Engineering topics

Paquit, Vincent C.

Publications and source records attributed to Paquit, Vincent C..

12 records

DOE OSTI2024

Deep-learning based artificial intelligence tool for melt pools and defect segmentation

Accelerating fabrication of additively manufactured components with precise microstructures is important for quality and qualification of built parts, as well as for a fundamental understanding of process improvement. Accomplishing this requires fast and robust characterization of melt pool geometries and structural defects in images. This paper proposes a pragmatic approach based on implementation of deep learning models and self-consistent workflow that enable systematic segmentation of defects and melt pools in optical images. Deep learning is based on an image-to-image translation–conditional generative adversarial neural network architecture. An artificial intelligence (AI) tool based on this deep learning model enables fast and incrementally more accurate predictions of the prevalent geometric features, including melt pool boundaries and printing-induced structural defects. We present statistical analysis of geometric features that is enabled by the AI tool, showing strong spatial correlation of defects and the melt pool boundaries. The correlations of widths and heights of melt pools with dataset processing parameters show the highest sensitivity to thermal influences resulting from laser passes in adjacent and subsequent layer passes. The presented models and tools are demonstrated on the aluminum alloy and datasets produced with different sets of processing parameters. However, they have universal quality and could easily be adapted to different material compositions. The method can be easily generalized to microstructural characterizations other than optical microscopy.

additive manufacturing↗

DOE OSTI2024

In-situ digital image correlation and thermal monitoring in directed energy deposition

A method and a system for digital image correlation and thermal monitoring during directed energy deposition are provided. The method and the system include global off-axis 3D mapping of surfaces features at high frame rates using the natural surface roughness of the additive build. Infrared thermography is projected onto these surface features to record the thermo-mechanical history of the finished component. As set forth herein, the method and the system provide a low-cost solution to monitoring and optimizing the unique temporal artifacts induced by complex scan strategies.

Haley, James↗

DOE OSTI2023

MDDC Multi-Length Scale Data Architecture Contribution Report – PNNL, INL, ANL, LANL and ORNL

This report offers a comprehensive view of data streams currently generated at Pacific Northwest National Laboratory, Idaho National Laboratory, Argonne National Laboratory, Los Alamos National Laboratory, and Oak Ridge National Laboratory set to integrate into the evolving Multi-Dimensional Data Correlation framework at Oak Ridge National Laboratory. Developed by the Advanced Materials and Manufacturing Technologies program, the Multi-Dimensional Data Correlation framework serves as a cutting-edge software to manage data relevant to advanced manufacturing and material behavior in advanced reactors. The report defines data streams, highlights their generation methods and visualization methods both for experimental and computational aspects relevant to the Advanced Materials and Manufacturing Technologies project. A logical next step for this work is to integrate the MDDC framework into PNNL’s, INL’s, ANL’s, LANL’s and ORNL’s fabrication, experimentation, and modelling workflows. This would require setting up the MDDC framework at PNNL, INL, ANL, and LANL and integrating it into the data collection and storage for these different activities.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Method and system for automated plant surveillance and manipulation

A method and a system for automated plant surveillance and manipulation are provided. Pursuant to the method and the system, images of target plants are obtained through a machine vision system having multiple cameras. The obtained images of the target plants are processed to determine tissue candidates of the target plants and to determine a position and an orientation of each tissue candidate. A tool is manipulated, based on the position and the orientation of each tissue candidate, to excise each tissue candidate to obtain tissue samples. The tissue samples are transported for subsequently manipulation including live processing of the tissue samples or destructive processing of the tissue samples.

Kalluri, Udaya C.↗

DOE OSTI2022

Systems and methods for powder bed additive manufacturing anomaly detection

Detection and classification of anomalies for powder bed metal additive manufacturing. Anomalies, such as recoater blade impacts, binder deposition issues, spatter generation, and some porosities, are surface-visible at each layer of the building process. A multi-scaled parallel dynamic segmentation convolutional neural network architecture provides additive manufacturing machine and imaging system agnostic pixel-wise semantic segmentation of layer-wise powder bed image data. Learned knowledge is easily transferrable between different additive manufacturing machines. The anomaly detection can be conducted in real-time and provides accurate and generalizable results.

Scime, Luke R.↗

DOE OSTI2021

A scalable digital platform for the use of digital twins in additive manufacturing

We report that while Additive Manufacturing promises to reshape the manufacturing landscape, challenges related to part, and process qualification hinder its widespread adoption. The Instance-Qualified approach seeks to qualify individual parts, even for processes with high variability, by leveraging the concept of a digital twin. This work proposes a scalable cyberphysical infrastructure to enable the construction and use of such digital twins. This work also introduces the concept of an Augmented Intelligence Relay, which allows Artificial Intelligence algorithms to predict component performance for a given application even when it is impractical to perform a large number of physical tests.

36 MATERIALS SCIENCE↗

DOE OSTI2019

Monitoring for Additive Manufacturing Technologies: Report on Progress, Achievements, and Limitations of Monitoring Techniques

The Transformational Challenge Reactor (TCR) program is leveraging additive manufacturing (AM) technologies to produce multiple nuclear components to be assembled into a fully functional microreactor core. AM was selected as the main manufacturing technology of choice for TCR because it has the potential to disrupt the nuclear industry on two fronts: (1) it enables the manufacturing of very complex geometries with optimized and tailored material properties for the intended use of the component, opening up new options for reactor designs, and (2) it allows for a better understanding of the manufacturing process through real-time in situ monitoring, data analytics, and artificial intelligence that can lead to a streamlined qualification and certification process. Within TCR, the development and deployment of a digital platform aims at addressing the latter opportunity. As part of this effort, the collection of pedigree data sets is vital, should these data be generated before, during, or after the manufacturing process. This report focuses on the collection of manufacturing process data using systems instrumentation and monitoring. It presents an inventory of the various monitoring modalities installed on the manufacturing systems by the machine manufacturer or specifically designed by our team to fill information gaps. It also provides details on other relevant data streams available and leverageable to evaluate the manufacturing process on all classes of AM systems investigated during the first year of this program. Through examples, the report gives an overview of the data collected and presents a path forward for the digital platform.

42 ENGINEERING↗

DOE OSTI2019

Electron Beam Melting Technology Improvements

ORNL and Arcam AB have collaborated to improve and broaden the application and dissemination of electron beam melting (EBM) technology. While EBM is a promising additive manufacturing technology with the potential to revolutionize many industries, several issues prevent its widespread adoption at an industrial scale. In collaboration with Arcam, ORNL researchers have worked to improve the reliability of EBM processes using in-situ monitoring methods and data analytics, developed new scan strategies to allow site-specific microstructure control, and expanded EBM technologies to high-temperature materials. This report details the results of this collaboration.

42 ENGINEERING↗

DOE OSTI2018

Innovative Method for Enhancing Carbon Fibers Dispersion in Wet-Laid Nonwovens

The production of wet laid (WL) reinforcing fiber mats is adopted from the paper making industry to produce carbon fiber (CF) mats. The resulting mats are prone to defects induced by the mixing regime. Here, this study explores a new mixer design that achieved fully dispersed mats with 20 minutes processing time using 25.4 mm long CF. The proposed mixing method is compared against the traditional method and the density distribution of fibers is characterized using Back Light Scattering (BLS) technique. The mats showed high consistency with less than 8% standard deviation from the data collected from different regions within the mats. The innovative mixer resulted in mats with fiber distribution 70% closer to the theoretical distribution than that of the traditional mixer. This innovative method of preparing nonwoven CF mats will create new opportunities for CF nonwoven composite applications.

36 MATERIALS SCIENCE↗

DOE OSTI2018

Correlations Between Powder Feedstock Quality, In Situ Porosity Detection, and Fatigue Behavior of Ti-6Al-4V Fabricated by Powder Bed Electron Beam Melting: A Step Towards Qualification

Ti-6Al-4V is the most studied alloy via electron beam melting (EBM) with regards to microstructure and mechanical behavior, but there have been no attempts to correlate in situ porosity detection and fatigue behavior. This is required for widespread adoption of EBM because conventional evaluation is often time-consuming and expensive. This study presents the use of near-infrared imaging to detect and quantify porosity in Ti-6Al-4V builds fabricated from different powder feedstocks and its correlation to their fatigue response. Finally, we report that, for identical processing parameters, the variability in powder feedstock causes variations in porosity and scatter in the respective fatigue response.

36 MATERIALS SCIENCE↗

DOE OSTI2018

Apparatus and methods for imaging interior surfaces of a tube or the like

An exemplary device includes, on a longitudinal axis, an illumination-light source, an axicon (conic) mirror, an image sensor, and a tilted optical element. The light source provides illumination light propagating forwardly on the axis. The axicon mirror reflects the illumination light radially outward, relative to the axis, to the interior surface of a tube to produce reflected light propagating, from the illuminated interior surface, as imaging light back to the axicon, which reflects the imaging light rearwardly. The image sensor receives at least a portion of the imaging light rearwardly reflected by the axicon mirror. The tilted optical element, situated between the axicon mirror and the interior surface, moves a selected first portion of the imaging light away from being incident on the image sensor, while allowing a second portion of the imaging light to be incident on the image sensor.

Kisner, Roger A.↗

DOE OSTI2017

Characterization of topology optimized Ti-6Al-4V components using electron beam powder bed fusion

The use of manufacturing to generate topology optimized components shows promise for designers. However, designers who assume that additive manufacturing follows traditional manufacturing techniques may be misled due to the nuances in specific techniques. Since commercial topology optimization software tools are neither designed to consider orientation of the parts nor large variations in properties, the goal of this research is to evaluate the limitations of an existing commercial topology optimization software (i.e. Inspire®) using electron beam powder bed fusion (i.e. Arcam®) to produce optimized Ti-6Al-4V alloy components. Emerging qualification tools from Oak Ridge National Laboratory including in-situ near-infrared imaging and log file data analysis were used to rationalize the final performance of components. While the weight savings of each optimized part exceeded the initial criteria, the failure loads and locations proved instrumental in providing insight to additive manufacturing with topology optimization. In conclusion, this research has shown the need for a comprehensive understanding of correlations between geometry, additive manufacturing processing conditions, defect generation, and microstructure for characterization of complex components such as those designed by topology optimization.

42 ENGINEERING↗