Abstract
The computational cost and memory demand required by computational fluid dynamics (CFD) codes simulations can become very high. Therefore, the application of convolutional neural networks (CNN) in this field has been studied owing to its capacity to learn patterns from sets of input data, which can considerably approximate the results of the CFD simulations with relative low errors. DeepCFD code has been taken as a basis and with some slight variations in the parameters of the CNN, while the net is able to solve the Navier–Stokes equations for steady turbulent flows with variable input velocities to the domain. In order to acquire extensive input data to the CNN, a data augmentation technique, which considers the similarity principle for fluid dynamics, is implemented. As a consequence, DeepCFD is able to learn the velocities and pressure fields quite accurately, speeding up the time-consuming CFD simulations.
Highlights
For many years, turbulence in fluids has been a popular research topic thanks to its impact on a wide variety of applications
computational fluid dynamics (CFD) problem solving, it remains a limitation for product development in a wide range of applications, such as aerodynamic design optimization and fluid–structure interaction [1]
This fact, in addition to the growth in recent years in the development of artificial intelligence, has resulted in many authors using deep learning (DL) techniques to obtain an approximation of the results of CFD simulations
Summary
Turbulence in fluids has been a popular research topic thanks to its impact on a wide variety of applications. CNN for predicting velocity and pressure fields of stationary fluids around simple shaped obstacles, reducing the computational cost between three and five orders of magnitude in comparison with CFD simulations. Guo et al [4] and Nowruzi et al [13], most studies of this type are focused on 2D geometries, owing to the limited computational domain available for 3D geometries [14] To avoid this problem, Mohan et al [14] developed a DL-based infrastructure that reduces the geometry in order to subsequently analyse the characteristics of the flow. This technique generates different synthetics cases to increase the training and validation data, keeping the Reynolds number constant
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
