Towards defect-free lattice structures in additive manufacturing: A holistic review of machine learning advancements

Additive manufacturing has transformed modern production by enabling the fabrication of complex and lightweight structures, particularly lattice geometries, which are widely used in aerospace, automotive, medical, and energy industries. Renowned for their superior strength-to-weight ratios and energy absorption properties, lattice structures have unlocked new possibilities for weight-critical, high-performance applications. However, their intricate geometries and susceptibility to defects, such as surface roughness, voids, and porosity, pose significant challenges to ensuring mechanical integrity and functional reliability. Traditional methods of defect mitigation, process control and optimization, are often constrained by high computational costs and limited adaptability to complex defect mechanisms. To address these challenges, machine learning (ML) has emerged as a transformative tool, offering data-driven solutions for defect prediction, detection, and minimization. These techniques excel in optimizing designs, tuning process parameters, and enabling real-time adjustments to mitigate defects, thereby enhancing manufacturing outcomes. While numerous studies have explored ML applications in additive manufacturing, current literature lacks a specific focus on its use for defect minimization in lattice structures, which require defect-free fabrication to achieve optimal performance. This review paper fills this critical research gap by investigating the application of advanced ML techniques across key areas: design optimization, properties prediction, process parameter tuning, and defect detection and real-time monitoring for lattice structures. In doing so, it gives a comprehensive outline of lattice structures, the challenges posed by manufacturing defects, and state-of-the-art ML applications in AM. This study paves the way for defect-free lattice structures, maximizing their industrial potential.