A hybrid machine learning model for in-process estimation of printing distance in laser Directed Energy Deposition

Ribeiro, Kandice Suane Barros; Núñez, Henrique Hiram Libutti; Venter, Giuliana Sardi; Doude, Haley; Coelho, Reginaldo Teixeira

doi:10.1007/s00170-023-11582-z

Cited by 5 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Printing out of focus is a significant challenge encountered in Laser Directed Energy Deposition (L-DED) and has been shown to adversely affect the quality and dimensional accuracy of the printed parts [12,28]. Defocused printing refers to a condition in which the laser focal point (where the laser delivers its maximum energy) and the feedstock powder are not positioned on the printing surface [12].…”

Section: Dataset Generationmentioning

confidence: 99%

“…Defocused printing refers to a condition in which the laser focal point (where the laser delivers its maximum energy) and the feedstock powder are not positioned on the printing surface [12]. This misalignment can lead to variations in the melt pool geometry [29], leading to irregular bead height [12], and overall part shape, ultimately compromising the structural integrity and functionality of the manufactured components. Achieving precise focus is crucial for ensuring the proper heat distribution, optimal fusion between adjacent beads, and accurate deposition of material layer by layer in L-DED.…”

Section: Dataset Generationmentioning

confidence: 99%

“…This work investigates the variation of bead width in different levels of printing focus, based on the dataset released by Ribeiro et al [12]. The experimental setup employed for acquiring this dataset was based on the build of 60 single beads 135 mm long (two ways) with printing distance ranging from 2.5 mm to 5.5 mm, with 0.05 mm increment between sets, as presented in Fig.…”

Section: Dataset Generationmentioning

confidence: 99%

“…The images were generated during deposition by a coaxial Basler ACA2000-50GM-NIR camera (pixel size of 30.25 µm 2 ) and acquired by the pylon software at the rate of 50 f ps. More details on the experimental setup are thoroughly described in [12].…”

Section: Dataset Generationmentioning

confidence: 99%

“…One of the most critical defect that occurs in L-DED is porosity, which significantly affects the mechanical properties and the overall quality of the manufactured part. Porosity refers to the presence of voids or gas-filled cavities within the material [10], and can result from gas entrapment in the melt pool, incomplete fusion between adjacent beads or inadequate control of process parameters [11], supplying an irregular deposited bead height [12] and width. Overall, the presence of porosity compromises the structural integrity of the components, reducing their load-bearing capacity and potentially leading to catastrophic failures [13].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Real-time prediction of deposited bead width in L-DED using Semi-Supervised Transfer Learning

Mochi,

Núñez,

Ribeiro

et al. 2023

Preprint

View full text Add to dashboard Cite

Laser Directed Energy Deposition (L-DED) is an additive manufacturing (AM) technology that offers unique advantages for creating and repairing metallic parts. The quality of the final print is highly dependent on the consistency of the printing parameters, and as a result, the deposited bead geometry along the printing pathway. Inconsistencies, particularly in the bead width, can produce defects between adjacent beads, increasing the material susceptibility to failure. Therefore, it is crucial to monitor and predict the printing parameters in real-time during the process. The objective of this study is to develop a machine learning model that accurately predicts the width of the deposited track in real-time. To achieve this, a dataset with approximately 12,379 melt pool images was used to train the algorithm and predict the width of the deposited track. Each one of the deposited track was measured by a profilometer at 10 points along the pathway, and intermediate labels were predicted using a spline curve, making the model semi-supervised. To implement the machine learning model, pre-trained frozen networks based on Convolutional Neural Networks (CNN) architectures VGG, ResNet, and DenseNet were employed, using transfer learning principles. These networks were integrated into a dense, fully connected network containing trainable parameters. The results demonstrate a good model fit, with a mean absolute error of 4.5% and a mean absolute error of 0.0358 mm. Moreover, the processing frequency of the best model, at 55 Hz, enables real-time control of the L-DED manufacturing process. It is important to highlight, however, that the VGG based model shows a frequency of 250 Hz and similar results. Thus, accurately predicting the width of the deposited bead has the potential to significantly improve the quality of the final part by reducing overall defects, such as lack of fusion and porosity, whenever this data is used as input to a feed-back control system. This is particularly valuable in industries where mechanical properties and fatigue life are critical, such as automotive, aerospace, and biomedical sectors. The models developed in this study offer a promising approach to effectively provide data to control the L-DED manufacturing process in real-time, enabling the reliable production of high-quality components associated with reduced manufacturing costs.

show abstract

Section: Dataset Generationmentioning

confidence: 99%

Section: Dataset Generationmentioning

confidence: 99%

Section: Dataset Generationmentioning

confidence: 99%

Section: Dataset Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real-time prediction of deposited bead width in L-DED using Semi-Supervised Transfer Learning

Mochi,

Núñez,

Ribeiro

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Real-time prediction of deposited bead width in L-DED using semi-supervised transfer learning

Mochi,

Núñez,

Ribeiro

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Real-time monitoring and quality assurance for laser-based directed energy deposition: integrating co-axial imaging and self-supervised deep learning framework

Pandiyan,

Cui,

Richter

et al. 2023

J Intell Manuf

View full text Add to dashboard Cite

Artificial Intelligence (AI) has emerged as a promising solution for real-time monitoring of the quality of additively manufactured (AM) metallic parts. This study focuses on the Laser-based Directed Energy Deposition (L-DED) process and utilizes embedded vision systems to capture critical melt pool characteristics for continuous monitoring. Two self-learning frameworks based on Convolutional Neural Networks and Transformer architecture are applied to process zone images from different DED process regimes, enabling in-situ monitoring without ground truth information. The evaluation is based on a dataset of process zone images obtained during the deposition of titanium powder (Cp-Ti, grade 1), forming a cube geometry using four laser regimes. By training and evaluating the Deep Learning (DL) algorithms using a co-axially mounted Charged Couple Device (CCD) camera within the process zone, the down-sampled representations of process zone images are effectively used with conventional classifiers for L-DED process monitoring. The high classification accuracies achieved validate the feasibility and efficacy of self-learning strategies in real-time quality assessment of AM. This study highlights the potential of AI-based monitoring systems and self-learning algorithms in quantifying the quality of AM metallic parts during fabrication. The integration of embedded vision systems and self-learning algorithms presents a novel contribution, particularly in the context of the L-DED process. The findings open avenues for further research and development in AM process monitoring, emphasizing the importance of self-supervised in situ monitoring techniques in ensuring part quality during fabrication.

show abstract

A hybrid machine learning model for in-process estimation of printing distance in laser Directed Energy Deposition

Cited by 5 publications

References 32 publications

Real-time prediction of deposited bead width in L-DED using Semi-Supervised Transfer Learning

Real-time prediction of deposited bead width in L-DED using Semi-Supervised Transfer Learning

Real-time prediction of deposited bead width in L-DED using semi-supervised transfer learning

Real-time monitoring and quality assurance for laser-based directed energy deposition: integrating co-axial imaging and self-supervised deep learning framework

Contact Info

Product

Resources

About