عنوان سخنرانی: 4D Lagrangian Particle Tracking Velocimetry and AI-based Data Assimilation

سخنران : Dr. Kyung Chun Kim, Professor, School of Mechanical Engineering,Pusan National University, Busan 46241, South Korea

چكيده:

A time-resolved three-dimensional Lagrangian Particle Tracking Velocimetry (4D PTV) has developed adopting the Shake-the-box algorithm with four high-speed cameras. Helium filled soap bubbles are used as tracers in the wind tunnel experiment to characterize flow structures around automobile side mirror models. Full volumetric velocity fields and evolution of vortex structures are obtained and analyzed for three different side mirror models. Three dimensional arch vortices and trailing vortices are clearly obtained and the structures are strongly related with downwash and upwash flows due to geometric effect of the mirror model.   Instantaneous pressure fields are deduced by solving a Poisson equation based on the 4D PTV data. Direct measurement of pressure fluctuation agrees well with the estimated pressure by the 4D PTV. To increase spatial and temporal resolutions of velocity field, artificial intelligence (AI)-based data assimilation method has applied. ANFIS (Adaptive Neural Fuzzy Inference System) based machine learning algorithm works well to find hidden 3D vortical structures and sound level spectra behind the automobile side mirror models. Deep learning algorithms such as LSTM (Long Short-Term Memory) and GAN (Generative Adversarial Network) were also applied to obtain super resolution particle image velocimetry reconstructions.

زمان برگزاری: 28 بهمن 1398

:فايل صوتی سخنرانی