Avnet Silica and byteLAKE are among gold partners of Machine Learning Prague | Online conference, the most practical online conference focusing on ML, AI, and Deep Learning applications. If you’d like to participate, here’s a 20% discount code for our community members, just use — avnetsilica20 or bytelake20 (insert it in lower case) when purchasing a ticket.
From byteLAKE’s perspective, we decided that this year we will focus completely, 100% on our research and development efforts related to leveraging Artificial Intelligence (AI) to accelerate Computational Fluid Dynamics (CFD) engineering simulations.
This year, during MLPrague’21, byteLAKE will talk and present the results of their R&D efforts in accelerating CFD simulations with Deep Learning.
For those of you who might not be familiar with what CFD is, well, these are very complex algorithms if you will, or software tools that are used to study and understand fluid flow related problems. It’s widely used across industries in chemical mixing, process sciences, pharmaceutical and biomedical science, in engineering etc. Moreover, CFD has been accepted for regulatory purposes to assess safety, architectural or environmental impact aspects of various phenomena. CFD helps for instance investigate the effect of parameters such as bottle geometry, surface tension, or inclination on bottle emptying processes, enables engineers to model optimal tanks of any size by taking into account various flow details, such as internal velocities, turbulence parameters, or even bubble sizes, particle sizes, as well as overall quantities, such as mixing time.
CFD simulations take time, usually anything between many hours to many days, and process huge amounts of data over the span of thousands or tens or hundreds of thousands of iterations. Therefore a very valid question is: can we reduce the time of such simulations from hours to minutes? Or can we predict the final result in 100 or even 10 iterations instead of many thousands?
Real world challenge: can we accelerate CFD simulations so that we get the results withing minutes vs. hours or days? Or within 10 or 100 iterations vs. many thousands?
And the short answer is: YES, it can be achieved with a help of AI or should I say Deep Learning to be more specific. So, without any further due, I’d like to invite you to join our dedicated sessions during the upcoming Machine Learning Prague online event. There our CTO, Krzysztof Rojek will have a technical presentation during which he will describe how we reduced the time of chemical mixing simulations from hours to minutes. This will be followed by a question&answers session and continued with a mastermind / moderated panel discussion where we look at the subject from various perspectives like: do we really need AI or can we just add more cores, upgrade HPC infrastructure or perhaps add GPUs or even FPGAs to accelerate time to results? accuracy of predictions and how to train the AI models, future of AI in CFD and how this is going to revolutionize the way industries do the modelling and many more. We’ll also talk about how engineers can add AI to their existing CFD workflows or toolchains and address the concenrs related to… do we really need the AI strategy to start using AI in CFD? Last but not least, let me add that personally I am also very happy that we’ve managed to invite a great lineup of panelists too! So, book your calendars and RSVP to the event https://www.mlprague.com/#schedule-saturday.
Ah… last but not least. It’s an online event but we will have a virtual booth as well. So feel free to stop by and have a chat with us. You can also meet us at Avnet Silica’s booth and I highly recommend that you actually do so as very soon we will also be talking about leveraging their amazing portfolio in AI-powered applications for Industry 4.0 i.e. AI-assisted Visual Inspection and Big Data analytics.
AI-accelerated Computational Fluid Dynamics (CFD)
Presenter: Krzysztof Rojek, byteLAKE, CTO, PhD, DSc
When: Saturday, Feb 27th, 10:00–10:30 CET
CFD, Computational Fluid Dynamics are numerical methods or algorithms to solve fluid flows problems. They help model fluids density, velocity, pressure, temperature, and chemical concentrations in relation to time and space. Many industries such as automotive, chemical, aerospace, biomedical, power and energy, and construction rely on fast CFD analysis turnaround time. Typical applications include weather simulations, aerodynamic characteristics modeling and optimization, and petroleum mass flow rate assessment.
ByteLAKE has been working on leveraging Artificial Intelligence (AI) and Deep Learning to significantly accelerate CFD simulations. These typically take anything between hours, days or weeks. byteLAKE’s CFD Suite, a collection of AI models helps predict accurate results within minutes. During his presentation, Krzysztof Rojek will take share more details about the solution, its scalability, compatibility with CAE tools and OpenFOAM solvers and present benchmarks for commercial simulations. Also, Krzysztof will present how to get started with CFD Suite and accelerate your simulations.
Artificial Intelligence (AI) accelerating industrial Computational Fluid Dynamics (CFD) simulations
When: Saturday, Feb 27th, 13:30–14:30 CET / 7:30–8:30 ET
Computational Fluid Dynamics (CFD) are numerical methods used across many industries (chemical, pharma, automotive, construction, oil&gas just to name a few) to model fluids pressure, velocity, temperature, etc. Typical applications include modeling aerodynamics, chemical mixing, air flows around buildings, etc. CFD simulations usually take anything between many hours to even days, depending on the amount of information that needs to be processed i.e. geometry, boundary conditions, initial parameters like velocities, viscosity, etc. byteLAKE, a company specializing in machine and deep learning, has been developing a collection of Artificial Intelligence (AI) models that are targeted to significantly reduce time to results for such simulations.
We invite you to a moderated panel discussion where byteLAKE co-founders, together with a producer of the leading CFD tool for enterprise mixing analysis (MixIT), a company named Tridiagonal Solutions will discuss how Deep Learning models accelerate complex chemical mixing simulations. Panelists will talk about how such simulations help address various industries’ challenges, explain how AI helps reduce the cost of trial & error experiments and discuss the future of AI in the CFD space. We will also have representatives from Lenovo Data Center and Intel Corporation who will weigh in on the scalability of the technology, and how various hardware configurations can deliver maximum value for AI+CFD adopters.
Panelists:
- Marcin Rojek, Mariusz Kolanko, byteLAKE co-founders
- Damo Vedapuri, Tridiagonal Solutions, co-founder and Head — North American Operations
- Ashish Kulkarni, Tridiagonal Solutions, Head of Delivery
- Robert Daigle, Lenovo Data Center, Artificial Intelligence Innovation & Business Leader
- Andrzej Jankowski, Intel Corporation, Artificial Intelligence and IoT
Discussion will be moderated by: Valerio Rizzo, Lenovo, AI Lead
Read more about the AI-accelerated CFD topic in our dedicated blog post series at www.byteLAKE.com/en/AI4CFD-toc or go to our website at www.byteLAKE.com/en/CFDSuite.
PLATINUM PARTNER
CO-ORGANIZING PARTNER
GOLD PARTNERS
SILVER PARTNERS