检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]中车青岛四方机车车辆股份有限公司国家高速动车组总成工程技术研究中心,山东青岛266111 [2]中国科学院力学研究所流固耦合系统力学重点实验室,北京100190
出 处:《浙江大学学报(工学版)》2016年第4期631-640,782,共11页Journal of Zhejiang University:Engineering Science
基 金:"十二五"国家科技支撑计划资助项目(2013BAG24B02);国家"973"重点基础研究发展规划资助项目(2011CB711100);国家"863"高技术研究发展计划资助项目(2015AA01A302)
摘 要:基于支持向量机响应面模型,发展高速列车头型有约束气动反设计方法.为了减少流场计算量,针对反设计指标和约束条件分别建立对应的响应面模型,通过粒子群优化算法寻找满足设计目标值和约束条件的反设计外形.为了验证该方法的有效性,以3辆编组真实外形高速列车的1∶8缩比外形为研究对象,将整车气动阻力系数和流线型部分容积作为设计指标,研究单目标无约束、有约束及多目标无约束反设计方法.结果表明:采用提出的反设计方法能够快速得到满足设计指标和约束条件的高速列车头型,很容易拓展为能够解决任意复杂几何外形的多目标、有约束气动反设计方法,有利于提高高速列车头型工程设计的效率及针对性.A constrained inverse design method for the aerodynamic shape of high-speed train nose was developed based on the support vector regression(SVR)model.The SVRs for the design and constraint objectives were respectively established in order to reduce the CFD computation.Then the inverse design shapes that meet the target values and constraints could be found by the particle swarm optimization(PSO)algorithm.The scaled real shape(1∶8)for high-speed train with three carriages was taken as the study object in order to verify the inverse design method.The aerodynamic drag coefficient of the whole train and the volume of the streamlined part were taken as the design targets.The constrained and unconstrained single objective and multi-objective design method without constraints were analyzed.Results show that the proposed approach can quickly get the inverse shape that meets the design specifications and constraints.The approach can be easily expanded to solve constrained and multiobjective inverse problems for arbitrarily complex geometries.The approach may improve the engineering design efficiency of high-speed train nose.
关 键 词:反设计 支持向量机模型(SVR) 多目标设计 高速列车
分 类 号:U238[交通运输工程—道路与铁道工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.229