横风环境下高速列车头型的多目标优化设计
|
摘要
基于高速列车初始外形的参数化设计,针对各个优化目标建立对应的基于交叉验证方法的Kriging模型;为保证预测精度且尽量减少加点数量,基于最优解点和预测标准差最大点的2点加点准则,利用多目标优化算法得到满足约束条件的Pareto最优解集;利用测试函数验证优化设计方法的可靠性。以3辆编组高速列车为例,以整车气动阻力系数、流线型部分容积、尾车气动侧向力系数和尾车倾覆力矩系数为优化目标,以鼻锥厚度、鼻锥引流、鼻锥高度、车体宽度、司机室视角和排障器形状为设计参数,进行横风环境下高速列车的外形优化。结果表明:多目标优化算法可应用于高速列车头型的优化设计;利用各设计参数与优化目标的作用规律,可指导高速列车头型的工程改进设计。
Parametric design was done based on the initial shape of a high speed train.Corresponding Kriging model based on cross validation method was established for each optimization objective.In order to guarantee the prediction accuracy and reduce the number of adding points as many as possible,based on the two-point adding criterion of optimal solution point and the maximum prediction standard deviation point,the Pareto optimal solutions satisfying constraints were obtained by using multi-objective optimization algorithm.Then the test function was used to verify the reliability of the optimization design method.Taking the high speed train with 3-car formation as an example,the aerodynamic drag coefficient of the whole train,the partial volume of streamline as well as both the aerodynamic lateral force coefficient and the overturning moment coefficient of the tail car were taken as the optimization targets.The thickness,drainage and height of nose cone,the width of car body,the view of driver's cab and the shape of rail guard were taken as design parameters.The shape optimization of high speed train in cross wind conditions was carried out.Results show that the multi-objective optimization algorithm can be applied to the optimization design for the nose shape of high speed train.The function laws between parameters and objectives can be used to guide the engineering improvement design for the nose shape of high speed train.
Parametric design was done based on the initial shape of a high speed train.Corresponding Kriging model based on cross validation method was established for each optimization objective.In order to guarantee the prediction accuracy and reduce the number of adding points as many as possible,based on the two-point adding criterion of optimal solution point and the maximum prediction standard deviation point,the Pareto optimal solutions satisfying constraints were obtained by using multi-objective optimization algorithm.Then the test function was used to verify the reliability of the optimization design method.Taking the high speed train with 3-car formation as an example,the aerodynamic drag coefficient of the whole train,the partial volume of streamline as well as both the aerodynamic lateral force coefficient and the overturning moment coefficient of the tail car were taken as the optimization targets.The thickness,drainage and height of nose cone,the width of car body,the view of driver's cab and the shape of rail guard were taken as design parameters.The shape optimization of high speed train in cross wind conditions was carried out.Results show that the multi-objective optimization algorithm can be applied to the optimization design for the nose shape of high speed train.The function laws between parameters and objectives can be used to guide the engineering improvement design for the nose shape of high speed train.
引文
[1]田红旗.风环境下的列车空气阻力特性研究[J].中国铁道科学,2008,29(5):108-112.(TIAN Hongqi.Study on the Characteristics of Train Air Resistance under Wind Environment[J].China Railway Science,2008,29(5):108-112.in Chinese)
[2]YANG Guowei,GUO Dilong,YAO Shuanbao,et al.Aerodynamic Design for China New High-Speed Trains[J].Science China:Technological Sciences,2012,55(7):1923-1928.
[3]姚拴宝,郭迪龙,孙振旭,等.基于Kriging代理模型的高速列车头型多目标优化设计[J].中国科学:技术科学,2013,43(2):186-200.(YAO Shuanbao,GUO Dilong,SUN Zhenxu,et al.Multi-Objective Optimization of the Streamlined Head of High-Speed Trains Based on the Kriging Model[J].Science China:Technological Sciences,2013,43(2):186-200.in Chinese)
[4]姚拴宝,郭迪龙,杨国伟.基于GA-GRNN的高速列车头型三维优化设计[J].中国科学:技术科学,2012,42(11):1283-1294.(YAO Shuanbao,GUO Dilong,YANG Guowei.Three-Dimensional Aerodynamic Optimization Design of High-Speed Train Nose Based on GA-GRNN[J].Science China:Technological Sciences,2012,42(11):1283-1294.in Chinese)
[5]KWON Hyeokbin,JANG Kihyeok,KIM Yushin,et al.Nose Shape Optimization of High-Speed Train for Minimization of Tunnel Sonic Boom[J].JSME International Journal Series C,2001,44(3):890-899.
[6]LEE Jongsoo,KIM Junghui.Approximate Optimization of High-Speed Train Nose Shape for Reducing Micropressure Wave[J].Industrial Applications,2008,35:79-87.
[7]CUI Kai,WANG Xiuping,HU Shouchao,et al.Shape Optimization of High-Speed Train with the Speed of 500kph[C]//Lecture Notes in Electrical Engineering-Proceedings of the 1st International Workshop on High-Speed and Intercity Railways.Germany:Springer Verlag,2012:187-197.
[8]VYTLA V V,HUANG P G,PENMETSA R C.Multi Objective Aerodynamic Shape Optimization of High Speed Train Nose Using Adaptive Surrogate Model[C]//28th AIAA Applied Aerodynamics Conference.Chicago:American Institute of Aeronautics and Astronautics,2010.
[9]KU Y C,KWAK M H,PARK H I,et al.Multi-Objective Optimization of High-Speed Train Nose Shape Using the Vehicle Modeling Function[C]//48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition.Orlando,USA:American Institute of Aeronautics and Astronautics,2010.
[10]胥红敏,孙加林,高芒芒,等.横风风速和车速对CRH2型动车组运行安全性指标影响规律的研究[J].中国铁道科学,2014,35(2):65-71.(XU Hongmin,SUN Jialin,GAO Mangmang,et al.Study on the Influence Laws of Crosswind Speed and Train Speed on the Operation Safety Indexes of CRH2EMU[J].China Railway Science,2014,35(2):65-71.in Chinese)
[11]NADEAU C,BENGIO Y.Inference for the Generalization Error[J].Machine Learning,2003,52(3):239-281.
[12]JONES Donald R.A Taxonomy of Global Optimization Methods Based on Response Surfaces[J].Journal of Global Optimization,2001,21:345-383.
[13]GAO Yuehua,TURNG Lihsheng,WANG Xicheng.Adaptive Geometry and Process Optimization for Injection Molding Using Kriging Surrogate Model Trained by Numerical Simulation[J].Advances in Polymer Technology,2008,26(5):1-16.
[14]CHRISTOPH B,JOSE M B.On the Use of Cross-Validation for Time Series Predictor Evaluation[J].Information Sciences,2012,191:192-213.
[15]MARKATOU M,BISWAS S.Analysis of Variance of Cross-Validation Estimators of the Generalization Error[J].Journal of Machine Learning Research,2005,6:1127-1168.
[2]YANG Guowei,GUO Dilong,YAO Shuanbao,et al.Aerodynamic Design for China New High-Speed Trains[J].Science China:Technological Sciences,2012,55(7):1923-1928.
[3]姚拴宝,郭迪龙,孙振旭,等.基于Kriging代理模型的高速列车头型多目标优化设计[J].中国科学:技术科学,2013,43(2):186-200.(YAO Shuanbao,GUO Dilong,SUN Zhenxu,et al.Multi-Objective Optimization of the Streamlined Head of High-Speed Trains Based on the Kriging Model[J].Science China:Technological Sciences,2013,43(2):186-200.in Chinese)
[4]姚拴宝,郭迪龙,杨国伟.基于GA-GRNN的高速列车头型三维优化设计[J].中国科学:技术科学,2012,42(11):1283-1294.(YAO Shuanbao,GUO Dilong,YANG Guowei.Three-Dimensional Aerodynamic Optimization Design of High-Speed Train Nose Based on GA-GRNN[J].Science China:Technological Sciences,2012,42(11):1283-1294.in Chinese)
[5]KWON Hyeokbin,JANG Kihyeok,KIM Yushin,et al.Nose Shape Optimization of High-Speed Train for Minimization of Tunnel Sonic Boom[J].JSME International Journal Series C,2001,44(3):890-899.
[6]LEE Jongsoo,KIM Junghui.Approximate Optimization of High-Speed Train Nose Shape for Reducing Micropressure Wave[J].Industrial Applications,2008,35:79-87.
[7]CUI Kai,WANG Xiuping,HU Shouchao,et al.Shape Optimization of High-Speed Train with the Speed of 500kph[C]//Lecture Notes in Electrical Engineering-Proceedings of the 1st International Workshop on High-Speed and Intercity Railways.Germany:Springer Verlag,2012:187-197.
[8]VYTLA V V,HUANG P G,PENMETSA R C.Multi Objective Aerodynamic Shape Optimization of High Speed Train Nose Using Adaptive Surrogate Model[C]//28th AIAA Applied Aerodynamics Conference.Chicago:American Institute of Aeronautics and Astronautics,2010.
[9]KU Y C,KWAK M H,PARK H I,et al.Multi-Objective Optimization of High-Speed Train Nose Shape Using the Vehicle Modeling Function[C]//48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition.Orlando,USA:American Institute of Aeronautics and Astronautics,2010.
[10]胥红敏,孙加林,高芒芒,等.横风风速和车速对CRH2型动车组运行安全性指标影响规律的研究[J].中国铁道科学,2014,35(2):65-71.(XU Hongmin,SUN Jialin,GAO Mangmang,et al.Study on the Influence Laws of Crosswind Speed and Train Speed on the Operation Safety Indexes of CRH2EMU[J].China Railway Science,2014,35(2):65-71.in Chinese)
[11]NADEAU C,BENGIO Y.Inference for the Generalization Error[J].Machine Learning,2003,52(3):239-281.
[12]JONES Donald R.A Taxonomy of Global Optimization Methods Based on Response Surfaces[J].Journal of Global Optimization,2001,21:345-383.
[13]GAO Yuehua,TURNG Lihsheng,WANG Xicheng.Adaptive Geometry and Process Optimization for Injection Molding Using Kriging Surrogate Model Trained by Numerical Simulation[J].Advances in Polymer Technology,2008,26(5):1-16.
[14]CHRISTOPH B,JOSE M B.On the Use of Cross-Validation for Time Series Predictor Evaluation[J].Information Sciences,2012,191:192-213.
[15]MARKATOU M,BISWAS S.Analysis of Variance of Cross-Validation Estimators of the Generalization Error[J].Journal of Machine Learning Research,2005,6:1127-1168.