High-Speed Trains Automatic Operation with Protection Constraints: A Resilient Nonlinear Gain-based Feedback Control Approach

This paper addresses the control design for automatic train operation of high-speed trains with protection constraints.A new resilient nonlinear gain-based feedback control approach is proposed,which is capable of guaranteeing,under some proper non-restrictive initial conditions,the protection constraints control raised by the distance-to-go(moving authority)curve and automatic train protection in practice.A new hyperbolic tangent function-based model is presented to mimic the whole operation process of high-speed trains.The proposed feedback control methods are easily implementable and computationally inexpensive because the presence of only two feedback gains guarantee satisfactory tracking performance and closed-loop stability,no adaptations of unknown parameters,function approximation of unknown nonlinearities,and attenuation of external disturbances in the proposed control strategies.Finally,rigorous proofs and comparative simulation results are given to demonstrate the effectiveness of the proposed approaches.

Energy Saving for Automatic Train Control in Moving Block Signaling System

With rapid development of the railway traffic, the moving block signaling system （MBS） method has become more and more important for increasing the track capacity by allowing trains to run in a shorter time-headway while maintaining the required safety margins. In this framework, the tracking target point of the following train is moving forward with its leading train. This paper focuses on the energy saving tracking control of two successive trains in MBS. Nonlinear programming method is used to optimize the energy-saving speed trajectory of the following train. The real-time location of the leading train could be integrated into the optimization process. Due to simplicity, it can be used for online implementation. The feasibility and effectiveness are verified through simulation. The results show that the new method is efficient on energy saving even when disturbances present.

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.

Tracking performance of large margin classifier in automatic modulation classification with a software radio environment

Automatic modulation classification is the process of identification of the modulation type of a signal in a general environment. This paper proposes a new method to evaluate the tracking performance of large margin classifier against signal-tonoise ratio （SNR）, and classifies all forms of primary user＇s signals in a cognitive radio environment. For achieving this objective, two structures of a large margin are developed in additive white Gaussian noise （AWGN） channels with priori unknown SNR. A combination of higher order statistics and instantaneous characteristics is selected as effective features. Simulation results show that the classification rates of the proposed structures are well robust against environmental SNR changes.

Configuration Synthesis and Performance Analysis of 9‑Speed Automatic Transmissions

Current research of automatic transmission(AT)mainly focuses on the improvement of driving performance,and configuration innovation is one of the main research directions.However,finding new configurations of ATs is one of the main limitations of configuration innovation.In the present study,epicyclic gear trains(EGTs)are applied to investigate mechanisms of 9-speed ATs.Then four kinematic configurations are proposed for automatic transitions.In order to evaluate the performance of proposed mechanisms,the lever analogy method is applied to conduct kinematic and mechanical analyses.The power flow analysis is conducted,and then transmission efficiencies are calculated based on the torque method.The comparative analysis between the proposed and existing mechanisms is carried out where obtained results show that proposed mechanisms have reasonable performance and can be used in ATs.The prototype of an AT is manufactured and the speed test is conducted,which proves the accuracy of analysis and the feasibility of proposed mechanisms.

Joint On-Demand Pruning and Online Distillation in Automatic Speech Recognition Language Model Optimization

Automatic speech recognition(ASR)systems have emerged as indispensable tools across a wide spectrum of applications,ranging from transcription services to voice-activated assistants.To enhance the performance of these systems,it is important to deploy efficient models capable of adapting to diverse deployment conditions.In recent years,on-demand pruning methods have obtained significant attention within the ASR domain due to their adaptability in various deployment scenarios.However,these methods often confront substantial trade-offs,particularly in terms of unstable accuracy when reducing the model size.To address challenges,this study introduces two crucial empirical findings.Firstly,it proposes the incorporation of an online distillation mechanism during on-demand pruning training,which holds the promise of maintaining more consistent accuracy levels.Secondly,it proposes the utilization of the Mogrifier long short-term memory(LSTM)language model(LM),an advanced iteration of the conventional LSTM LM,as an effective alternative for pruning targets within the ASR framework.Through rigorous experimentation on the ASR system,employing the Mogrifier LSTM LM and training it using the suggested joint on-demand pruning and online distillation method,this study provides compelling evidence.The results exhibit that the proposed methods significantly outperform a benchmark model trained solely with on-demand pruning methods.Impressively,the proposed strategic configuration successfully reduces the parameter count by approximately 39%,all the while minimizing trade-offs.

基于Co-training的图像自动标注

图像自动标注是图像理解与模式识别等领域中具有挑战性的关键研究问题.目前图像自动标注领域存在着一些问题,如未标注数据规模要远大于标注数据规模,只能单独使用某种图像分割策略与某类图像表示方法.针对上述问题,提出了基于Co-training的图像自动标注方法,通过构建4个独立的特征属性进而建立4个子分类器,将不同的图像分割方法与特征表示方法整合到一个统一框架中,利用提出的基于投票与一致性相结合的自适应算法扩展原始训练集.该方法通过使用Co-training算法,利用大量未标注数据来提升图像自动标注的性能.通过在Corel 5K数据库上进行实验,验证了提出方法的有效性.

DIRECT FUZZY NEURAL CONTROL FOR TRAIN TRAVELING PROCESS

ＤＩＲＥＣＴＦＵＺＺＹＮＥＵＲＡＬＣＯＮＴＲＯＬＦＯＲＴＲＡＩＮＴＲＡＶＥＬＩＮＧＰＲＯＣＥＳＳ①ＷａｎｇＪｉｎｇ，ＣａｉＺｉｘｉｎｇ，ＪｉａＬｉｍｉｎＲｅｓｅａｒｃｈＣｅｎｔｅｒｆｏｒＩｎｔｅｌｌｉｇｅｎｔＣｏｎｔｒｏｌ，ＣｅｎｔｒａｌＳ...

Research on Optimization of Freight Train ATO Based on Elite Competition Multi-Objective Particle Swarm Optimization

In view of the complex problems that freight train ATO (automatic train operation) needs to comprehensively consider punctuality, energy saving and safety, a dynamics model of the freight train operation process is established based on the safety and the freight train dynamics model in the process of its operation. The algorithm of combining elite competition strategy with multi-objective particle swarm optimization technology is introduced, and the winning particles are obtained through the competition between two elite particles to guide the update of other particles, so as to balance the convergence and distribution of multi-objective particle swarm optimization. The performance comparison experimental results verify the superiority of the proposed algorithm. The simulation experiments of the actual line verify the feasibility of the model and the effectiveness of the proposed algorithm.

How to Deal with Revolutions in Train Control Systems

Train control systems ensure the safety of railways. This paper begins with a summary of the typical train control systems in Japan and Europe. Based on this summary, the author then raises the following question regarding current train control systems： What approach should be adopted in order to enhance the functionality, safety, and reliability of train control systems and assist in commercial operations on railways？ Next, the author provides a desirable architecture that is likely to assist with the development of new train control systems based on current information and communication technologies. A new unified train control system （UTCS） is proposed that is effective in enhancing the robustness and com- petitiveness of a train control system. The ultimate architecture of the UTCS will be only composed of essential elements such as point machines and level crossing control devices in the field. Finally, a pro- cessing method of the UTCS is discussed.

The influence of AAR coupler features on estimation of in-train forces

Inadequate management of large in-train forces transferred through coupler systems of a railway train leads to running and structural failures of vehicles.Understanding these phenomena and their mitigation requires accurate estimation of relative motions and in-train forces between vehicle bodies.Previous numerical studies have ignored inertia of coupling elements and the impacts between couplers.Thus,existing models underestimate the additional dynamic variations in in-train forces.Detailed multi-body dynamic models of two AAR(Association of American Railroads)coupler systems used in passenger and freight trains are developed,incorporating coupler inertia and various slacks.Due to the modeling and simulation com-plexities involved in a full train model,with such details of coupler system,actual longitudinal train dynamics is not studied.A system comprising only two coupling units,inter-connecting two consecutive vehicles,is modeled.Considered system has been fixed at one end and an excitation force is applied at the other end,to mimic a relative force transmission through combined coupler system.Simulation results obtained from this representative system show that,noticeable influence in in-train forces are expected due to the combined effect of inertia of couplers and intermittent impacts between couplers in the slack regime.Maximum amplitude of longitudinal reaction force,transferred from draft gear housing to vehicle body,is expected to be significantly higher than that predicted using existing models of coupler system.It is also observed that the couplers and knuckles are subjected to significant longitudinal and lateral contact forces,due to the intermittent impacts between couplers.Thus,accurate estimation of draft gear reaction force and impact forces between couplers are essential to design vehicle and coupler components,respectively.

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.

Automated Burned Scar Mapping Using Sentinel-2 Imagery

The Sentinel-2 satellites are providing an unparalleled wealth of high-resolution remotely sensed information with a short revisit cycle, which is ideal for mapping burned areas both accurately and timely. However, the high detail and volume of information provided actually encumbers the automation of the mapping process, at least for the level of automation required to map systematically wildfires on a national level. This paper proposes a fully automated methodology for mapping burn scars using Sentinel-2 data. Information extracted from a pair of Sentinel-2 images, one pre-fire and one post-fire, is jointly used to automatically label a set of training patterns via two empirical rules. An initial pixel-based classification is derived using this training set by means of a Support Vector Machine (SVM) classifier. The latter is subsequently smoothed following a multiple spectral-spatial classification (MSSC) approach, which increases the mapping accuracy and thematic consistency of the final burned area delineation. The proposed methodology was tested on six recent wildfire events in Greece, selected to cover representative cases of the Greek ecosystems and to present challenges in burned area mapping. The lowest classification accuracy achieved was 92%, whereas Matthews correlation coefficient (MCC) was greater or equal to 0.85.

机车充风能力对重载列车缓解性能及车钩力影响研究

机车充气与排气性能是列车制动系统重要指标,目前机车制动系统验收指标仅对排气性能有明确要求,对充气性能无要求。机车供风能力不仅影响重载列车缓解特性和车钩力,而且严重制约重载列车在循环制动中的操纵方法。了解机车充气能力对缓解特性和车钩力的影响规律,以及重载列车安全运行和制动系统设计具有重要意义。通过建立列车空气制动系统仿真模型,分析机车充风能力对重载列车缓解特性和车钩力的影响。分析发现,机车充风能力对列车再充风时间、缓解波传播和车钩力都有明显影响;充风能力越弱,则缓解波传递越慢,车钩力越大。在本文研究范围内,合适的充气能力将比弱充风能力首尾车缓解时间差缩短3 s,最大车钩力降低16.2%。建议机车验收时增加机车充风能力检测,并给出了建议检测标准。针对重载列车充风能力,建议多部门联合系统性开展实验与仿真研究,制订重载列车制动系统检测标准与方法。

具有未知时变参数城轨列车的精准停车鲁棒控制

列车运行情况复杂多变,使得列车质量、基本运行阻力及线路状况等参数难以精确获得且随着列车运行存在明显的时变特性。列车模型参数的不确定性和时变特性会对列车的精准停车性能产生重要的影响。在动车组多质点动力学模型的基础上,根据Lyapunov再设计方法设计了一种非线性列车鲁棒控制器。该控制器将系统中的不确定性因素视为等价干扰,并设计相应的鲁棒补偿项。根据参数的先验区间,设计的鲁棒补偿项能够抑制模型估计误差,使得列车的位置和速度跟踪误差快速收敛,最终实现精准停车的控制目标;同时,也证明了系统的最终一致有界稳定性。最后,选取城市轨道交通场景进行仿真验证,仿真结果表明:本文提出的控制方法在列车模型参数未知且时变情景下也能实现对期望停车曲线的快速、精确追踪,表现出较强的鲁棒特性。

自动飞行员复诵指令生成方法研究

为了提高效率,降低培训成本并推广使用计算机来取代管制模拟机中的飞行员席位,采用集成学习的策略来生成飞行员复诵指令。选用5个大规模预训练语言模型进行微调,并使用K折交叉验证来筛选出性能较好的4个模型作为基础模型来构建集成学习模型。所构建的集成学习模型在管制指令数据集上取得在本领域中的最优效果。在通用的ROUGE(recall-oriented understudy for gisting evaluation)评价标准中,取得R_(OUGE-1)=0.998,R_(OUGE-2)=0.995,R_(OUGE-L)=0.998的最新效果。其中,R_(OUGE-1)关注参考文本与生成文本之间单个单词的匹配度,R_(OUGE-2)则关注两个连续单词的匹配度,R_(OUGE-L)则关注最长公共子序列的匹配度。为了克服通用指标在本领域的局限性,更准确地评估模型性能,针对生成的复诵指令提出一套基于关键词的评价标准。该评价指标准基于管制文本分词后的结果计算各个关键词指标来评估模型的效果。在基于关键词的评价标准下,所构建模型取得整体准确率为0.987的最优效果,对航空器呼号的复诵准确率达到0.998。

城轨列车自动驾驶积分反步线性自抗扰控制

针对列车在外部干扰和不确定动态下的速度控制问题,设计了融合积分反步法和线性自抗扰的复合控制方案.首先,考虑列车具有强耦合性,为了更加符合列车真实的纵向动力学特性和受力情况,建立了具有时变系数的多质点模型.其次,为了降低参数调节的难度,跟踪微分器和扩张状态观测器均采用线性形式.跟踪微分器用于求取微分信号,同时具有滤波作用.利用跟踪微分器对虚拟控制量进行求导,正好可解决反步法中存在的“微分爆炸”问题.扩张状态观测器用于实时估计总和扰动.此外,利用积分反步法改进了误差反馈控制律,设计了一种积分反步线性自抗扰控制(IBS-LADRC)算法.最后,证明了观测误差的收敛性及闭环系统稳定性.结合杭州地铁6号线AH型动车组参数和实际线路数据进行仿真,并将IBSLADRC与反步法、线性自抗扰算法、PID控制进行对比,结果表明:IBS-LADRC方法下各动力单元速度误差均处在±0.04 km/h以内,加速度处在±1 m/s2以内,加速度和速度误差均变化较平稳;车钩力相对其他3类方法最小,变化也最平缓,最大车钩力仅为2 320 N;本文控制策略对列车期望速度具有较高的跟踪精度,有利于保证车钩安全,防止车钩断裂,并提高列车运行的安全性、平稳性及乘客舒适度.

融合GPT和知识图谱的洪涝应急决策智能问答系统研究

为提高生成式预训练语言大模型(generative pre-trained transformer, GPT)的应急管理信息分析能力,以实现洪涝灾害应急处置过程中的在线辅助决策,提出融合GPT和知识图谱的应急决策智能问答系统(KG-GPT)。改进GPT架构以识别问题中的关键信息,利用知识图谱推理应急领域知识并生成具有逻辑性的回答;结合洪涝灾害的实际应急决策问答数据集并编制演练脚本,使用自动评估和专家评估方法将本系统与GPT进行对比实验。研究结果表明:该系统成功融合应急领域知识图谱和GPT模型,能够深刻理解问题的背景信息并生成流畅回答;与GPT相比,该系统可为决策者提供更快速准确的在线辅助决策工具。研究结果可提升洪涝灾害应急信息分析和决策效率。

基于自适应终端滑模的高速列车迭代学习速度控制

针对高速列车的速度追踪控制问题,充分利用列车运行的重复性,考虑工程应用中迭代初始状态不同和复杂的外部环境,提出一种基于线性扩张状态观测器(LESO)的自适应非奇异终端滑模迭代学习控制算法,使系统在任意迭代初值时均能保证追踪精度。提出一种时变非奇异终端滑模面以抑制初态误差影响,采用LESO估计并补偿列车扰动,设计自适应迭代更新律估计LESO的观测误差,设计全饱和自适应迭代控制律计算输入并将其约束于允许范围内。建立类Lyapunov的复合能量函数,通过严格的数学分析证明其迭代域的差分负定性和有界性,证明所设计的时变滑模面可实现渐进收敛,并证明追踪误差在滑模面内可在有限时间内收敛至平衡点。将本文提出的算法与滑模控制、变增益迭代学习控制、自抗扰控制等算法进行比较。仿真结果表明:无论是否存在迭代初始误差,在相同的条件下,本文提出的算法较其他算法具有更强的抗干扰能力,速度追踪精度提高90%及以上,停车误差可迭代收敛至001 m。

工程训练模式下的火灾自动报警控制系统设计实践与探索

以工程训练中心的基础实践课程为主线,探索OBE模式下的火灾报警控制系统设计,即在基础实践技能篇的基础上,提出一种能够体现学生对电子元件、工具使用具有导向价值的实践项目,同时保持一定的可塑性和拓展性,设计一种基于AT89C51单片机的新型火灾自动报警装置,仿真实现了声光电一体化报警、烟雾浓度测量和温度测量显示等检测功能,进而培养学生的创新实践能力。