Machine Learning (ML) and Artificial Intelligence (AI) are currently hot topics in the community of engineering simulation. These techniques have applications across the product lifecycle. For example, a design engineer can train an AI system to find optimal designs using data from simulations. AI assisted simulations can also be used for many other purposes such as manufacturing process control, predictive maintenance, tolerance analysis, and computational risk analysis.
Using ML and AI for simulation poses several major challenges. Many engineering simulations are deterministic, whereas the underlying problems they are modeling are subject to uncertainties and therefore stochastic in nature. The AI may produce an optimal solution, but one that corresponds to the unrealistic scenario where uncertainty does not exist, rather than the desired solution incorporating real world uncertainty. To achieve the true aim, the AI 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 webinar will discuss how building ML and AI models for engineering simulations can be challenging and methods to address these challenges.
