基于GAPSO-RBFNN的动车组电机吊架多目标稳健优化设计

基于遗传粒子群(GAPSO)算法获取最优平滑系数,从而改进径向基神经网络(RBFNN);通过电机吊架的灵敏度分析筛选出对其总质量和自然频率等质量特性影响较大的关键设计变量;结合正交试验设计与有限元分析得出电机吊架各质量特性值及对应的信噪比,将试验数据作为输入、信噪比作为输出用于GAPSO-RBFNN的训练和测试,并对比分析预测精度;基于GAPSO-RBFNN构建电机吊架的多目标稳健优化模型,采用NSGA-II多目标优化算法对其寻优求解,并与传统设计方案进行对比。结果表明:GAPSO-RBFNN的预测误差远低于传统RBFNN;优化后电机吊架各质量特性信噪比得到提高,实现了对电机吊架的多目标稳健优化,降低了电机吊架总质量,提高了其自然频率。     

Integrated optimisation design of a dynamic umbilical based on an approximate model

An optimised design of a dynamic umbilical requires an extreme cross-sectional stress to be maintained within an allowable limit and a fatigue life to be guaranteed to be sufficient. It should be noted that a dynamic umbilical is a typical geometric bi-scale structural system. It consists of a local cross-sectional scale and a global configuration scale, which are significantly different in terms of geometric sizes. In this study, we established an approximate model to achieve an optimised design of the dynamic umbilical by considering the parameters of local cross-sections and global configurations simultaneously. The design variables of a dynamic umbilical are independently identified and defined at both local sectional and global configuration scales in the approximate model. Furthermore, we selected the maximum tension strain and the maximum bending moment, for covering local and global properties, as the objectives to be minimised. The approximate model was observed to be effective in integrating the local and global responses into one loop so that the computational efficiency could be significantly increased. We implemented the optimisation framework on a dynamic umbilical with a lazy-wave configuration, which is considered to be a basis for a case study. Furthermore, we verified the feasibility and effectiveness of the integrated optimisation strategy by numerical simulations. Moreover, we compared the optimised dynamic umbilical properties with those without optimisation. It was observed that the fatigue life of the optimised dynamic umbilical was improved significantly, thereby indicating that the integrated optimisation methodology provides a new model and algorithm for an efficient design of the dynamic umbilical.     

基于捕食搜索策略的混合动力汽车参数优化

混合动力汽车模型是一个较复杂的非线性系统,且设计参数较多,为一种处理燃油经济性和排放的多目标问题。文章以一辆实例样车的动力系统和逻辑门限值控制策略为例,分析并建立了以动力性能为控制约束,以最小化油耗和排放为控制目标的非线性规划模型。采用捕食搜索遗传算法,对模型进行了仿真。结果表明,该方法相对于简单遗传算法更能有效地改善车辆燃油经济性和排放。     

Multi-objective signal control of urban junctions – Framework and a London case study

This paper presents an approach to multi-objective signal control using fuzzy logic. The signal control uses fuzzy logic where the membership functions are optimised according to the Bellman–Zadeh principle of fuzzy decision-making. This approach is both practical for the decision-maker and efficient, as it leads directly to a Pareto-optimal solution. Signal control priorities are ultimately a political decision. Therefore the tool developed in this research allows the traffic engineer to balance the objectives easily by setting acceptability and unacceptability thresholds for each objective. Particular attention is given in the example to pedestrian delays. The membership functions of the fuzzy logic are optimised by a genetic algorithm coupled to the VISSIM microscopic traffic simulator. The concept is illustrated with a case study of the Marylebone Road–Baker Street intersection in London at which pedestrians as well as vehicle flows are high. The results prove the feasibility of the framework and show the vehicle delays for a more pedestrian friendly signal control strategy.     

客观量化多目标决策模型分析

公路网规划方案优选是一个复杂的过程,由于众多因素的不确定和具体问题的特殊性,虽然,在理论上有很多决策模型可以应用,但哪个模型选出的实施方案更符合实际,从某种意义上还存在一定的不确定性.本文选择了使用率较高的传统的逼近于理想解法(TOPSIS)、灰关联与理想解法的组合法及最小隶属度偏差法等三种方法对某省干线公路网规划方案的优选进行了比较,其优选结果出现了差异.公路网规划决策中,在不确切知道哪个决策模型较合适的情况下,应多选几个决策模型进行计算择优,从而使所选实施方案可信度更高.     

基于多目标粒子群算法的船舶主尺度优化设计研究

粒子群优化是一种新兴的进化计算技术。文章基于多目标粒子群优化算法讨论了船舶主尺度论证中的多目标优化和决策问题。对于多目标优化问题,采用基于Pareto占优方法的多目标粒子群算法得到最优解,然后采用距离理想解最近的方法对这些Pareto最优解给出排序。应用文中给出的两个阶段求解方法,对散装货船概念设计阶段主尺度确定的问题进行了分析。结果表明,综合多目标粒子群优化和决策技术,能够迅速、客观地选择合理的船舶主尺度,可以给设计人员提供更多的选择。这种综合方法也能够广泛用于船舶其他设计领域。     

高速磁浮列车头型多目标气动优化设计

针对常温常导高速磁浮列车头型的几何特点,将其分为流线型和设备舱2个部分,采用改进的VMF参数化方法和曲面离散方法,分别进行参数化设计;对提取的12个设计参数,结合计算流体力学方法、支持向量机模型和多目标粒子群算法,以整车气动阻力系数和尾车气动升力系数为优化目标,以头车气动升力系数为约束条件,进行高速磁浮列车头型多目标气...     

基于ADAMS的前悬架仿真优化

悬架在整车中占据着举足轻重的地位,决定了车辆操纵稳定性及平顺性的好坏。为了使得初步设计的双横臂式独立悬架性能得到提升,论文采用多目标拓扑优化的方法对前悬架进行了优化。首先在ADAMS/CAR中建立了车辆前悬架模板子系统,仿真出车轮定位参数变化曲线。接着在ADAMS/Insight模块里,设计目标选为车轮定位参数,设计变量选为前悬架硬点坐标,根据敏感度大小,对前悬架硬点坐标进行了优化,曲线对比结果显示优化有效。     

A multi-objective train scheduling model and solution

This paper develops a multi-objective optimization model for the passenger train-scheduling problem on a railroad network which includes single and multiple tracks, as well as multiple platforms with different train capacities. In this study, lowering the fuel consumption cost is the measure of satisfaction of the railway company and shortening the total passenger-time is being regarded as the passenger satisfaction criterion. The solution of the problem consists of two steps. First the Pareto frontier is determined using the -constraint method, and second, based on the obtained Pareto frontier detailed multi-objective optimization is performed using the distance-based method with three types of distances. Numerical examples are given to illustrate the model and solution methodology.     

客运专线线路走向多目标决策分析

在对客运专线线路走向决策的特点进行深入细致分析的基础上,围绕客运专线线路走向方案优选系统的建立,开展了理论与应用研究工作;运用系统工程和软件工程理论与方法,采用数据仓库技术提出了客运专线线路走向方案优选系统中数据管理方法,并构造了相应的数据仓库结构以及客运专线线路走向方案优选系统功能结构,实现了客运专线线路基本走向决策支持系统关键技术;运用开发的"客运专线线路方案优选系统",实现计算机辅助进行成都至重庆客运专线线路走向方案的多目标决策分析。经反复筛选确定了成都至重庆客运专线线路走向的五个非劣方案,建立决策指标体系,进行权重计算和分析,确定了客运专线线路走向方案的优先顺序。