DeepPIV

The description of turbulent flow fields by means of Particle Image Velocimetry (PIV) is crucial for advancing our understanding of complex fluid systems. In turbulent multiphase flows conventional PIV is often challenging to apply due to the scattering interference. By leveraging cutting-edge optical flow detection models, such as RAFT (Recurrent All-Pairs Field Transforms), we aim to achieve high-precision turbulent multiphase flow measurements based on Mie scattering or phosphorescence double frame or time resolved images. In this project, we couple advanced deep learning techniques with our established supervised learning pipeline to generate annoted ground truth training data with minimum effort. By integrating these ML models, we enhance the efficiency and accuracy of the corresponding data analysis, thereby unlocking potential for a more in-depth description of complex turbulent multiphase flow system and involved turbulence-phase interactions. This approach further facilitates improvements in system design and performance. 

If you are interested in our project, have further questions, or would like to support us through student work, internships, or thesis projects, we would be delighted to hear from you via email or phone. Contact details can be found below.