Search NASA⌕ Search

SEARCH · Search NASA

Results for “Adaptive tuning”

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 343 records · Page 19
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

MPEX AI Digital Twins

All magnetically confined plasma fusion power plant concepts (Tokamak, Spherical Tokamak, Stellarator, Mirror, ...) must exhaust the heat and plasma from the core confinement region to the material walls. The primary channel for this exhaust is through a plasma divertor which directs plasma along open magnetic field lines to a material target. The Material Plasma Exposure eXperiment (MPEX) illustrated in Figure 1, is a high-power, steady-state linear plasma device designed to produce the plasma material interaction (PMI) conditions of the divertor of future magnetic confinement fusion power plants: energy flux 20MW/m 2 , ion fluence 1031/m 2 , pulse duration 106 sec. These goals of plasma exposure in MPEX are well beyond those achieved in magnetic fusion experimental devices. Successfully achieving these high power steady state conditions for long pulses requires operational control of the heating and particle sources and the plasma flux to the walls and target. The MPEX AI Hot Spot Controller, proposed in this project, will help achieve the operational milestones of MPEX. The MPEX device will begin commissioning at the end of FY26. A smaller proto-MPEX was operated for 14,666 plasma discharges and will resume operation in September of 2025 as proto-MPEX-lite, with reduced capability, to test a new window for the Helicon plasma source. The proto-MPEX data has undergone surrogate modeling with machine learning methods (R. Archibald, 2022 IEEE International Conference on Big Data). This proto-MPEX data will be used to begin development of the AI digital twins described in this white paper. The scientific mission of MPEX is to qualify materials of different composition for use in the high energy and plasma flux conditions of a fusion power plant. The materials exposed in MPEX will in some cases be exposed to high neutron fluxes at other ORNL facilities to measure the changes to their PMI properties. The targets exposed in MPEX will be transported under vacuum to a Surface Analysis Station (SAS). The SAS will be equipped with the following diagnostics: Focused Ion Beam (FIB) for trench milling, 100-400 angstrom resolution scanning electron microscope (SEM), surface mapping x-ray spectrometer, high resolution camera, and a future upgrade to a laser induced breakdown spectroscopy quadruple mass spectrometer (LIBS-QMS). The MPEX experiments will generate diverse pre- and post-exposure measurement data of detailed material properties down to the crystal grain level in 3D for post-exposure assessment of PMI damage (e.g. cracking, melting, erosion and redeposition of the material). Physics models for the PMI, and how the material composition and manufacturing impact its performance under high energy plasma exposure, need to be validated with MPEX data to guide the selection of new candidate materials. Our vision for the MPEX AI Digital Twins project is to supply experimental and physics model simulation data to train Artificial Intelligence (AI) models for data processing, analysis, operational control, PMI and materials simulation to maximize the scientific output of the MPEX device. Ultimately, an AI digital twin of MPEX material assessment metrics for tested and synthetic material types with simulated PMI will be trained by the AI Modeling Teams on the experimental and physics simulation data submitted to the American Science Cloud by this project. A purely empirical search for the best material is inefficient given the finite number of samples that can be tested on MPEX. In order to expand the material properties database for training the MPEX Material Assessment AI Digital Twin, and to gain physics understanding of the PMI processes, physics models of the material properties and PMI processes are required. The physics simulations provide detailed simulation data, like impact angles for plasma ions, sputtering yields, transport of the ionized sputtered target material in the plasma, and redeposition locations. This simulation data expands the measurement data for deeper physics understanding. The experimental data is essential to validate the PMI and material structure simulation models. The validated models can then be used to generate new simulation data of MPEX material assessments for synthetic material compositions that have not been exposed in MPEX. These predictive simulations, plus the whole experimental dataset, will be used to train the MPEX Material Assessment AI Digital Twin allowing a rapid generative AI search for new materials with reduced PMI damage by interpolating the domain of the training set. These new optimum materials can be simulated with the physics codes and/or tested in MPEX. The ability of AI neural networks to interpolate multi-dimensional parameter spaces and generate virtual data is exploited for a more efficient search for optimum materials. The advent of the Transformational AI Models Consortium (TAIMC) is an opportunity to engage with state of the art private and public AI developers to achieve the goals of the AI digital twins and AI accelerated physics models proposed in this project. Our partners at ORNL from the Advance Scientific Computing Research (ASCR) organization will collaborate in accelerating the integrated plasma material interaction simulation framework. This simulation framework will provide a platform for generating simulation data across a range of physical fidelities, including hybrid methods that produce multi-fidelity results. This data will be leveraged for AI model development, both for generation of surrogates and the automation of simulation campaigns. A part of the research below will include collaborative efforts with the TAIMC to (i) adapt data storage approaches to ensure AI-readiness, (ii) provide a protypical exemplar to inform and exercise constructed workflows, and (iii) generate and share data, using the TAIMC unified AI data standard, for foundational models that will be trained from multiple sources across the DOE complex. We will also collaborate with the TAIMC, as well as the planned AI modeling teams, to develop approaches for reducing the cost of data generation. These include tailored multi-fidelity approaches as well as fine-tuning strategies to augment general, large-scale foundational models.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

PRIMED for the Future: Purposing Raw Intake for Machine Learning-Enabled Detection (Final Report)

The COVID-19 pandemic demonstrated how a novel, elusive, and diffuse biological threat can engender uncertainty and misinformation, and it underscored the need for flexible analytical modalities agnostic to the identity of biological material. Yet even before the pandemic, recognition of the limitations of the current, list-based approach, which focuses on known pathogens and biotoxins, and of the importance of agent-agnostic biodetection was growing within the biosecurity community. In a 2018 report on “Biodefense in the Age of Synthetic Biology,” for example, the National Academy of Sciences stated that “an overreliance on the Select Agent List is a systematic weakness affecting many aspects of the United States’ current biodefense mitigation capability”. More recently, a group of biodefense researchers proposed the identification and adoption of “bioagent-agnostic signatures (BASs)” as a way of detecting and characterizing not only existing agents but also novel ones, an approach they believe will “enable a more flexible and resilient biodefense posture”. Indeed, the future of biodetection requires us to begin developing novel analytics that can identify anomalies and/or characteristics that indicate a potential threat, whether known or unknown, without looking for a specific signature that has been identified previously. To assess potential threats more rapidly, it is critical to develop agnostic artificial intelligence (AI)/machine learning (ML) systems that can be employed for real-time assessment of the nature and source of a perturbation. Such systems should be multi scale and multi-dimensional, integrating sensor data from a range of biological, chemical, and physical application spaces. Emerging deep learning (DL) models demonstrate exceptional promise for identification of discriminatory features within multi-dimensional datasets. DL models have the capacity to recognize and encode highly complex patterns in a wide range of input data modalities, including images, text, and biological/chemical/physical spectra. As such, they can execute a wide range of assessments and determinations that have traditionally required a human operator. The promise of advances in DL is apparent in the realm of human health and medicine. DL models have been validated for evaluating a variety of clinical threats to human health in a range of contexts, including infection and cancer, and they demonstrated improved performance in predicting stroke relative to human neurologists in some categories of data. Continuously evolving advances in AI/ML are expected to support more efficient evaluation of raw sequence, spectroscopy, and spectrometry data. For instance, recent advances and deployment of large language models (LLM) such as Generative Pre training Transformer (GPT) and Bidirectional Encoder Representations from Transformers (BERT) have already motivated application of these models for biological function prediction. As frameworks such as LLMs become larger and more complex in their representations, their capacity to serve as pre-trained models that can be fine-tuned for biological/biodetection purposes will similarly be amplified. While existing and emerging AI/ML have found broad applicability and use cases in the clinical sciences, development for environmental evaluation and biodetection has been limited. Functionalizing such capabilities for this purpose requires an understanding of the existing technical landscape and how the respective tools and algorithms are currently being employed. This landscape awareness then allows an assessment of the current practical capabilities of existing models and the anticipated requirements and development efforts that will be needed to adapt available algorithms for biodetection applications relevant to DHS. Leveraging expertise in biodetection, ML, and operational biodetection, the effort described in this report is comprised of a systematic landscape assessment (Subtask 2.1), comparative evaluation (Subtask 2.2), and formulation of a value proposition (Subtask 2.3) for the prospect of ML-enabled, agnostic biodetection from raw, or minimally-processed, datasets.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1979

Development of drive mechanisms for communicaton satellites

A distinguished pedigree is an important asset in the development of Aerospace mechanisms. Four drives recently developed for communication satellites are outgrowths of a previously-proven drive configuration. Pedigree by itself, however is not enough to generate success. Inevitably, design changes which are thought to be minor, are generally introduced to fine tune the pedigreed hardware to meet particular requirements of a specific new application. Such design changes are often viewed too casually and are not thoroughly tested in the early development stages of the program. Two areas of design change are described on the solar array drive applied to the Japanese Broadcast Satellite which led to subsequent problems during the development phase of the program. The methods applied to establish the cause and the solution of these problems are described as well as the testing approach adapted to prevent similar occurrences on the current Communication Satellite Program, The Defense System Communications Satellite III.

Schneider, A. C.↗
DOE OSTI2022

Thermodynamic Control of Activity Patterns in Cytoskeletal Networks

Biological materials, such as the actin cytoskeleton, exhibit remarkable structural adaptability to various external stimuli by consuming different amounts of energy. In this Letter, we use methods from large deviation theory to identify a thermodynamic control principle for structural transitions in a model cytoskeletal network. Specifically, we demonstrate that biasing the dynamics with respect to the work done by nonequilibrium components effectively renormalizes the interaction strength between such components, which can eventually result in a morphological transition. Further, our work demonstrates how a thermodynamic quantity can be used to renormalize effective interactions, which in turn can tune structure in a predictable manner, suggesting a thermodynamic principle for the control of cytoskeletal structure and dynamics.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS1999

Co-evolution for Problem Simplification

This paper explores a co-evolutionary approach applicable to difficult problems with limited failure/success performance feedback. Like familiar "predator-prey" frameworks this algorithm evolves two populations of individuals - the solutions (predators) and the problems (prey). The approach extends previous work by rewarding only the problems that match their difficulty to the level of solut,ion competence. In complex problem domains with limited feedback, this "tractability constraint" helps provide an adaptive fitness gradient that, effectively differentiates the candidate solutions. The algorithm generates selective pressure toward the evolution of increasingly competent solutions by rewarding solution generality and uniqueness and problem tractability and difficulty. Relative (inverse-fitness) and absolute (static objective function) approaches to evaluating problem difficulty are explored and discussed. On a simple control task, this co-evolutionary algorithm was found to have significant advantages over a genetic algorithm with either a static fitness function or a fitness function that changes on a hand-tuned schedule.

Haith, Gary L.↗
DOE OSTI2024

Tunable noninteracting free-energy density functionals for high-energy-density physics applications

In this work, we introduce the concept of a tunable noninteracting free-energy density functional and present two examples realized: (i) via a simple one-parameter convex combination of two existing functionals and (ii) via the construction of a generalized gradient approximation (GGA) enhancement factor that contains one free parameter and is designed to satisfy a set of incorporated constraints. Functional (i), constructed as a combination of the local Thomas–Fermi and a pseudopotential-adapted GGA for the noninteracting free-energy, has already demonstrated its practical usability for establishing the high temperature end of the equation of state of deuterium [Phys. Rev. B 104, 144104 (2021)] and CHON resin [Phys. Rev. E 106, 045207 (2022)] for inertial confinement fusion applications. Hugoniot calculations for liquid deuterium are given as another example of how the application of computationally efficient orbital-free density functional theory (OF-DFT) can be utilized with the employment of the developed functionals. Once the functionals have been tuned such that the OF-DFT Hugoniot calculation matches the Kohn–Sham solution at some low-temperature point, agreement with the reference Kohn–Sham results for the rest of the high temperature Hugoniot path is very good with relative errors for compression and pressure on the order of 2% or less.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Neural Network Analysis of Nuclear Magnetic Resonance and Infrared Spectra

Nuclear magnetic resonance (NMR) spectroscopy and infrared (IR) spectroscopy are powerful chemical characterization techniques with broad general usage. However, the manual evaluation of the resulting spectra is time-consuming and requires significant expertise, preventing insights from being used in real-time applications. With recent advances in computation and artificial intelligence (AI), new tools are available for automating spectral interpretation. In this work, machine learning (ML) algorithms using 1-dimensional convolutional neural networks (CNNs) were applied to identify common functional groups from spectral information. Raw spectra were collected virtually from the Human Metabolome Database (HMDB) and National Institute of Standards and Technology (NIST) Chemistry WebBook and processed into a suitable standard. Algorithm design was tailored to best fit the nature of the problem, with built-in flexibility to accommodate relevant parameters beyond the raw spectral input, specifically solvent identity and magnetic frequency for NMR. The predictive capability of the algorithm in identifying functional groups is displayed in several examples. This methodology has been compiled into a code repository and could easily be modified to adapt alternative data sources, including other spectrum types. To mitigate overfitting, a common problem in mathematical modeling where overfamiliarity with training data produces trends that are not representative of the general data, a novel metric was developed, referred to as Accufit. Accufit includes a parameter that penalizes substantial differences in the training accuracy and the accuracy of an independent validation set. Examples are presented showing the effectiveness of Accufit in maintaining the model’s predictive capability while controlling the overfitting when used as a custom metric for hyperparameter tuning.

Sturgill, James↗
DOE OSTI2021

Dimensional Control of Octahedral Tilt in SrRuO 3 via Infinite-Layered Oxides

Manipulation of octahedral distortion at atomic scale is an effective means to tune the ground states of functional oxides. Previous work demonstrates that strain and film thickness are variable parameters to modify the octahedral parameters. However, selective control of bonding geometry by structural propagation from adjacent layers is rarely studied. Here we propose a new route to tune the ferromagnetism in SrRuO 3 (SRO) ultrathin layers by oxygen coordination of adjacent SrCuO 2 (SCO) layers. The infinite-layered CuO 2 exhibits a structural transformation from “planar-type” to “chain-type” with reduced film thickness. Two orientations dramatically modify the polyhedral connectivity at the interface, thus altering the octahedral distortion of SRO. The local structural variation changes the spin state of Ru and orbital hybridization strength, leading to a significant change in the magnetoresistance and anomalous Hall resistivity. Furthermore, these findings could launch investigations into adaptive control of functionalities in quantum oxide heterostructures using oxygen coordination.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Reversible Electron-Beam Patterning of Colloidal Nanoparticles at Fluid Interfaces

The directed self-assembly of colloidal nanoparticles (NPs) using external fields guides the formation of sophisticated hierarchical materials but becomes less effective with decreasing particle size. As an alternative, electron-beam-driven assembly offers a potential avenue for targeted nanoscale manipulation, yet remains poorly controlled due to the variety and complexity of beam interaction mechanisms. Here, we investigate the beam–particle interaction of silica NPs pinned to the fluid–vacuum interface of ionic liquid droplets. In these experiments, scanning electron microscopy of the droplet surface resolves NP trajectories over space and time while simultaneously driving their reorganization. With this platform, we demonstrate the ability to direct particle transport and create transient, reversible colloidal patterns on the droplet surface. By tuning the beam voltage, we achieve precise control over both the strength and sign of the beam–particle interaction, with low voltages repelling particles and high voltages attracting them. This response stems from the formation of well-defined solvent flow fields generated from trace radiolysis of the ionic liquid, as determined through statistical analysis of single-particle trajectories under varying solvent composition. Altogether, electron-beam-guided assembly introduces a versatile strategy for nanoscale colloidal manipulation, offering new possibilities for the design of dynamic, reconfigurable systems with applications in adaptive photonics and catalysis.

36 MATERIALS SCIENCE↗
DOE OSTI2025

A Neural Optimizer With Decision-Focused Learning for Optimal Energy Storage Operation

Here, this article introduces a neural optimizer-based framework for optimizing battery energy storage system (BESS) control for grid services, including demand charge and energy cost reduction. By leveraging decision-focused learning (DFL), the proposed framework ensures seamless integration and adaptation, significantly enhancing control performance. A patch time-series transformer is employed for peak load forecasting, incorporating aleatoric uncertainty quantification to account for forecasting uncertainties within the decision-making process. The framework utilizes a solver-in-the-loop approach to generate optimal BESS actions, which are then used to train the neural optimizer-based agent. By co-optimizing both BESS operational modes and output power within the NN, the system achieves improved performance and robustness. After initial training, the forecasting and control models are jointly fine-tuned to account for forecasting errors, further improving decision precision and efficiency through DFL. Case studies are performed to validate the performance of the framework using multiple real-world datasets, demonstrating superior performance in monthly peak load forecasting compared to state-of-the-art models. In addition, the results are compared against existing decision-making approaches. The results demonstrate a reduction in monthly peak forecasting error by approximately 15% across various performance measures and achieve an optimization gap for BESS operation that is about three times smaller compared to existing methods.

Kim, Hyeonjin [Pacific Northwest National Laborato↗
DOE OSTI2026

Preparing large area of thermochromic nanocomposite films for smart window application

The challenges posed by high building energy bill necessitate proactive implementation of energy-efficient strategies to minimize the uses of both electricity and heating gas and promote the use of free solar energy sources. "Smart" window films/glass, leveraging thermochromic vanadium dioxide (VO 2 ), offer an adaptive approach to harness solar energy, significantly reducing the thermal load of buildings. This is achieved by reflecting the infrared portion of the solar spectrum through a phase transition in the monoclinic M-phase (M) of VO 2 induced by heating. In this study, a scalable continuous flow synthesis process invented by Argonne was employed to explore a wide parameter space, targeting the controlled synthesis of monoclinic VO 2 (M) nanoparticles with well-controlled sizes and morphologies. Additionally, a doping strategy and surface modifications were utilized for high-throughput tuning of the metal-to-insulator transition temperature. Strategies to enhance the solar modulation properties of VO 2 nanoparticles in polymer films were investigated through (i) morphological transformation from spherical to nanorod structures, (ii) surface modification with low refractive index ligands, and (iii) incorporation of additional thermochromic materials for improved solar energy modulation and aesthetically appealing colors in smart films. Furthermore, the study outlines scaling-up synthesis methods for VO 2 nanoparticles in a continuous flow reactor using hydrazine monohydrate. This comprehensive investigation provides valuable insights into the upscaling synthesis and design of advanced VO 2 /polymer composite smart window films with enhanced functionality, solar energy modulation and visible light transmittance, driving the technology a step close for industrial application.

14 SOLAR ENERGY↗
DOE OSTI2023

Solid-State Lighting Using Side-by-Side White Phosphorescent Organic Light-Emitting Diodes

White organic light-emitting diodes (WOLEDs) have become increasingly popular for use in solid-state illumination, where diffuse, large area light sources that achieve a high color rendering index and luminous power efficiency are desirable. Color-tunable emission, where the light source combines emission from multiple, separately addressed color elements, is conveniently provided by WOLEDs for the purpose of adapting the lighting source to a particular illumination requirement. In this work, we demonstrate a method for side-by-side positioning of monochromatic blue and yellow phosphorescent OLED stripes that are combined to create tunable white light, using a high resolution mechanical peel-off patterning method. We achieve a peak luminous power efficiency of 17.1 ± 0.3 lm W –1 and an external quantum efficiency of 11.8 ± 0.2% and demonstrate color tunability of the 1960 Commission Internationale d’Eclairage chromaticity coordinates from (u,v) = (0.33,0.36) to (0.12,0.32). This corresponds to a tuning rnge of the color rendering index from 74 ± 1 to 86 ± 1 and the correlated color temperature from 2000 to 8000 ± 500 K. Here, due to the nondestructive nature of the peel-off technique, patterned devices exhibit a lifetime comparable to conventional, shadow mask-patterned devices.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2013

An Application of UAV Attitude Estimation Using a Low-Cost Inertial Navigation System

Unmanned Aerial Vehicles (UAV) are playing an increasing role in aviation. Various methods exist for the computation of UAV attitude based on low cost microelectromechanical systems (MEMS) and Global Positioning System (GPS) receivers. There has been a recent increase in UAV autonomy as sensors are becoming more compact and onboard processing power has increased significantly. Correct UAV attitude estimation will play a critical role in navigation and separation assurance as UAVs share airspace with civil air traffic. This paper describes attitude estimation derived by post-processing data from a small low cost Inertial Navigation System (INS) recorded during the flight of a subscale commercial off the shelf (COTS) UAV. Two discrete time attitude estimation schemes are presented here in detail. The first is an adaptation of the Kalman Filter to accommodate nonlinear systems, the Extended Kalman Filter (EKF). The EKF returns quaternion estimates of the UAV attitude based on MEMS gyro, magnetometer, accelerometer, and pitot tube inputs. The second scheme is the complementary filter which is a simpler algorithm that splits the sensor frequency spectrum based on noise characteristics. The necessity to correct both filters for gravity measurement errors during turning maneuvers is demonstrated. It is shown that the proposed algorithms may be used to estimate UAV attitude. The effects of vibration on sensor measurements are discussed. Heuristic tuning comments pertaining to sensor filtering and gain selection to achieve acceptable performance during flight are given. Comparisons of attitude estimation performance are made between the EKF and the complementary filter.

Eure, Kenneth W.↗
DOE OSTI2023

Adaptive Deep Reinforcement Learning Algorithm for Distribution System Cyber Attack Defense With High Penetration of DERs

With grid modernization, smart inverters are increasingly used to execute advanced controls for distribution network reliability. However, this also increases the cyber-attack space. Here this paper focuses on the defense approaches to restore the system to normal operation circumstances in the presence of cyber-attacks. A unique deep reinforcement learning (DRL) method is developed to minimize voltage violations and reduce power losses for impacted feeders. The defense problem is reformulated as a Markov decision-making process to dynamically control DERs while minimizing load shedding. This is achieved via an improved soft actor-critic (SAC)-based DRL algorithm, which can govern DER set points and load-shedding scenarios in discrete and continuous modes via the auto-tune entropy and Gaussian policy features. Numerical comparison results on the modified IEEE 123-node system with other control approaches, such as Volt-VAR (VV), Volt-Watt (VW), and model predictive control (MPC) show that the proposed method can eliminate voltage violations and provide feasible control actions that perform complete mitigation of cyber-threats.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2013

Memory-Efficient Onboard Rock Segmentation

Rockster-MER is an autonomous perception capability that was uploaded to the Mars Exploration Rover Opportunity in December 2009. This software provides the vision front end for a larger software system known as AEGIS (Autonomous Exploration for Gathering Increased Science), which was recently named 2011 NASA Software of the Year. As the first step in AEGIS, Rockster-MER analyzes an image captured by the rover, and detects and automatically identifies the boundary contours of rocks and regions of outcrop present in the scene. This initial segmentation step reduces the data volume from millions of pixels into hundreds (or fewer) of rock contours. Subsequent stages of AEGIS then prioritize the best rocks according to scientist- defined preferences and take high-resolution, follow-up observations. Rockster-MER has performed robustly from the outset on the Mars surface under challenging conditions. Rockster-MER is a specially adapted, embedded version of the original Rockster algorithm ("Rock Segmentation Through Edge Regrouping," (NPO- 44417) Software Tech Briefs, September 2008, p. 25). Although the new version performs the same basic task as the original code, the software has been (1) significantly upgraded to overcome the severe onboard re source limitations (CPU, memory, power, time) and (2) "bulletproofed" through code reviews and extensive testing and profiling to avoid the occurrence of faults. Because of the limited computational power of the RAD6000 flight processor on Opportunity (roughly two orders of magnitude slower than a modern workstation), the algorithm was heavily tuned to improve its speed. Several functional elements of the original algorithm were removed as a result of an extensive cost/benefit analysis conducted on a large set of archived rover images. The algorithm was also required to operate below a stringent 4MB high-water memory ceiling; hence, numerous tricks and strategies were introduced to reduce the memory footprint. Local filtering operations were re-coded to operate on horizontal data stripes across the image. Data types were reduced to smaller sizes where possible. Binary- valued intermediate results were squeezed into a more compact, one-bit-per-pixel representation through bit packing and bit manipulation macros. An estimated 16-fold reduction in memory footprint relative to the original Rockster algorithm was achieved. The resulting memory footprint is less than four times the base image size. Also, memory allocation calls were modified to draw from a static pool and consolidated to reduce memory management overhead and fragmentation. Rockster-MER has now been run onboard Opportunity numerous times as part of AEGIS with exceptional performance. Sample results are available on the AEGIS website at http://aegis.jpl.nasa.gov.

Burl, Michael C.↗
DOE OSTI2023

Iterative sampling of expensive simulations for faster deep surrogate training

Deep neural network (DNN) surrogates of expensive physics simulations are enabling a rapid change in the way that common experimental design and analysis tasks are approached. Surrogate models allow simulations to be performed in parallel and separately from downstream tasks, thereby enabling analyses that would be impossible with the simulation in-the-loop; surrogates based on DNNs can effectively emulate diverse non-scalar data of the types collected in fusion and laboratory-astrophysics experiments. The challenge is in training the surrogate model, for which large ensembles of physics simulations must be run, preferably without wasting computational effort on uninteresting simulations. Here, in this paper, we present an iterative sampling scheme that can preferentially propose simulations in interesting regions of parameter space without neglecting unexplored regions, allowing high-quality and wide-ranging surrogate models to be trained using 2–3 times fewer simulations compare to space-filling designs. Our approach uses an explicit importance function defined on the simulation output space, balanced against a measure of simulation density which serves as a proxy for surrogate accuracy. It is easy to implement and can be tuned to find interesting simulations early in the study, allowing surrogates to be trained quickly and refined as new simulations become available; this represents an important step towards the routine generation of deep surrogate models quickly enough to be truly relevant to experimental work.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Two-Stage Reinforcement Learning Policy Search for Grid-Interactive Building Control

This paper develops an intelligent grid-interactive building controller, which optimizes building operation during both normal hours and demand response (DR) events. To avoid costly on-demand computation and to adapt to non-linear building models, the controller utilizes reinforcement learning (RL) and makes real-time decisions based on a near-optimal control policy. Learning such a policy typically amounts to solving a hard non-convex optimization problem. We propose to address this problem with a novel global-local policy search method. In the first stage, an RL algorithm based on zero-order gradient estimation is leveraged to search for the optimal policy globally, due to its scalability and the potential to escape some poor performing local optima. The obtained policy is then fine-tuned locally to bring the first-stage solution closer to that of the original unsmoothed problem. Experiments on a simulated five-zone commercial building demonstrate the advantages of the proposed method over existing learning approaches. They also show that the learned control policy outperforms a pragmatic linear model predictive controller (MPC) and approaches the performance of an oracle MPC in testing scenarios. Using a state-of-the-art advanced computing system, we demonstrate that the controller can be learned and deployed within hours of training.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS2000

THUNDER Piezoelectric Actuators as a Method of Stretch-Tuning an Optical Fiber Grating

A method of stretching optical fiber holds interest for measuring strain in smart structures where the physical displacement may be used to tune optical fiber lasers. A small, light weight, low power tunable fiber laser is ideal for demodulating strain in optical fiber Bragg gratings attached to smart structures such as the re-usable launch vehicle that is being developed by NASA. A method is presented for stretching optical fibers using the THUNDER piezoelectric actuators invented at NASA Langley Research Center. THUNDER actuators use a piezoelectric layer bonded to a metal backing to enable the actuators to produce displacements larger than the unbonded piezoelectric material. The shift in reflected optical wavelength resulting from stretching the fiber Bragg grating is presented. Means of adapting THUNDER actuators for stretching optical fibers is discussed, including ferrules, ferrule clamp blocks, and plastic hinges made with stereo lithography.

Allison, Sidney G.↗