Presentation
Computationally-Accelerated Engineering at GE: Physics + Deep Learning
Presenter
Event Type
HPC Impact Showcase
W
TUT
TP
EX
EXH
Industry
TimeWednesday, November 14th4:30pm - 5pm
LocationD171
DescriptionIn support of a global team of engineers working on designing, building and servicing complex machines such as jet engines and gas turbines, GE Global Research hosts a centralized HPC environment for computational modeling, simulation and analytics. GE’s Digital Thread for Design (DT4D) framework revolutionizes product engineering by harnessing data services, automation and machine learning to advance multi-disciplinary modeling and simulation productivity and capability. Engineers can offload previously labor-intensive, manual, and ad-hoc tasks to focus on improving product performance and reliability. Through collaborations between domain experts and data scientists, we introduce “Deep Physics” – blending traditional physics models and knowledge with the emerging power of deep learning to enable deeper exploration of parametric trade-off spaces and reshape the state of the art.
