基于双目视觉计算的车辆跟驰状态实时感知系统

双目视觉技术能够实现目标的识别与距离计算，在自动驾驶领域有很大的应用空间。然而，现阶段双目视觉存在光照干扰、遮挡、弱纹理区域歧义匹配等问题，影响其测量的准确性和可靠性。提出基于双目视觉的跟驰状态实时感知系统，该系统采用基于车辆跟驰模型的扩展卡尔曼滤波方法对车辆跟驰状态进行实时估计，包括跟驰距离、前后车速度差等。通过实际道路试验，证明了该系统能够识别并修正测量数据中的异常值，解决弱纹理区域误匹配问题。试验结果表明：25 mm焦距与12 mm焦距的双目系统跟驰间距测量值的平均误差分别为2.66%与9.14%；在相对速度测量方面，2种焦距系统的测量精度基本相同，平均误差均为1 m·s^-1左右。所提出的方法在自动驾驶车辆环境感知领域有较好的应用前景。     

城市雨水规划探讨

雨水规划对城市管网建设、河涌整治等相关工作有指导作用,文章从排水体制、排涝模数、雨水分区等三方面作了一些探讨,可供规划建设参考。     

多源激励水下复杂壳体结构振动与辐射声场试验研究

设计了一个接近实际情况的多舱段复杂壳体模型,安装小型机械设备,分别进行了单台设备激励与多台设备同时激励的水下复杂壳体振动与声辐射试验;试验结果表明,多源激励下水中复杂壳体的结构响应、辐射声场近似为单源激励下结构响应、辐射声场的非相干叠加.然后从结构声辐射理论上推导了激励源与结构响应、辐射声场之间的传递关系,并以两个源激励为例分析了非相干叠加引起的误差,从而解释了多源激励下结构响应、辐射声场近似为单源激励下结构响应、辐射声场非相干叠加的合理性.这些研究表明,非相干叠加方法可推广应用于水下复杂壳体在多源激励情况下的振动与声场计算,对指导工程设计具有重要价值.     

开发国产300 km/h以上速度动车组的设想

讨论了CRH系列动车组消化吸收再创新的总体目标与主要思路。提出了国产300km/h以上速度动车组的技术创新总体方案的初步设想和技术路线,以及需要研究解决和完成的主要任务、具体内容与所要达到的技术指标。     

无源滤波器在开关电源设计中的应用

传导性电磁干扰是电气设备开关电源中的主要干扰源,所以电磁兼容性指标已经成为开关电源设计的重要参数。从开关电源的工作原理出发,对开关电源的电磁干扰机理进行分析,研究使用无源滤波技术减少电磁干扰。从实际应用角度对无源滤波器中电容、电感等元件的特性进行了分析,给出了实用电路和元件参数。无源滤波技术在轨道交通空调专用电源上的应用结果表明,使用无源滤波技术对电磁干扰有很好的抑制效果。     

Real-time freeway traffic state estimation based on extended Kalman filter: Adaptive capabilities and real data testing

This paper reports on real data testing of a real-time freeway traffic state estimator, with a particular focus on its adaptive capabilities. The pursued general approach to the real-time adaptive estimation of complete traffic state in freeway stretches or networks is based on stochastic macroscopic traffic flow modeling and extended Kalman filtering. One major innovative feature of the traffic state estimator is the online joint estimation of important model parameters (free speed, critical density, and capacity) and traffic flow variables (flows, mean speeds, and densities), which leads to three significant advantages of the estimator: (1) avoidance of prior model calibration; (2) automatic adaptation to changing external conditions (e.g. weather and lighting conditions, traffic composition, control measures); (3) enabling of incident alarms. These three advantages are demonstrated via suitable real data testing. The achieved testing results are satisfactory and promising for subsequent applications.     

基于约束卡尔曼滤波的短时交通流量组合预测模型

为了克服单一的交通流预测模型性能不稳定的问题,提出了基于约束卡尔曼滤波的短时交通流量组合预测模型。约束卡尔曼滤波组合预测模型以各单一预测模型的权重为状态变量,交通流量为观测变量,预测结果是单一预测模型的加权和,加权系数由约束卡尔曼滤波方程递推动态确定,最后通过广深高速公路上采集的交通流量数据对算法进行了验证。结果表明,在不同预测步长情况下,约束卡尔曼滤波组合预测模型要优于最佳的单一预测模型或与其持平,并且不受某一较差的预测模型影响,具有较高的鲁棒性。     

Measurements of car-body lateral vibration induced by high-speed trains negotiating complex terrain sections under strong wind conditions

Assessment of the vibration of high-speed trains negotiating complex sections of terrain under strong wind conditions is very important for research into the operation safety and comfort of passengers on high-speed trains. To assess the vibration of high-speed trains negotiating complex sections of terrain under strong wind conditions, we performed a field measurement when the train passes through typical sections of complex terrain along the Lanzhou–Xinjiang high-speed railway in China. We selected the lateral vibration conditions, including the roll angle and lateral displacement of car-body gravity centre through two typical representative sections (embankment–tunnel–embankment and embankment–rectangular transition–cutting) for analysis. The results show that the severe car-swaying phenomenon occurs when the high-speed train moves through the test section, and the car-body lateral vibration characteristic is related significantly to the state of the terrain and topography along the railway. The main causes for this car-swaying phenomenon may be the transitions between different windproof structures, and the greater the scale of the transition region between different windproof structures or landform changes, the more obvious the car-swaying phenomenon becomes. The lateral vibration of the car-body is relatively steady when the train is running through terrain with minor changes in topography, such as the windbreak installed on the bridge and embankment, but the tail car sways more violently than the head car. When the vehicle runs from the windbreak installed on the embankment into the tunnel (or in the opposite direction), the tail car sways more intensely than the head car, and the head car runs relatively stable in the tunnel.     

BP神经网络在解决电力消耗问题中的应用

由于BP神经网络在解决非线性复杂系统中存在很大的优势,以江西省1991—2011年人口、经济和耗电量等数据为研究对象,利用BP神经网络构建耗电量预测模型。模型一利用1991—2009年人口、经济和耗电量等数据作为训练样本,以2010—2011年作为测试样本来验证网络的准确性,再根据历史人口、经济等数据来预测历史耗电量;模型二采用传统的多元回归分析法,对非线性多元函数进行多元线性回归,通过回归模型得到的参数来预测耗电量。结果表明,模型一收敛性较好,所得预测结果绝对误差较小,而模型二传统方法得到的预测结果误差较大,因此,利用BP神经网络预测的结果具有非常大的参考价值,证明BP神经网络应用在电力消耗中的应用是可行的。     

基于"当前"统计模型的机动目标运动要素解算

在避碰过程中,舰船一般处于机动状态.因而,对机动目标运动要素解算的精度直接影响到避碰的效果.通过对多种模型的比较,选用了"当前"统计模型,"当前"统计模型相对于其他模型能够更为真实地反映目标的机动变化.仿真结果表明,此算法收敛迅速并有较高精度,其解算所得的目标运动要素能够满足舰船避碰等实用要求.