考虑支路路段双向车流相互影响的单向交通组织优化

考虑支路路段双向车流相互影响的因素,从道路负荷与公平性的角度出发,优化单向交通组织方案。建立一主多从的双层规划模型,上层规划是多目标规划,以单行交通组织方案为决策,以路段饱和度超限量最小化降低道路负荷、以车辆绕行系数最小化提高公平性。下层规划是考虑支路路段双向车流相互影响的均衡交通分配(每个点对之间的最短路各自由1个下层规划确定,但所有下层规划确定的最短路可一次性求解)。双层规划可用模拟退火算法求解,求解效果明显优于支路路段通行能力等量划分为双向分道行驶的传统优化方法。     

遗传算法在五连杆悬架优化中的应用

针对五连杆悬架的特点，运用多体系统动力学的理论建立了悬架的运动学分析模型，基于遗传算法开发了优化器的核心单元，并解决了它们之间的通讯和协调问题以实现在车轮上下跳动过程中车轮外倾角的运动学特性变化量与目标值之间的偏差最小作为优化设计的目标，说明了遗传算法在五连杆悬架优化中的应用。应用这种优化体系对某型轿车五连杆悬架进行了实例优化分析。     

液压半主动悬架的自适应神经网络控制

提出了液压半主动悬架系统的自适应神经网络控制策略 ,分析了系统模型及自适应神经网络控制器的设计和实现 ,并对控制效果进行了仿真研究。结果表明通过这种控制策略可以得到比较好的控制效果。     

基于神经网络实现交叉口多相位模糊控制

根据城市交叉口交通流的特点，给出了一种交叉口多相位自适应控制算法，综合考虑相邻车道上的车队长度，利用多层BP神经网络实现了道路交叉口多相位模糊控制。仿真结果表明，所设计的模糊神经网络控制器能有效地减少单交叉口平均车辆延误，具有较强的学习和泛化能力。     

遗传算法在区段站到发线的应用研究

为解决车站到发线的合理运用问题，采用遗传算建立了到发线运用的染色体结构和适应度函数，对这种复杂的非线性组合优化问题进行了仿真。     

基于人工神经网络的柴油机故障诊断

故障诊断是计算机模式识别领域的一个活跃课题。文中提出了基于人工神经网络的柴油机故障诊断方法，设计了适合该诊断系统的BP网络结构，并给出了一种基于黄金分割法改进的BP算法，用来自适应调整网络学习速率。仿真结果表明：该算法具有很快的学习速度和较高的学习精度，完全适用于柴油机故障诊断系统。     

基于自适应遗传算法的路堤边坡稳定性分析方法

基于圆弧滑动面假定,提出了一种用自适应遗传算法搜索最危险滑动面及其对应的最小安全系数的新方法。该方法是一种改进的遗传算法,采用自适应求取适值、动态调整交叉率和变异率、自适应区间收缩。自适应遗传算法有效克服了传统方法易陷入局部极小的缺陷,提高了算法的搜索效率、精度和稳定性。     

Consumer preferences and willingness to pay for advanced vehicle technology options and fuel types

The automotive industry is witnessing a revolution with the advent of advanced vehicular technologies, smart vehicle options, and fuel alternatives. However, there is very limited research on consumer preferences for such advanced vehicular technologies. The deployment and penetration of advanced vehicular technologies in the marketplace, and planning for possible market adoption scenarios, calls for the collection and analysis of consumer preference data related to these emerging technologies. This study aims to address this need, offering a detailed analysis of consumer preference for alternative fuel types and technology options using data collected in stated choice experiments conducted on a sample of consumers from six metropolitan cities in South Korea. The results indicate that there is considerable heterogeneity in consumer preferences for various smart technology options such as wireless internet, vehicle connectivity, and voice command features, but relatively less heterogeneity in the preference for smart vehicle applications such as real-time traveler information on parking and traffic conditions.     

Modeling duration choice in space–time multi-state supernetworks for individual activity-travel scheduling

Multi-state supernetworks have been advanced recently for modeling individual activity-travel scheduling decisions. The main advantage is that multi-dimensional choice facets are modeled simultaneously within an integral framework, supporting systematic assessments of a large spectrum of policies and emerging modalities. However, duration choice of activities and home-stay has not been incorporated in this formalism yet. This study models duration choice in the state-of-the-art multi-state supernetworks. An activity link with flexible duration is transformed into a time-expanded bipartite network; a home location is transformed into multiple time-expanded locations. Along with these extensions, multi-state supernetworks can also be coherently expanded in space–time. The derived properties are that any path through a space–time supernetwork still represents a consistent activity-travel pattern, duration choice are explicitly associated with activity timing, duration and chain, and home-based tours are generated endogenously. A forward recursive formulation is proposed to find the optimal patterns with the optimal worst-case run-time complexity. Consequently, the trade-off between travel and time allocation to activities and home-stay can be systematically captured.     

Air traffic assignment to reduce population noise exposure using activity-based approach

Aircraft noise has been regarded as one of the major environmental issues related to air transport. Many airports have introduced a variety of measures to reduce its impact. Several air traffic assignment strategies have been proposed in order to allocate noise more wisely. Even though each decision regarding the assignment of aircraft to routes should consider population exposure to noise, none of the air traffic assignment strategies has addressed daily migrations of population and number of people exposed to noise. The aim of this research is to develop a mathematical model and a heuristic algorithm that could assign aircraft to departure and arrival routes so that number of people exposed to noise is as low as possible, taking into account temporal and spatial variations in population in an airport’s vicinity. The approach was demonstrated on Belgrade airport to show the benefits of the proposed model. Numerical example showed that population exposure to noise could be reduced significantly by applying the proposed air traffic assignment model. As a consequence of the proposed air traffic assignment, overall fuel consumption increased by less than 1%.