The Laser Powder Bed Fusion (L-PBF) process is being adopted in different industrial fields. However, L-PBF currently lacks process reproducibility and quality. Hence, quality monitoring techniques need to be adopted in order to reduce the process variability and to ensure a high-quality process. Accordingly, this work proposes a quality monitoring approach based on machine learning which links the optical signal of a layer to the density of the final part. The approach consists of selecting relevant statistical features from optical data and validating these features by assessing their ability in predicting the different density classes of different products. Afterwards, the approach is compared to a new deep learning framework that allows predicting a part density from the corresponding raw optical signals. This comparison allows assessing the relevance of the identified statistical features. The proposed monitoring approach is applied on cubical specimens produced with different process parameters, and the results are then discussed and analyzed.

激光粉末床熔合（L-PBF）工艺正在不同的工业领域中采用。但是，L-PBF目前缺乏工艺可重复性和质量。因此，需要采用质量监控技术，以减少过程的可变性并确保高质量的过程。因此，这项工作提出了一种基于机器学习的质量监控方法，该方法将一层的光信号与最终部件的密度联系起来。该方法包括从光学数据中选择相关的统计特征，并通过评估其预测不同产品的不同密度等级的能力来验证这些特征。然后，将该方法与新的深度学习框架进行比较，该框架允许根据相应的原始光学信号预测零件密度。该比较允许评估所识别的统计特征的相关性。所提出的监测方法应用于具有不同工艺参数的立方试样，然后讨论和分析结果。