Presented by Gavin Jones, Principal Application Engineer
Gavin Jones, Principal Application Engineer, is responsible for performing simulation and statistical work for clients in the automotive, aerospace, defense, gas turbine, and other industries. He is a member of the SAE Chassis Committee as well as a member of AIAA’s Digital Engineering Integration Committee. Gavin is also a key contributor in SmartUQ’s Digital Twin/Digital Thread initiative.
Machine learning (ML) and artificial intelligence (AI) are hot topics in the engineering simulation community. These techniques have applications across the product lifecycle. For example, a design engineer can train an ML model to find optimal designs using data from simulations. ML-assisted simulations can also be used for many other purposes such as manufacturing process control, predictive maintenance, tolerance analysis, and computational risk analysis.
However, using ML and AI for simulation poses several major challenges. Many engineering simulations are deterministic, but the underlying problems they model are subject to uncertainties and, therefore, are stochastic in nature. Although AI may produce an optimal solution, it could be one that corresponds to an unrealistic scenario rather than the desired solution incorporating real-world uncertainty. To achieve its true aim, the AI system must be trained in the stochastic nature of the outcomes of interest by incorporating uncertainty into its decision rules. Other challenges include how to understand uncertainties in ML and AI models themselves and how to build such models for sparse or small data sets or data sets with many inputs.
This 60-minute webinar provides an introduction to the topics of AI and ML methods for analyzing COMSOL® simulations including how to address the associated challenges. Points will be illustrated in SmartUQ using data collected from a COMSOL® simulation via SmartUQ’s COMSOL® integration feature.
An audience Q&A follows the technical presentation.