Our collaborative paper with Case Western Reserve University, "Attention Mechanism-Incorporated Deep Learning for AM Quality Prediction", won the Best Paper Award at the 53^rd CIPR Conference on Manufacturing Systems, which is virtually hosted this year.

Abstract: To improve part quality consistency in Additive Manufacturing, it is critical to understand the relationship between mechanisms underlying the layer-wise printing process and the resulting product quality. This paper investigates this relationship by incorporating attention mechanism into a Long Short-term Memory network, using Fused Deposition Modeling as a case study. In-process thermal and mechanical variations, as reflected in the temperature and vibration measured in-situ, are fused with machine settings to establish a data-driven model for part tensile strength prediction. Analysis using attention mechanism quantified the influence of each process parameters on the prediction result, providing insight into the network operation.