Data Driven Smart Proxy for CFD Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics, Report Two: Model Building at the Cell Level
- West Virginia Univ., Morgantown, WV (United States). Petroleum and Natural Gas Engineering Dept.
- West Virginia Univ., Morgantown, WV (United States). Petroleum and Natural Gas Engineering Dept.; Oak Ridge Inst. for Science and Education (ORISE), Oak Ridge, TN (United States)
- National Energy Technology Lab. (NETL), Morgantown, WV (United States). Research and Innovation Center (R&IC) and Energy Conversion Engineering Directorate
- National Energy Technology Lab. (NETL), Morgantown, WV (United States). Research and Innovation Center (R&IC) and Energy Conversion Engineering Directorate; West Virginia Univ., Morgantown, WV (United States). Research Corp.
- National Energy Technology Lab. (NETL), Morgantown, WV (United States). Research and Innovation Center (R&IC) and Energy Conversion Engineering Directorate; AECOM, Morgantown, WV (United States)
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, which is typically required for non-intrusive UQ analysis. Smart proxy for CFD models are developed using pattern recognition capabilities of Artificial Intelligence (AI) 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 the entire geometry and inlet velocity range. The smart CFD proxy is validated with blind CFD runs (CFD runs that have not played any role during the development of the smart CFD proxy). The developed and validated smart CFD proxy generates its results in seconds with reasonable error (less than 10%). 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 simulation and the smart CFD proxy for pressure distribution across a fluidized bed at a given time-step (the layer number corresponds to the vertical location in the bed).
- Research Organization:
- National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)
- Sponsoring Organization:
- USDOE Office of Fossil Energy (FE)
- OSTI ID:
- 1431303
- Report Number(s):
- NETL-PUB-21634
- Country of Publication:
- United States
- Language:
- English
Similar Records
Data Driven Smart Proxy for CFD: Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics (Part 1)
Annual Report: Carbon Capture Simulation Initiative (CCSI) (30 September 2013)