CAE: Landscape of AI Models w.r.t. GenAI (not considering LLMs, agents, or copilots here)
ChatGPT is cool, but I'm more obsessed with 3D field predictions from AI/ML "ROMs". Let's cover a taxonomy of AI/ML models in the CAE space, and how some comprise "Generative AI" (CFD, FEA, etc.)
I’m a broken record - I spend my midnight hours writing to you in order to help sift through the cloud of hype/non-sense that gravitates around the very real value AI/ML can bring the CAE (simulation) engineering community. I shouldn’t even say ‘can bring’, since it’s already being used in industry for >2 years (and no, not just research teams in exploratory investigations for new methods).
Let’s start with Generative AI
(BTW, this entire article is human written).
We’ve all taken the online courses, listened to the podcasts, and read the thought pieces from big names on what Generative AI is/can do within the lens of the mainstream layman (chatbots, image generation, etc.). Pivot the definition of Generative AI into the context CAE/engineering simulation community, while removing use cases focused on agents/LLMs/copilots - then ask: what does it look like? The number of people who are comfortable explaining it thoroughly has dropped orders of magnitudes from the generic online “How Generative AI will change society” class. Not discrediting or putting down such courses — I have taken them a while ago and loved them — just to say, there’s a real lack of AI/ML knowledge for mechanical and aerospace engineering applications.
I am not a special person, but I do have lots of experience in this area and am happy to help incrementally crystalize your understanding at this time. For example, I pulled this project deep from my archives to get this image - even back in 2021 I did a “Generative AI” project for designing a compressor blade based on a machine learning model trained on CFD data.
