A deep neural network for classification of melt-pool images in metal additive manufacturing

• Published in: Journal of intelligent manufacturing Vol. 31; no. 2; pp. 375 - 386
• Main Authors: Kwon, Ohyung, Kim, Hyung Giun, Ham, Min Ji, Kim, Wonrae, Kim, Gun-Hee, Cho, Jae-Hyung, Kim, Nam Il, Kim, Kangil
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-02-2020; Springer Nature B.V
• Subjects: Additive manufacturing; Artificial neural networks; Business and Management; Classification; Control; Defective products; Failure rates; Image classification; Laser beam melting; Lasers; Machines; Manufacturing; Mechatronics; Neural networks; Processes; Production; Robotics; Powder bed fusion; Deep neural network; Additive manufacturing; Selective laser melting; Melt-pool classification
• ISSN: 0956-5515; 1572-8145
• DOI: 10.1007/s10845-018-1451-6

By applying a deep neural network to selective laser melting, we studied a classification model of melt-pool images with respect to 6 laser power labels. Laser power influenced to form pores or cracks determining the part quality and was positively-linearly dependent to the density of the part. Using the neural network of which the number of nodes is dropped with increasing the layer number achieved satisfactory inference when melt-pool images had blurred edges. The proposed neural network showed the classification failure rate under 1.1% for 13,200 test images and was more effective to monitor melt-pool images because it simultaneously handled various shapes, comparing with a simple calculation such as the sum of pixel intensity in melt-pool images. The classification model could be utilized to infer the location to cause the unexpected alteration of microstructures or separate the defective products non-destructively.