Machine Learning-enabled feedback loops for metal powder bed fusion additive manufacturing

Abstract

Abstract Metal Powder Bed Fusion (PBF) has been attracting an increasing attention as an emerging metal Additive Manufacturing (AM) technology. Despite its distinctive advantages compared to traditional subtractive manufacturing such as high design flexibility, short development time, low tooling cost, and low production waste, the inconsistent part quality caused by inappropriate product design, non-optimal process plan and inadequate process control has significantly hindered its wide acceptance in the industry. To improve the part quality control in metal PBF process, this paper proposes a novel Machine Learning (ML)-enabled approach for developing feedback loops throughout the entire metal PBF process. A categorisation of metal PBF feedback loops is proposed along with a summary of the critical PBF manufacturing data in each process stage. A generic framework of ML-enabled metal PBF feedback loops is proposed with detailed explanations and examples. The opportunities and challenges of the proposed approach are also discussed. The applications of ML techniques in metal PBF process allow efficient and effective decision-makings to be achieved in each PBF process stage, and hence have a great potential in reducing the number of experiments needed, thus saving a significant amount of time and cost in metal PBF production.