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.
修改评论