基于遗传算法的信号联锁故障处理中风险问题的研究

以遗传算法优化技术为基础,对铁路信号联锁故障处理中的风险问题因素进行了分析,期望减少电务部门故障处理流程中的风险,从而避免人为造成重大、大事故.     

Optimization of PERT Network and Compression of Time

In the traditional methods of program evaluation and review technique （PERT） network optimization and compression of time limit for project, the uncertainty of free time difference and total time difference were not considered as well as its time risk. The authors of this paper use the theory of dependent-chance programming to establish a new model about compression of time for project and multi-objective network optimization, which can overcome the shortages of traditional methods and realize the optimization of PERT network directly. By calculating an example with genetic algorithms, the following conclusions are drawn： （ 1 ） compression of time is restricted by cost ratio and completion probability of project; （2） activities with maximal standard difference of duration and minimal cost will be compressed in order of precedence; （3） there is no optimal solutions but noninferior solutions between chance and cost, and the most optimal node time depends on decision-maker＇s preference.     

Operational surface drift prediction using linear and non-linear hyper-ensemble statistics on atmospheric and ocean models

Multimodel super-ensemble forecasts, which exploit the power of an optimal local combination of individual models usually show superior forecasting skills when compared to individual models because they allow for local correction and/or bias removal. Deterministic approaches to the problem of surface drift are often limited by strong assumptions on the underlying physics. A new approach based on linear and non-linear optimization is proposed, using hyper-ensemble deduced statistics to forecast at short time scale Lagrangian drifts from combined atmospheric and ocean operational models and local observations that were made available during the MREA04 field experiment along the West coast of Portugal. Optimization methods are based on a training/forecast cycle. The performance and the limitations of the hyper-ensembles and the individual models are discussed. Results suggest that our statistical methods reduce the position errors significantly for 12 to 48 h forecasts and hence compete with pure deterministic approaches.     

Modeling a rail transit alignment considering different objectives

An optimization model for station locations for an on-ground rail transit line is developed using different objective functions of demand and cost as both influence the planning of a rail transit alignment. A microscopic analysis is performed to develop a rail transit alignment in a given corridor considering a many-to-one travel demand pattern. A variable demand case is considered as it replicates a realistic scenario for planning a rail transit line. A Genetic Algorithm (GA) based on a Geographical Information System (GIS) database is developed to optimize the station locations for a rail transit alignment. The first objective is to minimize the total system cost per person, which is a function of user cost, operator cost, and location cost. The second objective is to maximize the ridership or the service coverage of the rail transit alignment. The user cost per person is minimized separately as the third objective because the user cost is one of the most important decision-making factors for planning a transit system from the users’ perspective. A transit planner can make an informed decision between various alternatives based on the results obtained using different objective functions. The model is applied in a case study in the Washington, DC area. The optimal locations and sequence of stations obtained using the three objective functions are presented and a comparative study between the results obtained is shown in the paper. In future works we will develop a combinatorial optimization problem using the aforementioned objectives for the rail transit alignment planning and design problem.     

停车诱导信息系统条件下的城市交通网络SUE配流模型及算法

停车诱导信息系统(Parking Guidance Information System,PGIS)被认为是改善城市交通拥挤的一项有效技术,不同的PGIS市场占有率对道路交通的影响是不同的。文章将出行者分成两类:使用PGIS和不使用PGIS,考虑了PGIS对出行者道路和停车选择行为的影响以及PGIS的市场占有率,构造了随机用户均衡模型来描述PGIS条件下的道路和停车选择问题,设计了相应的算法。最后,通过一个算例对模型及算法进行了验证。     

城市公共交通枢纽客流量预测实用方法研究

通过全面分析遗传算法和神经网络的优缺点,在充分考虑各种可量化因素的影响权重的基础上,建立了遗传神经网络模型,提出了城市公共交通枢纽客流量预测实用方法,并通过实例进行了分析验证。结果表明,该方法在城市公共交通枢纽客流量预测的应用过程中具有较强的学习能力和自适应性,,其预测的精度明显得到提高。     

高速公路入口匝道的协调优化控制

为了实施高速公路路网交通流的优化控制,采用MATANET模型进行路网交通流建模,应用非线性最优控制方法,构造了路网入口匝道的协调控制模型。该模型应用全局实时交通数据,以总费用时间与密度控制的组合构建性能指标,能够提高交通运行效率,并有效处理交通拥挤。针对模型的非线性,应用遗传算法对性能指标进行优化,探究TTS-密度控制指标的优化对路网交通拥挤状况的控制效果。以南京市周边高速公路路网作为应用实例,验证了所研究模型与优化方法的可行性。     

有运送路径限制的多品种流交通网络最小费用流算法研究

传统的交通网络最小费用流分配是针对单一品种,但在实际的交通运输应用中,交通网络中往往会出现多品种流的运送情况,而且也有可能对某些品种的运送路径进行限制.首先针对交通网络中的多品种流及其流动现象进行分析,借鉴Ford-Fulkerson算法中构造伴随增流网络的思路,建立了多品种流交通网络图的顺推重构方法,在此基础上,构造了有运送路径限制的多品种流交通网络最小费用流算法.在交通运输领域,多品种流最小费用流问题普遍存在,此算法为解决实际交通网络的相关问题提供了基础.     

多车场协同运输的公共自行车调度方法研究

为改善城市公共自行车使用过程中“借车难,还车难”的问题,针对公共自行车调度问题展开研究。通过构建一个多车场协同运输的公共自行车调度优化模型,分析公共自行车系统静态调度的最优路径问题。在模型求解方面,设计一种融合遗传算法和禁忌搜索算法的启发式求解算法,通过M atlab编程对模型进行求解。最后,以中山市公共自行车系统为例进行分析,结果显示本调度方法比传统调度方法节约9.3％的调度成本。     

船体结构耐撞性优化设计方法研究

提出了一种船体结构耐撞性设计的优化方法,它是在试验设计、径向基神经网络和遗传算法的基础上发展而成的,用高精度的快速分析模块来代替计算量很大的复杂模型,且能处理混合离散变量和工程约束条件。为表征船体结构的耐撞性能,本文引入了耐撞指标的概念。应用上述优化方法对某散货船舷侧结构进行了耐撞性优化设计。优化过程中以耐撞指标作为目标函数,以结构重量作为约束条件,用非线性有限元动态响应分析程序ＭＳＣ／ＤＹＴＲＡ