Powder bed defect classification methods: deep learning vs traditional machine learning

Purpose This paper aims to discuss the development of a defect classification system that can be used to detect and classify powder bed surface defects from captured layer images without the need for specialised computational hardware. The idea is to develop this system by making use of more traditional machine learning (ML) models instead of using computationally intensive deep learning (DL) models. Design/methodology/approach The approach that is used by this study is to use traditional image processing and classification techniques that can be applied to captured layer images to detect and classify defects without the need for DL algorithms. Findings The study proved that a defect classification algorithm could be developed by making use of traditional ML models with a high degree of accuracy and the images could be processed at higher speeds than typically reported in literature when making use of DL models. Originality/value This paper addresses a need that has been identified for a high-speed defect classification algorithm that can detect and classify defects without the need for specialised hardware that is typically used when making use of DL technologies. This is because when developing closed-loop feedback systems for these additive manufacturing machines, it is important to detect and classify defects without inducing additional delays to the control system.