Abstract
Simulations can reduce the time and cost to develop and deploy advanced technologies and enable their rapid scale-up for fossil fuel-based energy systems. However, to ensure their usefulness in practice, the credibility of the simulations needs to be established with uncertainty quantification (UQ) methods. The National Energy Technology Laboratory (NETL) has been applying non-intrusive UQ methodologies to categorize and quantify uncertainties in computational fluid dynamics (CFD) simulations of gas-solid multiphase flows. To reduce the computational cost associated with gas-solid flow simulations required for UQ analysis, techniques commonly used in the area of artificial intelligence (AI) and data mining are used to construct smart proxy models, which can reduce the computational cost of conducting large numbers of multiphase CFD simulations. The feasibility of using AI and machine learning to construct a smart proxy for a gas-solid multiphase flow has been investigated by looking at the flow and particle behavior in a non-reacting rectangular fluidized bed. The NETL’s in house multiphase solver, Multiphase Flow with Interphase eXchanges (MFiX), was used to generate simulation data for the rectangular fluidized bed. The artificial neural network (ANN) was used to construct a CFD smart proxy, which is able to reproduce the CFD results with reasonable error (about 10%). Several blind cases were used to validate this technology. The results show a good agreement with CFD runs while the approach is less computationally expensive. The developed model can be used to generate the time averaged results of any given fluidized bed with the same geometry with different inlet velocity in couple of minutes.
Highlights
Fossil fuel continues to be a reliable source of energy for power generation in the United States and worldwide
The National Energy Technology Laboratory (NETL) has been applying non-intrusive uncertainty quantification (UQ) methodologies to categorize and quantify uncertainties in computational fluid dynamics (CFD) simulations of gas-solid multiphase flows, which are encountered in fossil fuel-based energy systems [1,2,3,4]
Multiphase Flow with Interphase eXchanges (MFiX) simulation results of the rectangular fluidized bed are used as the training, calibration, MFiXsimulation simulation results rectangular fluidized are as the training, calibration, and validation data to build a spatio-temporal database forbed thebed construction oftraining, a fluidized bed smart results ofof thethe rectangular fluidized are usedused as the calibration, and and validation data to build a spatio-temporal database for the construction of a fluidized bed smart proxy
Summary
Fossil fuel continues to be a reliable source of energy for power generation in the United States and worldwide. The goal of this research project is to build a smart proxy model constructed from simulation data generated by high-fidelity CFD models to, in effect, replace the use of computationally expensive CFD for the design space under study for further analysis, optimization, and uncertainty quantification. A few hundred seconds of CFD simulation time can be used to construct a smart proxy, which can be used to explore the design performance of the unit after many hours of performance The uniqueness of this approach is in: Developing a unique engineering-based data preparation technology that optimizes the training of the neural networks. Kalantari-Dehghani et al [14] coupled numerical reservoir simulation with AI methods to develop a shale proxy model that was able to regenerate numerical simulation results in just a few seconds They introduced three different well-based tier systems to achieve a comprehensive input data-set for the ANN. Boosari [22,23] used a similar approach to model the behavior of dam break flow with the goal of reducing the computational time for the fluid flow simulations by developing a smart proxy model
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
