Review of tensile anisotropy in laser powder bed fusion 316L stainless steel: Build orientation effects and optimisation using machine learning

Laser powder bed fusion (LPBF) is an advanced additive manufacturing technique that enables the production of near-net-shape metallic parts with complex geometries. Among commonly used alloys, 316L stainless steel stands out due to its excellent mechanical strength, corrosion resistance, and suitabi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of materials research and technology Jg. 38; S. 5318 - 5341
Hauptverfasser: Jagannati, Venumurali, Gurram, Mariyadas, Turaka, Seshaiah, Naidu B, Vishnu Vardhana, Verma, Govind Kumar, Krishnan, Pradeep Kumar, Sarimalla, Rambabu, Sebaey, Tamer A., Bandaru, Aswani Kumar
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.09.2025
Elsevier
Schlagworte:
Build orientation
Laser powder bed fusion
Machine learning
Optimisation
SS316L
Tensile anisotropy
Laser powder bed fusion
Build orientation
Optimisation
Tensile anisotropy
Machine learning
SS316L
ISSN:2238-7854
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Laser powder bed fusion (LPBF) is an advanced additive manufacturing technique that enables the production of near-net-shape metallic parts with complex geometries. Among commonly used alloys, 316L stainless steel stands out due to its excellent mechanical strength, corrosion resistance, and suitability for LPBF. One critical parameter influencing the quality and performance of LPBF-printed parts is build orientation (BO), which significantly affects microstructure, mechanical properties, and anisotropy. This review consolidates findings from numerous studies that examine the influence of BO on tensile anisotropy, melt pool morphology, microstructure, and crystallographic texture of LPBF-manufactured 316L stainless steel. A comparative analysis of ultimate tensile strength, yield strength, and elongation across different BOs is presented, supported by characterisation techniques such as light optical microscopy, scanning electron microscopy, and electron backscatter diffraction. Although extensive research has been conducted, no specific BO has consistently improved tensile anisotropy. As a result, selecting an optimal BO remains a significant challenge. Several studies have introduced optimisation frameworks and automated tools to identify optimal BOs for various materials. In recent years, machine learning (ML) has been applied to refine optimisation models, thereby improving dimensional accuracy, surface finish, and mechanical performance. However, there is a notable gap in the literature regarding ML applications that specifically address tensile anisotropy. This review identifies opportunities to enhance anisotropic behaviour in LPBF 316L stainless steel parts through ML-assisted optimisation of BO, to achieve greater mechanical uniformity within a single printed component.
ISSN:2238-7854
DOI:10.1016/j.jmrt.2025.08.249