skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • AFSD-Nets: A Physics-Informed Machine Learning Model for Predicting the Temperature Evolution During Additive Friction Stir Deposition
Title: AFSD-Nets: A Physics-Informed Machine Learning Model for Predicting the Temperature Evolution During Additive Friction Stir Deposition
Abstract This study models the temperature evolution during additive friction stir deposition (AFSD) using machine learning. AFSD is a solid-state additive manufacturing technology that deposits metal using plastic flow without melting. However, the ability to predict its performance using the underlying physics is in the early stage. A physics-informed machine learning approach, AFSD-Nets, is presented here to predict temperature profiles based on the combined effects of heat generation and heat transfer. The proposed AFSD-Nets includes a set of customized neural network approximators, which are used to model the coupled temperature evolution for the tool and build during multi-layer material deposition. Experiments are designed and performed using 7075 aluminum feedstock deposited on a substrate of the same material for 30 layers. A comparison of predictions and measurements shows that the proposed AFSD-Nets approach can accurately describe and predict the temperature evolution during the AFSD process.  more » « less
Award ID(s):
2133630
PAR ID:
10543703
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
Manufacturing Letters
Date Published:
Journal Name:
Journal of Manufacturing Science and Engineering
Volume:
146
Issue:
8
ISSN:
1087-1357
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Progress in Additive Manufacturing)
    Abstract Additive Friction stir deposition (AFSD) has been extensively utilized for processing Al alloys. The properties of the Al depositions under as-fabricated state, including mechanical strength and corrosion resistance, are typically inferior compared to the base material, especially for heat-treatable alloys. In this research, multilayers of Al7075 composites, reinforced by ceramic particles, were processed by AFSD to evaluate the effect of using feedstock materials containing reinforcing particles on the properties of the deposition. For comparison, a bare Al7075 part was also processed by AFSD under the same conditions. The results of mechanical testing revealed a significant reduction in the microhardness, tensile strength and compression stress of the bare alloy after deposition. However, the composite deposition exhibited only a slight decrease in the properties compared to its feedstock material. Additionally, the corrosion resistance of the composite enhanced after AFSD, in contrast to the bare alloy, where the corrosion resistance deteriorated. Microstructural analysis showed a uniform distribution of the reinforcing particles in the matrix for the deposition, closely resembling that of the feedstock composite. This, along with grain refinement and minimal change in precipitates, were the reasons for the minimum changes in mechanical properties, as well as the improvement in corrosion resistance. 
    more » « less
  2. ; ; ; ; (, Metals)
    Solid-state additive friction stir deposition (AFSD) is a thermomechanical-based additive manufacturing technique. For this study, AFSD was utilized to produce aluminum alloy 6061 (AA6061) blocks with varying layer thicknesses (1 mm, 2 mm, and 3 mm). The mechanical properties were assessed through uniaxial tensile tests and Vickers microhardness measurement, and statistical analysis was employed to investigate differences among data groups. The results revealed that the deposition layer thickness influences tensile properties in the building (Z) direction, while the properties in the X and Y directions showed minor differences across the three AFSD blocks. Furthermore, variations in tensile properties were observed depending on the sample orientation in the AFSD blocks and its depth-wise position in the part in the building direction. The microhardness values decreased non-linearly along the building direction, spread across the width of the part’s cross-section, and highlighted that the deposition layer thickness significantly affects this property. The 1 mm block exhibited lower average microhardness values than the 2 mm and 3 mm blocks. The temperature histories and dynamic heat treatment are influenced by the deposition layer thickness and depend on the location of the point being studied in the part, resulting in variations in the microstructure and mechanical properties along the building direction and across the part’s width. 
    more » « less
  3. ; ; ; ; ; ; (, Materials)
    The solid-state additive friction stir deposition (AFSD) process is a layer-by-layer metal 3D-printing technology. In this study, AFSD is used to fabricate Al–Cu–Li 2050 alloy parts. The hardness values for various regions of the as-deposited built parts are measured, and the results are contrasted with those of the feedstock material. The as-fabricated Al2050 parts are found to have a unique hardness distribution due to the location-specific variations in the processing temperature profile. The XRD results indicate the presence of the secondary phases in the deposited parts, and EDS mapping confirms the formation of detectable alloying particles in the as-deposited Al2050 matrix. The AFSD thermal–mechanical process causes the unique hardness distribution and the reduced microhardness level in the AFSD components, in contrast to those of the feedstock material. 
    more » « less
  4. ; ; ; ; (, Additive manufacturing)
    null (Ed.)
    Additive friction stir deposition (AFSD) is an emerging solid-state metal additive manufacturing technology renowned for strong interface adhesion and isotropic mechanical properties. This is postulated to result from the material flow phenomena near the interface, but experimental corroboration has remained absent. Here, we seek to understand the interface formed in AFSD via morphological and microstructural investigation, wherein the non-planar interfacial morphology is characterized on the track-scale (centimeter scale) using X-ray computed tomography and the material deformation history is explored by microstructure mapping at the interfacial regions. X-ray computed tomography reveals unique 3D features at the interface with significant macroscopic material mixing. In the out-of-plane direction, the deposited material inserts below the initial substrate surface in the feed-rod zone, while the substrate surface surges upwards in the tool protrusion-affected zone. Complex 3D structures like fins and serrations form on the advancing side, leading to structural interlocking; on the retreating side, the interface manifests as a smooth sloped surface. Microstructure mapping reveals a uniform thermomechanical history for the deposited material, which develops a homogeneous, almost fully recrystallized microstructure. The substrate surface develops partially recrystallized microstructures that are location-dependent; more intra-granular orientation gradients are found in the regions further away from the centerline of the deposition track. From these observations, we discuss the mechanisms for interfacial material flow and interface morphology formation during AFSD. 
    more » « less
  5. ; (, Engineering Applications of Artificial Intelligence)
    Understanding thermal stress evolution in metal additive manufacturing (AM) is crucial for producing high-quality components. Recent advancements in machine learning (ML) have shown great potential for modeling complex multiphysics problems in metal AM. While physics-based simulations face the challenge of high computational costs, conventional data-driven ML models require large, labeled training datasets to achieve accurate predictions. Unfortunately, generating large datasets for ML model training through time-consuming experiments or high-fidelity simulations is highly expensive in metal AM. To address these challenges, this study introduces a physics-informed neural network (PINN) framework that incorporates governing physical laws into deep neural networks (NNs) to predict temperature and thermal stress evolution during the laser metal deposition (LMD) process. The study also discusses enhanced accuracy and efficiency of the PINN model when supplemented with small simulation data. Furthermore, it highlights the PINN transferability, enabling fast predictions with a set of new process parameters using a pre-trained PINN model as an online soft sensor, significantly reducing computation time compared to physics-based numerical models while maintaining accuracy. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email