Report on Progress of correlation of in-situ and ex-situ data and the use of artificial intelligence to predict defects

Scime, Luke; Haley, James; Halsey, William; Singh, Alka; Sprayberry, Michael; Ziabari, Amirkoushyar; Paquit, Vincent

doi:10.2172/1684671

Cited by 5 publications

(8 citation statements)

References 5 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This sequence is referred to throughout this report as the test campaign and consists of calibration builds, builds to "debug" the digital workflow and associated procedures, and builds designed to produce large quantities of SS-J3 samples and burst tubes under different experimental conditions. The printer coordinate system used in this report is defined in Scime et al [6] and designates the vertical build direction as the +z-axis, the printer-front to printer-back direction as the +y-axis, and the printer-left to printer-right direction as the +x-axis. Table 1 enumerates all the builds undertaken as part of the test campaign.…”

Section: Test Campaign Build Sequencementioning

confidence: 99%

“…The database is then updated, and a globally unique identifier is assigned to the build dataset. Each as-built part and each possible child sample are automatically assigned a build-wise unique identifier by Peregrine as described in Scime et al [6], and this information is shared with the database via a dedicated application programming interface (API). Next, the heat-treatment operation (Section 2.3) is performed on the entire build, and the associated metadata are recorded using the DT; both the target and measured thermal profiles are also uploaded to the DP via the DT.…”

Section: Sample Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Diagnostic and predictive capabilities of the TCR digital platform

Scime¹,

Sprayberry²,

Collins³

et al. 2021

Self Cite

View full text Add to dashboard Cite

Section: Test Campaign Build Sequencementioning

confidence: 99%

Section: Sample Trackingmentioning

confidence: 99%

Diagnostic and predictive capabilities of the TCR digital platform

Scime¹,

Sprayberry²,

Collins³

et al. 2021

Self Cite

View full text Add to dashboard Cite

“…For a cylinder, the burst pressure, not under creep conditions, is related to UTS of the material. In FY20, 586 AM SS316L samples across three different LPBF builds were mechanically tested [37]. More samples are being tested in FY21 and FY22.…”

Section: Ex-situ (Physical) Data Collectionmentioning

confidence: 99%

Digital Platform Informed Certification of Components Derived from Advanced Manufacturing Technologies

Huning

Fair

Coates

et al. 2021

Self Cite

View full text Add to dashboard Cite

The Transformational Challenge Reactor is being designed at Oak Ridge National Laboratory to demonstrate the feasibility of constructing a reactor core using advanced manufacturing technology. This technology includes additive manufacturing combined with machine learning, materials science, and data science technologies in an effort to facilitate the expansion of additive manufacturing into advanced nuclear energy systems and other applications requiring a high level of quality assurance. The Transformational Challenge Reactor is employing additive manufacturing and artificial intelligence to deliver a new approach. Beginning in FY21, the focus of the program has shifted away from demonstrating a reactor, and instead, towards delivering on four key thrust areas: (1) artificial intelligence-informed design, (2) advanced materials, (3) integrated sensing and control, and (4) the digital platform. Of these four thrust areas, the most pertinent to this report is the digital platform. The digital platform has the potential to be a key enabler for a paradigm shift in how components, those derived from advanced manufacturing technologies, are certified for use in nuclear applications. This is achieved primarily using machine learning to discover correlations from the abundance of data produced through additive manufacturing and those physical properties critical to the performance of the component.A proposed approach towards the certification of advanced manufacturing technology-derived components using the digital platform is presented. This approach has similarities to and builds on those industry initiatives already in progress to qualify advanced manufacturing technology-derived components. However, aspects of where data and the digital platform can integrate with, are especially highlighted. This proposed approach is: a. generic (can be applicable to any advanced manufacturing technology, any supported material, and any application which may have a strong safety significance), b. flexible (can be scaled to large programs with a variety of advanced manufacturing technologyderived component applications, or small programs that have only a few, but clearly defined desired applications), c. complementary to existing industry approaches under development (those being developed by the U.S. Nuclear Regulatory Commission and other industry trade groups), and, d. performance-based (allows for operational feedback and building confidence in the digital platform).To envelop these attributes, a simple demonstration has been designed to employ the digital platform for component scale performance predictions. Results from this demonstration are expected around the time of publishing this report and therefore, will be presented in a follow-up report.The digital platform has the potential to transform how concepts of equivalency and expected component performance are measured. Currently, there is no discussion or pathway for using the data and artificial intelligence embedded within the digital platform to demonstrate equivalency ...

show abstract

“…These complexities and uncertainties complicate the ability to guarantee properties and performance, which are necessary for qualifying AM components for nuclear applications. The TCR program laid the foundation for qualifying AM-processed reactor components [11][12][13][14], but significant work remains. The general approach relies on integrating recent advances in artificial intelligence, computational modeling, in situ process monitoring, and ex situ characterization and mechanical testing methods into AM processes (e.g., LPBF) to attain more holistic understanding over component in a build [15].…”

Section: Introductionmentioning

confidence: 99%

Summary of Methodology for Mitigating Risks Associated with Licensing and Qualifying AM Nuclear Materials

Hyer¹,

Sweeney²,

Petrie³

2023

View full text Add to dashboard Cite

The US Department of Energy's Advanced Materials and Manufacturing Technologies (AMMT) program focuses on accelerating the development, qualification, demonstration, and deployment of advanced materials and manufacturing technologies to enable reliable and economical nuclear energy. Laser powder bed fusion (LPBF) is one of the most popular additive manufacturing (AM) processes for fabricating components with intrinsically complex geometries. LPBF was extensively explored for nuclear applications under the previous Transformational Challenge Reactor program. Additionally, Oak Ridge National Laboratory developed and licensed the Peregrine software and larger digital platform that couples machine learning and in situ data collection during AM to detect anomalies and any evolved defects. The digital platform will be critical to (1) the qualification of AM components for nuclear applications that link location-specific data to macroscopic properties and (2) predict final component performance. Current in situ process monitoring tools are valuable for observing the formation of stochastic flaws, but additional data are needed to predict the resulting microstructures and associated material performance. Rapid cooling rates and large thermal gradients have caused large heterogeneities in the microstructure, which cause anisotropy in mechanical performance. The AMMT program is evaluating the best approaches for addressing these heterogeneities and their effect on component performance using a combination of multiscale modeling, enhanced in situ process monitoring, and highthroughput experimental testing. This report summarizes strategies for mitigating the risks associated with qualifying AM components, including developing new sensing capabilities for in situ process monitoring and characterizing melt pool solidification and residual stresses to inform multiscale modeling efforts.

show abstract

Report on Progress of correlation of in-situ and ex-situ data and the use of artificial intelligence to predict defects

Cited by 5 publications

References 5 publications

Diagnostic and predictive capabilities of the TCR digital platform

Diagnostic and predictive capabilities of the TCR digital platform

Digital Platform Informed Certification of Components Derived from Advanced Manufacturing Technologies

Summary of Methodology for Mitigating Risks Associated with Licensing and Qualifying AM Nuclear Materials

Contact Info

Product

Resources

About