基于改进蚁群算法的城市交通最短路径算法

蚁群算法作为一种寻优性能良好的智能算法,是解决最短路径问题的一种有效的方式。但是,基本蚁群算法真接运用于交通网络中路径的寻优存在一些不足。文章针对基本蚁群算法的不足对其进行了改进,根据交通网络的特点限定了解的搜索范围和改进了蚁群算法的转移规则,并对信息素的更新规则作了改进。仿真实验结果表明,改进了的蚁群算法在求解最短路径时比基本蚁群算法性能有较大的提高。     

基于改进鱼群算法在管道最优抢修路径的研究

当油气管道发生安全事故时,为保证在最短的时间内达到事故现场,需选择最优的抢维修路径。文中提出了一种新型的最优路径计算方法——鱼群算法,并针对其在搜索空间、收敛性以及寻求最优解等方面存在的不足,提出了改进鱼群算法。结合实际工程案例,对鱼群算法和改进鱼群算法在相同循环次数下寻求最短路径做了对比,结果显示改进的鱼群算法成功率高、收敛快,具有一定的应用价值。     

基于增量搜索的车辆动态路径规划算法研究

D＊Lite算法是一种非常高效的增量搜索算法,适合于动态环境下的路径规划。文章基于D＊Lite算法的原理,对该算法的性能及应用于车辆路径规划的适用性进行改进,提高了算法的稳定性和结果的可靠性,并通过试验和算法评价验证了改进的D＊Lite算法在复杂、动态环境下规划路径的有效性。     

基于IDM的车辆弯道运动状态预测研究

弯道是道路交通安全事故频发的隐患路段之一,为快速准确预测车辆弯道运动状态,本研究基于智能驾驶员微观车辆跟驰模型(Intelligent Driver Model,IDM),通过弯道适应性改进,构建了车辆弯道运动状态预测算法.模型的弯道适应性改进考虑了弯道曲率半径、道路纵向坡度及驾驶员反应时间因素,并对改进优化后的预测算法进行参数标定,以保证预测算法能达到预期效果.     

基于改进蚁群算法的动态路径规划算法研究

针对交通导航最优路径问题,文章分析了传统蚁群算法的基本原理及其局限性,并为提高路径搜索效率,解决路径搜索初始阶段缺乏方向性、正反馈机制引发局部最优解的问题,提出了新的改进蚁群算法,通过信息素更新策略改进、启发因子改进和引入探索因子来寻求动态全局最优解。由MATLAB实验仿真可知,改进后的蚁群算法对比基本蚁群算法,在遍历相同道路网络节点时,其循环的平均路径长度和最短路径长度都较短,能够有效实现动态最短路径诱导,具有良好的收敛性和全局寻优性。     

车流波动理论在信号配时中的应用

道路交叉路口的信号配时计算,多采用F·韦伯斯特算法计算信号周期,但车辆在交叉路口停车会产生停车波。介绍了单点信号控制配时参数的F·韦伯斯特算法和车流波动理论,考虑到车辆排队产生的冲击波对红灯期间交叉路口内车辆排队长度的影响,通过车流波动理论计算路口车辆排队的实际长度,对F·韦伯斯特算法进行改进,提出了交叉路口信号控制中最短周期的计算公式,结果表明,改进的算法可以很好地应用在路口信号配时参数的计算中。     

基于改进蝙蝠算法的钢筋混凝土箱梁桥截面优化设计研究

桥梁截面尺寸参数改变会影响结构的整体重量及受力性能,在保证结构受力合理的前提下优化截面参数,可节约成本。文章基于改进的蝙蝠算法,结合有限元模型,对某已建钢筋混凝土箱梁桥截面进行优化设计,对比分析优化前后参数、挠度等数据变化情况。研究结果表明:改进蝙蝠算法改进了原始算法多样性不足、易于陷入局部最有解的缺陷;截面设计优化后,箱梁总体结构重量减少了9.2%,结构刚度有些许降低,挠度结果影响较小;优化后的桥梁整体结构安全可靠,使用阶段承载力满足要求。     

基于浮动车技术的高速公路地图匹配算法改进研究

地图匹配技术作为新一代智能交通系统中车辆导航方面的核心技术,提高其匹配效率,是有效提供车辆诱导,优化公众出行,精准交通服务信息的重要改进手段.本文针对高速公路上营运车辆的GPS信息,结合我国高速公路路网特点,重点研究了基于浮动车技术的高速公路地图匹配算法,通过引入距离判据、方向角判据及连通性判据进行地图匹配,并根据实例验证中的路网匹配情况对算法进行改进,使得匹配算法具有更强的适应性和更高的实效性.     

基于Kriging-NSGA-Ⅱ的大跨度斜拉桥多目标索力优化研究

文章针对大跨度斜拉桥的索力优化问题,提出了一种基于Kriging-NSGA-Ⅱ的多目标索力优化方法。以Kriging回归算法为基本模型建立了大跨度斜拉桥的结构代理模型,采用基于强度的非支配排序和动态交叉变异算子改进NASA-Ⅱ算法,求解考虑主梁弯曲应变和挠度双目标控制下的索力优化问题,并以某大跨度斜拉桥为工程背景验证了该方法的可行性。研究结果表明:Kriging模型对结构响应面的拟合良好;改进NSGA-Ⅱ算法可以实现对双目标索力优化问题的求解:优化后主梁弯曲应力和挠度得到明显改善。     

动态车辆路径问题的遗传算法研究

文章针对动态车辆路径的特点及模型对其算法进行了研究，并设计了改进的遗传算法对最优路径进行求解，结果显示采用改进的遗传算法提高了全局寻优能力与收敛速度，取得了较好的效果。     

More robust and better: a multiple kernel support vector machine ensemble approach for traffic incident detection

This paper presents a multiple kernel support vector machine (MKL‐SVM) ensemble algorithm to detect traffic incidents. It uses resampling technology to generate training set, test set, and training subset firstly; then uses different training subsets to train individual MKL‐SVM classifiers; and finally introduces ensemble methods to construct MKL‐SVM ensemble to detect traffic incidents. Extensive experiments have been performed to evaluate the performances of the four algorithms: standard SVM, SVM ensemble, MKL‐SVM, and the proposed algorithm (MKL‐SVM ensemble). The experimental results show that the proposed algorithm has the best comprehensive performances in traffic incidents detection. To achieve better performances, the proposed algorithm needs less individual classifiers to construct the ensemble than SVM ensemble algorithm. Thus, compared with SVM ensemble algorithm, the complexity of the ensemble classifier of the proposed algorithm is reduced greatly. Conveniently, the proposed algorithm also avoids the burden of selecting the appropriate kernel function and parameters. Copyright © 2013 John Wiley & Sons, Ltd.     

Towards universal freeway incident detection algorithms

This paper reports the intensive test of the new transport systems centre (TSC) algorithm applied to incident detection on freeways. The TSC algorithm is designed to fulfil the universality expectations of automated incident detection. The algorithm consists of two modules: data processing module and incident detection module. The data processing module is designed to handle specific features of different sites. The Bayesian network based incident detection module is used to store and manage general expert traffic knowledge, and to perform coherent reasoning to detect incidents. The TSC algorithm is tested using 100 field incident data sets obtained from Tullamarine Freeway and South Eastern Freeway in Melbourne, Australia. The performance of the algorithm demonstrates its competitiveness with the best performing neural network algorithm which was developed and tested using the same incident data sets in an early research. Most importantly, both the detection rate and false alarm rate of the TSC algorithm are not sensitive to the incident decision threshold, which greatly improves the stability of incident detection. In addition, a very consistent algorithm performance is achieved when the TSC algorithm is transferred from Southern Expressway of Adelaide to both Tullamarine Freeway and South Eastern Freeway of Melbourne. No substantial algorithm retraining is required. A significant step towards algorithm universality is possible from this research.     

A geometry-based algorithm to provide guidance for electric vehicle charging

Electric vehicles (EVs) have been regarded as effective options for solving the environmental and energy problems in the field of transportation. However, given the limited driving range and insufficient charging stations, searching and selecting charging stations is an important issue for EV drivers during trips. A smart charging service should be developed to help address the charging issue of EV drivers, and a practical algorithm for charging guidance is required to realise it. This study aims to design a geometry-based algorithm for charging guidance that can be effectively applied in the smart charging service. Geographic research findings and geometric approaches are applied to design the algorithm. The algorithm is practical because it is based on the information from drivers’ charging requests, and its total number of calculations is significantly less than that of the conventional shortest-first algorithm. The algorithm is effective because it considers the consistency of direction trend between the charging route and the destination in addition to the travel distance, which conforms to the travel demands of EV drivers. Moreover, simulation examples are presented to demonstrate the proposed algorithm. Results of the proposed algorithm are compared with those of the other two algorithms, which show that the proposed algorithm can obtain a better selection of charging stations for EV drivers from the perspective of entire travel chains and take a shorter computational time.     

An improved Dial's algorithm for logit-based traffic assignment within a directed acyclic network

Abstract

Dial's algorithm is one of the most effective and popular procedures for a logit-type stochastic traffic assignment, as it does not require path enumeration over a network. However, a fundamental problem associated with the algorithm is its simple definition of ‘efficient paths’, which sometimes produces unrealistic flow patterns. In this paper, an improved algorithm based on the route extension coefficient is proposed in order to circumvent this problem, in which ‘efficient paths’ simultaneously consider link travel cost and minimum travel cost. Path enumeration is still not required and a similar computing efficiency with the original algorithm is guaranteed. A limitation of the algorithm is that it can only be applied to a directed acyclic network because a topological sorting algorithm is used to decide the order of the sequential calculation. A numerical example based on the Beijing subway network illustrates the effectiveness of the proposed algorithm. It is found that it is able to exclude most unrealistic paths, but include all reasonable paths when compared with path enumeration and the original Dial's algorithm.     

An application of the CUSUM algorithm to freeway incident detection based on two contiguous detectors

The CUSUM (cumulative sum of log‐likelihood ratio) algorithm is a detection algorithm that shows potential for the improvement of incident detection algorithms because it is designed to minimize the mean detect delay for a given false alarm constraint and it can also detect changes with different patterns. In this study, the CUSUM algorithm was applied to freeway incident detection by integrating traffic measurements from two contiguous loop detectors and the non‐stationarity of traffic flows. The developed algorithm was tested based on incident data from the PATH program, with consideration given to the impact of different geometric conditions on algorithm performance. It was also compared with two existing algorithms, in order to address the influence of traffic patterns. The evaluation results show that the CUSUM incident detection algorithm can perform equally well in comparison with the selected algorithms.     

Ground delay program planning under uncertainty in airport capacity

Abstract

This paper presents an algorithm for assigning flight departure delays under probabilistic airport capacity. The algorithm dynamically adapts to weather forecasts by revising, if necessary, departure delays. The proposed algorithm leverages state-of-the-art optimization techniques that have appeared in recent literature. As a case study, the algorithm is applied to assigning departure delays to flights scheduled to arrive at San Francisco International Airport in the presence of uncertainty in the fog clearance time. The cumulative distribution function of fog clearance time was estimated from historical data. Using daily weather forecasts to update the probabilities of fog clearance times resulted in improvement of the algorithm's performance. Experimental results also indicate that if the proposed algorithm is applied to assign ground delays to flights inbound at San Francisco International airport, overall delays could be reduced up to 25% compared to current level.     

基于RBF神经网络的发动机怠速抖动故障诊断

针对难以获取发动机怠速抖动的精确数学模型,文章提出一种基于RBF神经网络的模型逼近算法。该算法利用RBF神经网络良好的模型逼近能力,对造成发动机怠速抖动的几种典型故障原因进行了诊断。实验结果表明该算法具有良好的逼近效率和诊断效果。     

Isolated intersection control for various levels of vehicle technology: Conventional,connected, and automated vehicles

Connected vehicle technology can be beneficial for traffic operations at intersections. The information provided by cars equipped with this technology can be used to design a more efficient signal control strategy. Moreover, it can be possible to control the trajectory of automated vehicles with a centralized controller. This paper builds on a previous signal control algorithm developed for connected vehicles in a simple, single intersection. It improves the previous work by (1) integrating three different stages of technology development; (2) developing a heuristics to switch the signal controls depending on the stage of technology; (3) increasing the computational efficiency with a branch and bound solution method; (4) incorporating trajectory design for automated vehicles; (5) using a Kalman filter to reduce the impact of measurement errors on the final solution. Three categories of vehicles are considered in this paper to represent different stages of this technology: conventional vehicles, connected but non-automated vehicles (connected vehicles), and automated vehicles. The proposed algorithm finds the optimal departure sequence to minimize the total delay based on position information. Within each departure sequence, the algorithm finds the optimal trajectory of automated vehicles that reduces total delay. The optimal departure sequence and trajectories are obtained by a branch and bound method, which shows the potential of generalizing this algorithm to a complex intersection.Simulations are conducted for different total flows, demand ratios and penetration rates of each technology stage (i.e. proportion of each category of vehicles). This algorithm is compared to an actuated signal control algorithm to evaluate its performance. The simulation results show an evident decrease in the total number of stops and delay when using the connected vehicle algorithm for the tested scenarios with information level of as low as 50%. Robustness of this algorithm to different input parameters and measurement noises are also evaluated. Results show that the algorithm is more sensitive to the arrival pattern in high flow scenarios. Results also show that the algorithm works well with the measurement noises. Finally, the results are used to develop a heuristic to switch between the different control algorithms, according to the total demand and penetration rate of each technology.