生物地理学算法求解一类非线性线性双层规划

用生物地理学优化算法的实数编码来求解下层为凸规划的非线性双层规划问题。基于上层目标函数设置了一种新的适宜度函数,可以简单区分不同类型的解;对下层问题先用坐标轮换法求解,然后利用基于下层问题的KKT最优性等价条件来检验求解结果。分别运用4种不同的迁移率模型来求解问题,实验结果表明,生物地理学优化算法求解这类双层问题是稳定、有效的。     

基于双层规划的综合运输网络优化研究

针对综合运输网络中干线运输和末端配送的分离问题,本文将两者综合考虑,统一用双层规划模型表达。上层规划优化物流总成本,下层规划考虑客户配送成本最小化。采用遗传算法求解该双层模型,实例计算结果验证了该模型的可行性和求解方法的高效性。     

基于智能控制算法的自动驾驶系统优化研究

针对传统自动驾驶系统的目标检测与识别模块易受到周围环境的影响而使得系统在准确性、实时性存在不足等问题,文中在分析传统算法的基础上,利用智能化控制算法中的SVM方法对现有的车辆自动化驾驶系统进行优化。该优化算法通过对输入图像特征的提取与训练得到相应的分类器模型,然后利用该模型进行目标的检测与识别。测试结果表明,该优化系统对于车道线、车辆及行人等目标的检测效率与准确率等方面均优于基于特征的传统算法,验证了该方法的可行性。     

城市交通连续平衡网络设计问题的量子进化算法

在研究连续平衡网络设计的网络双层规划模型的算法中,很多求解思路是在下层用户平衡配流模型用GP算法或Frank-Wolfe算法等,在上层模型求解算法用遗传算法、模拟退火算法、粒子群算法等,而文中的上下层模型都是用量子进化算法去求解的。文中通过一个实例对算法进行验证,并与其他算法进行比较,结果表明量子进化算法性能优于遗传算法。     

基于递归搜索的公交换乘算法研究

在城市的公共交通网络中,公交换乘是乘客出行的一个重要的问题。随着城市公交规模的不断扩大,有相当部分的出行难以直达,乘客必须换乘才可到达目的地。在研究公交换乘的最优路径算法时,有必要先了解乘客出行时所考虑的因素,通过对乘客出行心理、行为的研究来确定模型的优化目标和约束条件。文中从换乘算法、出行时间、出行距离等方面进行分析,在综合考虑相关因素的情况下,加权平均得出了一种最小换乘次数为主的广度优先算法,并应用于武汉号码百事通系统中。     

基于改进鲸鱼算法虚拟电厂经济优化调度

针对分布式不可控电源接入系统引起的波动问题,文中基于虚拟电厂提出一种考虑市场电价的经济优化调度模型,根据负荷需求,对虚拟电厂中的各分布式发电的功率输出进行优化,以达到经济最优化.将鲸鱼算法应用于所建立的虚拟电厂经济优化调度模型,并对算例结果进行了分析,结果表明,该模型是合理有效的.针对鲸鱼算法在求解过程中存在的收敛速度...     

基于Anylogic的交通信号灯配时优化设计

为解决城市道路拥堵问题,以淮南市某一道路交叉口为例,基于AnyLogic道路交通库,建立车辆进出路网的仿真模型,利用Optquest优化器,以车辆在路网的平均停留时间为角度,迭代信号灯时间,模拟不同信号灯时间下的车辆平均停留时间,得出在停留时间最小时信号灯的时间设置。优化结果表明：原先实际信号灯配时不合理,对信号灯时间设置进行优化后,可以改变当前不合理的现状,缩短车辆在该路网停留的时间。     

城市道路交叉口信号配时多目标优化方法研究

针对目前交叉口信号配时优化目标单一、综合运行效率不高的问题,提出一种交叉口信号配时多目标优化方法。考虑绿灯时间、周期长度和饱和度等约束条件,通过加权系数法定义代价函数,使交叉口的延误时间、停车次数和通行能力在某种程度上达到最优。基于免疫克隆算法在处理多目标问题中具有最优解分布宽广性、均匀性好等特点,引入环境变异算子,提出环境变异免疫克隆算法对模型求解,增强了算法的全局搜索能力,提高了解的质量。仿真结果表明,与传统配时方法和改进粒子群算法相比,该文方法能有效减少信号交叉口的延误时间和停车次数,提高交叉口的运行效率。     

基于非线性模型预测控制的交叉口自动驾驶车辆轨迹规划与控制

为保证自动驾驶车辆在交叉口内安全且高效的行驶,本文提出一种基于非线性模型预测控制(NMPC)的交叉口内自动驾驶车辆的轨迹规划与轨迹控制算法。以自动驾驶车辆完成期望的驾驶行为为目标,基于车辆轮廓不互相重叠的原理建立防碰撞约束,并根据交叉口的几何信息构建车道约束;为了保证车辆行驶符合运动学规律,根据交通规则和车辆特性设置运动约束。通过运用公开自然驾驶智能汽车仿真测试环境(Onsite)接口,将该算法在300个由真实世界孪生的测试场景中进行了仿真测试,测试结果表明：本文算分在安全、效率和舒适度3个方面都有良好的表现。     

模拟退火算法在公交调度中的应用

公交车辆调度是智能交通系统中的重要环节,它关系到公交公司的经济效益与社会效益。文中通过对固定公交车车次来保证公交公司的利益,建立以乘客等车时间最小为优化目标的公交优化调度模型。然后应用模拟退火算法对模型进行求解,并用实际的运营数据对提出的模型及算法进行了验证。结果显示,可得到比较合理的公交车发车时刻表,可以证明此方法是有效且可行的。     

多品类生活垃圾收运的车辆路径优化问题研究

近年来随着中国逐步制定并开展垃圾分类的政策法规,多品类生活垃圾分类收运问题就逐步凸显出来。国内使用多车舱车辆收运多品类生活垃圾的研究还较少,针对这一需求,本文基于生活垃圾分类利用多车舱垃圾收运车辆同时收运多品类生活垃圾的收运问题,以降低城市生活垃圾收运成本为目标,构建考虑车辆收运成本的多品类垃圾收运车辆的路径优化模型,并进行仿真实验,用蚁群算法对算例进行求解,验证了算法模型的良好寻优效果,为新式垃圾车辆的投产使用提供参考。     

Optimal bidirectional spine layout for overhead material handlingsystems

Overhead automated material handling systems have become the only material handling solution in semiconductor fabs to achieve zero footprint material handling in the expensive cleanroom floor. This paper provides two rectilinear layout configurations, single-spine and double-spine, for overhead track design. Given the locations of loadports and a pod from-to flow matrix, we determine the rectilinear layout of material flow systems with the objective of minimizing the total loaded travel distances. The optimal single-spine problem can be transformed to a known single-facility layout problem and solved with a linear-time algorithm. The optimal double-spine layout is obtained from the optimal single X-spine and Y-spine and is formulated as an allocation problem. We demonstrate the system designs by a numerical example. The resulting spine layouts are then compared with the Minimum Rectilinear Steiner Tree (MRST) and Shortest Rectilinear Flow Network (SRFN) layouts. MRST layout provides the shortest track length while the SRFN layout guarantees the shortest flow distances. The result shows that spine layout is a potential track layout pattern with respect to simplicity, track lengths and flow distances for overhead flow systems     

汽车偏离车道预警控制系统设计

随着汽车使用量的不断激增,交通事故发生率急剧上升,成为困扰出行安全的主要问题,而根据数据统计多数交通事故均源于汽车偏离正道形式轨道而引发的,而车道偏离预警控制系统的开发与应用,可在汽车偏离车道之时及时发出预警,规避或减少交通事故发生,针对此,本文将以TMS320DM642多媒体图像处理器作为系统核心,设计了一款嵌入式车道偏离预警控制系统,给出了系统总体结构,软硬件配置等内容,以此满足车道偏离图像实时采集、提取及预警需求.     

高速公路ETC车道单双天线布局的分析与比较

为了分析在ETC专用车道建设中双天线布局的必要性,采用单天线与双天线布局相比较的方法,通过对陕西省路网环境及170多万条交易数据分析,并计算交易耗时和行车安全约束的车辆通行限速,认为双天线布局并不会提高车辆的通过速度,交易成功率也不优于单天线布局。陕西省百余条ETC专用车道均采用单天线布局。实践证明,单天线布局能够大幅节约ETC车道的建设和维护成本,降低系统故障率和逻辑处理复杂度,能够满足ETC建设要求,很好地为公众服务。     

Estimation of left-turning travel time at traffic intersection

Traffic guidance is a promise approach of traffic congestion alleviation, and the travel time is one of the most important basic data for the reasonable and effective route planning which is the core of traffic guidance. The traffic intersection is one of the chief components of the whole traffic road networks, so the estimation of travel time of the intersection plays an important role in traffic guidance. This paper pays more attention to the estimation of travel time for left-turning lane connected to an intersection, introduces the features for travel time estimation, and designs an estimator based on the learning vector quantity (LVQ) neural network. A suite of reasonable test shows that the method can effectively estimate the travel time of vehicles at left-turning lane with lower error to the real data.     

基于GPRS的智能公交系统通信平台的实现

传统的公交系统已经不能满足道路交通管理"自动化",车辆行驶"智能化"的要求,因此,智能公交系统便应运而生。但是,如何才能将车辆、道路信息等及时、准确地传递?这就需要一个稳定、可靠、实时的通信平台。文中将详细论述基于GPRS的智能公交系统通信平台的实现。     

Vehicle counting based on double virtual lines

Traditionally, magnetic loop detectors are often used to count vehicles passing over them in intelligent transportation system. Real-time image sequences are captured by video surveillance system. Virtual loop, which emulates the functionality of inductive loop detectors, is placed on images. It is more convenient, but it occurs in false detection and discrimination when vehicles are lane departure due to overtaking or crossing. This paper presents an effective approach for vehicle counting based on double virtual lines (DVL). Double virtual lines are assigned on images, which are across bidirectional multi-lane. The region between DVL is the detection zone, rather than virtual loop zone in each lane, so as to reduce the proportion of false detection and misjudgment from lane departure for vehicles. Then, in the detection zone, the dual-template convolution is designed to detect and locate moving vehicles to eliminate the mapping of one to many, many to one. The effective rules are given in terms of the constraint of the horizontal and vertical distances to improve the accuracy of vehicle counting. Experimental comparisons with the other method demonstrate the performance of the proposed method.     

System Reliability of a Limited-Flow Network in Multicommodity Case

Network analysis is an important approach to model real-world systems. System reliability, and system unreliability are two related performance indices useful to measure the quality level of a supply-demand system. For a binary-state network without flow, the system unreliability is the probability that the system can not connect the source and the sink. Extending to a limited-flow network in the single-commodity case, the arc capacity is stochastic, and the system capacity (i.e. the maximum flow) is not a fixed number. The system unreliability for (d+1), the probability that the upper bound of the system capacity equals d, can be computed in terms of upper boundary points. An upper boundary point is the maximal system state such that the system fulfills the demand. This paper concentrates on a multicommodity limited-flow network (MLFN) in which multicommodity are transmitted through unreliable nodes and arcs. Nevertheless, the system capacity is not suitable to be treated as the maximal sum of the commodity because each commodity consumes the capacity differently. We define the system capacity as a demand vector if the system fulfills at most such a demand vector. The main problem of this paper is to measure the quality level of a MLFN. We propose a new performance index, the probability that the upper bound of the system capacity equals the demand vector subject to the budget constraint, to evaluate the quality level of a MLFN. A branch-and-bound algorithm based on minimal cuts is presented to generate all upper boundary points in order to compute the performance index. The computational complexity of the proposed algorithm is analyzed     

交通监控视频中的车辆异常行为检测

构建了利用交通监控视频对车辆异常行为进行检测的系统框架.使用改进Surendra背景差分与三帧差分相结合的算法进行车辆目标检测,结合CamShift算法与Kalman滤波器进行车辆目标跟踪,提取车辆质心绘制运动轨迹,针对车辆运动方向判别、违章变道、调头等行为提出了检测方法.实验结果表明,提出的交通监控视频中的车辆异常行为检测系统具有较高的实时性与准确性,部署简易快速,维护成本低廉,可以满足当今智能交通系统日益增长的需求.     

Bi-level Dynamic Optimization of Pumped-storage Hydroplants in a Competitive Power Pool. Part I: Model and Algorithm

The pumped-storage hydroplant are designed to save costs of fuel by generating electric power when the demand is higher and by pumping water into the upper reservoir when the demand is lower. The aim of this work is to present a model for the programming of daily operation of the pumped-storage hydroplant in a competitive power pool. The model is presented as a problem of bi-level dynamic optimization; the first level is the maximization of the benefits of the pumped-storage hydroplant where the decision variables are the power in the intervals of generation and pumping, whereas the second level is de problem of the daily scheduling of the system to minimize the variable costs of the operation, subject to the operative and technological restrictions of the system. The algorithm used for the numerical simulations is based on Dynamic Programming.