Search NASA⌕ Search

SEARCH · Search NASA

Results for “Training Analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 541 records · Page 30

On-Line Monitoring for Control and Safeguarding of Radiochemical Streams at Spent Fuel Reprocessing Plant

There is a renewed interest worldwide to promote the use of nuclear power and close the nuclear fuel cycle. The long term successful use of nuclear power is critically dependent upon adequate and safe processing and disposition of the spent nuclear fuel Liquid-liquid extraction is a separation technique commonly employed for the processing of the dissolved spent nuclear fuel. Our approach is based on prerequisite that real time monitoring of the solvent extraction flowsheets provides unique capability to quickly detect unwanted manipulations with fissile isotopes present in the radiochemical streams during reprocessing activities. The instrumentation used to monitor these processes must be robust, require little or no maintenance, and be able to withstand harsh environments such as high radiation fields and aggressive chemical matrices. In addition, the ability for continuous on-line monitoring allows for numerous benefits. Our team experimentally assessed the potential of Raman and vis-NIR spectrophotometric techniques for on-line real-time monitoring of the U(VI)/nitrate ion/nitric acid and Pu(IV)/Np(V)/Nd(III), respectively, in solutions relevant to spent fuel reprocessing. Both techniques demonstrated robust performance in the repetitive batch measurements of each analyte in a wide concentration range using simulant and commercial dissolved spent fuel solutions. Static spectroscopic measurements served as training sets for the multivariate data analysis to obtain partial least squares predictive models, which were validated using on-line centrifugal contactor extraction tests. The corresponding spectrometers used under the laboratory conditions are easily convertible to the process-friendly configurations allowing remote measurements under the flow conditions. A fiber optic Raman probe allows monitoring of the high concentration species encountered in both aqueous and organic phases within the PUREX suite of flowsheets, including metal oxide ions, such as uranyl, components of the organic solvent, inorganic oxo-anions, and water. The actinides and lanthanides are monitored remotely by UV-vis-NIR spectroscopy in aqueous and organic phases. This paper summarizes our methodology and shows results of specific examples.

Bryan, Samuel A↗

SPECTROSCOPIC ON-LINE MONITORING FOR PROCESS CONTROL AND SAFEGUARDING OF RADIOCHEMICAL STREAMS

There is a renewed interest worldwide to promote the use of nuclear power and close the nuclear fuel cycle. The long term successful use of nuclear power is critically dependent upon adequate and safe processing and disposition of the spent nuclear fuel. Liquid-liquid extraction is a separation technique commonly employed for the processing of the dissolved spent nuclear fuel. The instrumentation used to monitor these processes must be robust, require little or no maintenance, and be able to withstand harsh environments such as high radiation fields and aggressive chemical matrices. In addition, the ability for continuous online monitoring allows for numerous benefits. Our team experimentally assessed the potential of Raman and spectrophotometric techniques for on-line real-time monitoring of the U(VI)/nitrate ion/nitric acid and Pu(IV)/Np(V)/Nd(III), respectively, in solutions relevant to spent fuel reprocessing. Both techniques demonstrated robust performance in the repetitive batch measurements of each analyte in a wide concentration range using simulant and commercial dissolved spent fuel solutions. Static spectroscopic measurements served as training sets for the multivariate data analysis to obtain partial least squares predictive models, which were validated using on-line centrifugal contactor extraction tests. This paper summarizes or methodology and results of the U(VI)/nitrate system as a specific example.

separations, PUREX, U, Pu, Np, nitic acid, TBP dod↗

Integrating The Non-Electrical Worker Into The Electrical Safety Program

The intent of this paper is to demonstrate an electrical safety program that incorporates all workers into the program, not just the electrical workers. It is largely in response to a paper presented at the 2012 ESW by Lanny Floyd entitled "Facilitating Application of Electrical Safety Best Practices to "Other" Workers" which requested all attendees to review their electrical safety program to assure that non-electrical workers were protected as well as electrical workers. The referenced paper indicated that roughly 50% of electrical incidents involve workers whose primary function is not electrical in nature. It also encouraged all to "address electrical safety for all workers and not just workers whose job responsibilities involve working on or near energized electrical circuits." In this paper, a program which includes specific briefings to non-electrical workers as well as to workers who may need to perform their normal activities in proximity to energized electrical conductors is presented. The program uses a targeted approach to specific areas such as welding, excavating, rigging, chart reading, switching, cord and plug equipment and several other general areas to point out hazards that may exist and how to avoid them. NFPA 70E-2004 was incorporated into the program several years ago and with it the need to include the "other" workers became apparent. The site experience over the years supports the assertion that about half of the electrical incidents involve non-electrical workers and this prompted us to develop specific briefings to enhance the knowledge of the non-electrical worker regarding safe electrical practices. The promotion of "May is Electrical Safety Month" and the development of informative presentations which are delivered to the general site population as well as electrical workers have greatly improved the hazards awareness status of the general worker on site.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Spectroscopic Online Monitoring for Process Control and Safeguarding of Radiochemical Fuel Reprocessing Streams

There is a renewed interest worldwide to promote the use of nuclear power and close the nuclear fuel cycle. The long term successful use of nuclear power is critically dependent upon adequate and safe processing and disposition of the spent nuclear fuel. Liquid-liquid extraction is a separation technique commonly employed for the processing of the dissolved spent nuclear fuel. The instrumentation used to monitor these processes must be robust, require little or no maintenance, and be able to withstand harsh environments such as high radiation fields and aggressive chemical matrices. In addition, the ability for continuous online monitoring allows for numerous benefits. This paper reviews application of the absorption and vibrational spectroscopic techniques supplemented by physicochemical measurements for radiochemical process monitoring. In this context, our team experimentally assessed the potential of Raman and spectrophotometric techniques for on-line real-time monitoring of the U(VI)/nitrate ion/nitric acid and Pu(IV)/Np(V)/Nd(III), respectively, in solutions relevant to spent fuel reprocessing. Both techniques demonstrated robust performance in the repetitive batch measurements of each analyte in a wide concentration range using simulant and commercial dissolved spent fuel solutions. Static spectroscopic measurements served as training sets for the multivariate data analysis to obtain partial least squares predictive models, which were validated using on-line centrifugal contactor extraction tests. Satisfactory prediction of the analytes concentrations in these preliminary experiments warrants further development of the spectroscopy-based methods for radiochemical safeguards and process control.

spectroscopic process monitoring, Pu, U, Np↗

SPECTROSCOPIC ONLINE MONITORING FOR PROCESS CONTROL AND SAFEGUARDING OF RADIOCHEMICAL STREAMS

There is a renewed interest worldwide to promote the use of nuclear power and close the nuclear fuel cycle. The long term successful use of nuclear power is critically dependent upon adequate and safe processing and disposition of the used nuclear fuel. Liquid-liquid extraction is a separation technique commonly employed for the processing of the dissolved used nuclear fuel. The instrumentation used to monitor these processes must be robust, require little or no maintenance, and be able to withstand harsh environments such as high radiation fields and aggressive chemical matrices. This paper summarizes application of the absorption and vibrational spectroscopic techniques supplemented by physicochemical measurements for radiochemical process monitoring. In this context, our team experimentally assessed the potential of Raman and spectrophotometric techniques for online real-time monitoring of the U(VI)/nitrate ion/nitric acid and Pu(IV)/Np(V)/Nd(III), respectively, in solutions relevant to spent fuel reprocessing. These techniques demonstrate robust performance in the repetitive batch measurements of each analyte in a wide concentration range using simulant and commercial dissolved spent fuel solutions. Spectroscopic measurements served as training sets for the multivariate data analysis to obtain partial least squares predictive models, which were validated using on-line centrifugal contactor extraction tests. Satisfactory prediction of the analytes concentrations in these preliminary experiments warrants further development of the spectroscopy-based methods for radiochemical process control and safeguarding. Additionally, the ability to identify material intentionally diverted from a liquid-liquid extraction contactor system was successfully tested using on-line process monitoring as a means to detect the amount of material diverted. A chemical diversion and detection from a liquid-liquid extraction scheme was demonstrated using a centrifugal contactor system operating with the simulant PUREX extraction system of Nd(NO3)3/nitric acid aqueous phase and TBP/n-dodecane organic phase. During a continuous extraction experiment, a portion of the feed from a counter-current extraction system was diverted while the spectroscopic on-line process monitoring system was simultaneously measuring the feed, raffinate and organic products streams. The amount observed to be diverted by on-line spectroscopic process monitoring was in excellent agreement with values based from the known mass of sample directly taken (diverted) from system feed solution.

fuel reprocessing↗

Model-based Hierarchical Reinforcement Learning for Improved Physical Security Design: A Prototype

Prior work in FY24 developed an adversarial AI agent aid in path analysis of physical protection systems. This agent, trained using a model-based reinforcement learning algorithm, was able to successfully learn the most vulnerable path in facilities. It was able to extend the current state of practice for physical protection design by exhibiting dynamic behavior based on current environmental conditions. Whereas PathTrace largely performs a static, graph-based analysis, the AI agent was able to make decisions based on relative position in the facility, current conditions (was the adversarial agnet discovered?), and proximity to secondary targets. The agent demonstrated some novel capabilities, but had limitations that need to be resolved before it can be used for production purposes. For example, the adversarial agent generalizes poorly and takes a relatively long time to train. Nonetheless, there is still considerable promise for developing the adversarial agent further in order to explore even richer, more dynamic behaviors (e.g., adversary motivations, environmental debris, and more). This work considers a complementary idea; development of a planning agent. The planning agent is envisioned as an auto-complete-like tool that can help accelerate security system design by human experts. The agent would respect existing barriers and sensors placed by a human expert while offering cost-effective suggestions (i.e., implicitly balancing effectiveness with cost) to improve the design. The goal is for this agent to be part of an expert’s toolbox, not to totally upend the current state-of-practice, or to displace human experts. The ultimate goal would be concurrent training of both the adversarial and planning agent together, to learn entirely through self-play. This would represent an entirely new way of performing system deign. We selected a hierarchical, model-based reinforcement learning algorithm to serve as the planning agent. This is an extension of concepts used in the prior FY24 adversarial agent work. There, we had a single agent acting an environment. Here, we have two different sub-agents (policies), working together, to form a complete agent. There is a manager policy, which can select abstract goals on slower time scales, and a worker, which performs primitive actions to reach goals selected by the manager. It is worth noting that this class of algorithm is challenging to work with. From our understanding, our work is one of the first successful uses of model-based reinforcement learning (MBRL) in nuclear energy1 , and likely the first hierarchical model-based reinforcement learning application in nuclear energy. Further, this work is one of the first known attempts to apply AI to perform a design tasks in nuclear energy. Consequently, there were significant implementation challenges and the bulk of the work was focused on successful implementation and algorithm design. The results presented here are very low technology readiness level as a consequence of the lack of related literature, but still represent a significant step forward in the pursuit of applied AI for design.

42 ENGINEERING↗

LANDSAT-4 image data quality analysis

Seven heterogeneous areas within the Des Moines, Iowa area test site were selected to define candidate spectral training classes using a clustering algorithm. In addition to the 91 cluster (nonsupervised) classes, three supervised training classes were defined and subsequently included in the training statistics file. The identity of all 94 candidate classes were determined using available reference data. Through analysis of the interclass separabilities, the original 94 candidate training classes were reduced to 42 spectrally separable final classes. The minimum average transformed divergence values for the 42 spectral classes and for the best subsets of TM spectral bands are shown in a table.

Anuta, P. E.↗

Landing and Population Hazard Analysis for Stardust Entry in Operations and Entry Planning

Stardust is a comet sample return mission that successfully returned to Earth on January 15, 2006. Stardust's targeted landing area was the Utah Test and Training Range in the Northwest corner of Utah. Requirements for the risks associated with landing were levied on Stardust by the Utah Test and Training Range and NASA. This paper describes the analysis to verify that these requirements were met and and includes calculation of debris survivability, generation of landing site selection plots, and identification of keep-out zones, as well as appropriate selection of the landing site. Operationally the risk requirements were all met for both of the GOMO-GO polls, so entry was authorized.

simulation↗

Optimizing Distributed Training on Frontier for Large Language Models

Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Loss scaling studies have demonstrated the superior performance of larger LLMs compared to their smaller counterparts. Nevertheless, training LLMs with billions of parameters poses significant challenges and requires considerable computational resources. For example, training a one trillion parameter GPT-style model on 20 trillion tokens requires a staggering 120 million exaflops. This research explores efficient distributed training strategies to extract this computation from Frontier, the world's first exascale supercomputer. We enable and investigate various model and data parallel training techniques, such as tensor parallelism, pipeline parallelism, and sharded data parallelism, to facilitate training a trillion-parameter model on Frontier. We empirically assess these techniques and their associated parameters to determine their impact on memory footprint, communication latency, and GPU's computational efficiency. We analyze the complex interplay among these techniques and find a strategy to combine them to achieve high throughput through hyperparameter tuning. We have identified efficient strategies for training large LLMs of varying sizes through empirical analysis and hyperparameter tuning. For 22 Billion, 175 Billion, and 1 Trillion parameters, we achieved GPU throughputs of 38.38%, 36.14%, and 31.96%, respectively. For the training of the 175 Billion parameter model and the 1 Trillion parameter model, we achieved 100% weak scaling efficiency on 1024 and 3072 Mi250X GPUs, respectively. We also achieved strong scaling efficiencies of 89% and 87% for these two models. We trained these models only tens of iterations instead of training till completion.

Yin, Junqi↗

Dynamics Modeling and Simulation of Large Transport Airplanes in Upset Conditions

As part of NASA's Aviation Safety and Security Program, research has been in progress to develop aerodynamic modeling methods for simulations that accurately predict the flight dynamics characteristics of large transport airplanes in upset conditions. The motivation for this research stems from the recognition that simulation is a vital tool for addressing loss-of-control accidents, including applications to pilot training, accident reconstruction, and advanced control system analysis. The ultimate goal of this effort is to contribute to the reduction of the fatal accident rate due to loss-of-control. Research activities have involved accident analyses, wind tunnel testing, and piloted simulation. Results have shown that significant improvements in simulation fidelity for upset conditions, compared to current training simulations, can be achieved using state-of-the-art wind tunnel testing and aerodynamic modeling methods. This paper provides a summary of research completed to date and includes discussion on key technical results, lessons learned, and future research needs.

Foster, John V.↗

SETI Pulse Detection Algorithm: Analysis of False-alarm Rates

Some earlier work by the Search for Extraterrestrial Intelligence (SETI) Science Working Group (SWG) on the derivation of spectrum analyzer thresholds for a pulse detection algorithm based on an analysis of false alarm rates is extended. The algorithm previously analyzed was intended to detect a finite sequence of i periodically spaced pulses that did not necessarily occupy the entire observation interval. This algorithm would recognize the presence of such a signal only if all i-received pulse powers exceeded a threshold T(i): these thresholds were selected to achieve a desired false alarm rate, independent of i. To simplify the analysis, it was assumed that the pulses were synchronous with the spectrum sample times. This analysis extends the earlier effort to include infinite and/or asynchronous pulse trains. Furthermore, to decrease the possibility of missing an extraterrestrial intelligence signal, the algorithm was modified to detect a pulse train even if some of the received pulse powers fall below the threshold. The analysis employs geometrical arguments that make it conceptually easy to incorporate boundary conditions imposed on the derivation of the false alarm rates. While the exact results can be somewhat complex, simple closed form approximations are derived that produce a negligible loss of accuracy.

Levitt, B. K.↗

Functional approximation using artificial neural networks in structural mechanics

The artificial neural networks (ANN) methodology is an outgrowth of research in artificial intelligence. In this study, the feed-forward network model that was proposed by Rumelhart, Hinton, and Williams was applied to the mapping of functions that are encountered in structural mechanics problems. Several different network configurations were chosen to train the available data for problems in materials characterization and structural analysis of plates and shells. By using the recall process, the accuracy of these trained networks was assessed.

Alam, Javed↗

Medical Student–Reported Outcomes of a Radiation Oncologist–Led Preclinical Course in Oncology: A Five-Year Analysis

Purpose: There is a recognized need for more robust training in oncology for medical students. At our institution, we have offered a core dedicated oncology block, led by a radiation oncologist course director, during the second year of the medical school curriculum since the 2008-2009 academic year. Herein, we report the outcomes of the oncology block over the past 5 years through an analysis of student perceptions of the course, both immediately after completion of the block and in the third year. Methods and Materials: We analyzed 2 separate surveys. The first assessed student impressions of how well the course met each of the course's learning objectives through a survey that was administered to students immediately after the oncology block in 2012. The second was administered after students completed the oncology block during the required radiology clerkship in the third year. All questions used a 5-level Likert scale and were analyzed by use of a Wilcoxon signed-rank test. Results: Of the 169 students who took the oncology course in 2012, 127 (75.1%) completed the course feedback survey. Over 73% of students agreed or strongly agreed that the course met its 3 learning objectives. Of the 699 medical students who took the required radiology clerkship between 2010 and 2013, 538 participated in the second survey, for a total response rate of 77%. Of these students, 368 (68.4%) agreed or strongly agreed that the course was effective in contributing to their overall medical education. Conclusion: Student perceptions of the oncology block are favorable and have improved across multiple categories since the inception of the course. Students self-reported that a dedicated preclinical oncology block was effective in helping identify the basics of cancer therapy and laying the foundation for clinical electives in oncology, including radiation oncology.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Development of Digital Twin Predictive Model for PWR Components: Updates on Multi Times Series Temperature Prediction Using Recurrent Neural Network, DMW Fatigue Tests, System Level Thermal-Mechanical-Stress Analysis

The long-term operation (LTO) of nuclear power plant (NPP) beyond their original design life of 40 years, can lead to more material damage associated with cyclic fatigue under thermal-mechanical loading cycles and associated long-term exposure of reactor material to the deleterious reactor-coolant environments. However, under this LTO condition the reactor components can still safely operate but may require more frequent Nondestructive Evaluation (NDE) of reactor components. Frequent NDE requirement may lead to frequent shutdown of the NPP. This in turn can lead to power outage and additional NDE-inspection-cost related economic loss. The economic loss can be minimized by reducing uncertainty in life estimation of safety-critical pressure boundary components and by implementing more digital approach such as by using upcoming digital-twin (DT) technology for predicting the structural states (e.g., time and location dependent inside/outside thickness temperature, stress, strain, plastic deformation, etc.) and associated fatigue life of a component in real time. Towards this goal Argonne National Laboratory (ANL) with the sponsorship of DOE Light Water Reactor Sustainability (LWRS) program is working on the development of a DT framework that can be used for real time environmental fatigue prediction of reactor components. The DT framework is based on limited experiment-data, Artificial-intelligence (AI) – Machine-Learning (ML) - Deep-Learning (DL) based techniques and Multiphysics-computational-mechanics such as finite element (FE) based modeling tools. Towards this overall goal, following are some of the major contributions made during the FY21: 1) Multiple 82/182 dissimilar metal weld (DMW) specimens (both solid-weld and joint-weld representing the actual reactor multi-metal nozzles) were fatigue tested. The resulting fatigue lives were compared to the NUREG-6909 based best-fit and design fatigue curves. Additionally, the results of 52/152 DMW fatigue specimens (which were recently tested at Republic of Korea under the sponsorship of International Nuclear Energy Research Initiative - INERI program) were compared to the NUREG-6909 based best-fit and design fatigue curves. From the comparison of 82/182 and 52/152 DMW test data with NUREG-6909 best-fit curve, most of the reported test data fall way away from the NUREG-6909 suggested best-fit or mean curve. The NUREG-6909 suggested best-fit curve is the best-fit curve of austenitic stainless steel and due to lack of enough data on Nickel-based welds, this is currently being used for predicting the life of Nickel-alloy-based welded components. However, the above observation may require higher scaling factor (e.g., ASME suggested factor of 20 on cycles rather than the current NUREG-6909 suggested factor of 12 on cycles) for scaling the austenitic-stainless-steel best-fit-curve for estimating the design or safe-life of a welded component. Accordingly, for example, if a DMW component experience a strain amplitude of 0.6% the PWR-water life of the component would be 52 cycles instead of 85 cycles. However, more DMW tests are required to further ascertain the above-mentioned observations. 2) A system level CAD and finite element model were developed which consists of reactor pressure vessel (RPV), part of steam generator (SG), part of pressurizer (PRZ), hot leg (HL), and surge line (SL). This is with detailed nozzle geometry and thermal-mechanical material properties of different metals to simulate realistic thermal-mechanical stress under connected system global thermal-mechanical boundary conditions. 3) Different system level heat transfer analyses were performed with estimation of relevant heat transfer coefficients. The resulting data were used in subsequent system level thermal-mechanical stress analysis and for generating spatial-temporal training and validation data for a system level digital-twin based temperature predictor. Transient heat transfer analyses were performed considering thermal boundary condition under design-basis (DB) loading and EDF (Électricité de France) data-based grid-load-following (EDF-GLF) loading cycles. 4) System level thermal-mechanical stress analysis was performed for identifying damage-prone hotspots and for future extension of the model for cyclic state prediction. From the system-level model simulation under DB loading cycle it is found that HL and the SL nozzle that connect to the HL can experience significant stress and strain and could be one of the weakest links in the overall reactor coolant system (RCS). 5) An AI/ML based DT model was developed for multi-time-series temperature prediction at any inside/outside thickness locations of PWR pressure boundary components. This is by using Recurrent-neural-network (RNN) and keras machine learning libraries. The RNN model was validated against two laboratory test-based data sets with one obtained through ANL’s in-air fatigue test system and other through PWR-water test loop. The experimentally validated DT model further validated against FE model results to predict thermal scarification related spatialtemporal temperatures at random locations of a component. The well validated DT model was then used for demonstrating spatial-temporal temperature prediction under 100+ years of reactor operation subjected to combined DB, EDF-GLF and randomized grid-load-following (RANDOMGLF) loading Cycles. The expert-elicitation DT model framework was developed assuming field/input/process measurements can be available from a few existing plant sensors and can readily be used by the NPP operators. The above temperature prediction model will feed to the next-step stress analysis model based on which the life of a component can be predicted in realtime, which is one of our future works.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Safe Operations at Roadway Junctions - Design Principles from Automated Guideway Transit

Herein this paper describes a system-level view of a fully automated transit system comprising a fleet of automated vehicles (AVs) in driverless operation, each with an SAE level 4 Automated Driving System, along with its related safety infrastructure and other system equipment. This AV system-level control is compared to the automatic train control system used in automated guideway transit technology, particularly that of communications-based train control (CBTC). Drawing from the safety principles, analysis methods, and risk assessments of CBTC systems, comparable functional subsystem definitions are proposed for AV fleets in driverless operation. With the prospect of multiple AV fleets operating within a single automated mobility district, the criticality of protecting roadway junctions requires an approach like that of automated fixed-guideway transit systems, in which a guideway switch zone "interlocking" at each junction location deconflicts railway traffic, affirming safe passage. The analogous AV protection safety subsystem is defined as fail-safe equipment that monitors roadway intersections and junctions, communicates traffic signal status, perceives and communicates alerts and signals to AV connected vehicles concerning potential unsafe conditions, and performs related primary safety functions. Conclusions are drawn that the AV protection roadway intersection functions must be performed by local roadside equipment dedicated to protecting each roadway intersection and junction. Further, it is concluded that the communications technology connecting the infrastructure with the vehicle to perform this vital, fail-safe protection should meet specific functional and performance criteria.

33 ADVANCED PROPULSION SYSTEMS↗

Education in Safeguards and Security Technology Meeting Challenges with Technology and Experience

Education and hands-on experience are crucial to ensuring a workforce of safeguards and security professionals who can meet the challenges currently faced in global nuclear safeguards and security. Global demand for nuclear energy and technology, the new Strategic Arms Reduction Treaty (START), and the cleanup of Cold War facilities have resulted in an increased need for trained safeguards and security personnel. At the same time, the global community is facing a growing shortage of experienced workers with hands-on knowledge of nuclear material processing. Limited access to operating facilities has dramatically reduced the opportunities for next-generation practitioners to obtain hands-on training experience. To address these needs, the Safeguards Technology Integration Center (STIC) at Oak Ridge National Laboratory was created as a Department of Energy User Facility to provide access both to the latest technology and to field-experienced professionals. The STIC provides real-world conditions, process equipment mock-ups, and controlled access to encapsulated radioactive materials (including highly enriched uranium and plutonium) for training and technology evaluation encompassing various techniques and skills, such as Radiation Inspection Systems, Containment and Surveillance Systems, Nondestructive Assay, Security System Performance Testing, and System Design and Analysis. The STIC facilities, laboratories, test beds, and training facilities are described along with the more notable aspects of the training program, which has included more than 1000 participants in the last four years.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Operational Influence on Thermal Behavior of High-Speed Helical Gear Trains

An experimental effort has been conducted on an aerospace-quality helical gear train to investigate the thermal behavior of the gear system as many important operational conditions were varied. Drive system performance measurements were made at varying speeds and loads (to 5,000 hp and 15,000 rpm). Also, an analytical effort was undertaken for comparison to the measured results. The influence of the various loss mechanisms from the analysis for this high speed helical gear train gearbox will be presented and compared to the experimental results.

Handschuh, Robert F.↗

Building Datasets and Training Methods for ML Based Magnet Quench Detection

Detecting quenches in superconducting (SC) magnets during training is a challenging process that involves capturing physical events that occur at different frequencies and appear as various signal features. These events may be correlated across instrumentation type, thermal cycle, and ramp. These events together build a more complete picture of continuous processes occurring in the magnet, and may allow us to flag potential precursors for quench detection. We present our work on building an automatic machine learning (ML) based quench detection system. We build upon our existing work on unsupervised auto-encoders for acoustic sensors and quench antenna (QA) by first establishing a supervised ML training pipeline. We show the results of an event tagging, analysis, and simulation framework on our QA and acoustic data which are used concurrently to build a training dataset for a supervised implementation. We then show how this supervised training can be used as a prior in a semi-supervised framework and compare this to the unsupervised neural network auto-encoder performance.This allows us to have a more concrete understanding of the performance of our algorithms relative to physical events occurring in the magnet, and also provides a baseline software tool to generically evaluate our quench prediction autoencoders under completely unsupervised, supervised, and semi-supervised training conditions.

Khan, Maira [Fermilab]↗