Practicability study on the suitability of artificial,neural networks for the approximation of unknown steering torques

For steer-by-wire systems, the steering feedback must be generated artificially due to the system characteristics. Classical control concepts require operating-point driven optimisations as well as increased calibration efforts in order to adequately simulate the steering torque in all driving states. Artificial neural networks (ANNs) are an innovative control concept; they are capable of learning arbitrary non-linear correlations without complex knowledge of physical dependencies. The present study investigates the suitability of neural networks for approximating unknown steering torques. To ensure robust processing of arbitrary data, network training with a sufficient volume of training data is required, that represents the relation between the input and target values in a wide range. The data were recorded in the course of various test drives. In this research, a variety of network topologies were trained, analysed and evaluated. Though the fundamental suitability of ANNs for the present control task was demonstrated.     

A self-regulation traffic-condition-based route guidance strategy with realistic considerations: Overlapping routes,stochastic traffic,and signalized intersections

Variable message signs that provide various types of route guidance information have been widely deployed in large cities. To release proper information only using easily collected data, a simple traffic-condition-based (TCB) route guidance strategy was recently proposed. The strategy works based on the estimation of free-flow and congested traffic conditions and is capable of approximating user optimal equilibrium stably. Due to little consideration of the complexity of urban road networks, the TCB strategy is still away from field applications in urban areas. To further push the strategy toward field tests, this article improves the TCB strategy in the following aspects: supplementing the strategy with a self-regulation ability by considering existing traffic conditions; decomposing link capacity to solve the problem of overlapping routes by comparing link capacity on alternative routes; coping with stochastic traffic; and the impact of signalized intersections by utilizing aggregated data. A scenario for an urban road network in Beijing, China, is simulated to test the improved strategy, and the simulation results clearly indicate the effectiveness of the proposed improvements. The improvements extend the TCB strategy on moderately complicated urban road networks, and still have the advantages of simple diversion rules, easily obtained input data, and stable and effective diversion processes.     

过饱和道路交通控制信号周期优化解分析

分析了过饱和交通条件下城市道路信号控制交叉口周期参数值的优化解。以拥挤消散时间和路网总延误为控制目标,采用定时信号控制策略,基于元胞传输模型建立了路网优化控制模型,并采用遗传算法优化信号配时,对比了不同信号周期条件下拥挤消散时间和路网总延误的变化规律。最后,本文以某市L路为算例分析了周期值与消散时间及路网总延误的关系,结论表明路网在过饱和拥堵条件下,当控制周期大于某一临界周期值时,相位差和绿信比的优化将无法抑制消散时间的持续增长趋势;最优配时结果的路网总延误值比采用传统最大周期控制策略的路网总延误值降低17％以上。     

汽车车内噪声有源控制技术

有源噪声控制技术是目前国内外噪声控制界的研究热点。对有源噪声控制的概念、原理和实现作了介绍。根据有源控制方法对于低频噪声控制的优势,结合车内噪声的特点和现代控制领域的理论发展,讨论了在车内应用有源噪声控制技术的可行性,提出了一条可行的技术路线。     

一种区域公路交通线圈检测器优化布设的简捷方法

利用数学方法优化布设交通检测器难在求解困难。提出根据检测器布设的目的从总体上把握区域公路网的交通状况,可以简单快速的实现区域公路交通线圈检测器的优化布设。     

基于RBF神经网络桩土荷载分担比计算研究

将神经网络理论应用在桩土荷载分担比计算领域,借助自控领域信号处理的思路,利用高度的非线性拟合和预测功能,应用径向基函数神经网络的映射模式进行桩土荷载分担比的计算.经分析和实例验证,说明使用RBF神经网络来计算桩土分担荷载比是可行的.     

多用户多准则城市交通网络非稳定均衡分析

为了反映现实中交通出行者实施出行与否的决策过程,通过对实际城市交通网络状态的分析,引入了非稳定均衡网络状态的概念。同时通过对出行者出行选择行为的深入分析,引入了多用户多准则非稳定均衡网络状态的非线性互补问题模型和变分不等式模型,并利用超级网络的概念证明了两者的等价性。新模型能够将出行者的路径选择决策、目的地选择决策、出行方式选择决策以及出行与否决策合理的整合在一起,从而可完整的反映城市交通流的形成模式。给出了求解多用户非稳定均衡态的变分不等式模型的修正投影算法,并通过一个数值例子验证了算法的有效性。结论部分给出了多个可进一步深入研究的方向。     

BP神经网络在路面模量反分析中的应用

使用MATLAB神经网络工具箱研究了BP神经网络在路面模量反分析中的应用。研究结果表明,只要合理的处理输入和输出参数,利用BP神经网络可以较好的预测路面各层的弹性模量,并且相对于其他分析方法,该方法运算速度非常快,适合于实际工程中应用。     

基于神经网络的公交客流预测

公交客流量具有动态性,受多种因素的影响,不能或无法用精确的数学模型进行预测。通过对公交客流量预测的Elman和BP神经网络的建立、学习和训练。并以前三年的公交客流量、国内生产总值、工业总产值、城市人口数作为两种神经网络的输入神经元,第四年的公交客流量作为输出神经元,同时以合肥市公交客流量为例进行分析,结果表明：所建的Elman模型比EBP模型的预测精度高,效果好。     

新疆公路网现状分析与综合评价

利用公路网的主要评价指标对新疆公路网现状进行分析,同时以路网饱和度、网连通度、里程饱和率、网等级为指标,采用模糊综合评判法对新疆公路网的现状进行综合评价,结果表明,新疆公路网现状属于中等水平,符合实际情况。