skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Data Driven Smart Proxy for CFD Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics, Part Three: Model Building at the Layer Level

Abstract

To ensure the usefulness of simulation technologies in practice, their credibility needs to be established with Uncertainty Quantification (UQ) methods. In this project smart proxy is introduced to significantly reduce the computational cost of conducting large number of multiphase CFD simulations. Smart proxy for CFD models are developed using pattern recognition capabilities of Artificial Intelligence (AI), Machine Learning (LM) and Data Mining (DM) technologies. Several CFD simulation runs with different inlet air velocities for a rectangular fluidized bed are used to create a smart CFD proxy that is capable of replicating the CFD results for a wide variety of inlet velocities. The smart CFD proxy is validated with blind CFD runs (CFD runs that have not played any role during the development [training, calibration and validation] of the smart CFD proxy). In our earlier work, CFD data was used to train ANN at the cell level. That is an ANN was trained for each computational cell used in the CFD simulations. In the present work, the ANN is constructed and trained based on cross sectional area average of each variable, such as pressure, velocities and volume fraction (Layer Level). This leads to improvements in the training time at the expensemore » of less spatial resolution. The resulting trained ANN provides spatially average value of parameters of interest, along the length of the fluidized bed. Upon completion of this project, UQ studies that rely on hundreds or thousands of smart CFD proxy runs can be accomplished in minutes. Following figure demonstrates a validation example (blind CFD run) showing the results from the MFiX and the smart CFD proxy for pressure drop across a fluidized bed at time-step of 1400 (the layer number corresponds to the vertical location in the bed).« less

Authors:
 [1];  [2];  [3];  [4];  [5];  [6]
  1. West Virginia Univ., Morgantown, WV (United States). Petroleum & Natural Gas Engineering Dept.
  2. West Virginia Univ., Morgantown, WV (United States). Petroleum & Natural Gas Engineering Dept.; Oak Ridge Inst. for Science and Education (ORISE), Oak Ridge, TN (United States)
  3. National Energy Technology Lab. (NETL), Morgantown, WV (United States)
  4. National Energy Technology Lab. (NETL), Morgantown, WV (United States); West Virginia Univ., Morgantown, WV (United States). Research Corporation
  5. National Energy Technology Lab. (NETL), Morgantown, WV (United States); AECOM, Morgantown, WV (United States)
  6. National Energy Technology Lab. (NETL), Morgantown, WV (United States); ALPEMI Consulting, LLC, Phoenix, AZ (United States)
Publication Date:
Research Org.:
National Energy Technology Lab. (NETL), Pittsburgh, PA, and Morgantown, WV (United States)
Sponsoring Org.:
USDOE Office of Fossil Energy (FE)
OSTI Identifier:
1463895
Report Number(s):
NETL-PUB-21860
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Machine Learning; Neural Network; Multiphase Flow; CFD

Citation Formats

Ansari, A., Mohaghegh, S., Shahnam, M., Dietiker, J. F., Li, T., and Gel, A. Data Driven Smart Proxy for CFD Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics, Part Three: Model Building at the Layer Level. United States: N. p., 2018. Web. doi:10.2172/1463895.
Ansari, A., Mohaghegh, S., Shahnam, M., Dietiker, J. F., Li, T., & Gel, A. Data Driven Smart Proxy for CFD Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics, Part Three: Model Building at the Layer Level. United States. doi:10.2172/1463895.
Ansari, A., Mohaghegh, S., Shahnam, M., Dietiker, J. F., Li, T., and Gel, A. Tue . "Data Driven Smart Proxy for CFD Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics, Part Three: Model Building at the Layer Level". United States. doi:10.2172/1463895. https://www.osti.gov/servlets/purl/1463895.
@article{osti_1463895,
title = {Data Driven Smart Proxy for CFD Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics, Part Three: Model Building at the Layer Level},
author = {Ansari, A. and Mohaghegh, S. and Shahnam, M. and Dietiker, J. F. and Li, T. and Gel, A.},
abstractNote = {To ensure the usefulness of simulation technologies in practice, their credibility needs to be established with Uncertainty Quantification (UQ) methods. In this project smart proxy is introduced to significantly reduce the computational cost of conducting large number of multiphase CFD simulations. Smart proxy for CFD models are developed using pattern recognition capabilities of Artificial Intelligence (AI), Machine Learning (LM) and Data Mining (DM) technologies. Several CFD simulation runs with different inlet air velocities for a rectangular fluidized bed are used to create a smart CFD proxy that is capable of replicating the CFD results for a wide variety of inlet velocities. The smart CFD proxy is validated with blind CFD runs (CFD runs that have not played any role during the development [training, calibration and validation] of the smart CFD proxy). In our earlier work, CFD data was used to train ANN at the cell level. That is an ANN was trained for each computational cell used in the CFD simulations. In the present work, the ANN is constructed and trained based on cross sectional area average of each variable, such as pressure, velocities and volume fraction (Layer Level). This leads to improvements in the training time at the expense of less spatial resolution. The resulting trained ANN provides spatially average value of parameters of interest, along the length of the fluidized bed. Upon completion of this project, UQ studies that rely on hundreds or thousands of smart CFD proxy runs can be accomplished in minutes. Following figure demonstrates a validation example (blind CFD run) showing the results from the MFiX and the smart CFD proxy for pressure drop across a fluidized bed at time-step of 1400 (the layer number corresponds to the vertical location in the bed).},
doi = {10.2172/1463895},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2018},
month = {5}
}