Numerical modeling and neural networks to identify model parameters from piezocone tests: I. FEM analysis of penetration in two-phase continuum

2010 ◽  
Vol 35 (16) ◽  
pp. 1703-1730 ◽  
Author(s):  
Rafał F. Obrzud ◽  
Andrzej Truty ◽  
Laurent Vulliet
Keyword(s):  
Neural Networks ◽  
Numerical Modeling ◽  
Fem Analysis ◽  
Model Parameters ◽  
Two Phase

The Numerical Modeling of Spherical Explosion in the Foam

2016 ◽  
Vol 11 (1) ◽  
pp. 60-65 ◽  
Author(s):  
R.Kh. Bolotnova ◽  
E.F. Gainullina
Keyword(s):  
Shock Wave ◽  
Numerical Modeling ◽  
Initial Pressure ◽  
Water Volume ◽  
Symmetric Model ◽  
Two Phase ◽  
Experimental Conditions ◽  
Initial Water ◽  
Aqueous Foam ◽  
Spherical Explosion

The spherical explosion propagation process in aqueous foam with the initial water volume content α10=0.0083 corresponding to the experimental conditions is analyzed numerically. The solution method is based on the one-dimensional two-temperature spherically symmetric model for two-phase gas-liquid mixture. The numerical simulation is built by the shock capturing method and movable Lagrangian grids. The amplitude and the width of the initial pressure pulse are found from the amount of experimental explosive energy. The numerical modeling results are compared to the real experiment. It’s shown, that the foam compression in the shock wave leads to the significant decrease in velocity and in amplitude of the shock wave.

Numerical Modeling of Evolution of Boundary Between Incompressible Gas and Liquid in Two-Dimensional Region

2006 ◽  
Vol 4 ◽  
pp. 224-236
Author(s):  
A.S. Topolnikov
Keyword(s):  
Numerical Modeling ◽  
Interphase Boundary ◽  
Incompressible Liquid ◽  
Stokes Equations ◽  
Numerical Code ◽  
Navier Stokes ◽  
Two Phase ◽  
Navier Stokes Equations ◽  
Incompressible Media ◽  
Good Agreement

The paper is devoted to numerical modeling of Navier–Stokes equations for incompressible media in the case, when there exist gas and liquid inside the rectangular calculation region, which are separated by interphase boundary. The set of equations for incompressible liquid accounting for viscous, gravitational and surface (capillary) forces is solved by finite-difference scheme on the spaced grid, for description of interphase boundary the ideology of Level Set Method is used. By developed numerical code the set of hydrodynamic problems is solved, which describe the motion of two-phase incompressible media with interphase boundary. As a result of numerical simulation the solutions are obtained, which are in good agreement with existing analytical and experimental solutions.

Simulation of mechanically stirred two-phase liquid-gas flow

1986 ◽  
Vol 51 (5) ◽  
pp. 1001-1015 ◽  
Author(s):  
Ivan Fořt ◽  
Vladimír Rogalewicz ◽  
Miroslav Richter
Keyword(s):  
Spatial Distribution ◽  
Velocity Field ◽  
Gas Flow ◽  
Liquid Velocity ◽  
Model Parameters ◽  
Two Phase ◽  
Mean Velocity ◽  
Rushton Turbine ◽  
Low Viscosity ◽  
Volumetric Gas Flow Rate

The study describes simulation of the motion of bubbles in gas, dispersed by a mechanical impeller in a turbulent low-viscosity liquid flow. The model employs the Monte Carlo method and it is based both on the knowledge of the mean velocity field of mixed liquid (mean motion) and of the spatial distribution of turbulence intensity ( fluctuating motion) in the investigated system - a cylindrical tank with radial baffles at the wall and with a standard (Rushton) turbine impeller in the vessel axis. Motion of the liquid is then superimposed with that of the bubbles in a still environment (ascending motion). The computation of the simulation includes determination of the spatial distribution of the gas holds-up (volumetric concentrations) in the agitated charge as well as of the total gas hold-up system depending on the impeller size and its frequency of revolutions, on the volumetric gas flow rate and the physical properties of gas and liquid. As model parameters, both liquid velocity field and normal gas bubbles distribution characteristics are considered, assuming that the bubbles in the system do not coalesce.

scholarly journals Application of Artificial Neural Networks to Streamline the Process of Adaptive Cruise Control

2021 ◽  
Vol 13 (8) ◽  
pp. 4572
Author(s):  
Jiří David ◽  
Pavel Brom ◽  
František Starý ◽  
Josef Bradáč ◽  
Vojtěch Dynybyl
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Adaptive Cruise Control ◽  
Control Unit ◽  
Driving Safety ◽  
Model Parameters ◽  
Cruise Control ◽  
Artificial Neural ◽  
Dynamic Obstacle ◽  
Braking Process

This article deals with the use of neural networks for estimation of deceleration model parameters for the adaptive cruise control unit. The article describes the basic functionality of adaptive cruise control and creates a mathematical model of braking, which is one of the basic functions of adaptive cruise control. Furthermore, an analysis of the influences acting in the braking process is performed, the most significant of which are used in the design of deceleration prediction for the adaptive cruise control unit using neural networks. Such a connection using artificial neural networks using modern sensors can be another step towards full vehicle autonomy. The advantage of this approach is the original use of neural networks, which refines the determination of the deceleration value of the vehicle in front of a static or dynamic obstacle, while including a number of influences that affect the braking process and thus increase driving safety.

scholarly journals Trigonometric Inference Providing Learning in Deep Neural Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6704
Author(s):  
Jingyong Cai ◽  
Masashi Takemoto ◽  
Yuming Qiu ◽  
Hironori Nakajo
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Activation Function ◽  
Trigonometric Approximation ◽  
Model Parameters ◽  
Training Algorithms ◽  
Activation Functions ◽  
Classical Training ◽  
Sum Formula

Despite being heavily used in the training of deep neural networks (DNNs), multipliers are resource-intensive and insufficient in many different scenarios. Previous discoveries have revealed the superiority when activation functions, such as the sigmoid, are calculated by shift-and-add operations, although they fail to remove multiplications in training altogether. In this paper, we propose an innovative approach that can convert all multiplications in the forward and backward inferences of DNNs into shift-and-add operations. Because the model parameters and backpropagated errors of a large DNN model are typically clustered around zero, these values can be approximated by their sine values. Multiplications between the weights and error signals are transferred to multiplications of their sine values, which are replaceable with simpler operations with the help of the product to sum formula. In addition, a rectified sine activation function is utilized for further converting layer inputs into sine values. In this way, the original multiplication-intensive operations can be computed through simple add-and-shift operations. This trigonometric approximation method provides an efficient training and inference alternative for devices with insufficient hardware multipliers. Experimental results demonstrate that this method is able to obtain a performance close to that of classical training algorithms. The approach we propose sheds new light on future hardware customization research for machine learning.

scholarly journals Explaining Neural Networks Using Attentive Knowledge Distillation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1280
Author(s):  
Hyeonseok Lee ◽  
Sungchan Kim
Keyword(s):  
Neural Networks ◽  
Model Prediction ◽  
Saliency Map ◽  
Model Parameters ◽  
Learning Capability ◽  
Fine Grained ◽  
Network Layers ◽  
Saliency Maps ◽  
Novel Approach ◽  
Knowledge Distillation

Explaining the prediction of deep neural networks makes the networks more understandable and trusted, leading to their use in various mission critical tasks. Recent progress in the learning capability of networks has primarily been due to the enormous number of model parameters, so that it is usually hard to interpret their operations, as opposed to classical white-box models. For this purpose, generating saliency maps is a popular approach to identify the important input features used for the model prediction. Existing explanation methods typically only use the output of the last convolution layer of the model to generate a saliency map, lacking the information included in intermediate layers. Thus, the corresponding explanations are coarse and result in limited accuracy. Although the accuracy can be improved by iteratively developing a saliency map, this is too time-consuming and is thus impractical. To address these problems, we proposed a novel approach to explain the model prediction by developing an attentive surrogate network using the knowledge distillation. The surrogate network aims to generate a fine-grained saliency map corresponding to the model prediction using meaningful regional information presented over all network layers. Experiments demonstrated that the saliency maps are the result of spatially attentive features learned from the distillation. Thus, they are useful for fine-grained classification tasks. Moreover, the proposed method runs at the rate of 24.3 frames per second, which is much faster than the existing methods by orders of magnitude.

Numerical modeling of two-phase binary fluid mixing using mixed finite elements

2012 ◽  
Vol 16 (4) ◽  
pp. 1101-1124 ◽  
Author(s):  
Shuyu Sun ◽  
Abbas Firoozabadi ◽  
Jisheng Kou
Keyword(s):  
Numerical Modeling ◽  
Finite Elements ◽  
Mixed Finite Elements ◽  
Fluid Mixing ◽  
Two Phase ◽  
Binary Fluid
Sign in / Sign up

Export Citation Format

Share Document