Integration of AI in NCSA Delta System Boosts Stress Prediction – A Review by


At the National Center for Supercomputing Applications (NCSA) and The Grainger College of Engineering, University of Illinois Urbana-Champaign (UIUC), researchers have made promising advancements in stress prediction research with the application of artificial intelligence. They have centered their efforts on developing deep operator network (DeepONet) methods, hoping to enhance the predictions of stress responses in intricate geometries, such as those found in additive manufacturing. By using the NCSA’s Delta platform, these researchers have produced significantly faster outcomes compared to the traditional finite element methodologies.

The conducted research was facilitated through the Illinois Computes program, which provides comprehensive computing and data storage resources. The program has fostered cross-disciplinary collaborations, combining the fields of machine learning with computational mechanics. The Delta system, known for its top-notch GPU computing capabilities, proved fundamental in the training of deep neural networks and the generation of training data via Abaqus software.

This research has produced two notable publications. The first publication, featured in “Computer Methods in Applied Mechanics and Engineering,” presents a pioneering DeepONet utilizing residual U-Net (ResUNet) to encode intricate geometries. This method represents the first application of ResUNet within DeepONet architecture, showing a superior memory efficiency and flexibility compared to traditional techniques.

The second paper, published in “Engineering Applications of Artificial Intelligence,” details another advanced version of DeepONet, known as S-DeepONet. This employs sophisticated sequential learning techniques, offering enhanced precision in multi-physics solutions varying under thermal and mechanical loads.

“The advent of additive manufacturing has revolutionized the field, introducing nearly infinite possibilities for its application,” remarked Iwona Jasiuk, a Professor of Mechanical Science and Engineering at UIUC.

“DeepONet serves as a robust and fast computational tool capable of simulating the additive manufacturing process at various spatial and temporal scales. These simulations are crucial for gaining a deeper understanding of the additive manufacturing process, how to implement it, and how to monitor it.”

This research is not only a significant advancement in AI applications, but it also has considerable implications on advanced manufacturing processes and the development of digital twins. The joint venture between NCSA and MechSE emphasizes the harmonious blend of multidisciplinary expertise and state-of-the-art technology.

Come and let us know your thoughts on our Facebook, Twitter, and LinkedIn pages, and don’t forget to sign up for our weekly additive manufacturing newsletter to get all the latest stories delivered right to your inbox.

Original source


“Why did the 3D printer go to therapy? Because it had too many layers of unresolved issues!”

Like it? Share with your friends!


Meet the mastermind behind GCode-Guru, a 3D printing wizard whose filament collection rivals their sock drawer. Here to demystify 3D tech with a mix of expert advice, epic fails, and espresso-fueled rants. If you've ever wondered how to print your way out of a paper bag (or into a new coffee cup), you're in the right place. Dive into the world of 3D printing with us—where the only thing more abundant than our prints is our sarcasm.


Your email address will not be published. Required fields are marked *

Choose A Format
Personality quiz
Series of questions that intends to reveal something about the personality
Trivia quiz
Series of questions with right and wrong answers that intends to check knowledge
Voting to make decisions or determine opinions
Formatted Text with Embeds and Visuals
The Classic Internet Listicles
The Classic Internet Countdowns
Open List
Submit your own item and vote up for the best submission
Ranked List
Upvote or downvote to decide the best list item
Upload your own images to make custom memes
Youtube and Vimeo Embeds
Soundcloud or Mixcloud Embeds
Photo or GIF
GIF format