[HTML][HTML] Convective heat transfer modelling in dry-running polymer spur gears

V Roda-Casanova, F Sanchez-Marin… - International Journal of …, 2023 - Elsevier
Heat convection is an important phenomenon in the process of cooling polymer spur gears
running in dry conditions, which ultimately affects the strength of the gears. In order to gain …

[HTML][HTML] Validation of CFD models of urban microclimates under high temperature and humidity conditions during daytime heatwaves in dense low-rise areas

G Kim, G Lee - Building and Environment, 2024 - Elsevier
In the midst of the ongoing climate crisis, there is a growing need to study the effects of
climate on humans, especially those of the microclimates that surround humans and their …

Optimizing throughput of Seq2Seq model training on the IPU platform for AI-accelerated CFD simulations

P Rościszewski, A Krzywaniak, S Iserte, K Rojek… - Future Generation …, 2023 - Elsevier
Abstract Intelligence Processing Units (IPU) have proven useful for many AI applications. In
this paper, we evaluate them within the emerging field of AI for simulation, where traditional …

A study on the performance of distributed training of data-driven CFD simulations

S Iserte, A González-Barberá… - … Journal of High …, 2023 - journals.sagepub.com
Data-driven methods for computer simulations are blooming in many scientific areas. The
traditional approach to simulating physical behaviors relies on solving partial differential …

Unleashing the Potential of Mixed Precision in AI-Accelerated CFD Simulation on Intel CPU/GPU Architectures

K Halbiniak, K Rojek, S Iserte… - … on Computational Science, 2024 - Springer
CFD has emerged as an indispensable tool for comprehending and refining fluid flow
phenomena within engineering domains. The recent integration of CFD with AI has unveiled …

Physics-informed reduced-order learning from the first principles for simulation of quantum nanostructures

M Veresko, MC Cheng - Scientific Reports, 2023 - nature.com
Multi-dimensional direct numerical simulation (DNS) of the Schrödinger equation is needed
for design and analysis of quantum nanostructures that offer numerous applications in …

Adaptation of AI-accelerated CFD Simulations to the IPU Platform

P Rościszewski, A Krzywaniak, S Iserte, K Rojek… - … Conference on Parallel …, 2022 - Springer
Abstract Intelligence Processing Units (IPU) have proven useful for many AI applications. In
this paper, we evaluate them within the emerging field of AI for simulation, where traditional …

Chemical Mixing Simulations with Integrated AI Accelerator

K Rojek, R Wyrzykowski, P Gepner - International Conference on …, 2023 - Springer
In this work, we develop a method for integrating an AI model with a CFD solver to predict
chemical mixing simulations' output. The proposed AI model is based on a deep neural …

[PDF][PDF] Unleashing the Potential of Mixed Precision in AI-Accelerated CFD Simulation on Intel CPU/GPU Architectures

S Iserte, R Wyrzykowski - iccs-meeting.org
CFD has emerged as an indispensable tool for comprehending and refining fluid flow
phenomena within engineering domains. The recent integration of CFD with AI has unveiled …