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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,441 records · Page 80

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Pd–Methyl Bond Energy─Property Correlations, Noncorrelations, Machine Learning Models, and Application to Polymerization Catalysis

Metal–carbon bonds are a key intermediate in a variety of homogeneous organometallic transformations and often determine the critical thermodynamics and kinetics of catalytic processes. Surprisingly, the influence of different ligands on metal–carbon bond strengths has been largely overlooked. Here, in this study, we evaluated nearly 700 experimental Pd–methyl complexes by calculating their bond dissociation energies using density functional theory (DFT) and compared these bond strengths to several fundamental molecular properties, and this revealed several surprising correlations and noncorrelations. Most surprising was that several fundamental properties, such as the bond length, bond force constant, and bond electron density, have no correlation with bond strength, despite these correlations often holding for main-group compounds. We were indeed able to identify key ligand-dependent chemical features/descriptors that provided a highly accurate machine learning model and provided insight into the general factors that control the Pd–carbon bond strength, such as radical delocalization and nucleophilicity. Insights gained from the Pd–Me bond energy analysis were then applied to CO migratory insertion steps that are part of copolymerization reactions.

binding energy↗

DOE OSTI2023

Cutting force estimation from machine learning and physics-inspired data-driven models utilizing accelerometer measurements

Monitoring cutting forces for process control may be challenging because force measurements typically require invasive instrumentation. To remedy this situation, two new methods were recently developed to estimate cutting forces in real time based on the use of on-machine accelerometer measurements. One method uses machine learning, while another uses a physics-inspired data-driven approach, to generate a model that estimates cutting forces from on-machine accelerations. The estimated forces from both approaches were compared against cutting force data collected during various milling operations on several machine tools. The results reveal the advantages and disadvantages of each model to estimate real-time cutting forces.

Vogl, Greg↗

DOE OSTI2025

Prediction of electric and magnetic fields from spectral data using machine learning algorithms for Doppler-free saturation spectroscopy diagnostics

The prediction of electric and magnetic field amplitudes from atomic spectral data is critical for plasma control in fusion devices such as tokamaks. Conventional approaches that rely on physics-based models are computationally expensive and unsuitable for real-time applications. In this work, we develop and benchmark three machine learning algorithms—simulation-based inference (SBI), fully connected neural networks (FCNN), and histogram-based gradient boosting regression (GBR-Hist)—to infer field intensities directly from Doppler-free saturation spectroscopy (DFSS) spectra. Synthetic datasets of spectra were generated using the EZSSS code and evaluated both with and without added Poisson noise to mimic experimental conditions. We find that SBI achieves the highest accuracy and robustness, FCNN provides a strong balance of accuracy and computational efficiency for real-time applications, and GBR-Hist offers the fastest inference but is more sensitive to noise. Furthermore, these results demonstrate the potential of machine learning to accelerate DFSS analysis and enhance its utility for plasma diagnostics and control.

Doppler-free saturation spectroscopy↗

DOE OSTI2022

Dual-Biometric Human Identification Using Radar Deep Transfer Learning

Accurate human identification using radar has a variety of potential applications, such as surveillance, access control and security checkpoints. Nevertheless, radar-based human identification has been limited to a few motion-based biometrics that are solely reliant on micro-Doppler signatures. This paper proposes for the first time the use of combined radar-based heart sound and gait signals as biometrics for human identification. The proposed methodology starts by converting the extracted biometric signatures collected from 18 subjects to images, and then an image augmentation technique is applied and the deep transfer learning is used to classify each subject. A validation accuracy of 58.7% and 96% is reported for the heart sound and gait biometrics, respectively. Next, the identification results of the two biometrics are combined using the joint probability mass function (PMF) method to report a 98% identification accuracy. To the best of our knowledge, this is the highest reported in the literature to date. Lastly, the trained networks are tested in an actual scenario while being used in an office access control platform to identify different human subjects. We report an accuracy of 76.25%.

47 OTHER INSTRUMENTATION↗

DOE OSTI2023

Surface enrichment dictates block copolymer orientation

Orientation of block copolymer (BCP) morphology in thin films is critical to applications as nanostructured coatings. Despite being well-studied, the ability to control BCP orientation across all possible block constituents remains challenging. Here, in this study, we deploy coarse-grained molecular dynamics simulations to study diblock copolymer ordering in thin films, focusing on chain makeup, substrate surface energy, and surface tension disparity between the two constituent blocks. We explore the multi-dimensional parameter space of ordering using a machine-learning approach, where an autonomous loop using a Gaussian process (GP) control algorithm iteratively selects high-value simulations to compute. The GP kernel was engineered to capture known symmetries. The trained GP model serves as both a complete map of system response, and a robust means of extracting material knowledge. We demonstrate that the vertical orientation of BCP phases depends on several counter-balancing energetic contributions, including entropic and enthalpic material enrichment at interfaces, distortion of morphological objects through the film depth, and of course interfacial energies. BCP lamellae are found more resistant to these effects, and thus more robustly form vertical orientations across a broad range of conditions; while BCP cylinders are found to be highly sensitive to surface tension disparity.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

NASA NTRSDate not supplied

CELA NextGen 2020 Abstract

Creating a new technology development is hard! But, experience canbe the best teacher. Through our journey in maturing CELA, africtionless, direct-drive Reaction Sphere (RS) (Figure 1), lessonsour team learned have given us valuable insights that can help youon your own technology development journey. CELA (CorrelatedElectromagnetic Levitation Actuator), like all state-of-the-art starts, is a technology development project. This idea started by addressing a problem posed in a classroom setting, and has morphed into its current state today. At first, the problem was to create a novel separation system. Then, as oftenhappens with new ideas, there was a bump in the road: CELA did not align with stakeholder priorities. So, we had to pivot. The team learned that the funding organization was more excited about an Attitude Control System solution than a Separation System solution. CELA then became a Reaction Wheel. Through more pivots, the technology development advanced into a RS. This example shows that the process for maturing an idea is just as important as the technology itself. Other aspects of the process include finding funding sources, conducting research, obtaining patents, engaging partners, and finally creating systems to keep you on track and pointed in the right direction. Going through this process will teach you many valuable lessons: you never know when an idea will arrive, you will experience rejection, and you will learn a lot about your own strengths and weaknesses.The importance of this is not to teach you to give up, but to teach you to keep going, and to learn what works and what does not work in order to set yourself up for success.

technology↗

DOE OSTI2018

Deep learning: A guide for practitioners in the physical sciences

Machine learning is finding increasingly broad applications in the physical sciences. This most often involves building a model relationship between a dependent, measurable output, and an associated set of controllable, but complicated, independent inputs. We present a tutorial on current techniques in machine learning—a jumping-off point for interested researchers to advance their work. We focus on deep neural networks with an emphasis on demystifying deep learning. We begin with background ideas in machine learning and some example applications from current research in plasma physics. We discuss supervised learning techniques for modeling complicated functions, beginning with familiar regression schemes, and then advancing to more sophisticated deep learning methods. We also address unsupervised learning and techniques for reducing the dimensionality of input spaces. Along the way, we describe methods for practitioners to help ensure that their models generalize from their training data to as-yet-unseen test data. We describe classes of tasks—predicting scalars, handling images, and fitting time-series—and prepare the reader to choose an appropriate technique. We finally point out some limitations to modern machine learning and speculate on some ways that practitioners from the physical sciences may be particularly suited to help.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

NASA NTRS2001

Learning Sequences of Actions in Collectives of Autonomous Agents

In this paper we focus on the problem of designing a collective of autonomous agents that individually learn sequences of actions such that the resultant sequence of joint actions achieves a predetermined global objective. We are particularly interested in instances of this problem where centralized control is either impossible or impractical. For single agent systems in similar domains, machine learning methods (e.g., reinforcement learners) have been successfully used. However, applying such solutions directly to multi-agent systems often proves problematic, as agents may work at cross-purposes, or have difficulty in evaluating their contribution to achievement of the global objective, or both. Accordingly, the crucial design step in multiagent systems centers on determining the private objectives of each agent so that as the agents strive for those objectives, the system reaches a good global solution. In this work we consider a version of this problem involving multiple autonomous agents in a grid world. We use concepts from collective intelligence to design goals for the agents that are 'aligned' with the global goal, and are 'learnable' in that agents can readily see how their behavior affects their utility. We show that reinforcement learning agents using those goals outperform both 'natural' extensions of single agent algorithms and global reinforcement, learning solutions based on 'team games'.

Turner, Kagan↗

DOE OSTI2020

MFNets: Multifidelity data-driven networks for Bayesian learning and prediction

This paper presents a multifidelity uncertainty quantification framework called MFNets. We seek to address three existing challenges that arise when experimental and simulation data from different sources are used to enhance statistical estimation and prediction with quantified uncertainty. Specifically, we demonstrate that MFNets can (1) fuse heterogeneous data sources arising from simulations with different parameterizations, e.g simulation models with different uncertain parameters or data sets collected under different environmental conditions; (2) encode known relationships among data sources to reduce data requirements; and (3) improve the robustness of existing multi-fidelity approaches to corrupted data. MFNets construct a network of latent variables (LVs) to facilitate the fusion of data from an ensemble of sources of varying credibility and cost. These LVs are posited as explanatory variables that provide the source of correlation in the observed data. Furthermore, MFNets provide a way to encode prior physical knowledge to enable efficient estimation of statistics and/or construction of surrogates via conditional independence relations on the LVs. We highlight the utility of our framework with a number of theoretical results which assess the quality of the posterior mean as a frequentist estimator and compare it to standard sampling approaches that use single fidelity, multilevel, and control variate Monte Carlo estimators. We also use the proposed framework to derive the Monte Carlo-based control variate estimator entirely from the use of Bayes rule and linear-Gaussian models -- to our knowledge the first such derivation. Finally, we demonstrate the ability to work with different uncertain parameters across different models.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2020

An Overview of NASA’s Learn-to-Fly Technology Development

“Learn-to-Fly” (L2F) is an advanced technology development effort within the Modeling and Control for Agile Aircraft Development (MCAAD) group, a part of the NASA Transformative Aeronautics Concepts Program’s (TACP) Transformational Tools and Technologies (TTT) project. The goal of L2F is to develop technologies for enabling self-learning flight vehicles, using both ground- and flight-test approaches. Specifically, research has been conducted to demonstrate the potential to merge two enabling technologies, real-time aerodynamic modeling and adaptive flight controls, to substantially reduce the typical ground- and flight-testing time requirements for air vehicle design. This effort involved development of real-time, on-board algorithms to demonstrate key L2F technologies including aerodynamic modeling and control for an aircraft with minimal a priori knowledge. This research included both ground-based wind tunnel experiments utilizing modern design of experiments (DOE) techniques, as well as a flight test campaign, and was intended to rapidly advance these technologies and demonstrate key capabilities of the L2F approach. This paper presents the overview of the methods used to develop L2F technologies in NASA Langley Research Center’s 12-Foot Low Speed Tunnel, as well as in flight experiments. These methods include efficient wind tunnel data collection, real-time global nonlinear aerodynamic modeling in both the time and frequency domains, and the integration of the modeling techniques with adaptive flight controls, all of which were demonstrated using experimental validation.

Stephen E Riddick↗

DOE OSTI2023

Machine learning surrogate of physics-based building-stock simulator for end-use load forecasting

Building energy models are used to simulate heat and mass transfer and estimate end-use load in buildings. With the proliferation of solar photovoltaics on residential and commercial buildings, increasingly, buildings are expected to provide grid services, for which accurate and computationally efficient building energy simulations and end-use load prediction are imperative. Existing building energy simulation tools, however, have significant computational overhead that make them less practical in real-time deployment for optimization, design, uncertainty quantification and control in building energy management systems. Here this article presents a data-driven machine learning model based on light gradient boosting method (LightGBM) as a surrogate for a physics-based simulator for residential buildings to predict end-use load. The machine learning based surrogate model accounts for time-series related variables, seasonality and trend component of end-use load, and history of end-use load. The accuracy of the surrogate model is assessed on the prediction of the load profiles of 100 different houses in Cook County, Illinois, USA. The LightGBM surrogate model is shown to reduce the root-mean-squared error by 53% relative to a reference decision tree (DT) based model reported previously in the literature. Moreover, the model predicts the load spikes and high-ramp rate events throughout the year which are often the Achilles heel of other models in the literature. The machine learning based surrogate model is demonstrated to be computationally efficient, with a ten-fold reduction in the computational time compared to a physics-based building energy simulation, and suitable for uncertainty analysis and real-time control of building characteristics in response to uncertainty.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA NTRS2019

Reusing Data and Metadata to Create New Metadata Through Machine-Learning & Other Programmatic Methods

Recent improvements in natural language processing (NLP) enable metadata to be created programmatically from reused original metadata or even the dataset itself. Transfer-learning applied to NLP has greatly improved performance and reduced training data requirements. In this talk, we’ll compare machine-generated metadata to human-generated metadata and discuss characteristics of metadata and data archives that affect suitability for machine-learning reuse of metadata. Where as human-generated metadata is often populated once, populated from the perspective of data supplier, populated by many individuals with different words for the same thing, and limited in length, machine-generated metadata can be updated any number of times, generated from the perspective of any user, constrained to a standardized set of terms that can be evolved over time, and be any length required. Machine-learning generated metadata offers benefits but also additional needs in terms of version control, process transparency, human-computer interaction, and IT requirements. As a successful example, we’ll discuss how a dataset of abstracts and associated human-tagged keywords from a standardized list of several thousand keywords were used to create a machine-learning model that predicted keyword metadata for open-source code projects on code.nasa.gov. We’ll also discuss a less successful example from data.nasa.gov to show how data archive architecture and characteristics of initial metadata can be strong controls on how easy it is to leverage programmatic methods to reuse metadata to create additional metadata.

Gosses, Justin↗

NASA NTRS1992

Adaptive defuzzification for fuzzy systems modeling

We propose a new parameterized method for the defuzzification process based on the simple M-SLIDE transformation. We develop a computationally efficient algorithm for learning the relevant parameter as well as providing a computationally simple scheme for doing the defuzzification step in the fuzzy logic controllers. The M-SLIDE method results in a particularly simple linear form of the algorithm for learning the parameter which can be used both off- and on-line.

Yager, Ronald R.↗

NASA NTRS2002

Effects of heavy particle irradiation and diet on amphetamine- and lithium chloride-induced taste avoidance learning in rats

Rats were maintained on diets containing either 2% blueberry or strawberry extract or a control diet for 8 weeks prior to being exposed to 1.5 Gy of 56Fe particles in the Alternating Gradient Synchrotron at Brookhaven National Laboratory. Three days following irradiation, the rats were tested for the effects of irradiation on the acquisition of an amphetamine- or lithium chloride-induced (LiCl) conditioned taste avoidance (CTA). The rats maintained on the control diet failed to show the acquisition of a CTA following injection of amphetamine. In contrast, the rats maintained on antioxidant diets (strawberry or blueberry extract) continued to show the development of an amphetamine-induced CTA following exposure to 56Fe particles. Neither irradiation nor diet had an effect on the acquisition of a LiCl-induced CTA. The results are interpreted as indicating that oxidative stress following exposure to 56Fe particles may be responsible for the disruption of the dopamine-mediated amphetamine-induced CTA in rats fed control diets; and that a reduction in oxidative stress produced by the antioxidant diets functions to reinstate the dopamine-mediated CTA. The failure of either irradiation or diet to influence LiCl-induced responding suggests that oxidative stress may not be involved in CTA learning following injection of LiCl.

Non-NASA Center↗

DOE OSTI2024

Transient Optimization of the Cryogenic Moderator System Controller at the Spallation Neutron Source for Improved Performance

The high-energy neutron beam generated at the Spallation Neutron Source (SNS) at Oak Ridge National Laboratory is moderated to use cold (slow) neutrons for scientific discoveries. The Cryogenic Moderator System (CMS) removes heat from the neutron beam using cryogenic hydrogen (H 2 ) moderators connected via heat exchangers to a helium (He) refrigeration loop that dissipates heat using a compressor-brake system. However, the CMS is affected by sporadic losses in beam power, referred to as "beam trips," as these events generate significant disturbances in cooling requirements. To accommodate the heat load transients during beam trips, the CMS uses a decentralized control strategy consisting of four flow valves and one electric heater adjusted by independent proportional-integral (PI) controllers. During the CMS’s initial commissioning, the PI gains were calibrated based only on tracking performance, overlooking their effectiveness in disturbance rejection. A data-driven, control-oriented closed-loop model was developed to recalibrate the PI gains and minimize the transient disturbances caused by beam trips. The model consists of three main components: (1) a physics-based model of the He refrigeration loop, (2) a machine-learning model of the cryogenic H 2 cooling trains, and (3) the control logic used for feedback set-point tracking. Experimental results showed that the recalibrated gains obtained in this study improved the CMS’s transient response during beam trips.

Maldonado Puente, Bryan↗

DOE OSTI2023

Deep reinforcement learning to discover multi-fuel injection strategies for compression ignition engines

Over the past several decades, regulation of compression ignition engine emissions has become increasingly stringent as concern about the environmental and health implications of these emissions has grown. These changing constraints have led to a series of new, alternative fuel injection strategies that aim to maintain power output while reducing in-cylinder generated emissions by operating in the low-temperature combustion (LTC) regime. These advanced injection strategies are created and retuned for individual combinations of engine geometry, fuel, and emissions constraints. Deep reinforcement learning has been shown to be an effective alternative to traditional optimization approaches for highly combinatorial control problems, such as discovering the optimal injection schedules for compression ignition engines. In this study, we deploy a previously presented deep reinforcement learning framework to iteratively optimize a series of engine geometries over a range of increasingly strict NO x emissions regulations. We then examine the resulting injection schedules. We discuss the potential for using this deep reinforcement learning framework for fuel selection screening and for discovering unique injection strategies for different engine geometries and future emissions standards.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2022

Time Sequence Machine Learning-Based Data Intrusion Detection for Smart Voltage Source Converter-Enabled Power Grid

Smart inverters of distributed energy resources can enable cloud computing, condition monitoring, result visualization, remote control, and peer-to-peer energy trading in advanced power systems. However, the advent of data injection attacks in the communication architecture can alter measurement characteristics of power grids and have devastating consequences. In this article, we propose a time sequence machine learning-based anomaly detection methodology for detecting cyber intrusion into control signal setpoints and dc voltage signal measurement bias of the voltage source converter (VSC) in wind generators. We first investigated the effects of four types of denial of service, tampering signal, and stealthy-type data intrusion attacks on smart VSCs and overall wind farms. We then proposed a novel time sequence machine learning-based intrusion detection framework that can be implemented to detect different cyberattacks in the VSCs. The performance of the proposed framework has been compared with that of autoencoder and clustering-based intrusion detection framework. The proposed framework was validated by using the IEEE 39 bus power system in the presence of four wind farms in different locations. Using several metrics for intrusion detection performance, we validated the effectiveness of the proposed framework.

42 ENGINEERING↗

NASA NTRS1984

What you thought you knew about motion sickness isn't necessarily so

Motion sickness symptoms, stimuli, and drug therapy are discussed. Autogenic feedback training (AFT) methods of preventing motion sickness are explained. Research with AFT indicates that participants who had AFT could withstand longer periods of Coriolis acceleration, participants with high or low susceptibility to motion sickness could control their symptoms with AFT, AFT for Coriolis acceleration is transferable to other motion sickness stimuli, and most people can learn AFT, though with varying rates of learning.

Autogenic Training↗