Statistical analysis of spatial distribution of pores in metal additive manufacturing

Ghamarian, Iman; Ball, S.; Ghayoor, Milad; Pasebani, Somayeh; Tabei, Ali

doi:10.1016/j.addma.2021.102264

Cited by 5 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite careful parameter optimization, lack-of-fusion defects may occur, while melt pool instabilities can also introduce material voids [79]. The resulting pores with varying sizes from nanoscale or macroscale [80] have a significant influence on the mechanical and thermal properties of additively manufactured components [81][82][83]. Such a defect may originate from in-service operations [84,85], manufacturing [65], or material processing [86], exerting substantial influence on mechanical performance by acting as regions of stress concentration and crack initiation.…”

Section: Case Study: Stress Field Prediction Around An Additive Manuf...mentioning

confidence: 99%

Prediction of 4D stress field evolution around additive manufacturing-induced porosity through progressive deep-learning frameworks

Rezasefat,

Hogan

2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

This study investigates the application of machine learning models to predict time-evolving stress fields in complex three-dimensional structures trained with full-scale finite element simulation data. Two novel architectures, the Multi-Decoder CNN (MUDE-CNN) and the Multiple Encoder-Decoder Model with Transfer Learning (MTED-TL), were introduced to address the challenge of predicting the progressive and spatial evolutional of stress distributions around defects. The MUDE-CNN leveraged a shared encoder for simultaneous feature extraction and employed multiple decoders for distinct time frame predictions, while MTED-TL progressively transferred knowledge from one encoder-decoder block to another, thereby enhancing prediction accuracy through transfer learning. These models were evaluated to assess their accuracy, with a particular focus on predicting temporal stress fields around an additive manufacturing-induced isolated pore, as understanding such defects is crucial for assessing mechanical properties and structural integrity in materials and components fabricated via additive manufacturing. The temporal model evaluation demonstrated MTED-TL's consistent superiority over MUDE-CNN, owing to transfer learning's advantageous initialization of weights and smooth loss curves. Furthermore, an autoregressive training framework was introduced to improve temporal predictions, consistently outperforming both MUDE-CNN and MTED-TL. By accurately predicting temporal stress fields around AM-induced defects, these models can enable real-time monitoring and proactive defect mitigation during the fabrication process. This capability ensures enhanced component quality and enhances the overall reliability of additively manufactured parts.

show abstract

Section: Case Study: Stress Field Prediction Around An Additive Manuf...mentioning

confidence: 99%

Prediction of 4D stress field evolution around additive manufacturing-induced porosity through progressive deep-learning frameworks

Rezasefat,

Hogan

2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The pore defects in AM parts can appear due to several mechanisms such as keyhole pore formation [21,22], pores resulting from lack of fusion [23,24], pores formed during gas atomization [25,26], escaping gas bubbles from the melt pool [27], etc. The resulting pores with varying sizes from nanoscale or macroscale [28] have a significant influence on the part's mechanical and thermal properties [11,29,30].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Assisted Characterization of Pore-Induced Variability in Mechanical Response of Additively Manufactured Components

Rezasefat,

Hogan

2023

Modelling

View full text Add to dashboard Cite

Manufacturing defects, such as porosity and inclusions, can significantly compromise the structural integrity and performance of additively manufactured parts by acting as stress concentrators and potential initiation sites for failure. This paper investigates the effects of pore system morphology (number of pores, total volume, volume fraction, and standard deviation of size of pores) on the material response of additively manufactured Ti6Al4V specimens under a shear–compression stress state. An automatic approach for finite element simulations, using the J2 plasticity model, was utilized on a shear–compression specimen with artificial pores of varying characteristics to generate the dataset. An artificial neural network (ANN) surrogate model was developed to predict peak force and failure displacement of specimens with different pore attributes. The ANN demonstrated effective prediction capabilities, offering insights into the importance of individual input variables on mechanical performance of additively manufactured parts. Additionally, a sensitivity analysis using the Garson equation was performed to identify the most influential parameters affecting the material’s behaviour. It was observed that materials with more uniform pore sizes exhibit better mechanical properties than those with a wider size distribution. Overall, the study contributes to a better understanding of the interplay between pore characteristics and material response, providing better defect-aware design and property–porosity linkage in additive manufacturing processes.

show abstract

Enhancing surface quality of metal parts manufactured via LPBF: ANN classifier and bayesian learning approach

Arunadevi,

Veeresha,

Kharche

et al. 2024

Int J Interact Des Manuf

View full text Add to dashboard Cite

Statistical analysis of spatial distribution of pores in metal additive manufacturing

Cited by 5 publications

References 52 publications

Prediction of 4D stress field evolution around additive manufacturing-induced porosity through progressive deep-learning frameworks

Prediction of 4D stress field evolution around additive manufacturing-induced porosity through progressive deep-learning frameworks

Machine Learning-Assisted Characterization of Pore-Induced Variability in Mechanical Response of Additively Manufactured Components

Enhancing surface quality of metal parts manufactured via LPBF: ANN classifier and bayesian learning approach

Contact Info

Product

Resources

About