Developing Digital Twins for Energy Applications using PhysicsNeMo

, Senior Software Engineer, NVIDIA
, General Engineer, Battelle
Developing efficient techniques for reducing carbon emissions, carbon capture, and mitigation and storage processes involves detailed computer simulations of phenomena involving fluid mechanics, heat transfer, and chemical reactions. Conventional modeling techniques such as computational fluid dynamics (CFD) are far too slow for large-scale design and engineering optimization processes and uncertainty quantification, which are integral components in a product development cycle. We'll focus on developing a digital twin of a power plant boiler, capable of modeling turbulent reacting flows, using NVIDIA’s Physics Informed Neural Network (PINN) product, which requires orders-of-magnitude less time than traditional CFD methods for providing predictions over a very high-dimensional input space, while maintaining very high accuracy.
活动: GTC Digital Spring
日期: March 2022
行业: Energy
话题: HPC - Computational Fluid Dynamics
级别: 中级技术
语言: 英语
所在地: