Development of an Intelligent Passive Device Generator for Road Vehicle Applications

Flow control has a tremendous technological and economic impact, such as aerodynamic drag reduction on road vehicles which translates directly into fuel savings, with consequent in greenhouse gas emissions operating costs. In recent years, machine learning also been used to develop new approaches flow place of more laborious methods, parametric studies, find optimal parameters few exceptions. This paper proposes an intelligent passive device generator (IPDG) that combines computational fluid dynamics (CFD) genetic algorithm, specifically, the Non-dominated Sorting Genetic Algorithm II (NSGA II). The IPDG is not application specific can be applied generate various devices given design space. particular, it creates three-dimensional unique shapes are aerodynamically efficient terms cost function (i.e., lift). this paper, demonstrated using rear flap underbody diffuser devices. Reynolds-averaged Navier-stokes (RANS) equations were solve problem. Relative baseline, generated flap-only, diffuser-only provide reductions 6.3% 5.4%, respectively, whereas flap-diffuser combination provides 7.4%. Furthermore, increase downforce significant from 624.4% flap-only 4930% 4595% combination. proposed method potential evolve universal integration learning.