Diagnostic and predictive capabilities of the TCR digital platform

Scime, Luke; Sprayberry, Michael; Collins, David W.; Singh, Alka; Joslin, Chase; Duncan, Ryan P.; Simpson, J.; List, F.A.; Carver, Keith; Huning, Alex; Haley, James; Paquit, Vincent

doi:10.2172/1831630

Cited by 5 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These components include nuclear cores, turbine blades, heat exchangers, and fuel assemblies (Watkins et al, 2013;Terrani et al, 2015;Hehr et al, 2017;Betzler et al, 2019;Betzler et al, 2019;Simpson et al, 2019). Figure 5 shows an example of additive manufacturing for nuclear applications; the components were printed at Oak Ridge National Laboratory (ORNL), which operates under the US Department of Energy (Jackson et al, 2016;Scime et al, 2020;Scime et al, 2021). These components were produced using AM, allowing the creation of complicated designs with features such as tube wall cooling channels and irregular geometry that flawlessly align with the specific necessities of the design, showcasing the outstanding versatility and precision of this technology.…”

Section: Frontiers In Energy Researchmentioning

confidence: 99%

Advanced manufacturing and digital twin technology for nuclear energy*

Mondal,

Martinez,

Jain

2024

Front. Energy Res.

View full text Add to dashboard Cite

Advanced manufacturing techniques and digital twin technology are rapidly transforming the nuclear industry, offering the potential to enhance productivity, safety, and cost-effectiveness. Customized parts are being produced using additive manufacturing, automation, and robotics, while digital twin technology enables the virtual modeling and optimization of complex systems. These advanced technologies can significantly improve operational efficiency, predict system behavior, and optimize maintenance schedules in the nuclear energy sector, leading to heightened safety and reduced downtime. However, the nuclear industry demands the highest levels of safety and security, as well as intricate manufacturing processes and operations. Thus, challenges such as data management and cybersecurity must be addressed to fully realize the potential of advanced manufacturing techniques and digital twin technology in the nuclear industry. This comprehensive review highlights the critical role of digital twin technology with advanced manufacturing toward nuclear energy to improve performance, minimize downtime, and heighten safety, ultimately contributing to the global energy mix by providing dependable and low-carbon electricity.

show abstract

Section: Frontiers In Energy Researchmentioning

confidence: 99%

Advanced manufacturing and digital twin technology for nuclear energy*

Mondal,

Martinez,

Jain

2024

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…A total of five L-PBF builds were performed to generate 6299 SS-J3 tensile specimens used in the feedback loop connecting N6 and N5. Additional builds were performed for camera calibration, algorithm development, DSCNN training, process parameter development, specimen design, heat treatment development, and specimen extraction and tracking procedure development as described in [70]. Design requirements for the five builds discussed in this work include (1) facilitating the extraction of thousands of SS-J3 tensile specimens from trackable locations, (2) capturing the range of process and part vari-ability expected to occur during L-PBF manufacturing, and (3) generating a range of local tensile properties caused by various mechanisms hypothesized to correlate to signatures observable in the available in situ sensor data.…”

Section: Build Design and Conditionsmentioning

confidence: 99%

A Data-Driven Framework for Direct Local Tensile Property Prediction of Laser Powder Bed Fusion Parts

Scime,

Joslin,

Collins

et al. 2023

Materials

Self Cite

View full text Add to dashboard Cite

This article proposes a generalizable, data-driven framework for qualifying laser powder bed fusion additively manufactured parts using part-specific in situ data, including powder bed imaging, machine health sensors, and laser scan paths. To achieve part qualification without relying solely on statistical processes or feedstock control, a sequence of machine learning models was trained on 6299 tensile specimens to locally predict the tensile properties of stainless-steel parts based on fused multi-modal in situ sensor data and a priori information. A cyberphysical infrastructure enabled the robust spatial tracking of individual specimens, and computer vision techniques registered the ground truth tensile measurements to the in situ data. The co-registered 230 GB dataset used in this work has been publicly released and is available as a set of HDF5 files. The extensive training data requirements and wide range of size scales were addressed by combining deep learning, machine learning, and feature engineering algorithms in a relay. The trained models demonstrated a 61% error reduction in ultimate tensile strength predictions relative to estimates made without any in situ information. Lessons learned and potential improvements to the sensors and mechanical testing procedure are discussed.

show abstract

“…Under these conditions, there are many unique pressure-retaining and mechanical support components composed of AM316 that could be proposed for construction and use in a nuclear application to justify this certification approach using the DP. This application envelope is recommended because of the extensive experience base that TCR has generated [21]; its use would significantly lower the starting requirements for the execution of this roadmap.…”

Section: Establishing the Experimental Boundsmentioning

confidence: 99%

“…Task 5 could be a significant effort, depending on the material properties of interest and the tests needed to obtain such properties. Considering the multitude of different critical AMT parameters, and their impacts on the local material properties, to train and test the machine learning algorithm (generalized neural network) will likely require thousands, possibly tens of thousands, of specimens in the geometry relevant to the physical material property collection test [21]. TCR is continuing to contribute to the wealth of tensile data for AM SS316, which provides additional motivation for selecting it as the experimental bounds.…”

Section: Establishing the Experimental Boundsmentioning

confidence: 99%

Advancement of Certification Methods and Applications for Industrial Deployments of Components Derived from Advanced Manufacturing Technologies

Huning¹,

Smith²,

Scime³

et al. 2022

Self Cite

View full text Add to dashboard Cite

One goal of the Advanced Materials and Manufacturing Technologies subprogram, within the Department of Energy's (DOE) crosscutting technology development program, is to advance the qualification and certification of parts and components created via additive manufacturing (AM). AM offers a new paradigm for the design and optimization of new nuclear components, and for observing and tracking manufacturing performance and potential defects in a way that is not possible with traditional approaches. Tracking and evaluating these in situ data can lead to the estimation of local material properties and, with the use of engineering analysis tools, the estimation of component performance during operation. To achieve these objectives, a digital platform certification approach was developed and is summarized in this report.

show abstract

Diagnostic and predictive capabilities of the TCR digital platform

Cited by 5 publications

References 11 publications

Advanced manufacturing and digital twin technology for nuclear energy*

Advanced manufacturing and digital twin technology for nuclear energy*

A Data-Driven Framework for Direct Local Tensile Property Prediction of Laser Powder Bed Fusion Parts

Advancement of Certification Methods and Applications for Industrial Deployments of Components Derived from Advanced Manufacturing Technologies

Contact Info

Product

Resources

About