Laser powder bed fusion (LPBF) as one of the widely used technologies of additive manufacturing (AM), has a high capability to produce complex geometries such as notched parts in a layer-by-layer manner. LPBF parts in their as built state have inhomogeneous and anisotropic microstructure and poor surface quality. Post-treatments can play a key role in modulating these imperfections. In this study, the effects of four different post-treatments including heat treatment, shot peening and electro-chemical polishing as well as their combination as hybrid treatment were investigated on microstructure, surface and mechanical properties and finally fatigue behaviour of the LPBF V-notched AlSi10Mg samples. Afterward, a deep learning based approach was employed for modelling the fatigue behaviour via artificial neural network. Surface roughness, surface modification factor, hardness, residual stress and porosities were considered as inputs and fatigue life was considered as the output. Model function of the network was generated and the relevant parametric and sensitivity analyses were performed. The results indicated the importance of surface related properties and the notable effect of the surface post-treatments in enhancing the fatigue performance of the LPBF material.

Effects of hybrid post-treatments on fatigue behaviour of notched LPBF AlSi10Mg: Experimental and deep learning approaches

Maleki E.;Bagherifard S.;Guagliano M.
2021-01-01

Abstract

Laser powder bed fusion (LPBF) as one of the widely used technologies of additive manufacturing (AM), has a high capability to produce complex geometries such as notched parts in a layer-by-layer manner. LPBF parts in their as built state have inhomogeneous and anisotropic microstructure and poor surface quality. Post-treatments can play a key role in modulating these imperfections. In this study, the effects of four different post-treatments including heat treatment, shot peening and electro-chemical polishing as well as their combination as hybrid treatment were investigated on microstructure, surface and mechanical properties and finally fatigue behaviour of the LPBF V-notched AlSi10Mg samples. Afterward, a deep learning based approach was employed for modelling the fatigue behaviour via artificial neural network. Surface roughness, surface modification factor, hardness, residual stress and porosities were considered as inputs and fatigue life was considered as the output. Model function of the network was generated and the relevant parametric and sensitivity analyses were performed. The results indicated the importance of surface related properties and the notable effect of the surface post-treatments in enhancing the fatigue performance of the LPBF material.
2021
Procedia Structural Integrity
Additive manufacturing
Deep learning
Fatigue
Laser powder bed fusion
Shot peening
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S2452321621002626-main(2).pdf

accesso aperto

: Publisher’s version
Dimensione 1.43 MB
Formato Adobe PDF
1.43 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1233570
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 13
social impact