Search NASA⌕ Search

SEARCH · Search NASA

Results for “Match Machining”

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 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Controlling optical-cavity locking using reinforcement learning

Abstract This study applies an effective methodology based on Reinforcement Learning to a control system. Using the Pound–Drever–Hall locking scheme, we match the wavelength of a controlled laser to the length of a Fabry-Pérot cavity such that the cavity length is an exact integer multiple of the laser wavelength. Typically, long-term drift of the cavity length and laser wavelength exceeds the dynamic range of this control if only the laser’s piezoelectric transducer is actuated, so the same error signal also controls the temperature of the laser crystal. In this work, we instead implement this feedback control grounded on Q-Learning. Our system learns in real-time, eschewing reliance on historical data, and exhibits adaptability to system variations post-training. This adaptive quality ensures continuous updates to the learning agent. This innovative approach maintains lock for eight days on average.

47 OTHER INSTRUMENTATION↗
NASA NTRS1991

Lunar crane system

In many lunar construction scenarios, mechanical cranes in some form will be indispensible in moving large masses around with various degrees of fine positioning. While thorough experience exists in the use of terrestrial cranes new thinking is required about the design of cranes to be used in extraterrestrial construction. The primary driving force for this new thinking is the need to automate the crane system so that space cranes can be operated as telerobotic machines with a large number of automatic capabilities. This is true because in extraterrestrial construction human resources will need to be critically rationed. The design problems of mechanisms and control systems for a lunar crane must deal with at least two areas of performance. First, the automated crane must be capable of maneuvering a large mass, so that when the mass arrives at the target position there are only small vibrations. Secondly, any residue vibrations must be automatically damped out and a fine positioning must be achieved. For extraterrestrial use there are additional challenges to a crane design - for example, to design a crane system so that it can be transformed for other construction uses. This initial project in crane design does not address such additional issues, although they may be the subject of future CSC research. To date the Center has designed and analyzed many mechanisms. The fundamental problem of trade-offs between passively stabilizing the load and actively controlling the load by actuators was extensively studied. The capability of 3D dynamics modeling now exists for such studies. A scaled model of a lunar crane was set up and it has been most fruitful in providing basic understanding of lunar cranes. Due to an interesting scaling match-up, this scaled model exhibits the load vibration frequencies one would expect in the real lunar case. Using the analytical results achieved to date, a laboratory crane system is now being developed as a test bed for verifying a wide variety of mechanisms and control designs. Future development will be aimed at making the crane system a telerobotic test bed into which external sensors such as computer vision systems, and other small robotic devices such as CSC lunar rovers, will be integrated.

Mikulas, Martin M., Jr.↗
NASA NTRS2013

A Scala DSL for RETE-Based Runtime Verification

Runtime verification (RV) consists in part of checking execution traces against formalized specifications. Several systems have emerged, most of which support specification notations based on state machines, regular expressions, temporal logic, or grammars. The field of Artificial Intelligence (AI) has for an even longer period of time studied rule-based production systems, which at a closer look appear to be relevant for RV, although seemingly focused on slightly different application domains, such as for example business processes and expert systems. The core algorithm in many of these systems is the Rete algorithm. We have implemented a Rete-based runtime verification system, named LogFire (originally intended for offline log analysis but also applicable to online analysis), as an internal DSL in the Scala programming language, using Scala's support for defining DSLs. This combination appears attractive from a practical point of view. Our contribution is in part conceptual in arguing that such rule-based frameworks originating from AI may be suited for RV.

matching problem↗
DOE OSTI2025

Automated Waterbox Inspection for Nuclear Power Plants Using Computer Vision - Based Change Detection

Nuclear power plant waterboxes require regular inspection for leaks, missing components, and structural damage during maintenance outages. Traditional manual inspection is time-consuming and poses safety risks from confined space entry. We developed an automated computer vision system for drone-based waterbox inspection in partnership with Florida Light and Power. Our approach uses feature detection and matching to identify critical changes between baseline and current inspection images, automatically flagging additions (leaks/debris), removals (missing plugs), and translations (displaced components) while compensating for drone movement and environmental variations. We systematically evaluated six feature matching methods, from classical approaches (SIFT+BF) to state-of-the-art neural networks (SuperPoint+SuperGlue), using both standard benchmarks (HPatches) and waterbox-specific validation with real-world augmentations. SuperPoint+SuperGlue achieved superior performance with 7.82 pixels RMSE and 100% success rate—2.8x better accuracy than our baseline. While the pre-trained model has commercial licensing restrictions for nuclear deployment, our findings validate this architecture for custom training. We implemented a real-time GUI demonstrating the SIFT+BF approach for immediate deployment, processing drone feeds at 30 FPS with color-coded change visualization. Future work includes training a custom SuperPoint+SuperGlue model on waterbox data and integrating Vision-Language Models for automated reporting and maintenance guidance.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
DOE OSTI2025

Final Design for Thermal/Epithermal eXperiments (TEX) with Lithium Absorbers to Provide Validation Benchmarks for Y-12 Electrorefining Facility

One of the main goals of the Thermal/Epithermal eXperiments (TEX) project is to use existing Nuclear Criticality Safety Program (NCSP) assets to create critical experiment plutonium and uranium test beds for materials important to criticality safety that have insufficient benchmark evaluations. The plutonium test bed experiments were completed in 2018 and are published in the 2020 edition of the International Criticality Safety Benchmark Evaluation Project (ICSBEP) Handbook. The uranium test bed assemblies were completed in 2023 and accepted in the 2024 edition of the ICSBEP Handbook. The Nuclear Criticality Safety (NCS) group at Y-12 National Security Complex has identified programmatic need for validation cases for uranium electrorefining operations at Y-12. The electrorefining operation credits lithium enriched in 6 Li in addition to 35 Cl as absorbers in the design criticality safety evaluation for precluding criticality under upset conditions in the large and geometrically unfavorable electro-refiner. There is, however, inadequate experimental validation for the 6 Li absorbers. As an extension of the TEX uranium test bed, TEX-Cl critical experiments were performed with sodium chloride salt to address the 35 Cl thermal absorption as well as other validation needs at Los Alamos National Laboratory (LANL). These experiments were completed in 2024 and accepted into the 2025 ICSBEP Handbook. To continue the methodology used in TEX-Cl, TEX-Li aims to accomplish the same. The overall design of both experiments was to use commercially available, high purity, salts with polyethylene moderator and HEU plates to configure a critical assembly. Three experiments are planned for TEX-Li using encapsulated lithium carbonate (Li 2 CO 3 ), with natural 6 Li abundance. For all experiments, the highly enriched uranium (HEU) Jemima plates will be used as fissile material. Multiple layers will be stacked together with encapsulated Li 2 CO 3 alternated with polyethylene in standard configurations. Standard stacking was found to be optimal in matching the different sensitivity profiles provided by the Y-12 models. Three configurations are proposed with varying polyethylene moderation and a constant 1/4” absorber thickness. The first uses 11 layers of 5/4” polyethylene, the second uses 9 layers of 3/4” polyethylene, and the third uses 10 layers of 1/2” polyethylene. Calculations showed that some alternative forms of lithium-based materials provided slightly less-optimal sensitivity profiles when compared to lithium carbonate but come with other drawbacks. These alternatives included lithium aluminate (LiAlO 2 ), Aluminum-2050 alloy, Aluminum-8090, Aluminum-2095, lithium hydride (LiH), and lithium fluoride (LiF). Lithium aluminate and aluminum-2050 provided comparable sensitivity profiles when compared to lithium carbonate and can be used instead if lithium carbonate cannot be readily procured. After a broad material study, lithium carbonate outperformed any alternative material with a balance in affordability and workability. The assessment of experimental uncertainties of the non-absorber and absorber components was predicted to be 0.00089 and 0.00093 Δk eff , respectively. The largest uncertainties may be reduced with precision dimensional inspection of the components. Many of the parts and equipment for IER 575 have already been fabricated or procured for previous projects and therefore do not contribute significantly to the overall cost of this experiment. This includes the Jemima plates and Comet critical assembly machine, which are existing NCSP assets, as well as the aluminum platen and polyethylene reflector rings, which were fabricated and authorized for the TEX experiment involving HEU with polyethylene. Lithium carbonate containers will be procured by LANL and will be filled by LLNL. The total material costs for TEX-Li experiments are estimated to be on the order of $\$$47,400. Precision inspection, including dimensional, mass, density, and impurity, is recommended for all components for an estimated cost of $\$$12,000.

35Cl↗
DOE OSTI2024

Automated annotation of scientific texts for ML-based keyphrase extraction and validation

Advanced omics technologies and facilities generate a wealth of valuable data daily; however, the data often lack the essential metadata required for researchers to find, curate, and search them effectively. The lack of metadata poses a significant challenge in the utilization of these data sets. Machine learning (ML)–based metadata extraction techniques have emerged as a potentially viable approach to automatically annotating scientific data sets with the metadata necessary for enabling effective search. Text labeling, usually performed manually, plays a crucial role in validating machine-extracted metadata. However, manual labeling is time-consuming and not always feasible; thus, there is a need to develop automated text labeling techniques in order to accelerate the process of scientific innovation. This need is particularly urgent in fields such as environmental genomics and microbiome science, which have historically received less attention in terms of metadata curation and creation of gold-standard text mining data sets. In this paper, we present two novel automated text labeling approaches for the validation of ML-generated metadata for unlabeled texts, with specific applications in environmental genomics. Our techniques show the potential of two new ways to leverage existing information that is only available for select documents within a corpus to validate ML models, which can then be used to describe the remaining documents in the corpus. The first technique exploits relationships between different types of data sources related to the same research study, such as publications and proposals. The second technique takes advantage of domain-specific controlled vocabularies or ontologies. In this paper, we detail applying these approaches in the context of environmental genomics research for ML-generated metadata validation. Our results show that the proposed label assignment approaches can generate both generic and highly specific text labels for the unlabeled texts, with up to 44% of the labels matching with those suggested by a ML keyword extraction algorithm.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
NASA NTRS2014

James Webb Space Telescope: The First Light Machine

NASA James Webb Space Telescope (JWST) will search for the first luminous objects of the Universe to help answer fundamental questions about how the Universe came to look like it does today. At 6.5 meters in diameter, JWST will be the world's largest space telescope. Its architecture, e.g. aperture, wavelength range and operating temperature, is driven by JWST's science objectives. Introduction: Scheduled to start its 5 year mission after 2018, JWST will study the origin and evolution of galaxies, stars and planetary systems. Its science mission is to: Identify the first bright objects that formed in the early Universe, and follow the ionization history. Determine how galaxies form. Determine how galaxies and dark matter, including gas, stars, metals, overall morphology and active nuclei evolved to the present day. Observe the birth and early development of stars and the formation of planets. And, study the physical and chemical properties of solar systems for the building blocks of Life. Principle: To accomplish the JWST science objectives requires a larger aperture infrared cryogenic space telescope. A large aperture is required because the objects are very faint. The infrared spectral range is required because the objects are so far away that their ultraviolet and visible wavelength spectral lines are red-shifted into the infrared. Because the telescope is infrared, it needs to be cryogenic. And, because of the telescope is infrared, it must operate above the Earth's atmosphere, i.e. in space. JWST is probably the single most complicated mission that humanity has attempted. It is certainly the most difficult optical fabrication and testing challenge of our generation. The JWST 6.5 m diameter primary mirror is nearly a parabola with a conic constant of -0.9967 and radius of curvature at 30K of 15.880 m. The primary mirror is divided into 18 segments with 3 different prescriptions; each with its own off-axis distance and aspheric departure. The radius of curvature for all 18 segments must match to +/- 0.150 mm at 30K. JWST is diffraction limited at 2 micrometers which translates into a transmitted wavefront specification of 156 nm rms. Of that amount, 50 nm rms is allocated to the primary mirror. Each segment is allocated 22 nm rms surface error. At the start of the JWST program, the capability to make such a mirror did not exist. In 1996, NASA began a systematic and comprehensive mirror technology development effort which resulted in JWST. This program resulted in a qualified mirror fabrication process being approved in 2006. Today, all JWST primary mirror segments meet their requirements and are on schedule for a 2018 launch. The next step is system level assembly, integration and test. Ambient tests will be conducted at Goddard Space Flight Center and cryogenic system level testing will be performed in Chamber A at the Johnson Space Center.

Stahl, H. Philip↗
DOE OSTI2025

Detection of Isotopes in Urban Source Search Low-Count Gamma Spectra Using Hopfield Neural Networks

Source search campaigns involve measurements of background gamma-ray spectra with a mobile detector-spectrometer traveling along arbitrarily chosen trajectories over a wide screening area. Radiation counts are typically measured with a tellurium-doped sodium iodide [NaI(Tl)] scintillator detector-spectrometer in short acquisition intervals, usually 1 s. The objective is to detect orphan isotopes with half-lives shorter than those of the isotopes in the natural background. In principle, radioisotopes can be identified by their unique gamma emission spectrum. However, detecting orphan isotopes in search data is challenging because low counts measured in short acquisition intervals result in incomplete spectral lines. In this study, we investigate the performance of a Hopfield neural network (HNN) that implements an auto-associative memory for the detection of isotopes of interest in an urban search campaign. The HNN is trained on one example of gamma spectra with well-resolved spectral lines of each isotope of interest. During testing, the auto-associative memory implementation of the HNN processes low-count gamma spectra with partially complete isotopic lines by matching incoming measurements to the closest one of its memory-stored patterns. The testing database consisted of almost 10 000 1-s gamma spectra, including measurements of orphan isotopes 137 Cs, 241 Am, and 131 I, obtained during two urban search surveys with a NaI(Tl) detector. The performance of the HNN detection algorithm was evaluated using precision, recall, and F1 scores, and benchmarked with a multiple linear regression (MLR) identification algorithm. In conclusion, the test results demonstrate that HNN outperforms MLR in the detection of all the isotopes of interest.

Auto associative memory↗
NASA NTRS2011

Approximate Simulation of Acute Hypobaric Hypoxia with Normobaric Hypoxia

INTRODUCTION. Some manufacturers of reduced oxygen (O2) breathing devices claim a comparable hypobaric hypoxia (HH) training experience by providing F(sub I) O2 < 0.209 at or near sea level pressure to match the ambient O2 partial pressure (iso-pO2) of the target altitude. METHODS. Literature from investigators and manufacturers indicate that these devices may not properly account for the 47 mmHg of water vapor partial pressure that reduces the inspired partial pressure of O2 (P(sub I) O2). Nor do they account for the complex reality of alveolar gas composition as defined by the Alveolar Gas Equation. In essence, by providing iso-pO2 conditions for normobaric hypoxia (NH) as for HH exposures the devices ignore P(sub A)O2 and P(sub A)CO2 as more direct agents to induce signs and symptoms of hypoxia during acute training exposures. RESULTS. There is not a sufficient integrated physiological understanding of the determinants of P(sub A)O2 and P(sub A)CO2 under acute NH and HH given the same hypoxic pO2 to claim a device that provides isohypoxia. Isohypoxia is defined as the same distribution of hypoxia signs and symptoms under any circumstances of equivalent hypoxic dose, and hypoxic pO2 is an incomplete hypoxic dose. Some devices that claim an equivalent HH experience under NH conditions significantly overestimate the HH condition, especially when simulating altitudes above 10,000 feet (3,048 m). CONCLUSIONS. At best, the claim should be that the devices provide an approximate HH experience since they only duplicate the ambient pO2 at sea level as at altitude (iso-pO2 machines). An approach to reduce the overestimation is to at least provide machines that create the same P(sub I)O2 (iso-P(sub I)O2 machines) conditions at sea level as at the target altitude, a simple software upgrade.

Conkin, J.↗
NASA NTRSDate not supplied

Space Flown Rodent Liver RNA Sequencing Data for Machine Learning in Space Biology Research

High-throughput nucleic acid sequencing (DNA-seq, RNA-seq) has become widespread in biomedical research due to the growing availability and affordability of these assays. Data analysis has been accelerated in recent years by the adoption of artificial intelligence (AI) and machine learning (ML) techniques by biomedical researchers. In space biology research, RNAseq datasets from space-flown experimental samples are critical for characterizing the gene expression aberrations associated with exposure to spaceflight stressors. However, space biological experiments tend to be very low sample size, so identifying proper AI/ML algorithms for sequencing data analysis is an ongoing challenge since these algorithms typically require large sample size. The NASA Science Mission Directorate (SMD) has started the “Benchmark Initiative for AI/ML”, focused on creating datasets meant for three main applications: 1) scientific benchmarking, which finds the best algorithm for a specific problem; 2) application benchmarking, which measures algorithm performance against a set of parameters; and 3) system benchmarking, which evaluates performance of hardware and software architecture. These scientific benchmarks consist of an AI-ready dataset and a reference implementation on a specific scientific question. In this work, we focused on generating standardized datasets to allow the scientific community to benchmark AI/ML algorithms in the domain of space biology. We present here a standardized, AI-ready, publicly available benchmark dataset for space biology RNA-seq data as a collaboration between the NASA AI4LS (Artificial Intelligence for Life Sciences) working group. and NASA’s SMD. This dataset consists of space-flown and ground control mouse liver found in the NASA GeneLab omics database. However, to amplify the small sample number (n=112 samples) for ML purposes, we employ Gaussian noise and a generative adversarial network to extend this dataset to 6,000 synthetic samples, matching the original gene expression characteristics.

James Casaletto↗
DOE OSTI2026

First DIII-D-West hybrid scenario similarity experiments for iter-relevant long-pulse operation

For the first time, similarity experiments between DIII-D and WEST were performed in the ITER "hybrid-like" regime during dedicated campaigns in April and May 2025. The matched parameters include elongation, triangularity, ion ∇B drift direction toward the X-point, qprofile, and core normalized physics quantities in terms of normalized pressure, normalized gyroradius, electron collisionality, ratio of ion to electron temperature, T i /T e . Core transport physics is explored with different aspect ratio (R/a) values (typically 3 at DIII-D and 5 on WEST). DIII-D explored high-beta conditions (electromagnetic effect) with low torque injection (~0 ± 0.5 N•m) using high heating power (up to 6 MW NBI and 2 MW ECRH powers), while scanning the heating mix (ion vs electron), beta, T i /T e , core radiation via controlled tungsten injection using the Laser Blow-Off system. WEST extended operation toward long-duration pulses using its actively cooled tungsten divertor, achieving dominated electron heating regimes with reduced tungsten contamination. Boron impurity injection were scanned on WEST to control edge conditions and core performance. It is found that core confinement improves-manifested by higher electron temperature, total energy content, neutron rate, and ion temperatureunder conditions of low separatrix density, consistent with previous observations [Bourdelle et al., Nucl. Fusion 63 (2023) 056021]. Conditions for Hmode access and for ion heating in electron-dominated regimes in both WEST and DIII-D will be discussed and compared. The ratio of the thermal energy confinement time (τ E ) to the volume-averaged electron-ion collisional heat exchange time (τ e-i ) is a key parameter to enhance ion heating and potentially facilitate H-mode access in electron-heated regimes. These first-of-a-kind coordinated DIII-D and WEST experiments provide a unique multi-machine dataset to validate predictive models and to optimize ITER hybrid-scenario performance under diverse core and edge conditions.

DIII-D↗
NASA NTRS2015

A Vehicle Management End-to-End Testing and Analysis Platform for Validation of Mission and Fault Management Algorithms to Reduce Risk for NASA's Space Launch System

The development of the Space Launch System (SLS) launch vehicle requires cross discipline teams with extensive knowledge of launch vehicle subsystems, information theory, and autonomous algorithms dealing with all operations from pre-launch through on orbit operations. The characteristics of these systems must be matched with the autonomous algorithm monitoring and mitigation capabilities for accurate control and response to abnormal conditions throughout all vehicle mission flight phases, including precipitating safing actions and crew aborts. This presents a large complex systems engineering challenge being addressed in part by focusing on the specific subsystems handling of off-nominal mission and fault tolerance. Using traditional model based system and software engineering design principles from the Unified Modeling Language (UML), the Mission and Fault Management (M&FM) algorithms are crafted and vetted in specialized Integrated Development Teams composed of multiple development disciplines. NASA also has formed an M&FM team for addressing fault management early in the development lifecycle. This team has developed a dedicated Vehicle Management End-to-End Testbed (VMET) that integrates specific M&FM algorithms, specialized nominal and off-nominal test cases, and vendor-supplied physics-based launch vehicle subsystem models. The flexibility of VMET enables thorough testing of the M&FM algorithms by providing configurable suites of both nominal and off-nominal test cases to validate the algorithms utilizing actual subsystem models. The intent is to validate the algorithms and substantiate them with performance baselines for each of the vehicle subsystems in an independent platform exterior to flight software test processes. In any software development process there is inherent risk in the interpretation and implementation of concepts into software through requirements and test processes. Risk reduction is addressed by working with other organizations such as S&MA, Structures and Environments, GNC, Orion, the Crew Office, Flight Operations, and Ground Operations by assessing performance of the M&FM algorithms in terms of their ability to reduce Loss of Mission and Loss of Crew probabilities. In addition, through state machine and diagnostic modeling, analysis efforts investigate a broader suite of failure effects and detection and responses that can be tested in VMET and confirm that responses do not create additional risks or cause undesired states through interactive dynamic effects with other algorithms and systems. VMET further contributes to risk reduction by prototyping and exercising the M&FM algorithms early in their implementation and without any inherent hindrances such as meeting FSW processor scheduling constraints due to their target platform - ARINC 653 partitioned OS, resource limitations, and other factors related to integration with other subsystems not directly involved with M&FM. The plan for VMET encompasses testing the original M&FM algorithms coded in the same C++ language and state machine architectural concepts as that used by Flight Software. This enables the development of performance standards and test cases to characterize the M&FM algorithms and sets a benchmark from which to measure the effectiveness of M&FM algorithms performance in the FSW development and test processes. This paper is outlined in a systematic fashion analogous to a lifecycle process flow for engineering development of algorithms into software and testing. Section I describes the NASA SLS M&FM context, presenting the current infrastructure, leading principles, methods, and participants. Section II defines the testing philosophy of the M&FM algorithms as related to VMET followed by section III, which presents the modeling methods of the algorithms to be tested and validated in VMET. Its details are then further presented in section IV followed by Section V presenting integration, test status, and state analysis. Finally, section VI addresses the summary and forward directions followed by the appendices presenting relevant information on terminology and documentation.

Trevino, Luis↗
DOE OSTI2025

Model Residuals as Shields: A Two-Level Formulation to Defend Smart Grids From Poisoning Attacks

The advancement of smart grids presents both vast opportunities and heightened cybersecurity risks. Data-driven defense mechanisms, though designed as a shield against these threats, can fall prey to poisoning attacks. We delve into regression settings, underscoring the imperative to fortify defenses against a spectrum of poison ratios, notably those above 0.5—an issue scarcely addressed in prior studies. Recognizing the susceptibilities of smart grids and their manipulable sensors, we exploit the very intent of poisoning attacks, compromising model accuracy, as our defense mechanism. Our proposed two-level optimization framework discerns between poisoned and authentic data based on model residuals, outperforming or matching existing methods in 72% to 77% of precision and 75% to 80% of recalls across various poisoning attacks, poison ratios, and datasets. Once the authentic data are identified, the trained model is adaptable for a variety of applications. Comprehensive evaluations on different smart grid datasets, pitted against myriad poisoning schemes, validate our methodology’s edge over existing methods. Here, we also shed light on the implications of model misspecification originating from temporal auto-correlation, a common feature in Internet of Things and smart grid data.

Adversarial machine learning (ML)↗
DOE OSTI2024

A deep learning approach to fast analysis of collective Thomson scattering spectra

Fast analysis of collective Thomson scattering ion acoustic wave features using a deep convolutional neural network model is presented. The network was trained from spectra to predict the plasma parameters, including ion velocities, population fractions, and ion and electron temperatures. A fully kinetic particle-in-cell simulation was used to model a laboratory astrophysics experiment and simulate a diagnostic image of the ion acoustic wave feature. Network predictions were compared with Bayesian inference of the plasma model parameters for both the simulated and experimentally measured images. Both approaches were fairly accurate predicting the simulated image and the network predictions matched a good portion of the Bayesian results for the experimentally measured image. The Bayesian approach is more robust to noise and motivates future work to train deep learning models with realistic noise. The advantage of the deep learning model is making thousands of predictions in a few hundred milliseconds, compared to a few seconds to minutes per prediction for the optimization and Bayesian approaches presented here. The results demonstrate promising capabilities of deep learning models to analyze Thomson data orders of magnitude faster than conventional methods when using the neural network for standalone analysis. If more rigorous analysis is needed, neural network predictions can be used to quickly initialize other optimization methods and increase chances of success. This is especially useful when the dataset becomes very large or highly dimensional and manually refining initial conditions for the entire dataset are no longer tractable.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Discriminative versus generative approaches to simulation-based inference

Most of the fundamental, emergent, and phenomenological parameters of particle and nuclear physics are determined through parametric template fits. Simulations are used to populate histograms which are then matched to data. This approach is inherently lossy, since histograms are binned and low-dimensional. Deep learning has enabled unbinned and high-dimensional parameter estimation through neural likelihood(-ratio) estimation. We compare two approaches for neural simulation-based inference (NSBI): one based on discriminative learning (classification) and one based on generative modeling. These two approaches are directly evaluated on the same datasets, with a similar level of hyperparameter optimization in both cases. In addition to a Gaussian dataset, we study NSBI using a Higgs boson dataset from the FAIR Universe Challenge. We find that both the direct likelihood and likelihood ratio estimation are able to effectively extract parameters with reasonable uncertainties. For the numerical examples and within the set of hyperparameters studied, we found that the likelihood ratio method is more accurate and/or precise. Both methods have a significant spread from the network training and would require ensembling or other mitigation strategies in practice.

high energy physics↗
DOE OSTI2025

Scaling deep learning for material imaging with a pseudo 3D model for domain transfer

The recent introduction of deep learning methods for image processing has greatly advanced the characterization of materials using three-dimensional (3D) X-ray imaging techniques. However, deep learning models often have difficulty performing consistently across images owing to unavoidable variations in imaging conditions, which create inconsistencies even for the same material. As a result, networks must frequently be retrained for new datasets, limiting their applicability and generalization. Thus, it is critical to reduce the variations between images to enable a single model to process multiple datasets. Herein, we introduce P3T-Net, a pseudo-3D domain transfer network that transfers diverse 3D images into a uniform domain before processing using deep learning models. Remarkably, P3T-Net enables the reuse of previously trained networks for processing new images and considerably reduces the computational cost of transferring 3D images across domains. These unique capabilities were demonstrated in the following scenarios: (i) image enhancement of fast scans for geological rock and hydrogen fuel cells, (ii) enhancement of images to match the quality of multi-source imaging for lithium-ion batteries, (iii) accurate segmentation of images captured under different conditions, and (iv) tera-scale 3D transfer (10 11 voxels) on a single GPU. Overall, the proposed approach addresses cross-domain inconsistencies across various materials and conditions, thereby enabling more robust and generalizable deep learning solutions for a wide range of material imaging tasks.

25 ENERGY STORAGE↗
DOE OSTI2025

Subspace-Driven Learning for Anomaly Detection in Process Transients

Nuclear power plant (NPP) monitoring and diagnostic centers are actively investigating and implementing automated anomaly detection algorithms to help plants catch anomalies sooner, thereby preventing or reducing the duration of unexpected shutdowns. Current machine learning-based anomaly detection methods are expected to be highly effective during stable, full-power operations because NPPs typically operate as baseload power generators, meaning there are extensive operating data available from plant equipment. However, it is expected that anomaly detection methods will face significant challenges during transient conditions (i.e., when power output falls below full power) because plants only occasionally operate at these lower power levels, generating sparse transient operational data, and resulting in false alarms or missed detections. Here, to address this issue, transfer learning is used, which for this problem leverages knowledge (in the form of learned features) from stable, full-power operations to improve detection accuracy during transient conditions, even with limited data. In this effort, a novel subspace approach is developed to transfer a subset of the data features from full power operation to transients. This approach is validated through experiments using synthetic data and was found to outperform two baseline transfer learning approaches in anomaly detection performance across a range of amounts of transient data used in the training process.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
NASA NTRS2009

Hardware Implementation of a Bilateral Subtraction Filter

A bilateral subtraction filter has been implemented as a hardware module in the form of a field-programmable gate array (FPGA). In general, a bilateral subtraction filter is a key subsystem of a high-quality stereoscopic machine vision system that utilizes images that are large and/or dense. Bilateral subtraction filters have been implemented in software on general-purpose computers, but the processing speeds attainable in this way even on computers containing the fastest processors are insufficient for real-time applications. The present FPGA bilateral subtraction filter is intended to accelerate processing to real-time speed and to be a prototype of a link in a stereoscopic-machine- vision processing chain, now under development, that would process large and/or dense images in real time and would be implemented in an FPGA. In terms that are necessarily oversimplified for the sake of brevity, a bilateral subtraction filter is a smoothing, edge-preserving filter for suppressing low-frequency noise. The filter operation amounts to replacing the value for each pixel with a weighted average of the values of that pixel and the neighboring pixels in a predefined neighborhood or window (e.g., a 9 9 window). The filter weights depend partly on pixel values and partly on the window size. The present FPGA implementation of a bilateral subtraction filter utilizes a 9 9 window. This implementation was designed to take advantage of the ability to do many of the component computations in parallel pipelines to enable processing of image data at the rate at which they are generated. The filter can be considered to be divided into the following parts (see figure): a) An image pixel pipeline with a 9 9- pixel window generator, b) An array of processing elements; c) An adder tree; d) A smoothing-and-delaying unit; and e) A subtraction unit. After each 9 9 window is created, the affected pixel data are fed to the processing elements. Each processing element is fed the pixel value for its position in the window as well as the pixel value for the central pixel of the window. The absolute difference between these two pixel values is calculated and used as an address in a lookup table. Each processing element has a lookup table, unique for its position in the window, containing the weight coefficients for the Gaussian function for that position. The pixel value is multiplied by the weight, and the outputs of the processing element are the weight and pixel-value weight product. The products and weights are fed to the adder tree. The sum of the products and the sum of the weights are fed to the divider, which computes the sum of products the sum of weights. The output of the divider is denoted the bilateral smoothed image. The smoothing function is a simple weighted average computed over a 3 3 subwindow centered in the 9 9 window. After smoothing, the image is delayed by an additional amount of time needed to match the processing time for computing the bilateral smoothed image. The bilateral smoothed image is then subtracted from the 3 3 smoothed image to produce the final output. The prototype filter as implemented in a commercially available FPGA processes one pixel per clock cycle. Operation at a clock speed of 66 MHz has been demonstrated, and results of a static timing analysis have been interpreted as suggesting that the clock speed could be increased to as much as 100 MHz.

Huertas, Andres↗