Skip to main content

Meshfree and Novel Finite Element Methods with Applications


 

Berkeley, California


September 25-27, 2022

 

Front page menu

  • Home
  • Organizers
  • Program
  • Speakers
  • Lodging/Travel Information
  • Abstract Submission
  • MFEM2022 Travel Awards and Information
  • Minisymposia
  • Presenter Instructions
  • Registration
  • Sponsorship
  • Home

Contact Information

For administrative information about the conference, contact us at admin@usacm.org.

Important Dates

Abstract submission: March 1 - May 31 (deadline extended)

Early registration: March 15 - August 22 (extended)

Late/on site registration: August 23 - September 27

 

       USACMLOGO-3.jpg

Platinum Level

ANSYS logo without-blur.jpg

Gold Level

Oak Ridge National Laboratory

Silver Level

K&C Logo w Alpha-Resized.jpg

Sandia National Laboratories

Bronze Level

logo with slogan_2271x1029_0.png

 

 

 

JSOL_logo.png

 


 

 

 

 

Policies

USACM Code of Conduct

Using Artificial Intelligence in Engineering Simulation

ABSTRACT:

The world around us is governed by the laws of physics which are captured by equations that model various physics; we solve these equations using numerical methods such as finite element analysis and finite difference methods. In this talk we will explore the use of IA, Machine Learning and Deep Learning to accelerate these engineering simulations. We will describe how we are accelerating our solvers by factors of 10X-100X using Machine Learning in specific physics areas.  We have developed an ML-based Partial Differential Equation solver and applied it to accelerate Fluid Dynamics problems and will report our results on our Fluent CFD software.  We will report on an end-to-end chip packaging solution using a combination of data-driven and physics-informed neural networks. We have integrated it within our Redhawk/IcePak/Mechanical solutions for Conjugate Heat Transfer. We will describe approaches to support fast design exploration/optimization using ML frameworks. We are also providing ML-enabled assistance in various steps of simulation workflows such as initial meshing, smart sub-modeling, user experience and automati selection fo parameters. We will report on automatically setting the best parameters in Fluent/Live AMG solver. We report on geometry encoding methods to scale our ML methods to any geometry. We will discuss a Fusion model to combine test data with low fidelity simulation data to produce high fidelity simulations. We will also report on a new ML framework to improve the productivity of any ML developer working in the simulation area. Finally, we wil summarize various AI/ML enabled products that are being released this year and in future years.


BIOGRAPHY OF SPEAKER:
Prith Banerjee is Chief Technology Officer at Ansys, and is responsible for developing the long term technology strategy for the company Prior to that, he was EVP and CTO of ABB and Schneider Electric, and also Managing Director of Global R&D at Accenture, and Director of HP Labs. He spent his early years in academia as a Professor of Electrical and Computer Engineering, and Dean of Engineering at the University of Illinois and Northwestern University. Banerjee currently serves on the Board of Directors of Turntide Technologies. In the past, he has served on Boards for Cray, Inc., Cubic Corporation, the Anita Borg Institute, and the Technical Advisory Boards of Ambit, Atrenta , Calypto, and Cypress. He is a Fellow of the AAAS, ACM and IEEE and a recipient of the ASEE Terman Award and the NSF Presidential Young Investigator Award. He received a B.Tech. in electronics engineering from the Indian Institute of Technology, Kharagpur, and an M.S. and Ph.D. in electrical engineering from the University of Illinois, Urbana.
 
Powered by Drupal