Automatic Driving Operation Strategy of Urban Rail Train Based on Improved DQN Algorithm

To realize a better automatic train driving operation control strategy for urban rail trains,an automatic train driving method with improved DQN algorithm(classical deep reinforcement learning algorithm)is proposed as a research object.Firstly,the train control model is established by considering the train operation requirements.Secondly,the dueling network and DDQN ideas are introduced to prevent the value function overestimation problem.Finally,the priority experience playback and“restricted speed arrival time”are used to reduce the useless experience utilization.The experiments are carried out to verify the train operation strategy method by simulating the actual line conditions.From the experimental results,the train operation meets the ATO requirements,the energy consumption is 15.75%more energy-efficient than the actual operation,and the algorithm convergence speed is improved by about 37%.The improved DQN method not only enhances the efficiency of the algorithm but also forms a more effective operation strategy than the actual operation,thereby contributing meaningfully to the advancement of automatic train operation intelligence.

Predictive Control Algorithm for Urban Rail Train Brake Control System Based on T-S Fuzzy Model

Urban rail transit has the advantages of large traffic capacity,high punctuality and zero congestion,and it plays an increasingly important role in modern urban life.Braking system is an important system of urban rail train,which directly affects the performance and safety of train operation and impacts passenger comfort.The braking performance of urban rail trains is directly related to the improvement of train speed and transportation capacity.Also,urban rail transit has the characteristics of high speed,short station distance,frequent starting,and frequent braking.This makes the braking control system constitute a time-varying,time-delaying and nonlinear control system,especially the braking force changes directly disturb the parking accuracy and comfort.To solve these issues,a predictive control algorithm based on T-S fuzzy model was proposed and applied to the train braking control system.Compared with the traditional PID control algorithm and self-adaptive fuzzy PID control algorithm,the braking capacity of urban rail train was improved by 8%.The algorithm can achieve fast and accurate synchronous braking,thereby overcoming the dynamic influence of the uncertainty,hysteresis and time-varying factors of the controlled object.Finally,the desired control objectives can be achieved,the system will have superior robustness,stability and comfort.

Operation Optimal Control of Urban Rail Train Based on Multi-Objective Particle Swarm Optimization

The energy consumption of train operation occupies a large proportion of the total consumption of railway transportation.In order to improve the oper-ating energy utilization rate of trains,a multi-objective particle swarm optimiza-tion(MPSO)algorithm with energy consumption,punctuality and parking accuracy as the objective and safety as the constraint is built.To accelerate its the convergence process,the train operation progression is divided into several modes according to the train speed-distance curve.A human-computer interactive particle swarm optimization algorithm is proposed,which presents the optimized results after a certain number of iterations to the decision maker,and the satisfac-tory outcomes can be obtained after a limited number of adjustments.The multi-objective particle swarm optimization(MPSO)algorithm is used to optimize the train operation process.An algorithm based on the important relationship between the objective and the preference information of the given reference points is sug-gested to overcome the shortcomings of the existing algorithms.These methods significantly increase the computational complexity and convergence of the algo-rithm.An adaptive fuzzy logic system that can simultaneously utilize experience information andfield data information is proposed to adjust the consequences of off-line optimization in real time,thereby eliminating the influence of uncertainty on train operation.After optimization and adjustment,the whole running time has been increased by 0.5 s,the energy consumption has been reduced by 12%,the parking accuracy has been increased by 8%,and the comprehensive performance has been enhanced.

Study on Optimization of Urban Rail Train Operation Control Curve Based on Improved Multi-Objective Genetic Algorithm

A multi-objective improved genetic algorithm is constructed to solve the train operation simulation model of urban rail train and find the optimal operation curve.In the train control system,the conversion point of operating mode is the basic of gene encoding and the chromosome composed of multiple genes represents a control scheme,and the initial population can be formed by the way.The fitness function can be designed by the design requirements of the train control stop error,time error and energy consumption.the effectiveness of new individual can be ensured by checking the validity of the original individual when its in the process of selection,crossover and mutation,and the optimal algorithm will be joined all the operators to make the new group not eliminate on the best individual of the last generation.The simulation result shows that the proposed genetic algorithm comparing with the optimized multi-particle simulation model can reduce more than 10%energy consumption,it can provide a large amount of sub-optimal solution and has obvious optimization effect.

Optimization of train plan for urban rail transit in the multi-routing mode

The train plan of urban rail transit under multi-routing mode can be divided into three parts： train formation, train operation periods and corresponding train counts of each routing in each period. Based on the analysis of passen- ger＇s general travel expenses and operator＇s benefits, the constraints and objective functions are defined and the multiobjective optimization model for the train plan of urban rail transit is presented. Factors considered in the multi- objective optimization model include transport capacity, the requirements of traffic organization, corporation benefits, passenger demands, and passenger choice behavior under multi-train-routing mode. According to the characteristics of this model and practical planning experience, a three-phase solution was designed to gradually optimize the train formarion, train counts as well as operation periods. The instance of Changsha Metro Line 2 validates the feasibility and efficiency of this approach.

Urban rail departure capacity analysis based on a cellular automaton model

As an important traffic mode, urban rail transit is constantly developing toward improvement in service capacity and quality. When an urban rail transit system is evaluated in terms of its service capacity, the train departure capacity is an important index that can objectively reflect the service level of an urban rail transit facility. In light of the existing cellular automaton models, this paper proposes a suitable cellular automaton model to analyze the train departure capacity of urban rail transit under different variable factors and conditions. The established model can demonstrate the train operating processes by implementing the proposed sound rules, including the rules of train departure at the origin and intermediate stations, and the velocity and position updating rules. The properties of train traffic are analyzed via numerical experiments. The numerical results show that the departure capacity is negatively affected by the train departure control manner. In addition, （i） the real-time signal control can offer a higher train service frequency; （ii） the departure capacity gradually rises with the decrease in the line design speed to a limited extent; （iii） the departure capacity decreases with extension in the train length; （iv） the number of departed trains decreases as the train stop time increases; （v） the departure capacity is not affected by the section length. However, the longer the length, the worse the service quality of the urban rail transit line. The experiments show that the proposed cellular automaton model can be used to analyze the train service capacity of an urban rail transit system by performing quantitative analysis under various considered factors, conditions, and management modes.

基于车车通信列控系统的城市轨道交通列车运行效率分析

[目的]城市轨道交通T2T(车车通信)列控系统是一种新型的信号系统,其通过资源化管理方式对轨旁设备进行管控。为了验证该系统的优越性,需对该系统下的列车运行效率进行分析。[方法]针对T2T列控系统,基于资源管理层面和安全防护原理的特点,在折返工况下,将原本由联锁控制的双动道岔转变为两个单动道岔,并基于列车精确自定位实现ATP(列车自动防护),提高了岔区线路资源的使用能力;在区间和车站追踪工况下,通过前后车对于车速、加速度、所处线路位置等信息的实时互传,利用相对速度安全防护原理进一步缩小了列车的追踪间隔。通过上述两方面的技术革新,结合城市轨道交通线路的实际数据,对站后交叉渡线折返、站前单渡线折返、区间与车站追踪等运营场景进行了模拟仿真计算,确定了T2T列控系统的折返能力和区间追踪能力。[结果及结论]相较传统的CBTC(基于通信的列车控制系统),T2T列控系统在折返能力、追踪能力等方面均有着显著提升,更加适应于超大运量的城市轨道交通线路;T2T列控系统架构简单,轨旁设备少,尤其适合城市轨道交通的大修改造项目。

不同牵引特性城轨列车车轮磨耗与疲劳研究

针对列车频繁牵引起动对车轮磨耗与疲劳损伤产生的影响问题,在恒定牵引力的基础上,探究了不同牵引特性曲线恒功率区转折点速度对车轮磨耗与疲劳的影响规律。采用SIMPACK和MATLAB软件进行联合仿真,建立了不同牵引特性下城轨列车动力学模型和基于Archard的车轮磨耗模型,分析在牵引电机不同起动转矩下牵引特性曲线恒功率区转折点速度对城轨列车轮轨蠕滑率、车轮磨耗深度、磨耗面积以及疲劳指数的影响规律。结果表明:列车牵引起动过程中,电机起动转矩越大,轮轨蠕滑率、车轮磨耗深度和磨耗面积也越大,而疲劳指数则越小;电机起动转矩一定时,随着列车牵引特性曲线恒功率区转折点速度的增大,轮轨蠕滑率、车轮磨耗深度和磨耗面积也增大,疲劳指数则有所减小;当电机起动转矩从800 N·m增大到1400 N·m,车轮磨耗深度和磨耗面积增长率最大为6.9%和12.6%,而疲劳指数下降率最大为7.2%;当恒功率区转折点速度从50 km/h增加到80 km/h,车轮磨耗深度和磨耗面积增长率最大为4.4%和4.3%,疲劳指数下降率最大为1.9%。本文研究了车辆起动转矩与恒功率转折点速度变化对车轮磨耗与疲劳的影响规律,可为车辆牵引特性设计和电机控制以及车轮运维提供参考。

基于Sarsa算法的城轨列车节能控制策略研究

针对城市轨道交通节能运行问题,提出一种基于Sarsa强化学习算法的城轨列车节能控制策略,实现了城轨列车在自动驾驶状态下,面对不同路况,执行减少能源消耗驾驶策略的同时兼顾准时性和舒适性。根据线路条件将列车状态进行离散化处理,将连续的驾驶过程分为若干个子区间进行分段求解。结合区间限速、初始状态、终末状态等限制条件,基于能耗及运行时间分别构造适当的奖励函数。同时,用当前状态下可达的最大速度与最小速度对可选速度集合进行限制,缩小探索空间,加快算法收敛。最后,通过对北京铁路亦庄线小红门站至肖村站的实例进行仿真。实验结果表明,与传统的动态规划方法相比,Sarsa算法在满足舒适性和准时性要求的情况下节能9.32%。相比于强化学习中的Q学习算法,在速度的选取过程中,超速次数也有明显下降。仿真结果证明Sarsa算法具有更好的节能效果和安全性。在算法参数不变的情况下,调整限速条件,与传统动态规划算法进行二次对比,依旧节能4.21%,验证了算法的鲁棒性。

Preliminary Study on Selling Tickets in Reason for Last Trains on Beijing Rail Transit Network

With the increase of Beijing urban rail transport network, the structure of the road network is becoming more complex, and passengers have more travel options. Together with the complex paths and different timetables, taking the last train is becoming much more difficult and unsuccessful. To avoid losses, we propose feasible suggestions to the last train with reasonable selling tickets system.

面向虚拟连挂的城轨列车群组追踪运行仿真研究

城市轨道交通是解决城市交通拥堵问题最强有效的绿色交通方式,其高峰期客流激增且客流时空分布不均,而面向虚拟连挂的城轨列车动态灵活编组和群组追踪运行能有效满足复杂多变的城轨运营需求。本文剖析面向虚拟连挂的城轨列车群组追踪运行过程,给出虚拟连挂列车群组最小安全追踪距离计算公式;以单列标准车长的线路路段为一个元胞单元,设计速度及位移更新规则,构建基于元胞自动机的城轨列车群组追踪运行仿真模型;以某市地铁2号线为背景,多角度仿真刻画面向虚拟连挂的城轨列车群组追踪运行性能。仿真结果表明:面向虚拟连挂的城轨列车群组追踪运行模型能有效缩短列车最小安全追踪间隔时间,城轨线路通过能力较移动闭塞制式提高78.4%;头车延迟引起的后续列车晚点总数量及总晚点时间更小,呈现出更佳的抗干扰性与恢复性能,且宜采用小编组列车实现虚拟连挂;动态混合编组的城轨列车群组追踪运行性能最佳,单一小编组的次之,大编组列车群宜在小编组列车群前面运行;城轨列车群组旅行速度总体上与平均站间距呈正相关;当列车发车间隔大于延迟时间时,平均站间距对列车群组的延迟影响不敏感,相反,则影响较为显著。研究结论能够为面向虚拟连挂的城轨列车群组追踪运行决策提供技术支撑。

城市轨道交通正交异性钢桥面板疲劳损伤系数研究

基于城市轨道交通正交异性钢桥面板疲劳性能的重要性,对国内多个城市的轨道交通的交通荷载进行了调研,发现各线路各时段的客流量差异较大,各线路的载客平均轴重与空车平均轴重的比值不同,比值为1.02~1.51。轨道交通因乘客流量带来的轴重比例变化相对较小,因此每一列车都对钢桥结构的疲劳有一定影响。研究了疲劳损伤系数的组成,基于不同的应力循环次数,提出了基于列车荷载作用频次的城市轨道交通桥梁的3个疲劳损伤系数。研究结果可为城市轨道交通钢桥的疲劳设计提供参考,并为规范的修订提供技术依据,对完善城市轨道交通钢桥疲劳设计具有理论意义。

城市轨道交通乘务交路方案编制的禁忌搜索优化方法

针对城市轨道交通普遍采用轮乘制、日班和两头班混合等特点,对城市轨道交通乘务交路方案编制问题进行研究,旨在降低乘务成本并提高乘务效率.首先,通过分析城市轨道交通乘务交路方案的构成要素,考虑值乘时长、值乘片段接续时间和接续地点等要求,构建值乘片段、值乘任务构成和乘务规则约束,由此建立以乘务组数量和总接续时间等综合指标最小化为目标函数的多目标0-1整数规划模型.然后,针对该模型设计禁忌搜索(Tabu Search,TS)算法进行求解,以先到先走(First-In-First-Out,FIFO)的就近指派原则得到初始解,并设计4种邻域变换策略,以提高邻域解的多样性,并构建基于多邻域结构的禁忌搜索求解算法,实现对乘务交路方案的优化.最后,以广州地铁7号线的乘务交路方案为例进行实例验证.研究结果表明:优化方案较实际运营方案的乘务作业段数和总接续时间分别降低了20%和4.94%,每个乘务作业段值乘列车数量从8.2列增加到10.3列,有效驾驶时间从5.4 h增加到5.8 h,优化方案的各项指标均得到显著提升.研究成果可以为城市轨道交通乘务计划编制提供理论和方法支持.

基于乘客服务水平和安全的城市轨道交通扣车方案评价

[目的]扣车是城市轨道交通发生长时间初始延误条件下经常采用的列车运行方案。为了评价该方案的合理性,需构建基于乘客服务和安全的扣车方案评价模型,并对扣车方案进行评价。[方法]考虑到乘客出行规律的复杂性和特殊性,制定了城市轨道交通扣车方案。构建了基于最大发车间隔、列车总延误时间、列车均衡性、终到延误列车数、滞留乘客数及乘客总旅行时间的扣车方案评价模型。选取上海某条轨道交通线路的4个区间,以早高峰小时的实际OD(起讫点)客流量为例进行计算。[结果及结论]计算表明,方案6下的综合评价指标最小,为最优扣车调整方案。该方案可以有效提高列车运行图的均衡性,减少滞留乘客的数量,降低车站的安全隐患。

城市轨道交通列车加开计划编制模型研究

本文主要研究城市轨道交通在计划编制阶段由于客流不均衡需要在初始运行图加开列车的问题,在确保列车运行安全降低运营成本的前提下合理地加开列车实现运输能力的灵活配置。将列车运行过程形式化描述为事件-活动网络,构建了分时段多目标优化列车加开计划编制模型,提出了启发式决策规则与禁忌搜索算法相结合的两阶段求解算法。结合地铁运行实际数据,在高峰时段和平峰时段分别构建不同算例场景,验证了模型和算法的可行性和有效性。

跨线条件下城市轨道交通列车交路计划优化方法

跨线运营是城市轨道交通重点发展方向。针对跨线条件下列车交路计划编制问题,通过构造乘客出行时空网络图准确刻画复杂交路下的客流行为,建立以最小化列车走行公里与乘客出行时间成本为目标的混合整数规划模型。模型以列车交路方案、开行比例与频率为决策变量,并针对跨线交路与本线交路的行车冲突,考虑非等间隔发车,确定列车发车时刻。设计基于交路及开行频率搜索与运行间隔协调的定制分解算法。案例结果表明,列车跨线方向与乘客换乘主方向一致时,跨线交路可同时提升企业运营与乘客出行效益。换乘出行导致的断面客流量差异是跨线交路开行方案设置的主要依据。研究结论可为运营企业制定列车交路计划提供依据,有助于提高网络运输效率。

基于加线技术的轨道交通临客开行计划优化模型

基于运行图加线技术构建适于计划性临客开行的运行线铺画方法.以运力与客流匹配度最大化、对原运行图调整最小化为优化目标,考虑行车安全、临客加线位置、开行时间域等约束,构建临客运行线铺画非线性整数规划模型,并对其线性转换以提高求解效率.以北京地铁8号线某大型活动散场大客流为场景进行案例分析,结果表明:所构建方法能够在既有运行图上有效铺画临客运行线,满足不同行车密度及停站模式下的临客开行需求.建议在较高密度行车条件下不采用“空车直达”停站模式.

城市轨道交通超长隧道双车追踪模式下火灾烟气控制与人员安全疏散研究

[目的]城市轨道交通发车间隔一般较短,在超长隧道内会出现同方向行驶两列列车的情况,一旦发生火灾容易造成重大财产损失和人员伤亡,因此需对超长隧道双车追踪模式下的火灾烟气蔓延规律和人员安全疏散策略进行研究。[方法]采用FDS(火灾动力学模拟)软件和Path-finder软件,建立超长隧道火灾模型和人员安全疏散模型,对双车追踪模式下的火灾烟气蔓延规律,以及人员疏散进行仿真分析。[结果及结论]双车追踪模式下,前车尾部着火,通过临界风速纵向通风可保证前车火灾安全;火源下游烟气前锋的蔓延速度为3.20 m/s,至600 s时烟气蔓延至后车,620 s时烟气可完全覆盖后车;烟气温度沿隧道纵向衰减很快,且温度衰减符合双指数模型规律。双车追踪模式下,减小联络通道间距可减少人员疏散总时间,对人员疏散时离开列车的时间影响不大;开启列车端门和疏散平台一侧车门,可显著减少人员疏散时间。在超长隧道双车追踪的最不利火灾场景下,人员疏散存在困难,可通过减小联络通道间距保障人员疏散安全。

考虑动态随机客流的城市轨道交通列车时刻表仿真优化

为更加精准刻画动态随机客流与列车时刻表编制间的复杂匹配过程,综合考虑乘客动态随机到达过程、列车容量限制、车内拥挤度对乘客上下车速率影响、停站时间动态调整和列车运行安全防护等重要运营特征,构建城市轨道交通列车运行离散仿真模型。在此基础上,建立以最小化乘客平均候车时间为目标的随机非线性优化模型,并设计一种基于仿真的有限差分随机逼近算法,用于优化城市轨道交通发车方案。以国内某条线路的实际运营数据为例验证仿真模型及优化方法,结果表明所构建模型及算法具有较好的优化效果和计算效率,优化后的列车实绩运行时刻能更好地适应客流需求的动态随机性,且在不增加发车频次的前提下有效降低乘客平均候车时间,提升城市轨道交通运营管理水平。

利用A2C-ac的城轨车车通信资源分配算法

在城市轨道交通列车控制系统中,车车(T2T)通信作为新一代列车通信模式,利用列车间直接通信来降低通信时延,提高列车运行效率。在T2T通信与车地(T2G)通信并存场景下,针对复用T2G链路产生的干扰问题,在保证用户通信质量的前提下,该文提出一种基于多智能体深度强化学习(MADRL)的改进优势演员-评论家(A2C-ac)资源分配算法。首先以系统吞吐量为优化目标,以T2T通信发送端为智能体,策略网络采用分层输出结构指导智能体选择需复用的频谱资源和功率水平,然后智能体做出相应动作并与T2T通信环境交互,得到该时隙下T2G用户和T2T用户吞吐量,价值网络对两者分别评价,利用权重因子β为每个智能体定制化加权时序差分(TD)误差,以此来灵活优化神经网络参数。最后,智能体根据训练好的模型联合选出最佳的频谱资源和功率水平。仿真结果表明,该算法相较于A2C算法和深度Q网络(DQN)算法,在收敛速度、T2T成功接入率、吞吐量等方面均有明显提升。