GPyro: uncertainty-aware temperature predictions for additive manufacturing

Abstract

In additive manufacturing, process-induced temperature profiles are directly linked to part properties, and their prediction is crucial for achieving high-quality products. Temperature predictions require an accurate process model, which is usually either a physics-based or a data-driven simulator. Although many high-performance models have been developed, they all suffer from disadvantages such as long execution times, the need for large datasets, and error accumulation in long prediction horizons. These caveats undermine the utility of such modeling approaches and pose problems in their integration within iterative optimization and closed-loop control schemes. In this work, we introduce GPyro, a generative model family specifically designed to address these issues and enable fast probabilistic temperature predictions. GPyro combines physics-informed and parametric regressors with a set of smooth attention mechanisms and learns the evolution of the dynamics inherent to a system by employing Gaussian processes. The model predictions are equipped with confidence intervals quantifying the uncertainty at each timestep. We applied GPyro to Wire-arc additive manufacturing and learned an accurate model from a single experiment on a real welding cell, almost in real-time. Our model can be easily integrated within existing loop-shaping and optimization frameworks.