A Framework for Optimizing Process Parameters in Powder Bed Fusion (PBF) Process Using Artificial Neural Network (ANN)

Marrey, Mallikharjun; Malekipour, Ehsan; El-Mounayri, Hazim; Faierson, Eric J.

doi:10.1016/j.promfg.2019.06.214

Cited by 54 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used two different magnifications --60X and 300X (100µm and 10µm scale, respectively) -for each micrograph and then employed MATLAB image processing to measure the porosity of each sample in three steps (Figure 7). First, we generated bi-color black and white images from each micrograph; second, the threshold level was adjusted by comparing the pore size between the SEM image and the MATLAB-generated image to increase the method accuracy [36]; finally, we obtained the porosity percentage by calculating and averaging the ratio of black parts (pores) to the white parts in the micrographs related to each cross-section [37]. By analyzing the horizontal cross-section, we revealed three different types of porosity -low, medium, high --according to the level of VED.…”

Section: Phase I: Results and Discussionmentioning

confidence: 99%

A Novel Framework for Predictive Modeling and Optimization of Powder Bed Fusion Process

Marrey¹,

Malekipour²,

El-Mounayri³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Powder bed fusion (PBF) process is a metal additive manufacturing process which can build parts with any complexity from a wide range of metallic materials. PBF process research has predominantly focused on the impact of only a few parameters on product properties due to the lack of a systematic approach for optimizing a large set of process parameters simultaneously. The pivotal challenges regarding this process require a quantitative approach for mapping the material properties and process parameters onto the ultimate quality; this will then enable the optimization of those parameters. In this study, we propose a two-phase framework for optimizing the process parameters and developing a predictive model for 316L stainless steel material. We also discuss the correlation between process parameters -- i.e., laser specifications -- and mechanical properties and how to achieve parts with high density (> 98%) as well as better ultimate mechanical properties. In this paper, we introduce and test an innovative approach for developing AM predictive models, with a relatively low error percentage of 10.236% that are used to optimize process parameters in accordance with user or manufacturer requirements. These models use support vector regression, random forest regression, and neural network techniques. It is shown that the intelligent selection of process parameters using these models can achieve an optimized density of up to 99.31% with uniform microstructure, which improves hardness, impact strength, and other mechanical properties.

show abstract

Section: Phase I: Results and Discussionmentioning

confidence: 99%

A Novel Framework for Predictive Modeling and Optimization of Powder Bed Fusion Process

Marrey¹,

Malekipour²,

El-Mounayri³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The DMLS process utilizes a variety of metals and alloys and operates on the same concept of SLS AM process. The residual stress in product parts is an issue with this process and will be discussed in Section 6.2.1 of this chapter [26].…”

Section: Direct Metal Laser Sinteringmentioning

confidence: 99%

An Investigation of the Metal Additive Manufacturing Issues and Perspective for Solutions Approach

Al-Shebeeb¹

2021

Concepts, Applications and Emerging Opportunities in Industrial Engineering

View full text Add to dashboard Cite

Metal Additive Manufacturing (MAM) is delivering a new revolution in producing three-dimensional parts from metal-based material. MAM can fabricate metallic parts with complex geometry. However, this type of Additive Manufacturing (AM) is also impacted by several issues, challenges, and defects, which influence product quality and process sustainability. In this chapter, a review has been made on the types of small to medium-sized metallic parts currently manufactured using the MAM method. Then, investigation was undertaken to analyze the defects, challenges, and issues inherent to the design for additive manufacturing, by using MAM method. MAM-related obstacles are discussed in depth in this chapter and these obstacles occur in all size of metal printed parts. The reasons and solutions presented by previous researchers of these obstacles are discussed as well. A potential approach based on the author's knowledge and analysis for solving these issues and challenges is suggested in this chapter. Based on the author's conclusion, the MAM is not limited by part size, material, or geometry. In order to validate the potential solutions developed by the author of this work, performing actual MAM process is required and a local visit to manufacturing factories are also important to visualize these challenges and issues.

show abstract

“…Similarly, a popular method for the modeling and optimization of processes is conducted through the use of artificial neural networks (ANN). Marrey et al used an artificial neural network to develop an ANN model based on the results of a series of experiments and were able to draw conclusions on the effects of different process parameters on the mechanical properties of L-PBF parts [29]. Charles et al also employed a similar methodology to create an ANN model for L-PBF parts to predict surface roughness in down-facing surfaces [30].…”

Section: Introductionmentioning

confidence: 99%

Dimensional Errors Due to Overhanging Features in Laser Powder Bed Fusion Parts Made of Ti-6Al-4V

et al. 2020

View full text Add to dashboard Cite

The rise in popularity of Additive Manufacturing technologies and their increased adoption for manufacturing have created a requirement for their fast development and maturity. However, there is still room for improvement when compared with conventional manufacturing in terms of the predictability, quality, and robustness. Statistical analysis has proven to be an excellent tool for developing process knowledge and optimizing different processes efficiently and effectively. This paper uses a novel method for printing overhanging features in Ti-6Al-4V metal parts, by varying process parameters only within the down-facing area, and establishes a methodology for predicting dimensional errors in flat 45° down-facing surfaces. Using the process parameters laser power, scan speed, scan spacing, scan pattern, and layer thickness, a quadratic regression equation is developed and tested. An Analysis of variance (ANOVA) analysis concluded that, within the down-facing area, the laser power is the most significant process parameter, followed by the layer thickness and scan speed. Comparatively, the scanning pattern is determined to be insignificant, which is explained by the small down-facing area where the various scanning patterns play no role. This paper also discusses the interaction effects between parameters. Some thoughts on the next steps to be taken for further validation are discussed.

show abstract

A Framework for Optimizing Process Parameters in Powder Bed Fusion (PBF) Process Using Artificial Neural Network (ANN)

Cited by 54 publications

References 33 publications

A Novel Framework for Predictive Modeling and Optimization of Powder Bed Fusion Process

A Novel Framework for Predictive Modeling and Optimization of Powder Bed Fusion Process

An Investigation of the Metal Additive Manufacturing Issues and Perspective for Solutions Approach

Dimensional Errors Due to Overhanging Features in Laser Powder Bed Fusion Parts Made of Ti-6Al-4V

Contact Info

Product

Resources

About