Machine learning to assist filtered two‐fluid model development for dense gas–particle flows

AIChE Journal ◽  
2020 ◽  
Vol 66 (6) ◽  
Author(s):  
Li‐Tao Zhu ◽  
Jia‐Xun Tang ◽  
Zheng‐Hong Luo
Keyword(s):  
Machine Learning ◽  
Fluid Model ◽  
Model Development ◽  
Dense Gas ◽  
Particle Flows ◽  
Two Fluid Model ◽  
Two Fluid

Practical validation of the two-fluid model applied to dense gas–solid flows in fluidized beds

2007 ◽  
Vol 62 (21) ◽  
pp. 5854-5869 ◽  
Author(s):  
HÅvard Lindborg ◽  
Magne Lysberg ◽  
Hugo A. Jakobsen
Keyword(s):  
Fluidized Beds ◽  
Fluid Model ◽  
Dense Gas ◽  
Two Fluid Model ◽  
Practical Validation ◽  
Two Fluid

scholarly journals Machine Learning Augmented Two-Fluid Model for Segregated Flow

Fluids ◽  
2021 ◽  
Vol 7 (1) ◽  
pp. 12
Author(s):  
Ayush Rastogi ◽  
Yilin Fan
Keyword(s):  
Machine Learning ◽  
Oil And Gas ◽  
Fluid Model ◽  
Momentum Conservation ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Practical Applications ◽  
Segregated Flow ◽  
Two Fluid Model ◽  
Two Fluid

Segregated flow, including stratified and annular flows, is commonly encountered in several practical applications such as chemical, nuclear, refrigeration, and oil and gas industries. Accurate prediction of liquid holdup and the pressure gradient is of great importance in terms of system design and optimization. The current most widely accepted model for segregated flow is a physics-based two-fluid model that treats gas and liquid phases separately by incorporating mass and momentum conservation equations. It requires empirically derived closure relationships that have the limitation of being applicable only under a narrow range of input parameters under which they were developed. In this paper, we proposed a more generalized machine learning augmented two-fluid model, using a database that spans the range of various flowing conditions and fluid properties. Machine learning algorithms such as random forest, neural networks, and gradient boosting were tested for the best performing data-driven predictive model. The new model proposed in this work successfully captures the complex, dynamic, and non-linear relationships between the friction factor and flowing conditions. A comprehensive model evaluation against nineteen existing correlations shows the best results from the proposed model.

A Numerical Method for Gas-Particle Flows With Accumulation

2006 ◽  
Author(s):  
Xiang Zhao ◽  
Sijun Zhang
Keyword(s):  
Mathematical Model ◽  
Numerical Modelling ◽  
Numerical Method ◽  
Fluid Model ◽  
Particle Flow ◽  
Flow Conditions ◽  
Accumulation Zone ◽  
Particle Flows ◽  
Two Fluid Model ◽  
Two Fluid

A mathematical model is proposed to describe the gas-particle flow in a bed packed with particles. The model is in essence the same as the two fluid model developed on the basis of the space-averaged theorem but extended to consider the interactions among the gas, powder and packed particles and the static and dynamic holdups of powder. In particular, a method is proposed to determine the boundary between powder mobile and non-mobile zones, i.e. the profile of powder accumulation zone. The validity of the numerical modelling is examined by comparing the predicted and measured distributions of powder accumulation under various flow conditions.

Sign in / Sign up

Export Citation Format

Share Document