ANOMALY DETECTION OF LASER POWDER BED FUSION MELT POOL IMAGES USING COMBINED UNSUPERVISED AND SUPERVISED LEARNING METHODS
Paul Witherell, Brandon Lane, Ho Yeung, Zhuo Yang, Kincho Law
Laser Powder Bed Fusion (LPBF) is one of the most promising forms of Additive Manufacturing (AM), allowing easily customized metal manufactured parts. Industry use is currently limited due to the often unknown and unreliable part quality, which is in large part due to the complex relationships between process parameters that include laser power, laser speed, scan strategy, and other machine settings. To monitor part quality, a melt pool can be monitored with a camera aligned co-axially with the laser. However, the number of images acquired can be huge, exceeding hundreds of thousands of images for a single part. This paper investigates how the K-Means algorithm, an unsupervised machine learning method, can be used to cluster images of melt pools based on their shape, including undesirable anomalous melt pools. Another unsupervised learning method in this paper is the U-Net autoencoder, which identifies anomalous melt pools by identifying images with a large reconstruction loss. The K-Means clustering or autoencoder provides labels that can be used for training a convolutional neural network image classifier. The image classifier can then be used to identify anomalous melt pools during the LPBF process. This paper provides a first step for real time process control of the LPBF process by demonstrating how anomalous melt pools can potentially be automatically identified in real time.
International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
, Lane, B.
, Yeung, H.
, Yang, Z.
and Law, K.
ANOMALY DETECTION OF LASER POWDER BED FUSION MELT POOL IMAGES USING COMBINED UNSUPERVISED AND SUPERVISED LEARNING METHODS, International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, St Louis, MO, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=934397
(Accessed March 23, 2023)