ThermoPore: Predicting part porosity based on thermal images using deep learning

• Published in: Additive manufacturing Vol. 95; p. 104503
• Main Authors: Pak, Peter, Ogoke, Francis, Polonsky, Andrew, Garland, Anthony, Bolintineanu, Dan S., Moser, Dan R., Arnhart, Mary, Madison, Jonathan, Ivanoff, Thomas, Mitchell, John, Jared, Bradley, Salzbrenner, Brad, Heiden, Michael J., Barati Farimani, Amir
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.11.2024; Elsevier
• Subjects: Deep learning; Digital twin; Laser powder bed fusion; Thermal imaging; Video vision transformer; Deep learning; Laser powder bed fusion; Thermal imaging; Digital twin; Video vision transformer
• ISSN: 2214-8604
• DOI: 10.1016/j.addma.2024.104503

Part qualification is often a critical and labor-intensive process in additive manufacturing, particularly in the detection of defects such as porosity, which stands to benefit significantly from advancements in machine learning. We present a deep learning approach for quantifying and localizing ex-situ porosity within Laser Powder Bed Fusion fabricated samples utilizing in-situ thermal image monitoring data. Our goal is to build the real time porosity map of parts based on thermal images acquired during the build. The quantification task builds upon the established Convolutional Neural Network model architecture to predict pore count and the localization task leverages the spatial and temporal attention mechanisms of the novel Video Vision Transformer model to indicate areas of expected porosity. Our model for porosity quantification achieved a R2 score of 0.57 and our model for porosity localization produced an average Intersection over Union (IoU) score of 0.32 and a maximum of 1.0. This work is setting the foundations of part porosity “Digital Twins” based on additive manufacturing monitoring data and can be applied downstream to reduce time-intensive post-inspection and testing activities during part qualification and certification. In addition, we seek to accelerate the acquisition of crucial insights normally only available through ex-situ part evaluation by means of machine learning analysis of in-situ process monitoring data.