traffic control center, extract the site information that each train stops during operation;
步骤A2、按照正反两个运行方向对各个列车所停靠的站点信息进行分类，并将同一运行方向上的相同站点进行合并；Step A2, classify the station information where each train stops according to the positive and negative running directions, and merge the same stations in the same running direction;
步骤A3、根据站点合并结果，按照站点的空间布局形式用直线连接前后多个站点。Step A3, according to the site merging result, connect multiple sites before and after with straight lines according to the spatial layout of the sites.
步骤B、基于步骤A所构建的轨道交通网络的拓扑结构图，分析列车流的可控性和敏感性二类特性；其具体过程如下：Step B, based on the topological structure diagram of the rail transit network constructed in step A, analyze the controllability and sensitivity characteristics of the train flow; the specific process is as follows:
步骤Bl、见图1，构建单一子段上的交通流控制模型；其具体过程如下：Step B1, see Fig. 1, build the traffic flow control model on the single subsection; Its concrete process is as follows:
步骤Bl.1、引入状态变量Ψ、输入变量u和输出变量Ω，其中Ψ表示站点间相连路段上某时刻存在的列车数量，它包括单路段和多路段两种类型，u表示轨道交通调度员针对某路段所实施的调度措施，如调整列车速度或更改列车的在站时间等，Ω表示某时段路段上离开的列车数量；Step Bl.1. Introduce state variable Ψ, input variable u and output variable Ω, where Ψ represents the number of trains that exist at a certain moment on the connected section between stations, and it includes two types of single section and multi-section, and u indicates rail transit dispatcher The dispatching measures implemented for a certain road section, such as adjusting the speed of the train or changing the time of the train at the station, etc., Ω represents the number of trains leaving on the road section in a certain period of time;
步骤B1.2、通过将时间离散化，建立形如Ψ(t+△t)＝A1Ψ(t)+B1u(t)和Ω(t)＝C1Ψ(t)+D1u(t)的单一子段上的离散时间交通流控制模型,其中△t表示采样间隔，Ψ(t)表示t时刻的状态向量，A1、B1、C1和D1分别表示t时刻的状态转移矩阵、输入矩阵、输出测量矩阵和直接传输矩阵；Step B1.2, by discretizing the time, establish the form such as Ψ(t+△t)=A1 Ψ(t)+B1 u(t) and Ω(t)=C1 Ψ(t)+D1 u A discrete-time traffic flow control model on a single subsection of (t), where △t represents the sampling interval, Ψ(t) represents the state vector at time t, and A1 , B1 , C1 and D1 represent the State transition matrix, input matrix, output measurement matrix and direct transfer matrix;
步骤B2、构建多子段上的交通流控制模型；其具体过程如下：Step B2, constructing a traffic flow control model on multiple sub-sections; the specific process is as follows:
步骤B2.1、根据线路空间布局形式和列车流量历史统计数据，获取交叉线路各子段上的流量比例参数β；Step B2.1, according to the spatial layout form of the line and the historical statistical data of the train flow, obtain the traffic ratio parameter β on each sub-section of the crossing line;
步骤B2.2、根据流量比例参数和单一子段上的离散时间交通流控制模型，构建形如Ψ(t+△t)＝A1Ψ(t)+B1u(t)和Ω(t)＝C1Ψ(t)+D1u(t)的多子段上的离散时间交通流控制模型；Step B2.2. According to the traffic ratio parameter and the discrete-time traffic flow control model on a single subsection, construct a form such as Ψ(t+△t)=A1 Ψ(t)+B1 u(t) and Ω(t) = Discrete-time traffic flow control model on multi-subsections of C1 Ψ(t)+D1 u(t);
步骤B3、根据控制模型的可控系数矩阵[B1,A1B1,...,A1n-1B1]的秩与数值n的关系，定性分析其可控性，根据控制模型的敏感系数矩阵[C1(zI-A1)-1B1+D1]，定量分析其输入输出敏感性，其中n表示状态向量的维数，I表示单位矩阵，z表示对原始离散时间交通流控制模型进行转换的基本因子；Step B3, according to the relationship between the rank of the controllable coefficient matrix [B1 ,A1 B1 ,...,A1n-1 B1 ] of the control model and the value n, qualitatively analyze its controllability, according to the control model The sensitivity coefficient matrix [C1 (zI-A1 )-1 B1 +D1 ], quantitative analysis of its input and output sensitivity, where n represents the dimension of the state vector, I represents the identity matrix, z represents the original discrete time The basic factors for the transformation of the traffic flow control model;
步骤C、见图2，根据各个列车的计划运行参数，在构建列车动力学模型的基础上，依据列车运行冲突耦合点建立列车运行冲突预调配模型，生成多列车无冲突运行轨迹；其具体过程如下：Step C, see Figure 2, according to the planned operation parameters of each train, on the basis of constructing the train dynamics model, establish a train operation conflict pre-allocation model according to the train operation conflict coupling points, and generate multiple train conflict-free running trajectories; the specific process as follows:
步骤C1、列车状态转移建模，列车沿轨道交通路网运行的过程表现为在站点间的动态切换过程，根据列车运行计划中的站点设置，建立单个列车在不同站点间切换转移的Petri网模型：E＝(g,G,Pre,Post,m)为列车路段转移模型，其中g表示站点间各子路段，G表示列车运行速度状态参数的转换点，Pre和Post分别表示各子路段和站点间的前后向连接关系，m:表示列车所处的运行路段，其中m表示模型标识，Z+表示正整数集合；Step C1, train state transfer modeling, the process of the train running along the rail transit network is a dynamic switching process between stations, according to the station settings in the train operation plan, a Petri net model for a single train switching between different stations is established : E=(g, G, Pre, Post, m) is the train section transfer model, where g represents each sub-section between stations, G represents the transition point of the train speed state parameter, Pre and Post represent each sub-section and station respectively The forward and backward connection relationship between, m: Indicates the running section of the train, where m represents the model identifier, and Z+ represents a set of positive integers;
步骤C2、列车全运行剖面混杂系统建模，将列车在站点间的运行视为连续过程，从列车的受力情形出发，依据能量模型推导列车在不同运行阶段的动力学方程，结合外界干扰因素，建立关于列车在某一运行阶段速度vG的映射函数vG＝λ(T1,T2,H,R,α)，其中T1、T2、H、R和α分别表示列车牵引力、列车制动力、列车阻力、列车重力和列车状态随机波动参数；Step C2: Modeling the hybrid system of the train's full running profile, considering the running of the train between stations as a continuous process, starting from the stress situation of the train, deriving the dynamic equation of the train at different running stages according to the energy model, and combining external disturbance factors , establish a mapping function vG = λ(T1 , T2 , H, R, α) about the speed vG of the train in a certain running stage, where T1 , T2 , H, R and α represent the traction force of the train, Random fluctuation parameters of train braking force, train resistance, train gravity and train state;
步骤C3、采用混杂仿真的方式推测求解列车轨迹，通过将时间细分，利用状态连续变化的特性递推求解任意时刻列车在某一运行阶段距初始停靠位置点的距离，其中J0为初始时刻列车距初始停靠位置点的航程，△τ为时间窗的数值，J(τ)为τ时刻列车距初始停靠位置点的路程，由此可以推测得到单列车轨迹；Step C3, guessing and solving the train trajectory by means of hybrid simulation, and recursively solving the distance between the train at a certain operation stage and the initial stop position point at any time by subdividing the time and using the characteristics of continuous state change, Where J0 is the voyage of the train from the initial stop point at the initial moment, △τ is the value of the time window, and J(τ) is the distance between the train and the initial stop point at the time τ, from which the trajectory of a single train can be inferred;
步骤C4、列车在站时间概率分布函数建模，针对特定运行线路，通过调取列车在各车站的停站时间数据，获取不同线路不同站点条件下列车的停站时间概率分布；Step C4, train station time probability distribution function modeling, for a specific operating line, by calling the train stop time data at each station, to obtain the train stop time probability distribution under the conditions of different lines and different stations;
步骤C5、多列车耦合的无冲突鲁棒轨迹调配，根据各列车预达冲突点的时间，通过时段划分，在每一采样时刻t，在融入随机因子的前提下，按照调度规则对冲突点附近不满足安全间隔要求的列车轨迹实施鲁棒二次规划。Step C5, conflict-free robust trajectory allocation of multi-train coupling, according to the time when each train arrives at the conflict point, through the time period division, at each sampling time t, under the premise of incorporating random factors, according to the scheduling rules Robust quadratic programming for train trajectories that do not meet safety interval requirements.
步骤D、在每一采样时刻t，基于列车当前的运行状态和历史位置观测序列，对列车未来某时刻的行进位置进行预测；其具体过程如下：Step D. At each sampling time t, based on the current running state of the train and the historical position observation sequence, predict the traveling position of the train at a certain moment in the future; the specific process is as follows:
步骤D1、列车轨迹数据预处理，以列车在起始站的停靠位置为坐标原点，在每一采样时刻，依据所获取的列车原始离散二维位置序列x＝[x1,x2,...,xn]和y＝[y1,y2,...,yn]，采用一阶差分方法对其进行处理获取新的列车离散位置序列△x＝[△x1,△x2,...,△xn-1]和△y＝[△y1,△y2,...,△yn-1],其中△xi＝xi+1-xi,△yi＝yi+1-yi(i＝1,2,...,n-1)；Step D1, train track data preprocessing, take the stop position of the train at the starting station as the origin of coordinates, and at each sampling time, according to the acquired original discrete two-dimensional position sequence of the train x=[x1 ,x2 ,.. .,xn ] and y=[y1 ,y2 ,...,yn ], use the first-order difference method to process them to obtain a new train discrete position sequence △x=[△x1 ,△x2 ,...,△xn-1 ] and △y=[△y1 ,△y2 ,...,△yn-1 ], where △xi =xi+1 -xi ,△yi =yi+1 -yi (i=1,2,...,n-1);
步骤D2、对列车轨迹数据聚类，对处理后新的列车离散二维位置序列△x和△y，通过设定聚类个数M'，采用K-means聚类算法分别对其进行聚类；Step D2, clustering the train track data, clustering the new discrete two-dimensional position sequence △x and △y of the train after processing by setting the number of clusters M', using the K-means clustering algorithm to cluster them respectively ;
步骤D3、对聚类后的列车轨迹数据利用隐马尔科夫模型进行参数训练，通过将处理后的列车运行轨迹数据△x和△y视为隐马尔科夫过程的显观测值，通过设定隐状态数目N'和参数更新时段τ'，依据最近的T'个位置观测值并采用B-W算法滚动获取最新隐马尔科夫模型参数λ'；具体来讲：由于所获得的列车轨迹序列数据长度是动态变化的，为了实时跟踪列车轨迹的状态变化，有必要在初始轨迹隐马尔科夫模型参数λ'＝(π,A,B)的基础上对其重新调整，以便更精确地推测列车在未来某时刻的位置；每隔时段τ'，依据最新获得的T'个观测值(o1,o2,...,oT')对轨迹隐马尔科夫模型参数λ'＝(π,A,B)进行重新估计；Step D3. Use the Hidden Markov Model to perform parameter training on the clustered train trajectory data. By treating the processed train trajectory data △x and △y as the obvious observations of the hidden Markov process, by setting The number of hidden states N' and the parameter update period τ', according to the latest T' position observations and the BW algorithm to obtain the latest hidden Markov model parameters λ'; is dynamic. In order to track the state changes of the train trajectory in real time, it is necessary to readjust it on the basis of the initial trajectory hidden Markov model parameter λ'=(π,A,B), so as to more accurately speculate that the train is at The position at a certain moment in the future; every time period τ', according to the latest T' observations (o1 ,o2 ,...,oT' ) for trajectory hidden Markov model parameters λ'=(π, A, B) re-estimate;
步骤D4、依据隐马尔科夫模型参数，采用Viterbi算法获取当前时刻观测值所对应的隐状态q；Step D4, according to the Hidden Markov Model parameters, use the Viterbi algorithm to obtain the hidden state q corresponding to the observed value at the current moment;
步骤D5、每隔时段根据最新获得的隐马尔科夫模型参数λ'＝(π,A,B)和最近H个历史观测值(o1,o2,...,oH)，基于列车当前时刻的隐状态q，在时刻t，通过设定预测时域h'，获取未来时段列车的位置预测值O；Step D5, every time period According to the latest hidden Markov model parameters λ'=(π,A,B) and the latest H historical observations (o1 ,o2 ,...,oH ), based on the hidden state q of the train at the current moment , at time t, by setting the prediction time domain h', the predicted position value O of the train in the future period is obtained;
上述聚类个数M'的值为4，隐状态数目N'的值为3，参数更新时段τ'为30秒，T'为10，为30秒，H为10，预测时域h'为300秒。The value of the above clustering number M' is 4, the value of the number of hidden states N' is 3, the parameter update period τ' is 30 seconds, T' is 10, is 30 seconds, H is 10, and the prediction time domain h' is 300 seconds.
步骤E、见图3，建立从列车的连续动态到离散冲突逻辑的观测器，将地铁交通系统的连续动态映射为离散观测值表达的冲突状态；当系统有可能违反交通管制规则时，对地铁交通混杂系统的混杂动态行为实施监控，为控制中心提供及时的告警信息；Step E, as shown in Figure 3, establishes an observer from the continuous dynamics of the train to the discrete conflict logic, and maps the continuous dynamics of the subway traffic system to the conflict state expressed by discrete observations; when the system may violate traffic control rules, the subway The mixed dynamic behavior of traffic mixed system is monitored to provide timely alarm information for the control center;
所述步骤E的具体实施过程如下：The concrete implementation process of described step E is as follows:
步骤E1、构造基于管制规则的冲突超曲面函数集：建立超曲面函数集用以反映系统的冲突状况，其中，冲突超曲面中与单一列车相关的连续函数hI为第I型超曲面，与两列车相关的连续函数hII为第II型超曲面；Step E1, constructing a conflict hypersurface function set based on control rules: establishing a hypersurface function set to reflect the conflict situation of the system, wherein, the continuous function hI related to a single train in the conflict hypersurface is a type I hypersurface, and The continuous function hII related to the two trains is the type II hypersurface;
步骤E2、建立由列车连续状态至离散冲突状态的观测器，构建列车在交通路网内运行时需满足的安全规则集dij(t)≥dmin，其中dij(t)表示列车i和列车j在t时刻的实际间隔，dmin表示列车间的最小安全间隔；Step E2, establish an observer from the continuous state of the train to the discrete conflict state, and construct the safety rule set dij (t)≥dmin that the train needs to satisfy when running in the traffic network, where dij (t) represents the train i and The actual interval of train j at time t, dmin represents the minimum safe interval between trains;
步骤E3、基于人-机系统理论和复杂系统递阶控制原理，根据列车运行模式，构建人在环路的列车实时监控机制，保证系统的运行处于安全可达集内，设计从冲突到冲突解脱手段的离散监控器，当观测器的离散观测向量表明安全规则集会被违反时，立刻发出相应的告警信息。Step E3. Based on the human-machine system theory and the hierarchical control principle of complex systems, and according to the train operation mode, build a real-time monitoring mechanism for trains with people in the loop, to ensure that the operation of the system is within the safe reachable set, and design from conflict to conflict relief The discrete monitor of the means, when the discrete observation vector of the observer indicates that the security rule set will be violated, it will immediately send out the corresponding alarm information.
步骤F、见图4，当告警信息出现时，在满足列车物理性能、区域容流约束和轨道交通调度规则的前提下，通过设定优化指标函数，采用自适应控制理论方法对列车运行轨迹进行鲁棒双层规划，并将规划结果传输给各列车，各列车接收并执行列车避撞指令直至各列车均到达其解脱终点；其具体过程如下：Step F, as shown in Figure 4, when the alarm information appears, under the premise of satisfying the physical performance of the train, the regional flow capacity constraints and the rail traffic dispatching rules, by setting the optimization index function, the train trajectory is carried out using the adaptive control theory method Robust two-tier planning, and transmit the planning results to each train, each train receives and executes the train collision avoidance instruction until each train reaches its end of release; the specific process is as follows:
步骤F1、基于步骤B3和步骤E3的分析结果，确定具体所采取的交通流调控措施，包括调整列车的运行速度和/或调整列车在站时间两类措施，以及采用以上调控措施的具体地点和时机；Step F1, based on the analysis results of step B3 and step E3, determine the specific traffic flow control measures to be taken, including two types of measures: adjusting the running speed of the train and/or adjusting the train's time at the station, as well as the specific location and location of the above control measures opportunity;
步骤F2、设定列车避撞规划的终止参考点位置P、避撞策略控制时域Θ、轨迹预测时域Step F2, set the termination reference point position P of the train collision avoidance plan, the collision avoidance strategy control time domain Θ, and the trajectory prediction time domain
终止参考点位置P为列车的下一个停站站点，参数Θ的值为300秒，的值为300秒；Termination reference point position P is the next stop site of the train, and the value of parameter Θ is 300 seconds, The value of 300 seconds;
步骤F3、运行冲突解脱过程建模，将轨道交通网络上列车间的运行冲突解脱视为基于宏观和微观层面的内外双重规划问题，见图5，其中表示外层规划模型，即轨道交通路网上列车流流量-密度配置问题，表示内层规划模型，即轨道交通路段上单列车的状态调整问题；F、x1和u1分别是外层规划问题的目标函数、状态向量和决策向量，G(x1,u1)≤0是外层规划的约束条件，f、x2和u2分别是内层规划问题的目标函数、状态向量和决策向量，g(x2,u2)≤0是内层规划的约束条件，将宏观层面的外层规划结果作为微观层面内层规划的参考输入；Step F3, model the operation conflict resolution process, consider the operation conflict resolution between trains on the rail transit network as an internal and external dual programming problem based on the macro and micro levels, as shown in Figure 5, where Represents the outer planning model, that is, the train flow-density configuration problem on the rail transit network, Represents the inner planning model, that is, the state adjustment problem of a single train on a rail transit section; F, x1 and u1 are the objective function, state vector and decision vector of the outer planning problem, G(x1 ,u1 )≤ 0 is the constraint condition of the outer layer planning, f, x2 and u2 are the objective function, state vector and decision vector of the inner layer planning problem respectively, g(x2 , u2 )≤0 is the constraint condition of the inner layer planning, Use the macro-level outer-level planning results as the reference input for the micro-level inner-level planning;
步骤F4、运行冲突解脱变量约束建模，构建包含可调列车数量a、列车速度ω和列车在站时间γ等变量在内的宏观和微观约束条件：其中t时刻需实施冲突解脱的路段k的变量约束可描述为：ak(t)≤aM、ωk(t)≤ωM、γk(t)≤γM，aM、ωM、γM分别为最大可调列车数量、最大列车运行速度和最长列车在站时间，此类解脱变量会受到交通流分布状态、列车物理性能和安全间隔等方面的约束；Step F4, run conflict-relief variable constraint modeling, and construct macro- and micro-constraint conditions including variables such as adjustable train number a, train speed ω, and train on-station time γ: among them, the road section k that needs to implement conflict resolution at time t Variable constraints can be described as: ak (t)≤aM , ωk (t)≤ωM , γk (t)≤γM , aM , ωM , and γM are the maximum adjustable train number, the maximum The train running speed and the longest train station time, such release variables will be constrained by traffic flow distribution, train physical performance and safety interval;
步骤F5、多目标鲁棒最优路网流量配置方案求解：基于合作式避撞轨迹规划思想，针对不同的性能指标，通过选择不同的冲突解脱目标函数，在交通流运行宏观层面求解基于欧拉网络模型的多目标交通流最佳流量配置方案且各控制路段在滚动规划间隔内仅实施其第一个优化控制策略；其具体过程如下：令Step F5, multi-objective robust optimal road network flow configuration solution solution: Based on the idea of cooperative collision avoidance trajectory planning, according to different performance indicators, by selecting different conflict resolution objective functions, solve the problem at the macro level of traffic flow operation based on Euler The multi-objective traffic flow optimal flow allocation scheme of the network model and each control road section only implements its first optimal control strategy within the rolling planning interval; the specific process is as follows:
其中表示t时刻列车i当前所在位置和下一站点间的距离的平方，Pi(t)＝(xit,yit)表示t时刻列车i的二维坐标值，表示列车i下一停靠站点的二维坐标值，那那么t时刻列车i的优先级指数可设定为：in Indicates the square of the distance between the current position of train i and the next station at time t, Pi (t)=(xit , yit ) indicates the two-dimensional coordinate value of train i at time t, Indicates the two-dimensional coordinate value of the next stop of train i, then the priority index of train i at time t can be set as:
其中nt表示t时刻路段上存在冲突的列车数目，由优先级指数的含义可知，列车距离下一站点越近，其优先级越高；Where nt represents the number of conflicting trains on the road section at time t, from the meaning of the priority index, the closer the train is to the next station, the higher its priority;
设定优化指标Set Optimization Metrics
其中i∈I(t)表示列车代码且I(t)＝{1,2,...,nt}，Pi(t+s△t)表示列车在时刻(t+s△t)的位置向量，Π表示控制时段，即从当前时刻起未来轨迹规划的时间长度，ui表示待优化的列车i的最优控制序列，Qit为正定对角矩阵，其对角元素为列车i在t时刻的优先级指数λit，并且Where i∈I(t) represents the train code and I(t)={1,2,...,nt }, Pi (t+s△t) represents the train at time (t+s△t) Position vector, Π represents the control period, that is, the time length of future trajectory planning from the current moment, ui represents the optimal control sequence of train i to be optimized, Qit is a positive definite diagonal matrix, and its diagonal elements are train i in the priority index λit at time t, and
步骤F6、多目标鲁棒最优路段列车运行状态调整：依据各路段或区域流量配置结果，基于列车运行混杂演化模型和拉格朗日规划模型获取最优的单列车控制量，生成最优的单列车运行轨迹且各调控列车在滚动规划间隔内仅实施其第一个优化控制策略；Step F6, multi-objective robust optimal section train operation state adjustment: according to the traffic configuration results of each section or area, based on the hybrid evolution model of train operation and the Lagrangian programming model, the optimal single-train control quantity is obtained, and the optimal Single train running trajectory and each control train only implements its first optimal control strategy within the rolling planning interval;
步骤F7、各列车接收并执行列车避撞指令；Step F7, each train receives and executes the train collision avoidance instruction;
步骤F8、在下一采样时刻，重复步骤F5至F7直至各列车均到达其解脱终点。Step F8. At the next sampling time, repeat steps F5 to F7 until each train reaches its release end point.
显然，上述实施例仅仅是为清楚地说明本发明所作的举例，而并非是对本发明的实施方式的限定。对于所属领域的普通技术人员来说，在上述说明的基础上还可以做出其它不同形式的变化或变动。这里无需也无法对所有的实施方式予以穷举。而这些属于本发明的精神所引伸出的显而易见的变化或变动仍处于本发明的保护范围之中。Apparently, the above-mentioned embodiments are only examples for clearly illustrating the present invention, rather than limiting the implementation of the present invention. For those of ordinary skill in the art, on the basis of the above description, other changes or changes in different forms can also be made. It is not necessary and impossible to exhaustively list all the implementation manners here. And these obvious changes or modifications derived from the spirit of the present invention are still within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710078412.0ACN106828545A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method based on robust strategy |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510150696.0ACN105083333B (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method |
| CN201710078412.0ACN106828545A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method based on robust strategy |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510150696.0ADivisionCN105083333B (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method |
| Publication Number | Publication Date |
|---|---|
| CN106828545Atrue CN106828545A (en) | 2017-06-13 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710078608.XAPendingCN106777833A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method based on robust strategy |
| CN201710078412.0APendingCN106828545A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method based on robust strategy |
| CN201710078413.5APendingCN106828546A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow control method |
| CN201510150696.0AActiveCN105083333B (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method |
| CN201710078414.XAPendingCN106853833A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow control method |
| CN201710078938.9APendingCN106672028A (en) | 2015-03-31 | 2015-03-31 | Double-layer subway traffic flow optimization control method based on robust strategy |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710078608.XAPendingCN106777833A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method based on robust strategy |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710078413.5APendingCN106828546A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow control method |
| CN201510150696.0AActiveCN105083333B (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow optimization control method |
| CN201710078414.XAPendingCN106853833A (en) | 2015-03-31 | 2015-03-31 | Subway traffic flow control method |
| CN201710078938.9APendingCN106672028A (en) | 2015-03-31 | 2015-03-31 | Double-layer subway traffic flow optimization control method based on robust strategy |
| Country | Link |
|---|---|
| CN (6) | CN106777833A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647802A (en)* | 2018-03-26 | 2018-10-12 | 华东师范大学 | Based on the anti-congestion methods of double-layer traffic network model |
| CN108898321A (en)* | 2018-07-09 | 2018-11-27 | 西北工业大学 | A kind of manufacturing technology problem rule violations parameter acquiring method based on semantic template |
| CN114815852A (en)* | 2022-06-14 | 2022-07-29 | 北京航空航天大学 | A CACC Fleet Trajectory Planning Method Based on Spatial Discretization |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403273B (en)* | 2017-07-28 | 2020-11-27 | 中铁程科技有限责任公司 | Information processing method, device and non-transitory computer readable storage medium |
| CN108873737B (en)* | 2018-07-18 | 2020-12-25 | 东北大学 | Automatic sorting control and decision-making system based on M-HSTPN model |
| CN109703606B (en)* | 2019-01-16 | 2020-12-15 | 北京交通大学 | Intelligent driving control method of high-speed train based on historical operation data |
| CN111191383B (en)* | 2020-01-17 | 2023-10-31 | 中车青岛四方机车车辆股份有限公司 | A method, device, storage medium and electronic equipment for generating simulation trajectories |
| CN114937364B (en)* | 2022-06-17 | 2023-09-15 | 北京交通大学 | A method for constructing hierarchical urban rail transit network based on topology transformation |
| CN117381805B (en)* | 2023-12-13 | 2024-02-27 | 成都航空职业技术学院 | Mechanical arm operation control method and system for conflict handling |
| CN117681932B (en)* | 2024-01-02 | 2025-04-29 | 北京交通大学 | A heavy-load train control method, system and storage medium based on virtual coupling |
| CN118082930B (en)* | 2024-03-21 | 2024-08-20 | 合肥工业大学 | Train operation adjustment method under continuous random interval multi-interference based on scene |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102011081995A1 (en)* | 2011-09-01 | 2012-10-25 | Siemens Ag | Drive optimization module for vehicle, particularly rail vehicle, has communication device for direct communication with one or multiple other vehicles for transmission of ride data or for receiving data of vehicles |
| CN102806923A (en)* | 2006-12-07 | 2012-12-05 | 通用电气公司 | Method for operating railway vehicle |
| CN103043084A (en)* | 2012-12-31 | 2013-04-17 | 北京交通大学 | Method and system for optimizing urban railway transit transfer |
| 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 |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9733625B2 (en)* | 2006-03-20 | 2017-08-15 | General Electric Company | Trip optimization system and method for a train |
| WO2012158906A1 (en)* | 2011-05-19 | 2012-11-22 | 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 |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102806923A (en)* | 2006-12-07 | 2012-12-05 | 通用电气公司 | Method for operating railway vehicle |
| DE102011081995A1 (en)* | 2011-09-01 | 2012-10-25 | Siemens Ag | Drive optimization module for vehicle, particularly rail vehicle, has communication device for direct communication with one or multiple other vehicles for transmission of ride data or for receiving data of vehicles |
| CN103043084A (en)* | 2012-12-31 | 2013-04-17 | 北京交通大学 | Method and system for optimizing urban railway transit transfer |
| 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 |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647802A (en)* | 2018-03-26 | 2018-10-12 | 华东师范大学 | Based on the anti-congestion methods of double-layer traffic network model |
| CN108898321A (en)* | 2018-07-09 | 2018-11-27 | 西北工业大学 | A kind of manufacturing technology problem rule violations parameter acquiring method based on semantic template |
| CN108898321B (en)* | 2018-07-09 | 2021-08-24 | 西北工业大学 | A Method for Obtaining Standard Conflict Parameters of Manufacturing Technology Problems Based on Semantic Templates |
| CN114815852A (en)* | 2022-06-14 | 2022-07-29 | 北京航空航天大学 | A CACC Fleet Trajectory Planning Method Based on Spatial Discretization |
| Publication number | Publication date |
|---|---|
| CN105083333B (en) | 2017-03-15 |
| CN106853833A (en) | 2017-06-16 |
| CN106672028A (en) | 2017-05-17 |
| CN106828546A (en) | 2017-06-13 |
| CN105083333A (en) | 2015-11-25 |
| CN106777833A (en) | 2017-05-31 |
| Publication | Publication Date | Title |
|---|---|---|
| CN105083333B (en) | Subway traffic flow optimization control method | |
| CN105083335B (en) | Subway traffic flow optimization control method | |
| Jin et al. | Platoon-based multi-agent intersection management for connected vehicle | |
| CN105083334B (en) | Subway train collision early warning method | |
| CN105095984B (en) | Real-time prediction method for subway train track | |
| CN105678411B (en) | A method for compiling an operation plan diagram of a passenger train | |
| Chen et al. | Real-time bus holding control on a transit corridor based on multi-agent reinforcement learning | |
| CN103208034A (en) | Rail transit passenger flow distribution predicting model building method and predicting method | |
| CN105083322B (en) | Subway train collision early warning method | |
| CN111785088A (en) | A two-layer collaborative optimization method for ramp merging of connected vehicles | |
| CN117252304A (en) | Rail transit congestion propagation assessment and control method considering large passenger flow early warning information | |
| CN116050669A (en) | Intelligent scheduling method and system for urban rail transit emergency | |
| CN105095983B (en) | Real-time prediction method for subway train track | |
| CN105093929B (en) | Planning method for conflict resolution of subway train | |
| Chu et al. | An ontology-based service model for smart infrastructure design | |
| khattak | Simulation-based particle swarm optimization technique for the breadth design of stairs and passageway network at interchange stations | |
| Huang et al. | Research on formation control of multi intelligent driving vehicles based on swarm motion | |
| Hajbabaie et al. | Dynamic Speed Harmonization in Connected Urban Street Networks: Improving Mobility | |
| Vu | Decentralised congestion control mechanisms for autonomous vehicles using distributed constraints optimisation | |
| Hajbabaie et al. | Center for Advanced Multimodal Mobility Solutions and Education | |
| Theodora | Comparison of Decentralized and Centralized Signal Control Methods on a Large-Scale Urban Network |
| 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:20170613 |