A study of tour-based mode choice based on a Support Vector Machine classifier

A new approach in recognizing travel mode choice patterns is proposed, based on the Support Vector Machine classification technique. The tour-based travel demand dataset that is analysed is for New York State, derived from the 2009 U.S. National Household Travel Survey. The main features characterizing each tour are the means used, travel-related variables and socioeconomic aspects. Results obtained demonstrate the ability to predict to some extent, in real settings where car use dominates, which tours are likely to be made by public transport or non-motorized means. Moreover, the flexibility of the technique allows assessing the predictive power of each feature according to the combination of travel means used in different tours. Potential applications range from activity-based travel choice simulators to search engines supporting personalized travel planners – in general, whenever ‘best guesses’ on mode choice patterns have to be made quickly on large amounts of data prejudicing the possibility of setting up a statistical model.     

基于变权综合原理的斜拉桥索力、线形状态评估

基于变权综合原理,建立斜拉桥索力、线形状态评估模型。以约束优化索力值为基准值,引入索力上下限;以成桥线形作为基准值,以控制点的竖向允许位移高次插值形成线形评估的上下限。编制状态评估算法,利用变权综合原理和斜率关联度,以适度指标模型进行线性插值,并根据一组实测数据,对索力、线形状态进行评估。计算结果表明,随着均衡系数的减小,桥梁构件评估结果是一个加速退化的过程;变权模式作用下的变权权重越发散,评估结果的退化过程越剧烈,均衡系数-评分曲线的曲率越大。对于每个测点评分状态完全一致的桥梁构件,其均衡系数-评分曲线的曲率恒等于0,即评估结果将与均衡系数的取值无关,数值模拟结果与预测基本吻合。     

模式识别技术在桥梁状态评估与安全监测中的应用

将模式识别技术应用于桥梁结构状态评估与安全监测中,提出修正的欧氏距离与相似系数两种对响应信号特征向量进行统计分析的量化参数。提取出能较好反映出桥梁结构状态的特征参数,组合成特征向量。选择正常使用状态下多次实测数据特征向量的平均值作为基准状态,分别计算其他各次实测数据的特征向量,得到各次实测情况下特征向量与基准状态下特征向量之间修正的欧氏距离与相似系数。对桥梁正常运营状态进行监测,可得到修正的欧氏距离与相似系数的统计容许范围,作为桥梁结构状态评估的经验数字依据。     

AES算法及其实现技术

章在简述AES算法产生背景的基础上对算法进行了分析，对算法的具体实现方法进行了说明，给出了算法的测试数据。最后，采用分割运算的方法对算法的并行处理性能进行了估测。     

基于滑模观测器的LSLSM位置辨识研究

基于长定子直线同步电机(LSLSM)的磁浮列车在中高速运行时,传统的车载位置传感器无法准确获取电机位置信息,并且位置信息易受到干扰,为此提出基于滑模观测器的位置辨识方法。在分析滑模观测器对定子电阻、d轴电感和q轴电感参数敏感性基础上,采用一种基于q轴电感校正的LSLSM位置辨识方法,可提高位置观测精度和系统可靠性。通过数字仿真和磁浮试验线验证了所提方法的正确性。     

400km·h^-1高速铁路无砟轨道基床结构及关键参数研究

为掌握列车荷载作用下路基应力概率分布特征,进行基于我国高速铁路无砟轨道不平顺谱条件下的车辆-线路耦合动力学计算;以路基累积变形效应区不超过基床范围为原则,分析基床厚度与基床以下路基性质的相互关系;结合模型试验获得的填料累积变形状态阈值,基于强度、变形、应变控制准则,进行400km·h^-1行车条件下的无砟轨道基床结构及关键参数研究。结果表明:路基面承受的列车荷载随轨面平顺性呈明显的随机变化特征,动力影响系数服从正态分布,轨道极端不平顺引起的最大动力影响系数为2.146,平均轨道谱下的常遇动力影响系数为1.491;路基累积变形效应区范围随填料强度降低而扩大,基床厚度为2.7m时,由低塑性土填筑的基床以下路基K30应大于等于100MPa·m^-1;以调控累积变形处于快速收敛状态为目标,提出基床表层采用0.7~0.3m厚级配碎石进行强化处理,K30大于等于190 MPa·m^-1,底层选用A,B组填料,相应K30控制值为130~150MPa·m^-1。     

用于城市轨道交通车辆永磁同步电机控制的一种新型滑模观测器

针对传统滑模观测器无法满足城市轨道交通车辆永磁同步电机无传感器控制的精度问题,使用了一种新型滑模观测器。通过建立城市轨道交通车辆永磁同步电机数学模型,在采用Sigmoid函数消除抖振的同时,引入反电动势观测器来估算反电动势值,消除了相位滞后;并采用指数趋近律代替传统等速趋近律。仿真和试验结果表明,与传统滑模观测器相比,新型滑模观测器能更好地抑制抖振,具有更好的观测精度和鲁棒性,达到了城市轨道交通车辆用永磁同步电机无传感器技术的控制要求。     

轨道电路智能短路装置研制与开发

轨道电路智能短路装置,其轨面吸合采用扼铁磁回路封闭吸合模式,恒流有源检测方式,不受轨道电路送、受端方向的限制;应用数字滤波技术,降低了交流轨道电路对分路线检测精度的干扰;运用软、硬件技术,实现分路线的分路状态在线检测功能,彻底消除了轨道电路分路防护存在的不安全隐患。     

纯电动汽车动力锂电池SOC估计策略综述

电池管理系统(BMS)采用了防止电池过放电和过充,提供电池均衡控制,能够实现新能源汽车动力锂电池的最佳利用和保护。电池管理系统实时精准估算电池电荷状态(SOC)是提高电动汽车续航里程和延长寿命的关键。然而,SOC不能直接测量,动力电池的充、放电又是一个复杂过程,导致目前现有的SOC估算策略很难精确地估算出实时在线SOC值。因此,如何提高SOC估算精度是当下BMS领域的研究热点。本文通过对各种SOC估算方法进行文献综述,分析和总结各个SOC估算方法的原理及优缺点,提出SOC估计策略未来发展趋势。     

Using the lead vehicle as preview sensor in convoy vehicle active suspension control

Both ride quality and roadholding of actively suspended vehicles can be improved by sensing the road ahead of the vehicle and using this information in a preview controller. Previous applications have used look-ahead sensors mounted on the front bumper to measure terrain beneath. Such sensors are vulnerable, potentially confused by water, snow, or other soft obstacles and offer a fixed preview time. For convoy vehicle applications, this paper proposes using the overall response of the preceding vehicle(s) to generate preview controller information for follower vehicles. A robust observer is used to estimate the states of a quarter-car vehicle model, from which road profile is estimated and passed on to the follower vehicle(s) to generate a preview function. The preview-active suspension, implemented in discrete time using a shift register approach to improve simulation time, reduces sprung mass acceleration and dynamic tyre deflection peaks by more than 50% and 40%, respectively. Terrain can change from one vehicle to the next if a loose obstacle is dislodged, or if the vehicle paths are sufficiently different so that one vehicle misses a discrete road event. The resulting spurious preview information can give suspension performance worse than that of a passive or conventional active system. In this paper, each vehicle can effectively estimate the road profile based on its own state trajectory. By comparing its own road estimate with the preview information, preview errors can be detected and suspension control quickly switched from preview to conventional active control to preserve performance improvements compared to passive suspensions.