Pradeep Ramuhalli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Pradeep Ramuhalli has a total of 417 co-authors. Here are the top co-authors by number of shared publications:
- Ryan Michael Meyer
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
14 shared publications L. Udpa
Michigan State University, ECE Department, East Lansing, MI 48824, USA
13 shared publications- Jamie Coble
Department of Nuclear Engineering, University of Tennessee, Knoxville, TN 37996, USA
11 shared publications Tariq Khan
Dept. of Electrical and Comupter Engineering, Michian State University, East Lansing, MI 48824, USA
10 shared publicationsJamie B. Coble
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
9 shared publicationsLeonard J. Bond
Iowa State University, Center for Nondestructive Evaluation, 1915 Scholl Rd., Ames, IA 50011, USA
9 shared publications
Latest Publications
- Open Access
- 1 September 2026
- Published by Office of Scientific and Technical Information (OSTI)
2026 NDE for Advanced Manufacturing Workshop Workshop Report
The 2026 Nondestructive Evaluation for Advanced Manufacturing (NDE for AM) Workshop was a two-day convening held at the ORNL Manufacturing Demonstration Facility (MDF) in Oak Ridge, Tennessee, on May 19–20, 2026. The workshop brought together researchers, federal program managers, end-users, OEMs, standards bodies, and regulatory agencies to assess the state of the art in NDE for AM parts, identify technology gaps, and establish R&D priorities. The workshop was structured around seven technical sessions, a keynote address, a working lunch talk, evening poster session, and a total of sixteen breakout groups distributed across Day 1 and Day 2 topics. This report provides summaries of each presentation, panel discussion, and breakout session, followed by a cross-cutting synthesis of themes, challenges, gaps, and priorities identified across the workshop.
- 1 September 2026
- Published by Office of Scientific and Technical Information (OSTI)
Open Access2026 NDE for Advanced Manufacturing Workshop Workshop Report
The 2026 Nondestructive Evaluation for Advanced Manufacturing (NDE for AM) Workshop was a two-day convening held at the ORNL Manufacturing Demonstration Facility (MDF) in Oak Ridge, Tennessee, on May 19–20, 2026. The workshop brought together researchers, federal program managers, end-users, OEMs, standards bodies, and regulatory agencies to assess the state of the art in NDE for AM parts, identify technology gaps, and establish R&D priorities. The workshop was structured around seven technical sessions, a keynote address, a working lunch talk, evening poster session, and a total of sixteen breakout groups distributed across Day 1 and Day 2 topics. This report provides summaries of each presentation, panel discussion, and breakout session, followed by a cross-cutting synthesis of themes, challenges, gaps, and priorities identified across the workshop.
- Open Access
- 29 June 2026
- Published by Elsevier in SSRN Electronic Journal
Validating Synthetic Ultrasonic Testing Datawith Actual Crack Responses
Ultrasonic testing (UT) is used prominently in the nuclear industryfor in-service volumetric examinations of safety-critical piping and vesselcomponents. Amid the rapid adoption of AI/ML in several industries,AI/ML solutions are also being sought to elevate the performance and efficiencyof UT for nuclear industry applications. To overcome the challengesinherent in obtaining training data from actual field cracks, methods togenerate training data synthetically are of significant interest. Syntheticmethods for training data generation often rely on surrogate flaw modelsthat are simple approximations to actual flaws that exist in the field.Despite recent efforts to systematically evaluate the influence of trainingdataset parameters on automated analysis of UT, validation with actualflaws has not yet been reported. This effort validates a method for derivingsynthetic training data from electrical discharge machined (EDM)notches with actual chloride-induced stress corrosion crack (CISCC) responses.Validation was performed via data cluster analysis with principalcomponents analysis (PCA), t-distributed stochastic neighbor embedding(t-SNE), and auto-encoder (AE) methods and through analysis of multipleimage similarity metrics, including mean squared error (MSE), peaksignal-to-noise ratio (PSNR), and structural similarity index (SSIM).Finally, the method was also validated by evaluating classifier performanceby several metrics, including the receiver operating characteristic(ROC) curve, area under the ROC curve, confusion matrices, and by actualclass probability distributions. The results show that the method forsynthetic data generation is valid for representing actual flaw responsesand that it is unnecessary to represent many of the complexities of actualflaw responses in training data. In addition, the results of this effort showthat the t-SNE data clustering method and SSIM metric are most effectiveat distinguishing the synthetic data from actual flaw response data.
- 29 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessValidating Synthetic Ultrasonic Testing Datawith Actual Crack Responses
Ultrasonic testing (UT) is used prominently in the nuclear industryfor in-service volumetric examinations of safety-critical piping and vesselcomponents. Amid the rapid adoption of AI/ML in several industries,AI/ML solutions are also being sought to elevate the performance and efficiencyof UT for nuclear industry applications. To overcome the challengesinherent in obtaining training data from actual field cracks, methods togenerate training data synthetically are of significant interest. Syntheticmethods for training data generation often rely on surrogate flaw modelsthat are simple approximations to actual flaws that exist in the field.Despite recent efforts to systematically evaluate the influence of trainingdataset parameters on automated analysis of UT, validation with actualflaws has not yet been reported. This effort validates a method for derivingsynthetic training data from electrical discharge machined (EDM)notches with actual chloride-induced stress corrosion crack (CISCC) responses.Validation was performed via data cluster analysis with principalcomponents analysis (PCA), t-distributed stochastic neighbor embedding(t-SNE), and auto-encoder (AE) methods and through analysis of multipleimage similarity metrics, including mean squared error (MSE), peaksignal-to-noise ratio (PSNR), and structural similarity index (SSIM).Finally, the method was also validated by evaluating classifier performanceby several metrics, including the receiver operating characteristic(ROC) curve, area under the ROC curve, confusion matrices, and by actualclass probability distributions. The results show that the method forsynthetic data generation is valid for representing actual flaw responsesand that it is unnecessary to represent many of the complexities of actualflaw responses in training data. In addition, the results of this effort showthat the t-SNE data clustering method and SSIM metric are most effectiveat distinguishing the synthetic data from actual flaw response data.
- Open Access
- 1 August 2025
- Published by Office of Scientific and Technical Information (OSTI)
Microreactor Automated Control System - Digital Twin Models and Advanced Control Systems Updates
- 1 August 2025
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessMicroreactor Automated Control System - Digital Twin Models and Advanced Control Systems Updates
- 11 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Temperature-Compensated Tuning Fork Sensor for Internal Pressure Monitoring of Spent Fuel Canisters
Measuring internal pressure is crucial in industrial applications, including non-destructive evaluation of spent fuel canisters. This study utilized a double-ended tuning fork (DETF) to measure internal pressure by detecting changes in hoop strain on the canister’s surface, which affects the tuning fork’s resonance frequency. Finite element simulations were conducted to analyze strain distribution and sensor response, followed by calibration and temperature compensation experiments. The sensor outperformed other strain sensors such as strain gauges and surface acoustic wave sensors, achieving a minimum measurable strain of 0.0679 μ and pressure of 0.3 kPa, with a pressure sensitivity of 0.6221 kHz/MPa (35286 ppm/MPa). The study highlights the effectiveness of DETF sensors for precise pressure measurement, demonstrating their suitability for use in harsh environments using the temperature compensation technique demonstrated in this work. The sensor’s performance highlights its potential for widespread adoption in applications where accurate pressure measurement is critical.
- 11 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Temperature-Compensated Tuning Fork Sensor for Internal Pressure Monitoring of Spent Fuel Canisters
Measuring internal pressure is crucial in industrial applications, including non-destructive evaluation of spent fuel canisters. This study utilized a double-ended tuning fork (DETF) to measure internal pressure by detecting changes in hoop strain on the canister’s surface, which affects the tuning fork’s resonance frequency. Finite element simulations were conducted to analyze strain distribution and sensor response, followed by calibration and temperature compensation experiments. The sensor outperformed other strain sensors such as strain gauges and surface acoustic wave sensors, achieving a minimum measurable strain of 0.0679 μ and pressure of 0.3 kPa, with a pressure sensitivity of 0.6221 kHz/MPa (35286 ppm/MPa). The study highlights the effectiveness of DETF sensors for precise pressure measurement, demonstrating their suitability for use in harsh environments using the temperature compensation technique demonstrated in this work. The sensor’s performance highlights its potential for widespread adoption in applications where accurate pressure measurement is critical.
- Open Access
- 1 September 2024
- Published by Office of Scientific and Technical Information (OSTI)
An Update on Microreactor Automated Control System (MACS)
The U.S. Department of Energy's Office of Scientific and Technical Information
- 1 September 2024
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessAn Update on Microreactor Automated Control System (MACS)
The U.S. Department of Energy's Office of Scientific and Technical Information
- Open Access
- 1 July 2024
- Published by Office of Scientific and Technical Information (OSTI)
Oak Ridge National Laboratory's Strategic Research and Development Insights for Digital Twins
The U.S. Department of Energy's Office of Scientific and Technical Information
- 1 July 2024
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessOak Ridge National Laboratory's Strategic Research and Development Insights for Digital Twins
The U.S. Department of Energy's Office of Scientific and Technical Information
- Open Access
- 1 March 2024
- Published by Office of Scientific and Technical Information (OSTI)
An Assessment of Machine Learning Applied to Ultrasonic Nondestructive Evaluation
The U.S. Department of Energy's Office of Scientific and Technical Information
- 1 March 2024
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessAn Assessment of Machine Learning Applied to Ultrasonic Nondestructive Evaluation
The U.S. Department of Energy's Office of Scientific and Technical Information