Deep learning object detection for optical monitoring of spatters in L-PBF

Chebil, Gwenaëlle; Bettebghor, Dimitri; Renollet, Y.; Lapouge, Pierre; Davoine, Cécile; Thomas, Marc; Favier,; Schneider, Matthias

doi:10.1016/j.jmatprotec.2023.118063

Cited by 8 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 70 ], the authors used an innovative L-PBF setup with an open cell and a fixed laser to provide quality images for spatter monitoring and enable a large set of data with numerous laser parameters. Two chamber windows enabled laser exposure and the observation of laser–matter interaction.…”

Section: Discussionmentioning

confidence: 99%

A Survey of Image-Based Fault Monitoring in Additive Manufacturing: Recent Developments and Future Directions

Kim,

Abisado,

Villaverde

et al. 2023

Sensors

View full text Add to dashboard Cite

Additive manufacturing (AM) has emerged as a transformative technology for various industries, enabling the production of complex and customized parts. However, ensuring the quality and reliability of AM parts remains a critical challenge. Thus, image-based fault monitoring has gained significant attention as an efficient approach for detecting and classifying faults in AM processes. This paper presents a comprehensive survey of image-based fault monitoring in AM, focusing on recent developments and future directions. Specifically, the proponents garnered relevant papers from 2019 to 2023, gathering a total of 53 papers. This paper discusses the essential techniques, methodologies, and algorithms employed in image-based fault monitoring. Furthermore, recent developments are explored such as the use of novel image acquisition techniques, algorithms, and methods. In this paper, insights into future directions are provided, such as the need for more robust image processing algorithms, efficient data acquisition and analysis methods, standardized benchmarks and datasets, and more research in fault monitoring. By addressing these challenges and pursuing future directions, image-based fault monitoring in AM can be enhanced, improving quality control, process optimization, and overall manufacturing reliability.

show abstract

Section: Discussionmentioning

confidence: 99%

A Survey of Image-Based Fault Monitoring in Additive Manufacturing: Recent Developments and Future Directions

Kim,

Abisado,

Villaverde

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

Exploring the Role of Explainable AI in the Development and Qualification of Aircraft Quality Assurance Processes: A Case Study

Milcke,

Dinglinger,

Holtmann

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Using defects as a ‘fossil record’ to help interpret complex processes during additive manufacturing: as applied to raster-scanned electron beam powder bed additively manufactured Ti–6Al–4V

O’Donnell,

Quintana,

Kenney

et al. 2023

J Mater Sci

View full text Add to dashboard Cite

Defects in parts produced by additive manufacturing, instead of simply being perceived as deleterious, can act as important sources of information associated with the complex physical processes that occur during materials deposition and subsequent thermal cycles. Indeed, they act as materials-state ‘fossil’ records of the dynamic AM process. The approach of using defects as epoch-like records of prior history has been developed while studying additively manufactured Ti–6Al–4V and has given new insights into processes that may otherwise remain either obscured or unquantified. Analogous to ‘epochs,’ the evolution of these defects often is characterized by physics that span across a temporal length scale. To demonstrate this approach, a broad range of analyses including optical and electron microscopy, X-ray computed tomography, energy-dispersive spectroscopy, and electron backscatter diffraction have been used to characterize a raster-scanned electron beam Ti–6Al–4V sample. These analysis techniques provide key characteristics of defects such as their morphology, location within the part, complex compositional fields interacting with the defects, and structures on the free surfaces of defects. Observed defects have been classified as banding, spherical porosity, and lack of fusion. Banding is directly related to preferential evaporation of Al, which has an influence on mechanical properties. Lack-of-fusion defects can be used to understand columnar grain growth, fluid flow of melt pools, humping, and spattering events. Graphical abstract

show abstract

Deep learning object detection for optical monitoring of spatters in L-PBF

Cited by 8 publications

References 26 publications

A Survey of Image-Based Fault Monitoring in Additive Manufacturing: Recent Developments and Future Directions

A Survey of Image-Based Fault Monitoring in Additive Manufacturing: Recent Developments and Future Directions

Exploring the Role of Explainable AI in the Development and Qualification of Aircraft Quality Assurance Processes: A Case Study

Using defects as a ‘fossil record’ to help interpret complex processes during additive manufacturing: as applied to raster-scanned electron beam powder bed additively manufactured Ti–6Al–4V

Contact Info

Product

Resources

About