In this paper, a data driven approach is presented for the prediction of incompressible laminar steady flow field over airfoils based on the combination of deep Convolutional Neural Network (CNN) and deep Multilayer Perceptron (MLP). The flow field over an airfoil depends on the airfoil geometry, Reynolds number, and angle of attack. In conventional approaches, Navier-Stokes (NS) equations are solved on a computational mesh with corresponding boundary conditions to obtain the flow solutions, which is a time consuming task. In the present approach, the flow field over an airfoil is approximated as a function of airfoil geometry, Reynolds number, and angle of attack using deep neural networks without solving the NS equations. The present approach consists of two steps. First, CNN is employed to extract the geometrical parameters from airfoil shapes. Then, the extracted geometrical parameters along with Reynolds number and angle of attack are fed as input to the MLP network to obtain an approximate model to predict the flow field. The required database for the network training is generated using the OpenFOAM solver by solving NS equations. Once the training is done, the flow field around an airfoil can be obtained in seconds. From the prediction results, it is evident that the approach is efficient and accurate.

This paper deals with an experimental and numerical study of the dynamics of an underwater explosion and its associated fluid–structure interaction. Experimental studies of the complex fluid–structure interaction phenomena were carried out in a specially designed test pond. The pond is equipped with a high-speed camera and pressure and displacement sensors. The high-speed camera was used to capture the expansion and collapse of the gas bubble created by the explosion. Several different structures were used in the experiments, including both rigid and resilient plates of circular shape. The deformation of the plate was measured with a non-contact laser telemetry device. The numerical simulations of the explosion bubble interacting with a submerged resilient structure were performed using a three-dimensional bubble dynamics code in conjunction with a structural code. The bubble code is based on the boundary-element method (BEM) and has been coupled to a structural finite-element code (PAM-CRASH$^{\rm TM})$. The experimental results were compared against the numerical results for different bubble–structure configurations and orientations. Several physical phenomena that have been observed, such as bubble jetting and bubble migration towards the structure are discussed.

A study of the interaction between a membrane and a submerged oscillating bubble is presented. Though the behavior of such a bubble near an elastic (relatively thick) boundary has been studied by several authors, much less attention is focused on the behavior of such a bubble near a (thin) elastic membrane. For membranes, it is the curvature and not the deflection that is responsible for a pressure buildup in the fluid close to the bubble. Due to this difference in physics, it is not a certainty if the dynamics of bubbles near a deformable elastic boundary vis-a-vis a membrane would exhibit any similarity. Our intent is a systematic study on the latter, which can be exploited in future work (e.g., in biomedical applications where elastic membranes are often involved). Experimental observations of transient bubble interaction with a thin elastic membrane are presented and the dynamics of the bubble in the vicinity of the membrane are compared to the boundary element method simulations. The bubble is generated using a very low voltage (only 55V) in contrast to the relatively much higher voltages usually employed in reported works. This is very attractive from a safety viewpoint and accords great simplification of the setup. The comparisons show that the interaction between the transient bubble and the membrane induces a perturbation on the bubble surface that strengthens the bubble contraction and can lead to mushroom shape, bubble elongation, and bubble splitting. The influence of the two main parameters, namely, the distance between the bubble and the membrane and the elasticity of the membrane, are also discussed.