Search NASA⌕ Search

SEARCH · Search NASA

Results for “CONDITIONING (LEARNING)”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
NASA NTRS2000

Space Infrared Astronomy in the 21st Century

New technology and design approaches have enabled revolutionary improvements in astronomical observations from space. Worldwide plans and dreams include orders of magnitude growth in sensitivity and resolution for all wavelength ranges, and would give the ability to learn our history, from the Big Bang to the conditions for life on Earth. The Next Generation Space Telescope, for example, will be able to see the most distant galaxies as they were being assembled from tiny fragments. It will be 1/4 as massive as the Hubble, with a mirror 3 times as large, cooled to about 30 Kelvin to image infrared radiation. I will discuss plans for NGST and hopes for future large space telescopes, ranging from the Space UV Optical (SUVO) telescope to the Filled Aperture Infrared (FAIR) Telescope, the Space Infrared Interferometric Telescope (SPIRIT), and the Submillimeter Probe of the Evolution of Cosmic Structure (SPECS).

Mather, John C.↗
NASA NTRS2005

Neurovestibular and Sensorimotor Studies in Space and Earth Benefits

This review summarizes what has been learned from studies of human neurovestibular system in weightless conditions, including balance and locomotion, gaze control, vestibular-autonomic function and spatial orientation, and gives some examples of the potential Earth benefits of this research. Results show that when astronauts and cosmonauts return from space flight, both the peripheral and central neural processes are physiologically and functionally altered. There are clear distinctions between the virtually immediate adaptive compensations to weightlessness and those that require longer periods of time to adapt. However, little is known to date about the adaptation of sensory-motor functions to long-duration space missions in weightlessness and to the transitions between various reduced gravitational levels, such as on the Moon and Mars. Results from neurovestibular research in space have substantially enhanced our understanding of the mechanisms and characteristics of postural, gaze, and spatial orientation deficits, analogous to clinical cases of labyrinthine-defective function. Also, space neurosciences research has participated in the development and application of significant new technologies, such as video recording and processing of three-dimensional eye movements and posture, hardware for the unencumbered measurement of head and body movement, and procedures for investigating otolith function on Earth. In particular, devices such as centrifugation or off-vertical axis rotation could enhance clinical neurological testing because it provides linear acceleration which specifically stimulates the otolith organs in a frequency range close to natural head and body movement.

Clement, Gilles↗
NASA NTRS2012

Phase Function Determination in Support of Orbital Debris Size Estimation

To recover the size of a space debris object from photometric measurements, it is necessary to determine its albedo and basic shape: if the albedo is known, the reflective area can be calculated; and if the shape is known, the shape and area taken together can be used to estimate a characteristic dimension. Albedo is typically determined by inferring the object s material type from filter photometry or spectroscopy and is not the subject of the present study. Object shape, on the other hand, can be revealed from a time-history of the object s brightness response. The most data-rich presentation is a continuous light-curve that records the object s brightness for an entire sensor pass, which could last for tens of minutes to several hours: from this one can see both short-term periodic behavior as well as brightness variations with phase angle. Light-curve interpretation, however, is more art than science and does not lend itself easily to automation; and the collection method, which requires single-object telescope dedication for long periods of time, is not well suited to debris survey conditions. So one is led to investigate how easily an object s brightness phase function, which can be constructed from the more survey-friendly point photometry, can be used to recover object shape. Such a recovery is usually attempted by comparing a phase-function curve constructed from an object s empirical brightness measurements to analytically-derived curves for basic shapes or shape combinations. There are two ways to accomplish this: a simple averaged brightness-versus phase curve assembled from the empirical data, or a more elaborate approach in which one is essentially calculating a brightness PDF for each phase angle bin (a technique explored in unpublished AFRL/RV research and in Ojakangas 2011); in each case the empirical curve is compared to analytical results for shapes of interest. The latter technique promises more discrimination power but requires more data; the former can be assembled in its essentials from fewer measurements but will be less definitive in its assignments. The goal of the present study is to evaluate both techniques under debris survey conditions to determine their relative performance and, additionally, to learn precisely how a survey should be conducted in order to maximize their performance. Because the distendedness of objects has more of an effect than their precise shape in calculating a characteristic dimension, one is interested in the techniques discrimination ability to distinguish between an elongated rectangular prism and a short rectangular prism or cube, or an elongated cylinder from a squat cylinder or sphere. Sensitivity studies using simulated data will be conducted to determine discrimination power for both techniques as a function of amount of data collected and range (and specific region) of phase angles sampled. Empirical GEODSS photometry data for distended objects (dead payloads with solar panels, rocket bodies) and compact objects (cubesats, calibration spheres, squat payloads) will also be used to test this discrimination ability. The result will be a recommended technique and data collection paradigm for debris surveys in order to maximize this type of discrimination.

Hejduk, M. D.↗
NASA NTRS2023

Airspace Automation Flight Tabletop Exercise

Interconnections of new systems are needed for airspace automation capabilities required in Urban Air Mobility (UAM). FAA Concept of Operations (CONOPS) V1.0 shows Provider of Services for UAM (PSU) at the center of the notional architecture; however, the functional role of the PSU in data exchange and the path to get there is unclear. In partnership with Wisk Aero, Avision, ANRA, Collins Aerospace, OneSky, SkyGrid, and AURA, the NASA National Campaign held discussions and tabletop exercises to test the functional allocations and work flows between an aircraft operator, airspace providers, Command and Control Communication Service Providers (C2CSP), and FAA air traffic in a real-world scenario. The exercise included preplanning and execution of a passenger mission with nominal, contingency, and conflict management scenarios for initial UAM operations. This working paper describes initial conditions for the flight tabletop exercise, exercise summaries, lessons learned, and recommendations for future work.

National Campaign↗
DOE OSTI2024

Learning the boundary-to-domain mapping using Lifting Product Fourier Neural Operators for partial differential equations

Neural operators such as the Fourier Neural Operator (FNO) have been shown to provide resolution-independent deep learning models that can learn mappings between function spaces. For example, an initial condition can be mapped to the solution of a partial differential equation (PDE) at a future time-step using a neural operator. Despite the popularity of neural operators, their use to predict solution functions over a domain given only data over the boundary (such as a spatially varying Dirichlet boundary condition) remains unexplored. In this paper, we refer to such problems as boundary-to-domain problems; they have a wide range of applications in areas such as fluid mechanics, solid mechanics, heat transfer etc. We present a novel FNO-based architecture, named Lifting Product FNO (or LP-FNO) which can map arbitrary boundary functions defined on the lower-dimensional boundary to a solution in the entire domain. Specifically, two FNOs defined on the lower-dimensional boundary are lifted into the higher dimensional domain using our proposed lifting product layer. We demonstrate the efficacy and resolution independence of the proposed LP-FNO for the 2D Poisson equation.

Kashi, Aditya↗
DOE OSTI2025

Integrating Crack Detection and Pipe Shape Optimization for Enhanced Sewage System Durability

Crack detection in underground reinforced concrete pipes has been essential in determining the state of stormwater infrastructure. Detection models have been implemented for detecting cracks and other defects in pipes using CCTV footage for stormwater drainage systems. In addition, Finite element models have been used to determine optimum shapes and pipe thickness for different boundary conditions such as header pipes in power plants. The concept of shape optimization emerges as a crucial factor in power plant design and operation, with the potential to maximize performance while minimizing the use of materials. Shape optimization not only enhances efficiency but also contributes to reducing the environmental footprint. This paper discusses the integration of both topics by using the cracks detected in underground pipes as boundary conditions for shape optimization of the pipes. A machine learning model has been developed which uses limited data for training and outlines the location of detected cracks. A shape optimization methodology is proposed in which ANSYS modules are used to analyze fluid flow and then optimize the shape of the pipe. The crack detection model developed has been applied to a crack detected in lab setting and machine learning model used has an accuracy of 98% using a random forest algorithm.

20 FOSSIL-FUELED POWER PLANTS↗
NASA NTRS2005

Challenges in Predicting Planetary Granular Mechanics

Through the course of human history, our needs in agriculture, habitat construction, and resource extraction have driven us to gain more experience working with the granular materials of planet Earth than with any other type of substance in nature, with the possible exception being water. Furthermore, throughout the past two centuries we have seen a dramatic and ever growing interest among scientists and engineers to understand and predict both its static and rheological properties. Ironically, however, despite this wealth of experience we still do not have a fundamental understanding of the complex physical phenomena that emerge even as just ordinary sand is shaken, squeezed or poured. As humanity is now reaching outward through the solar system, not only robotic ally but also with our immediate human presence, the need to understand and predict granular mechanics has taken on a new dimension. We must learn to farm, build and mine the regoliths of other planets where the environmental conditions are different than on Earth, and we are rapidly discovering that the effects of these environmental conditions are not trivial. Some of the relevant environmental features include the regolith formation processes throughout a planet's geologic and hydrologic history, the unknown mixtures of volatiles residing within the soil, the relative strength of gravitation, ~d the atm9spheric pressure and its seasonal variations. The need to work with soils outside our terrestrial experience base provides us with both a challenge and an opportunity. The challenge is to learn how to extrapolate our experience into these new planetary conditions, enabling the engineering decisions that are needed right now as we take the next few steps in solar system exploration. The opportunity is to use these new planetary environments as laboratories that will help us to see granular mechanics in new ways, to challenge our assumptions, and to help us finally unravel the elusive physics that lie behind complex granular phenomena. Toward these goals, a workshop was held recently at NASA's John F. Kennedy Space Center, attracting over a hundred scientists and engineers from around the world and from a broad crosssection of scientific and engineering disciplines. This talk will provide an out-briefing from that workshop, communicating some of its early findings in regard to lunar and Martian exploration: (1) the requirements for working with granular materials, (2) the challenges that granular materials will pose, (3) the environmental conditions that affect granular mechanics, (4) instruments and measurements that are needed on the Moon and Mars to support granular material research, and (5) some of the possible research avenues that should be pursued.

Metzger, Philip T.↗
DOE OSTI2025

Enhancing Unknown Waveform Detection by Learning Intra and Inter-domain Dependencies with Advanced Attention Fusion Mechanisms

Detection of unknown waveforms in mission-critical communications is a crucial area of interest for the Department of Energy (DoE). Traditional methods and recent deep learning-based approaches often assume that the training set includes all possible classes, which is impractical for detecting new waveforms. This limitation gives rise to the problem of open-set recognition (OSR), which involves correctly identifying known classes while detecting and rejecting unknown or unseen classes. To address this limitation, we propose a novel dual-domain complex-valued neural architecture that jointly processes time-domain and frequency-domain signal representations using transformer mechanisms. A transformer model is a deep learning architecture that uses self-attention mechanisms to process and learn relationships in sequential data. Our model employs a cosine similarity loss to extract domain-specific features and incorporates a transformer architecture in the latent space to weigh the importance of different features from the time and frequency domains. The transformer layer includes stacked self-attention and cross-attention modules to learn intra-domain and inter-domain dependencies, creating a more holistic signal representation. An attention-based fusion module intelligently combines the time and frequency-domain features using multi-head attention, enabling the network to learn the optimal feature for each domain in each input signal. Quantitative results demonstrate the impact of these architectural choices on overall performance, showing significant improvement after incorporating self and cross-attention modules and using complex attention fusion over simple weighted fusion. Our ongoing work will focus on addressing the limitations of threshold-based OSR methods by developing a novel generative framework that integrates a conditional diffusion probabilistic model (DPM). DPM is a generative framework that learns to synthesize complex data by reversing a gradual noising process using a neural network trained to denoise step-by-step. Our goal is to leverage the inherent strengths of DPMs for identifying unknown signals more robustly. One primary advantage of using a DPM is its ability to provide a more reliable anomaly score based on the model's reconstruction error, rather than relying solely on classifier confidence. Additionally, the iterative denoising process of DPMs makes this approach naturally resilient to low Signal-to-Noise Ratio (SNR) conditions, where traditional methods often fail. By implementing this generative framework, we aim to enhance the model's capability to accurately detect unknown waveforms and maintain performance in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗
NASA NTRS1993

Indirect learning control for nonlinear dynamical systems

In a previous paper, learning control algorithms were developed based on adaptive control ideas for linear time variant systems. The learning control methods were shown to have certain advantages over their adaptive control counterparts, such as the ability to produce zero tracking error in time varying systems, and the ability to eliminate repetitive disturbances. In recent years, certain adaptive control algorithms have been developed for multi-body dynamic systems such as robots, with global guaranteed convergence to zero tracking error for the nonlinear system euations. In this paper we study the relationship between such adaptive control methods designed for this specific class of nonlinear systems, and the learning control problem for such systems, seeking to converge to zero tracking error in following a specific command repeatedly, starting from the same initial conditions each time. The extension of these methods from the adaptive control problem to the learning control problem is seen to be trivial. The advantages and disadvantages of using learning control based on such adaptive control concepts for nonlinear systems, and the use of other currently available learning control algorithms are discussed.

Ryu, Yeong Soon↗
DOE OSTI2026

Comparison of DeePMD, MTP, GAP, ACE and MACE Machine‐Learned Potentials for Radiation‐Damage Simulations: A User Perspective

Accurate and efficient interatomic potentials are essential for molecular dynamics (MD) simulations of radiation damage, gas diffusion, and phase stability in complex ceramics such as LiAlO 2 , especially under extreme conditions relevant to tritium production. Here, we evaluate the performance of six machine-learned interatomic potentials (MLIPs), moment tensor potential (MTP), Gaussian approximation potential, deep potential (DeePMD), atomic cluster expansion (ACE), message-passing ACE (multilayer atomic cluster expansion (MACE) pretrained) and MACE (trained from-scratch), all trained on the same density functional theory dataset with inclusion of tritium. The MLIPs are benchmarked against traditional Buckingham and ReaxFF potentials in terms of energy accuracy, density predictions, thermal equilibration behavior, threshold displacement energy (E d ), tritium diffusivity, and computational cost. Among the models, MTP shows the best overall balance between efficiency and accuracy, with low force and energy errors and realistic E d values for Li and Al. The ACE and MACE (pretrained and trained from scratch) models exhibit high E d (>200 eV) and unphysical pair interactions. DeePMD underestimates Ed due to overly repulsive behavior even at equilibrium distances. All models over-estimate tritium diffusion but the pretrained MACE model behaves well during tritium-diffusion simulations up to 500 K, maintaining diffusivities in the physically consistent 10 −11 m 2 /s range. Finally, we quantify the computational cost of each potential in large-scale atomic/molecular massively parallel simulator, finding that only MTP is more efficient than traditional empirical potentials, while others are significantly more expensive. These findings explain the trade-offs between accuracy and computational cost in MLIP development and provide essential guidance for use in high-throughput radiation damage and gas diffusion simulations in nuclear ceramics.

74 ATOMIC AND MOLECULAR PHYSICS↗
NASA NTRS2016

IN11B-1621: Quantifying How Climate Affects Vegetation in the Amazon Rainforest

Amazon droughts in 2005 and 2010 have raised serious concern about the future of the rainforest. Amazon forests are crucial because of their role as the largest carbon sink in the world which would effect the global warming phenomena with decreased photosynthesis activity. Especially, after a decline in plant growth in 1.68 million km2 forest area during the once-in-a-century severe drought in 2010, it is of primary importance to understand the relationship between different climatic variables and vegetation. In an earlier study, we have shown that non-linear models are better at capturing the relation dynamics of vegetation and climate variables such as temperature and precipitation, compared to linear models. In this research, we learn precise models between vegetation and climatic variables (temperature, precipitation) for normal conditions in the Amazon region using genetic programming based symbolic regression. This is done by removing high elevation and drought affected areas and also considering the slope of the region as one of the important factors while building the model. The model learned reveals new and interesting ways historical and current climate variables affect the vegetation at any location. MAIAC data has been used as a vegetation surrogate in our study. For temperature and precipitation, we have used TRMM and MODIS Land Surface Temperature data sets while learning the non-linear regression model. However, to generalize the model to make it independent of the data source, we perform transfer learning where we regress a regularized least squares to learn the parameters of the non-linear model using other data sources such as the precipitation and temperature from the Climatic Research Center (CRU). This new model is very similar in structure and performance compared to the original learned model and verifies the same claims about the nature of dependency between these climate variables and the vegetation in the Amazon region. As a result of this study, we are able to learn, for the very first time how exactly different climate factors influence vegetation at any location in the Amazon rainforests, independent of the specific sources from which the data has been obtained.

global warming↗
DOE OSTI2025

Non-destructive evaluation and machine learning methods for inspection of spent nuclear fuel canisters: A state-of-the-art review

Nuclear energy is among the cleanest and most efficient energy sources currently available. The operation of nuclear power plants (NPPs) produces large amounts of high-level radioactive waste known as spent nuclear fuel (SNF). Currently, large amounts of SNF is stored in dry cask storage systems (DCSSs) for extended interim storage until a permanent disposal solution becomes available. During the extended interim storage, the DCSS, particularly the SNF canisters, may degrade and abnormal conditions may occur. Therefore, non-destructive evaluation (NDE) and machine learning (ML) approaches are necessary for inspection of SNF canisters. This paper presents a state-of-the-art review of literature by summarizing recent progress made on the applications of NDE and ML for inspection of SNF canisters. Sixteen NDE methods are examined and compared: visual inspection, ultrasonic guided waves (UGWs), laser-based approaches, acoustic emission (AE), eddy current testing (ECT), non-invasive acoustic sensing, dynamic modal testing, cosmic ray muons tomography, neutron imaging, gamma rays detection, fiber optical sensors, through-wall communications, X-ray computed tomography (CT), vibrothermography, monoenergetic photon sources, and surface acoustic wave (SAW) sensors. The technology readiness level (TRL) for each method is assessed and compared. Recent publications on ML-enhanced visual inspection, AE, non-invasive acoustic sensing, dynamic modal testing, and neutron imaging for SNF canisters are summarized and future research needs are identified. In conclusion, this review article provides a convenient reference on the state-of-the-art applications of NDE and ML methods for inspection of SNF canisters.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

The transformative capability of quantum-accurate machine learning interatomic potentials

Many materials’ properties and phase boundaries are generally not well known under extreme pressure and temperature conditions. Here, this is a consequence of the scarcity of experimental information and the difficulty of extrapolating approximations to the atomic interactions in such conditions. Nguyen-Cong and colleagues, in their publication (J.Phys.Chem.Lett. 15, 1152 (2024)) [1], achieved an impressive result using a SNAP (Spectral Neighbor Analysis Potential), an interatomic potential for carbon obtained by machine learning techniques. In a way, their contribution closes a full circle of research that spanned more than three decades.

Tedesco, Alfredo Correa [Lawrence Livermore Nation↗
NASA NTRSDate not supplied

Machine Learning Application for Improving Cloud Detection and Phase Determination Over Sunglint Regions for Geostationary Satellites

Cloud detection and phase determination over sunglint regions has been a challenge, especially for geostationary (GEO) satellites. Sunglint is observed when the sunlight specular reflection is at the same viewing angle of the satellite sensor. This intense reflection in the visible channels (VIS) is often comparable to that from optically thick clouds. It also contaminates the shortwave infrared channels (SWIR). Consequently, VIS and SWIR channels become less useful - or not useful- when they are saturated, hampering the detection of cloudy and clear-sky pixels. Sunglint contamination happens frequently and exists nearly in every daytime GEO full disk satellite images. However, sunglint intensity and region are difficult to model due to variable viewing geometry and ocean surface conditions. Moreover, existing physical models do not meet the accuracy required for operational GEO satellite cloud detection. We developed a machine learning algorithm to improve cloud detection in sunglint conditions for the NASA Langley’s Satellite ClOud and radiation Property retrieval System (SatCORPS). This poster presents our recent progress in the algorithm development, validation and applications. The algorithm is validated using collocated SatCORPS GOES-East and GOES-West cloud products. We demonstrate that the machine learning cloud detection in sunglint regions is superior to the traditional approach by improving temporal consistency between sunglint and non-sunglint conditions.

Machine Learning, Cloud detection, Sunglint, SatCO↗
DOE OSTI2026

Deep Learning and Photogrammetric Reconstruction for Automated Crack Detection and Dimensional Measurement in Mining Operations

Surface crack detection and dimensional measurement at active mining sites present significant safety and operational challenges. Manual inspection methods are labor-intensive, spatially incomplete, and expose personnel to hazardous environments, while existing automated approaches have been developed primarily for concrete civil infrastructure and have not been validated on the complex, variable surfaces characteristic of mining environments. This dissertation presents an automated pipeline that integrates deep learning semantic segmentation with Structure-from-Motion photogrammetry to detect surface cracks and measure their aperture, length, and vertical displacement from standard RGB imagery acquired during routine Uncrewed Aerial Vehicle (UAV) survey operations, without requiring additional sensor hardware or manual measurement. The pipeline combines a U-Net architecture with an EfficientNet-B0 encoder, pretrained on the SDNET2018 concrete crack dataset and fine-tuned on a mining-specific dataset spanning laboratory concrete specimens, coal refuse impoundment embankments, and post-blast limestone quarry benches. Photogrammetric reconstruction is performed using COLMAP Structure-from-Motion and Multi-View Stereo, with crack segmentation masks projected into the reconstructed point cloud to enable three-dimensional vertical displacement measurement through local plane fitting and bimodal surface detection. The pipeline was validated across 36 controlled laboratory specimens at three imaging distances and four vertical displacement levels, achieving aperture measurement RMSE of 0.047 cm and R² of 0.954, and vertical displacement RMSE of 0.140 cm and R² of 0.966, against independent caliper measurements. Field application at a coal refuse impoundment in southwestern Pennsylvania detected 71 crack components across the embankment crest, with a dominant longitudinal crack exhibiting aperture values reaching 28 cm and a 95th percentile vertical displacement of 35.53 cm, consistent in magnitude and spatial distribution with simultaneously acquired LiDAR-derived estimates. Application across four post-blast limestone quarry bench datasets in California successfully characterized blast-induced fracture networks at ground sampling distances ranging from 0.59 to 1.23 cm/pixel, with detected crack geometries physically consistent with observable surface conditions at each site. The results demonstrate that deep learning-based crack detection and photogrammetric measurement can be integrated into routine UAV inspection workflows at mining sites, providing repeatable, scalable, and quantitative crack characterization across surface types, crack scales, and displacement magnitudes not previously addressed in the literature. The pipeline requires no dedicated surveying equipment beyond the UAV platforms already deployed at mine sites for survey and monitoring purposes, supporting practical adoption within existing operational workflows.

Crack detection, Dimensional Measurement↗
NASA NTRSDate not supplied

Optimization of Airport Runway Configuration with Forecast-Augmented Offline Reinforcement Learning

Runway configuration Management (RCM) governs the optimal utilization of runways based on variables such as traffic and meteorological conditions, making it a daunting task in air traffic management due to its dependency on volatile operational and environmental factors. This paper improves upon our previous work [1] on using offline model-free reinforcement learning for creating a Runway Configuration Assistance (RCA) decision-support tool. A novel integration of forecast data from LAMP (Localized Aviation Model Output Statistics Program) and TAF (Terminal Area Forecast) is introduced, enhancing the tool’s accuracy and also its adaptability to quick wind changes. The performance is evaluated using two major US airports, Charlotte Douglas International Airport (CLT) and Denver International Airport (DEN). To counter scalability issues presented by the addition of discrete forecast variables, we transitioned to a continuous state space model, ensuring scalability and inclusion of longer forecast data. The results of our experiments reflect significant improvements in the RCA tool’s prediction accuracy.

Sumanth Nethi↗
DOE OSTI2025

Efficient and assured reinforcement learning-based building HVAC control with heterogeneous expert-guided training

Abstract Building heating, ventilation, and air conditioning (HVAC) systems account for nearly half of building energy consumption and $$20\%$$ of total energy consumption in the US. Their operation is also crucial for ensuring the physical and mental health of building occupants. Compared with traditional model-based HVAC control methods, the recent model-free deep reinforcement learning (DRL) based methods have shown good performance while do not require the development of detailed and costly physical models. However, these model-free DRL approaches often suffer from long training time to reach a good performance, which is a major obstacle for their practical deployment. In this work, we present a systematic approach to accelerate online reinforcement learning for HVAC control by taking full advantage of the knowledge from domain experts in various forms . Specifically, the algorithm stages include learning expert functions from existing abstract physical models and from historical data via offline reinforcement learning, integrating the expert functions with rule-based guidelines, conducting training guided by the integrated expert function and performing policy initialization from distilled expert function. Moreover, to ensure that the learned DRL-based HVAC controller can effectively keep room temperature within the comfortable range for occupants, we design a runtime shielding framework to reduce the temperature violation rate and incorporate the learned controller into it. Experimental results demonstrate up to 8.8 X speedup in DRL training from our approach over previous methods, with low temperature violation rate.

Xu, Shichao↗
DOE OSTI2026

A non-intrusive framework using acoustic signals and deep learning for boiling diagnostics in visual-limited environments

Accurate monitoring of boiling heat transfer is critical for safeguarding high-power systems operating in environments where conventional optical diagnostics are hindered by radiation fields or restricted visual accessibility. This study presents a non-intrusive framework that integrates hydroacoustic sensing with deep learning to infer near-wall boiling characteristics and enable predictive thermal assessment without visual access. In a prototypical subcooled flow-boiling facility representative of the Isotope Production Facility (IPF) at Los Alamos, hydrophones capture boiling-induced acoustic emissions that are transformed into background-removed Short-Time Fourier Transform (STFT) spectrograms. A convolutional neural network (CNN) then regresses heat flux, wall superheat, and key bubble parameters directly from these spectrograms. The CNN achieved predictive accuracy under nominal conditions and demonstrated robustness and generalization under acoustic noise for Signal-to-Noise Ratios (SNRs) down to approximately 0 dB. When integrated into an ANSYS CFX wall-boiling model, the acoustically inferred parameters reproduced boiling curve and critical heat flux (CHF) values consistent with image-based benchmarks. Furthermore, the model retained reliable performance under moderate variations in bulk temperature, flow rate, and hydrophone placement, confirming its generalizability across practical boundary conditions. These results demonstrate the feasibility of hydroacoustic-based deep learning as a viable path toward real-time, radiation-tolerant boiling diagnostics and predictive thermal safety assessment in inaccessible systems such as the IPF.

42 ENGINEERING↗