SEARCH · Search NASA
Results for “Learning control”
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.
Detection and Localization of Data Forgery Attacks in Automatic Generation Control
Not Available
Neural-Network-Enhanced COTSIM: Advancing Predictive Capabilities for Fast DIII-D Simulations
Sustaining fusion reactions in tokamaks requires heating plasma to thermonuclear temperatures while maintaining confinement and stability. Neutral beam injection (NBI) provides heating, current drive, torque, and fueling, while electron cyclotron (EC) waves are widely used for heating and current drive; together, these actuators shape the plasma current, temperature, and density profiles. The control-oriented tokamak simulator (COTSIM), a predictive, control-oriented code, has been enhanced with neural-network surrogates for transport and sources. Turbulent transport is predicted by MMMnet—a neural-network version of the updated multimode model (MMM 9.0.10)—with significantly reduced computation time relative to MMM; neoclassical transport follows the Chang–Hinton model. NUBEAMnet, a surrogate of the Monte Carlo NUBEAM module, predicts beam-driven heating, current, and torque. EC heating and current drive use a control-oriented, empirically scaled source model; plasma resistivity follows the Spitzer formulation; bootstrap current uses the Sauter model. Equilibrium is computed using both prescribed and fixed-boundary solvers (FBSs), and the pedestal structure is modeled with an empirical pedestal model. For a representative DIII-D discharge, COTSIM predicts electron and ion temperature and safety-factor profiles in close agreement with TRANSP predictive and interpretive simulations while extending predictions through the pedestal region to the plasma edge (versus 80% of the minor radius in TRANSP). Furthermore, the equivalent COTSIM simulation runs in under 3 min compared to about 2 h for TRANSP, enabling rapid scenario planning, optimization of tokamak operation, and between-pulse control design.
A Multi-Objective Bayesian Optimized Human Assessed Multi-Target Generated Spectral Recommender System for Rapid Pareto Discoveries of Material Properties
Optimization for different tasks like material characterization, synthesis, and functional properties for desired applications over multi-dimensional control parameter and function spaces need a rapid strategic search through active learning. However, in all cases prior to optimization, the target material properties are assumed known and fixed, which mostly deviates from real-world scenarios in material synthesis. This can be critical for running expensive experiments on new materials, when the experimental results are fuzzy for any scientific outcomes due to improper target setting, ultimately wasting time and cost. The failure rate and cost are even higher over exploring on multi-target space, where we want to learn the pareto among multiple properties, to jointly optimize during material synthesis for desired applications. To address the challenge, here we introduce the human-operator attempt flexibility in the active learning based automated experiment framework, with generating multiple human assessed targets through a voting-based recommender system during real-time microscope measurements over the large material image space, sequentially learn/update multiple desired targets through a weighting system, and adaptively search in multiple material properties functional space for non-dominated pareto discoveries to maximize the custom structural similarity based acquisition function. We term this a multi-objective Bayesian optimized human assessed multi-target generated spectral recommender systems (MOBO-HAM-SRS). The approach has been demonstrated to peizoresponse force spectroscopy of a ferroelectric thin film, exploring with different kernels and acquisition functions. This work shows an advancement towards human-AI collaborated automated experiments, steering optimization trajectories through human overpowering AI at the early stage when uncertainty is high and AI overpowering human at the later stage with rapid exploration towards optimal goal, following human-assessed multiple targets properties.
Concurrent Relaxation through Accelerated Deep Learning
CRADL captures performance metrics of machine learning algorithms operating on mesh data from multiphysics codes This proxy application is a tool to explore scalability of inference on HPC platforms, and also gather performance metrics for inference on new machine learning specific hardware. CRADL is designed to give users as fine a control as possible over an inference simulation. Users may select the number of cycles, amount of data, and batch size to pass to the accelerator of choice. Additionally the user may select a number of performance optimization libraries and flags. CRADL comes packaged with a repository of anonymized multi-physics simulation data, as well as a pretrained model for inference. The code allows a user to load their own pre-trained model and data if they wish. The code can operate in multiple parallelization schemes, with performance enhancing options such as half-precision libraries, PyTorch benchmarking, and pinned memory with non-blocking data transfers.
Optimizing collimator positions using bayesian optimization in the Fermilab MI-8 transfer line
Collimators are used to minimize losses and to remove particles that would otherwise get lost downstream and irradiate the machine. Finding the optimal jaw positions is time consuming and with the upstream beam properties changing, the collimation settings would need to be readjusted each time. Therefore, a method to optimize collimator positions and to operate them at full capacity in a short time is required for loss control downstream. A study of collimator positions was conducted and a machine learning (ML) model was developed to predict optimal collimator positions. Bayesian Optimization (BO) was used to calculate new jaw positions from the ML model. The results of BO and usage of ML for better performance of the collimation system are presented in this paper.
Enhancing Local Grid Resilience with Small Hydropower Hybrids: Proving the concept through demonstration, simulation, and analysis with Idaho Falls Power
Large hydropower, connected to the transmission system and typically possessing significant ability to balance grid frequency, has long been central to black start plans in regions where it is present. Small hydropower possesses most of the attributes required for black start but is often connected to distribution or sub-transmission systems and has less ability to balance grid frequency. Integrating energy storage such as batteries or ultracapacitors increases the combined asset’s ability to balance frequency. This asset integration enables a bottom-up grid restoration paradigm in which critical electric loads on the local distribution system can be powered even when the regional transmission system is down. This report presents a field demonstration conducted with Idaho Falls Power that proved this concept. The contribution of energy storage in restoring the small hydro-dominated distribution grid and its operational sensitivity across different control settings are further analyzed using high-fidelity simulations. Readers will learn about technical details on the field demonstration setup, energy storage contribution to black start, detailed simulation steps of islanded distribution grid restoration, and usage of field demonstration measurements for transient model refinements. Collectively this report points to a great opportunity for small hydropower to enhance resilience of local electric grids.
Adaptive Neurocontrol for Grid-Following Inverters
The new generation of power systems involve a large number of autonomous operating units with the flow of data being restricted by privacy concerns or infrastructure hurdles. The systems are also time-varying so the control should adjust in a timely manner to avoid failures that usually have very negative economical implications. Adaptive neurocontrol which takes elements from adaptive control (great for time-varying problems) and model identification (could be in the form of neural network) by using local available data is a compelling tool. In this work, we summarize analytical results for adaptive neurocontrol, followed with numerical verification of how the method could work for future grids.
Virtual Growth of SRF Materials
Niobium's native surface oxide affects SRF cavity and superconducting qubit performance, motivating interest in controlling its crystalline structure. We combine a literature-derived machine-learning analysis with temperature-dependent XRD to study crystalline ordering in Nb2O5. Random Forest models, trained on 74 processing conditions from 17 papers and validated by leave-one-group-out cross-validation, predicted broad crystallinity outcomes well (balanced accuracy 0.809), but struggled with specific polymorph identity (0.577). Annealing temperature was the dominant predictor across all targets; oxygen partial pressure showed negligible importance, reflecting narrow literature coverage rather than physical irrelevance. Temperature-dependent XRD on anodized and H2O2-treated Niobium showed structural evolution consistent with the machine learning predictions. Our model and overall approach provide a data-driven framework for identifying and optimizing conditions that promote crystallization in initially amorphous oxides. This framework can guide the selection of growth and post-annealing conditions for Nb surfaces by narrowing the experimental parameter space, thereby reducing trial-and-error efforts in developing oxide structures relevant to SRF applications.
A Voyager attitude control perspective on fault tolerant systems
In current spacecraft design, a trend can be observed to achieve greater fault tolerance through the application of on-board software dedicated to detecting and isolating failures. Whether fault tolerance through software can meet the desired objectives depends on very careful consideration and control of the system in which the software is imbedded. The considered investigation has the objective to provide some of the insight needed for the required analysis of the system. A description is given of the techniques which have been developed in this connection during the development of the Voyager spacecraft. The Voyager Galileo Attitude and Articulation Control Subsystem (AACS) fault tolerant design is discussed to emphasize basic lessons learned from this experience. The central driver of hardware redundancy implementation on Voyager was known as the 'single point failure criterion'.
Issues in NASA program and project management
This volume is the third in an ongoing series on aerospace project management at NASA. Articles in this volume cover the attitude of the program manager, program control and performance measurement, risk management, cost plus award fee contracting, lessons learned from the development of the Far Infrared Absolute Spectrometer (FIRAS), small projects management, and age distribution of NASA scientists and engineers. A section on resources for NASA managers rounds out the publication.
Assessment of the pharmacodynamics of intranasal, intravenous and oral scopolamine
Space motion sickness is an important issue in the space medical sciences program. One of the objectives of the ongoing clinical experimental protocol Pharmacokinetics of Intranasal Scopolamine in Normal Subjects is to evaluate the pharmacodynamics of scopolamine using salivary flow rate and pH profiles and cognitive performance tests as pharmacodynamic parameters. Normal volunteers collected saliva and performed the NTI Multiresource Performance Battery tests at designed time intervals to establish control saliva flow rates, salivary pH profiles, and the characteristics of the learning curve for the performance program under normal conditions. In the clinical part of the study, saliva samples and performance test scores are collected from healthy nonsmoking subjects after receiving a single 0.4 mg dose of either intranasal, intravenous, or oral scopolamine.
Issues in NASA program and project management
This volume is the third in an ongoing series on aerospace project management at NASA. Articles in this volume cover the attitude of the program manager, program control and performance measurement, risk management, cost plus award fee contracting, lessons learned from the development of the Far Infrared Absolute Spectrometer (FIRAS), small projects management, and age distribution of NASA scientists and engineers. A section on resources for NASA managers rounds out the publication.
Galileo Attitude Determination: Experiences with a Rotating Star Scanner
The Galileo experience with a rotating star scanner is discussed in terms of problems encountered in flight, solutions implemented, and lessons learned. An overview of the Galileo project and the attitude and articulation control subsystem is given and the star scanner hardware and relevant software algorithms are detailed. The star scanner is the sole source of inertial attitude reference for this spacecraft. Problem symptoms observed in flight are discussed in terms of effects on spacecraft performance and safety. Sources of thse problems include contributions from flight software idiosyncrasies and inadequate validation of the ground procedures used to identify target stars for use by the autonomous on-board star identification algorithm. Problem fixes (some already implemented and some only proposed) are discussed. A general conclusion is drawn regarding the inherent difficulty of performing simulation tests to validate algorithms which are highly sensitive to external inputs of statistically 'rare' events.
Some problems with the design of self-learning management systems
In this paper some problems in the design of management systems for complex objects are discussed. Considering the absence of adequate models and the fact that human expertise in the management of non-stationary objects becomes obsolete quickly, the use of self-learning together with a two-step optimization of on-line control rules is suggested. To prepare for the object analysis, a set of definitions has been proposed. Traditional and fuzzy sets approaches are used in the analysis. To decrease the reaction time of the control system, we propose the development of control rules without feedback.
A Survey of Collective Intelligence
This chapter presents the science of "COllective INtelligence" (COIN). A COIN is a large multi-agent systems where: i) the agents each run reinforcement learning (RL) algorithms; ii) there is little to no centralized communication or control; iii) there is a provided world utility function that, rates the possible histories of tile full system. Tile conventional approach to designing large distributed systems to optimize a world utility does not use agents running RL algorithms. Rather that approach begins with explicit modeling of the overall system's dynamics, followed by detailed hand-tuning of the interactions between the components to ensure that they "cooperate" as far as the world utility is concerned. This approach is labor-intensive, often results in highly non-robust systems, and usually results in design techniques that, have limited applicability. In contrast, with COINs we wish to solve the system design problems implicitly, via the 'adaptive' character of the RL algorithms of each of the agents. This COIN approach introduces an entirely new, profound design problem: Assuming the RL algorithms are able to achieve high rewards, what reward functions for the individual agents will, when pursued by those agents, result in high world utility? In other words, what reward functions will best ensure that we do not have phenomena like the tragedy of the commons, or Braess's paradox? Although still very young, the science of COINs has already resulted in successes in artificial domains, in particular in packet-routing, the leader-follower problem, and in variants of Arthur's "El Farol bar problem". It is expected that as it matures not only will COIN science expand greatly the range of tasks addressable by human engineers, but it will also provide much insight into already established scientific fields, such as economics, game theory, or population biology.
Operational thermal control of Cassini Titan flybys
This paper focuses on the technical thermal control evaluation and strategy, the systems-level approach taken, and lessons learned and recommendations in an operations environment.
A Resonant Damping Study Using Piezoelectric Materials
Excessive vibration of turbomachinery blades causes high cycle fatigue (HCF) problems requiring damping treatments to mitigate vibration levels. Based on the technical challenges and requirements learned from previous turbomachinery blade research, a feasibility study of resonant damping control using shunted piezoelectric patches with passive and active control techniques has been conducted on cantilever beam specimens. Test results for the passive damping circuit show that the optimum resistive shunt circuit reduces the third bending resonant vibration by almost 50%, and the optimum inductive circuit reduces the vibration by 90%. In a separate test, active control reduced vibration by approximately 98%.