Machine learning assisted quality control in metal additive manufacturing: a review

Abstract

Additive manufacturing (AM) promotes the production of metallic parts with significant design flexibility, yet its use in critical applications is hindered by challenges in ensuring consistent quality and performance. Process variability often leads to defects, insufficient geometric accuracy and inadequate material properties, which are difficult to effectively manage due to limitations of traditional quality control methods in modeling high-dimensional nonlinear relationships and enabling adaptive control. Machine learning (ML) offers a transformative approach to model intricate process-structure-property relationships by leveraging the rich data environment of AM. The study presents a comprehensive examination of ML-driven quality assurance implementations in metallic AM. First, it uniquely examines the innovative exploration of ML in predicting and understanding the fundamental multi-physics fields that influence the quality of a fabricated component, including temperature fields, fluid dynamics and stress/strain evolution. Subsequently, the application of ML in optimizing key quality attributes, including defect detection and mitigation (porosity, cracks, etc.), geometric fidelity enhancement (dimensional accuracy, surface roughness, etc.) and material property tailoring (mechanical strength, fatigue life, corrosion resistance, etc.), are discussed in detail. Finally, the development of ML-driven real-time closed-loop control systems for intelligent quality assurance, the strategies for addressing the data scarcity and cross-scenario transferability in metal AM are discussed. This article provides a novel perspective on the profound potential of ML technology for metal AM quality control applications, highlights the challenges faced during research, and outlines future development directions.