Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning based systems”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
NASA NTRS2023

Digital Engineering Design Center (DEDC): Modelling an ISRU System

The DEDC provides immersive project-based learning on digital engineering toolsets and processes supporting NASA’s digital transformation goals: - Digital Engineering uses authoritative sources of systems' data and models as a continuum across disciplines to support integrated digital approach life cycle activities from concept through disposal. - The digital environment provided includes the state-of-the-art digital engineering suite, Siemens Xcelerator. The pilot project is developing an end-to-end integrated model of an In-Situ Resource Utilization (ISRU) system for commodities production: - ISRU uses local resources to provide mission consumables to enable a sustainable Moon or Mars surface presence. - The final digital twin product will include a methanation reactor, condenser, and electrolyzer subsystem.

Digital Engineering Design Center↗
DOE OSTI2023

Probabilistic-learning-based stochastic surrogate model from small incomplete datasets for nonlinear dynamical systems

We consider a high-dimensional nonlinear computational model of a dynamical system, parameterized by a vector-valued control parameter, in the presence of uncertainties represented by an uncontrolled parameter modeled by a vector-valued random variable, and possibly with stochastic excitation. The objective is to construct a statistical surrogate model where the input is any deterministic value of the control parameter, and the output is a vector-valued observation of the computational model, which is a random vector whose probability measure is updated using a target dataset. To construct this statistical surrogate model, the stochastic response of the computational model must be built, which is a vector-valued time-discretized stochastic process in high dimension, depending on the control parameter. It is assumed that the computational cost of a single evaluation of the deterministic model is high. For the probabilistic updating, we consider a subset of the components of the observation of the computational model, defined as the “identification observation” of the computational model, for which a small target dataset is available. Therefore, the target dataset is associated with partial observability, corresponding to an incomplete data case. Given a prior probability model of the random control and uncontrolled parameters, a training dataset is constructed, consisting of realizations of the random triplet composed of the stochastic response, the random identification observation, and the random control parameter. Since the computational cost of a single evaluation of the deterministic model is assumed to be large, the training dataset is also of small size. The main challenges in this problem are the high dimensionality, partial observability leading to incomplete data in the target dataset for the identification observation of the computational model (which is not sufficient to identify the computational stochastic responses), and the availability of a small training dataset. To address these challenges, we propose a methodology based on statistical methods for constructing necessary reduced representations, direct probabilistic learning under constraints using probabilistic learning on manifolds (PLoM) constrained by the target dataset, and the use of a weak formulation of the Fourier transform of probability measures. Statistical conditioning is also employed to explore the learned dataset. The constructed predictive statistical surrogate model can be implemented in the context of online computation. Here, we apply this approach to a problem of nonlinear stochastic dynamics in high dimensions within the framework of deformable solids mechanics.

Engineering↗
NASA NTRS2022

Principles for Architecting Autonomous Systems

This paper distills principles for developing autonomous systems based on experience and lessons learned from past efforts. The purpose of these principles is to establish a common understanding and knowledge of architectural elements to guide the development of next-generation multi-mission autonomous systems and ensure the safe and productive operation of space assets. An attempt has been made to ground these principles in fundamentals that should withstand the test of time while allowing for and enabling the advancement of technologies. They are not intended to prescribe a design nor a software representation. There may be multiple designs that can honor these principles. These principles are focused on autonomy for robotic assets. As such, they do not address autonomy for crewed assets nor autonomy that can collectively generate intelligent behavior without top-level system cognizance (e.g., intelligent swarm behavior). These areas would be a subject of future efforts.

Day, John↗
NASA NTRSDate not supplied

Manual Crew Override of Vehicle Landings Following G-Transitions

BACKGROUND Manual control during exploration spaceflight consists of both planned automated supervisory control and unplanned crew override. This crew override capability is critical to enable overall mission success during landing contingencies. However, the introduction of manual override capabilities must be implemented to enable crews to mitigate risks introduced by human error. Adaptive changes in the sensorimotor system can manifest during g-transitions as spatial disorientation. While training and landing aids enable successful landing through disorientation, these adaptive changes may increase cognitive demand that needs to be accounted for in the manual control strategy. It is important to characterize these effects as soon as possible following the G-transition to develop appropriate countermeasures. METHODS The following study seeks to inform the risk associated with altered sensorimotor and vestibular function impacting critical mission tasks. We aim to characterize the effects of short and long-duration weightlessness on manual control following G-transitions using simulated lunar landing on a six-degree-of-freedom (6DOF) motion base, a fixed base simulation, and a supervisory control tablet task. The primary goal is to understand the impact of spaceflight on crew ability to perform manual crew override and supervisory control. This aim will be assessed by comparing pre- versus postflight simulation performance in crewmembers assigned to either short duration (< 30 day) or long duration (~6- month) missions to the International Space Station (ISS). We hypothesize there will be postflight increases in the percent time that pilots are outside of the acceptable range for recommended vehicle state parameters and the reaction time for secondary cognitive tasks. Ground-based control subjects, who are demographically matched to the crew considering age (± 5 years) and gender, will undergo the same testing schedule as the crew to examine the effects of flight phase independent of microgravity exposure. The second aim is to examine how adaptive changes in vestibular and cognitive function relate to changes in manual crew override proficiency. Crew performance for a sensorimotor perceptual test battery will evaluate motion perception tracking, roll nulling, and/or vection sensitivity using the 6DOF motion base. We hypothesize that a higher severity of vestibular alterations will be associated with increased percent time outside of guidance limits. Motion sickness severity and sleepiness will also be evaluated. To determine the impact of “just-in-time” training, the third aim seeks to compare performance during on-board lunar landing tasks conducted late in-flight to early postflight. We hypothesize that proficiency on the “just-in-time” laptop trainer late in mission will be positively correlated with early postflight proficiency on the same task. The final aim will establish assessments of performance, training protocols, and the learning progression in a ground-control cohort of first-time users. RESULTS The assessment of the learning progression associated with the piloting task on the motion base system with thirty ground subjects will be reported. Learning curves will be established across four distinct sessions and within session considering trial difficulty. The difficulty of the landing task can be modulated with the landing divert distance and cross or downrange difficulty. Results may include changes in performance across multiple trials of a multi-attribute lunar tablet supervisory control task. Preliminary investigations of eighteen subjects who completed vestibular threshold and motion perception tasks offer expected performance ranges for upcoming preflight crew evaluations. The results yielded an average roll threshold of 0.46 ± 0.30 deg/s and an average roll nulling root mean square error performance of 2.52 ± 0.52 deg/s. RELEVANCE This project will deliver an operational demonstration of crew monitoring capability following spaceflight and identify potential deficits that may require remediation. Comparison of individual vestibular and cognitive changes with crew performance will help better characterize the manual control risks associated with sensorimotor alterations. Ground testing will evaluate learning progression, refine training protocols, and serve as a control cohort for comparisons to crew performance. ACKNOWLEDGEMENTS: The authors acknowledge contributions from Draper, the Dynamic Skills Trainer (DST) Lab, and the Software, Robotics, and Simulation Division toward the development of the lunar landing simulation platforms. This project is funded by the Human Health Countermeasures Element.

Hannah M. Weiss↗
NASA NTRSDate not supplied

The Emphasis of Design Patterns in Expressing Expert Knowledge From A Technical Solution – A Framework for Continued Research

Digital Engineering is a transformative strategy that leverages an integrated model-based approach to improve communication, decision making, design understanding, and acquisition efficiency of system development. As modern systems are derived from pre-existing systems, harvesting expert knowledge from proven systems in a useful, model-based way will reduce the experiential learning and cognition required for new system development, contributing to a Digital Engineering transformation. Motivated by performance gains observed during a multi-year, sequential development activity, this survey reviews knowledge, architecture, and pattern literature to establish a framework for research of architectural methods for expert knowledge identification and description using Model Based System Engineering. The multi-year sequential development activity is offered as the experimental system of interest for this research. This work aims to enable a digital engineering strategy that improves concept phase decision making, accelerates knowledge acquisition from lessons learned repositories, and eases the burden of generational knowledge loss.

Lithium Ion↗
DOE OSTI2024

Deep-Learning-Based Multi-Timescale Load Forecasting in Buildings: Opportunities and Challenges from Research to Deployment

Electricity load forecasting for buildings and campuses is becoming increasingly important as the penetration of distributed energy resources (DERs) grows. Efficient operation and dispatch of DERs require reasonably accurate predictions of future energy consumption in order to conduct near-real-time optimized dispatch of on-site generation and storage assets. Electric utilities have traditionally performed load forecasting for load pockets spanning large geographic areas, and therefore, forecasting has not been a common practice by buildings and campus operators. Given the growing trends of research and prototyping in the grid-interactive efficient buildings domain, characteristics beyond simple algorithm forecast accuracy are important in determining the algorithm's true utility for smart buildings. Other characteristics include the overall design of the deployed architecture and the operational efficiency of the forecasting system. In this work, we present a deep-learning-based load forecasting system that predicts the building load at 1-hour intervals for 18 hours in the future. We also discuss challenges associated with the real-time deployment of such systems as well as the research opportunities presented by a fully functional forecasting system that has been developed within the National Renewable Energy Laboratory's Intelligent Campus program.

building load forecasting↗
DOE OSTI2020

Toward fusion plasma scenario planning for NSTX-U using machine-learning-accelerated models

One of the most promising devices for realizing power production through nuclear fusion is the tokamak. To maximize performance, it is preferable that tokamak reactors achieve advanced operating scenarios characterized by good plasma confinement, improved magnetohydrodynamic (MHD) stability, and a largely non-inductively driven plasma current. Such scenarios could enable steady-state reactor operation with high \emph{fusion gain} --- the ratio of produced fusion power to the external power provided through the plasma boundary. Precise and robust control of the evolution of the plasma boundary shape as well as the spatial distribution of the plasma current, density, temperature, and rotation will be essential to achieving and maintaining such scenarios. The complexity of the evolution of tokamak plasmas, arising due to nonlinearities and coupling between various parameters, motivates the use of model-based control algorithms that can account for the system dynamics. In this work, a learning-based accelerated model trained on data from the National Spherical Torus Experiment Upgrade (NSTX-U) is employed to develop planning and control strategies for regulating the density and temperature profile evolution around desired trajectories. The proposed model combines empirical scaling laws developed across multiple devices with neural networks trained on empirical data from NSTX-U and a database of first-principles-based computationally intensive simulations. The reduced execution time of the accelerated model will enable practical application of optimization algorithms and reinforcement learning approaches for scenario planning and control development. An initial demonstration of applying optimization approaches to the learning-based model is presented, including a strategy for mitigating the effect of leaving the finite validity range of the accelerated model. The approach shows promise for actuator planning between experiments and in real-time.

machine learning↗
DOE OSTI2025

Encrypted Control Using Modified Learning With Errors-based Schemes

Cyber-physical systems (CPSs) require reliable, safe, and secure control of critical infrastructure, combining computational and networking capabilities, which heighten the risk of cyber attacks. These attacks can disrupt the physical process, causing unforeseen consequences. One solution is the use of fully homomorphic encryption (FHE) to protect the control loop, allowing for secure computations and communications without compromising signal and control system privacy. The challenge with FHE, however, is its requirement for inputs to be integers. This paper introduces a modified Learning With Errors (LWE) FHE approach that encodes control system dynamics and signals into integers. Our proposed scheme leverages a generalized LWE encoding function and modifies the Gentry-Sahai-Waters (GSW) gadget decomposition tool to encrypt the control system. Using the modified LWE scheme, we formalize a fully encrypted control system, supported by simulated results.

42 - ENGINEERING↗
DOE OSTI2020

A machine learning model for predicting the minimum miscibility pressure of CO 2 and crude oil system based on a support vector machine algorithm approach

CO 2 enhanced oil recovery (EOR) is a potential way for carbon capture, utilization and storage (CCUS). Though, the effect of CO 2 injection is greatly influenced by the reservoir conditions. Typically, Minimum miscible pressure (MMP) is selected as one of the key parameters for the screening and evaluation of prospective CO 2 flooding. Conventional slim tube test is both accurate and widely accepted but it is inefficient. Existing empirical formulas for MMPs are easy to be used but have been proved inaccurate and unreliable. Machine learning-based methods have great advantages in predicting MMP. However, only predication accuracy is discussed for most models without the screening of the main control factors and further validation of the model reliability. In this paper, a new prediction model based on support vector machine (SVM) was developed for pure/impure CO 2 and crude oil system. This study was based on 147 sets of MMP data from the literature with full information on reservoir temperature, oil composition and gas composition. The main control factors were screened by several statistical methods. Unlike the conventional prediction models that verified by only prediction accuracy, learning curve and single factor control variable analysis are further validated to obtain the optimum model.

02 PETROLEUM↗
DOE OSTI2023

Autonomous sense and guide machine learning system

A system for generating a machine learning system to generate guidance information based on locations of objects is provided. The system accesses training data that includes training time-of-arrival (“TOA”) information of looks and guidance information for each look. The guidance information is based on a training collection of object locations. The TOA of a look represents, for each object location of a training collection of object locations, times between signals transmitted by transmitters and return signals received by receivers. The return signals represent signals reflected from an object at the object location. The system trains a machine learning system using the training data wherein the machine learning system inputs TOA information and outputs guidance information.

Beer, N. Reginald↗
NASA NTRS2009

Active Learning for Directed Exploration of Complex Systems

Physics-based simulation codes are widely used in science and engineering to model complex systems that would be infeasible to study otherwise. Such codes provide the highest-fidelity representation of system behavior, but are often so slow to run that insight into the system is limited. For example, conducting an exhaustive sweep over a d-dimensional input parameter space with k-steps along each dimension requires k(sup d) simulation trials (translating into k(sup d) CPU-days for one of our current simulations). An alternative is directed exploration in which the next simulation trials are cleverly chosen at each step. Given the results of previous trials, supervised learning techniques (SVM, KDE, GP) are applied to build up simplified predictive models of system behavior. These models are then used within an active learning framework to identify the most valuable trials to run next. Several active learning strategies are examined including a recently-proposed information-theoretic approach. Performance is evaluated on a set of thirteen synthetic oracles, which serve as surrogates for the more expensive simulations and enable the experiments to be replicated by other researchers.

oracles↗
DOE OSTI2021

Deep Reinforcement Scheduling of Energy Storage Systems for Real-time Voltage Regulation in Unbalanced LV Networks with High PV Penetration

The ever-growing higher penetration of distributed energy resources (DERs) in low-voltage (LV) distribution systems brings both opportunities and challenges to voltage support and regulation. This paper proposes a deep reinforcement learning (DRL)-based scheduling scheme of energy storage systems (ESSs) to mitigate system voltage deviations in unbalanced LV distribution networks. The ESS-based voltage regulation problem is formulated as a multi-stage quadratic stochastic program, with the objective of minimizing the expected total daily voltage regulation cost while satisfying operational constraints. While existing voltage regulation methods are mostly focused on onetime- step control, this paper explores a day-horizon systemwide voltage regulation problem. In other words, the size of action and state spaces are extremely high-dimensional and need to be delicately handled. Furthermore, in order to overcome the difficulty of modeling uncertainties and develop a realtime solution, a learn-to-schedule feedback control framework is proposed by adapting the problem to a model-free DRL setting. The proposed algorithm is tested on a customized 6-bus system and a modified IEEE 34-bus system. Simulation results validate the effectiveness and near-optimality of voltage regulation by ESS in comparison with a deterministic quadratic program solution.

Wang, Shengyi↗
DOE OSTI2023

Statistical Learning for Nonlinear Model Reduction from Local Simulations of Stochastic and Particle- and Agent-Based Systems

Stochastic physical systems across the sciences that have very high-dimensional state spaces, with a large number of fast degrees of freedom that force direct simulators to proceed by integration steps that are orders of magnitude smaller than events of interests (e.g., particle collisions). Examples range from molecular motion to dynamics of large populations of cells. A grand challenge in the simulation and understanding of such systems is the systematic construction of accurate, interpretable, reduced models, enabling faster simulations, revealing fundamental properties of the dynamics, and predicting phenomena of interest that the original simulator could not reached with sufficient accuracy or within a given computational budget. In this projected we developed novel statistical estimation/machine learning techniques for analyzing and building empirical reduced models for important families of high-dimensional stochastic systems, in particular: - we developed techniques for estimating interaction kernels in interacting particle- and agent-based systems, which are ubiquitous in Physics, Biology and many other sciences, given observed trajectories of the system; - we developed techniques for nonlinear model reduction for high-dimensional stochastic systems that have a small number of unknown, nonlinear slow variables, and a large number of fast modes, that are possibly of large magnitude, given observed short trajectories of the system in the form of bursts of trajectories from different initial conditions; - we developed novel techniques for estimating linear dynamical systems on graphs when both the dynamics and the underlying graph are unknown, and we have a sparse set of space-time observations; - we considered the problem of estimating an unknown nonlinear observation function of a standard process (e.g. Brownian motion), so that we can recognized if an observed dynamics is "just" a nonlinear version of a known dynamics; we also developed benchmarks for learning algorithms aimed at learning and classifying diffusion processes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Simulated wildfire burned area over the CONUS during 2001-2020

Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM). A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001-2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

Liu, Ye↗
NASA NTRS2004

Thermal Control Technologies for Complex Spacecraft

Thermal control is a generic need for all spacecraft. In response to ever more demanding science and exploration requirements, spacecraft are becoming ever more complex, and hence their thermal control systems must evolve. This paper briefly discusses the process of technology development, the state-of-the-art in thermal control, recent experiences with on-orbit two-phase systems, and the emerging thermal control technologies to meet these evolving needs. Some "lessons learned" based on experience with on-orbit systems are also presented.

Swanson, Theodore D.↗
DOE OSTI2020

Adaptive PV Frequency Control Strategy Based on Real-time Inertia Estimation

The declining cost of solar Photovoltaics (PV) generation is driving its worldwide deployment. As conventional generation with large rotating masses is being replaced by renewable energy such as PV, the power system’s inertia will be affected. As a result, the system’s frequency may vary more dramatically in the case of a disturbance, and the frequency nadir may be low enough to trigger protection relays such as under-frequency load shedding. The existing frequency-watt function mandated in power inverters cannot provide grid frequency support in a loss-of-generation event, as PV plants usually do not have power reserves. Here, a novel adaptive PV frequency control strategy is proposed to reserve the minimum power required for grid frequency support. A machine learning model is trained to predict system frequency response under varying system conditions, and an adaptive allocation of PV headroom reserves is made based on the machine learning model as well as real-time system conditions including inertia. Case studies show the proposed control method meets the frequency nadir requirements using minimal power reserves compared to a fixed headroom control approach.

14 SOLAR ENERGY↗
DOE OSTI2024

Improving North American Wildfire Prediction by Integrating a Machine-Learning Fire Model in a Land Surface Model

Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001-2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

54 ENVIRONMENTAL SCIENCES↗