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.
Turbulence in fluids has been a popular research topic for many years due to its influence on a wide range of applications. Computational Fluid Dynamics (CFD) tools are able to provide plenty of information about this phenomenon, but their computational cost often makes the use of these tools unfeasible. For that reason, in recent years, turbulence modelling using Artificial Neural Networks (ANNs) is becoming increasingly popular. These networks typically calculate directly the desired magnitude, having input information about the computational domain. In this paper, a Convolutional Neural Network (CNN) for predicting different magnitudes of turbulent flows around different geometries by approximating the equations of the Reynolds-Averaged Navier-Stokes (RANS)-based realizable k-ε two-layer turbulence model is proposed. Using that CNN, alternative network structures are proposed to predict the velocity fields of a turbulent flow around different geometries on a rectangular channel, with a preliminary stage to predict pressure and vorticity fields before calculating the velocity fields, and the obtained results are compared with the ones obtained with the basic structure. The results demonstrate that the proposed structures clearly outperform the basic one, especially when the flow becomes uncertain. In addition, considering the results, the best network configuration is proposed. That network is tested with a domain with multiple geometries and a domain with a narrowing of the channel, which are domains with different conditions from the training ones, showing fairly accurate predictions.
The nonstationary separated incompressible flows around Darrieus and Savonius rotors of vertical-axis wind turbines were investigated through computational simulation using the Reynolds averaged Navier–Stokes equations and Spalart–Allmaras turbulence model. The implicit finite-volume algorithm, the basis of which was artificial compressibility method, was chosen to obtain the numerical solution. The series of computational and physical experiments for Darrieus rotors with varied numbers and shapes of blades were performed. The detailed visualization of the flow was presented. The turbulent flows surrounding the Darrieus and Savonius rotors were studied, and as a part of these investigations, the major phases of vortex progress were identified. For this purpose, three series of computer tests on the aerodynamic and power properties of Savonius rotors with two and three buckets were performed, and their results are also presented. The influence of tip-speed ratio, solidity, and Reynolds numbers on the power coefficients of the Darrieus and Savonius rotors was investigated. It has been demonstrated that increasing Reynolds number from 104 to 106 causes a rise in Darrieus rotors power coefficient from 0.15 up to 0.5. The maximum values of power coefficient are moved away from higher values of tip-speed ratio from 2 to 5 as a result of a decrease in Darrieus rotor solidity from 1.0 to 0.33. The greatest power coefficient for a Savonius rotor with two blades is 0.23 and for a Savonius rotor with three blades is 0.19.
The application of computational fluid dynamics (CFD) to turbulent flow has been a considerable topic of research for many years. Nonetheless, using CFD tools results in a large computational cost, which implies that, for some applications, CFD may be unviable. To date, several authors have carried out research applying deep learning (DL) techniques to CFD-based simulations. One of the main applications of DL with CFD is in the use of convolutional neural networks (CNNs) to predict which samples will have the desired magnitude. In this study, a CNN which predicts the streamwise and vertical velocities and the pressure fields downstream of a circular cylinder for a series of time instants is presented. The CNN was trained using a signed distance function (SDF), a flow region channel (FRC) and the t-1 sample as inputs, and the ground-truth CFD data as the output. The results showed that the CNN was able to predict multiple time instants with low error rates for turbulent flows with variable input velocities to the domain.