AI for Simulation: Current Possibilities and Future Challenges

Artificial Intelligence (AI) is becoming more and more a part of the activities traditionally covered by the engineering analysis and simulation community. Recent advances in the application of AI, machine learning (deep learning) and predictive analytics, have brought these technologies to the fore in every area of industry.

This seminar hosted by the NAFEMS Americas Steering Committee brought together speakers from the end-user, consultancy, and academic industries to discuss where we are and how these technologies are being used to advance significantly the engineering analysis and simulation capabilities and approaches over the next 10 years.

Resource Abstract

If you have a smart phone then you have and using AI (data-driven artificial intelligence). A disruptive technology that is now ubiquitous in our daily life for work and play. Digital transformation, Industry 4.0, Society 5.0, digital twin, etc. are global topics driving a safe, sustainable and resilient society and businesses. AI and Simulation are key actors, individually and in combination. The latter is exciting, offers breakthroughs not possible before. For example, train a deep learning network model with existing physics-based simulation and metadata for AI to predict result to interact with users in real-time. With tacit and other knowledge learnt by the trained model, it further open up democratisation of simulation and usages. In this presentation, we look at the AI for Simulation journey so far – what is possible and challenges ahead. We will incorporate industrial use cases in CAD and CAE to demonstrate.