Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning 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 1,369 records · Page 76
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Deep reinforcement learning based optimization for a tightly coupled nuclear renewable integrated energy system

New ways to integrate energy systems to maximize efficiency are being sought to meet carbon emissions goals. Nuclear-renewable integrated energy system (NR-IES) concepts are a leading solution that couples a nuclear power plant with renewable energy, hydrogen generation plants, and energy storage systems, such that thermal and electrical power are dispatchable to fulfill grid-flexibility requirements while also producing hydrogen and maximizing revenue. Here, this paper introduces a deep reinforcement learning (DRL)-based framework to address the complex decision-making tasks for NR-IES. The objective is to maximize revenue by generating and selling hydrogen and electricity simultaneously according to their time-varying prices while keeping the energy flow in the subsystems in balance. A Python-based simulator for a NR-IES concept has been developed to integrate with OpenAI Gym and Ray/RLlib to enable an efficient and flexible computational framework for DRL research and development. Three state-of-the-art DRL algorithms have been investigated, including two-delayed deep deterministic policy gradient (TD3), soft-actor critic (SAC), proximal policy optimization (PPO), to illustrate DRL’s superiority for controlling NR-IES by comparing it with a conventional control approach, particle swarm optimization (PSO). In this effort, PPO has shown more-stable performance and also better generalization capability than SAC and TD3. Comparisons with PSO have demonstrated that, on average, PPO can achieve 13.9% more mean episode returns from the training process and 29.4% more mean episode returns from the testing process when different hydrogen-production targets are applied.

08 HYDROGEN↗
DOE OSTI2025

Hierarchical Speed Planner for Automated Vehicles: A Framework for Lagrangian Variable Speed Limit in Mixed-Autonomy Traffic

Here, this article presents a novel hierarchical speed planning framework for variable speed limits in mixed-autonomy traffic environments, leveraging server-side macroscopic control and vehicle-side microscopic execution. The framework integrates real-time traffic state estimation (TSE) and reinforcement learning (RL)-based control to mitigate congestion and improve traffic flow. A TSE enhancement module combines macroscopic data from sources like INRIX with high-resolution observations from connected autonomous vehicles (CAVs), enabling predictive modeling to address latency and noise. The target speed design module employs kernel smoothing and a buffer zone strategy to optimize traffic density and flow around bottlenecks. The proposed system was validated in the largest open-road test to date with 100 CAVs, demonstrating an overall 8% traffic density decrease, with a specific decrease of 7% upstream, 10% downstream, and a 52% decrease during the congestion formation phase at bottlenecks.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Integration of LIBS with Machine Learning for Real-Time Monitoring of Feedstock in H 2 Gasification Applications

This project, funded by the U.S. Department of Energy (DOE) – Office of Fossil Energy under Award Number DE-FE0032177, aimed to assess the feasibility of an integrated Laser-Induced Breakdown Spectroscopy (LIBS) system with advanced machine learning (ML) models for real-time characterization and potential control of hydrogen gasifiers running on waste materials as feedstocks. This was a multidisciplinary effort that encompassed the acquisition and standardized analysis of individual and blended feedstocks—comprising biomass, coal waste, and plastic waste, followed by the development of a dynamic LIBS bench system for material sample analysis and development of predictive ML models. Comprehensive laboratory testing enabled the creation of a robust elemental dataset that served as the foundation for ML model training. Techniques such as Random Forest, Gradient Boosting, Support Vector Regression, and Neural Networks were employed to predict key feedstock properties, including higher heating value (HHV), moisture content, thermal conductivity, and ash composition with high accuracy. The results were validated against experimental data and demonstrated strong potential for real-time application in gasifier control systems. The project concluded with a study on the integration of the LIBS+ML approach for gasifier control and a techno-economic analysis of the implementation of the approach into hydrogen (H 2 ) gasification systems. Dissemination of results was carried out at a DOE meeting. This work establishes a scalable framework for automated, in-line feedstock quality assessment, offering significant implications for process optimization and emissions reduction in hydrogen production.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2023

Exploring the $A$-V-Sb landscape beyond $A$$\mathrm{V_3}$ $\mathrm{Sb_5}$: A case study on the $\mathrm{KV_6}$ $\mathrm{Sb_6}$ Kagome compound

Kagome compounds have garnered attention in the past few years for their intriguing magnetic properties arising from spin frustration dictated by the geometry of the Kagome sublattice. In this paper, we highlight the success of the unconventional hydride route for the fast and easy synthesis of the Kagome compound $\mathrm{KV_6}$ $\mathrm{Sb_6}$. Here, high-temperature in situ powder x-ray diffraction (PXRD) studies proved to be useful in hinting at the existence of $\mathrm{KV_6}$ $\mathrm{Sb_6}$, identifying its synthesis conditions, and understanding the reaction mechanism. The crystal structure for $\mathrm{KV_6}$ $\mathrm{Sb_6}$ was determined from high-resolution PXRD data. The compound has a layered structure [$R\overline{3}m, a = 5.5318$ (9) Å, $c = 34.23$ (3)Å 3 $Z = 3$] at room temperature] and features a Kagome bilayer of V atoms. $\mathrm{KV_6}$ $\mathrm{Sb_6}$ is isostructural to the previously reported $\mathrm{RbV_6}$ $\mathrm{Sb_6}$ and $\mathrm{CsV_6}$ $\mathrm{Sb_6}$ compounds. $\mathrm{KV_6}$ $\mathrm{Sb_6}$ is thermally stable in vacuum up to 1173 K, as evident from the high-temperature in situ PXRD and differential scanning calorimetric analysis. Investigation of magnetic properties for $\mathrm{KV_6}$ $\mathrm{Sb_6}$ between 2 and 300 K reveals temperature-independent paramagnetism and an absence of superconductivity, like the Rb and Cs analogs. Furthermore, we compare the magnetic properties of K V 3 Sb 5 , another ternary Kagome compound, synthesized via two different methods: the hydride route and the traditional route from elements. Low-temperature transport property measurements of $\mathrm{KV_6}$ $\mathrm{Sb_6}$ indicate metallic behavior and an intrinsically low thermal conductivity of $\mathrm{1.0 W K^-1}$ $\mathrm{m^-1}$ at 300 K. The layered structure of $\mathrm{KV_6}$ $\mathrm{Sb_6}$ makes it an attractive candidate for deintercalation and doping studies to tune both magnetic and transport properties, laying a foundation for further studies.

36 MATERIALS SCIENCE↗
NASA NTRS1989

Techniques for studying the effects of microgravity on model particle/cell systems

In an effort to learn more about the effects of a simulated low gravity environment on skeletal muscle, skeletal muscle cell cultures were grown within the lumen of XM-80 hollow fibers (i.d. = 0.5 mm) in a Clinostat rotating at 100 rpm. Cells were isolated from the thigh muscle tissue of 12 day embryos and were cultured for up to 14 days in the hollow fiber environment. Cells proliferated to confluency within several days, and fusion into multinucleated myotubes was then apparent. Fibers were stretched by a built-in spring mechanism to hold the fiber tightly at the center of rotation, and sections of the fiber were removed at 3, 7 and 14 days for electron microscopic analysis. When the Clinostat is rotated in the horizontal position, the gravity vector approaches zero and the cells are in an environment that simulates microgravity. Control experiments consist of one fiber rotated in the vertical position in the clinostat and another fiber that is held in a horizontal configuration in a comparable sized tube that is not rotated at all. Examination of skeletal muscle cells by electron microscopy revealed that myoblast fusion and myofibril accumulation were extensive. Two general conclusions were apparent. First, muscle cells undergo the normal progression of proliferation, fusion, and myofibril assembly in the presence of simulated microgravity for the first week in culture. After 14 days, however, many muscle fibers undergo degeneration such that myofibrillar structures are not extensive or well organized. Second, although no major abnormalities in myofibril assembly were detected in Clinostat-rotated cultures in comparison to controls that were not rotated in a Clinostat, the myofibrils in non-rotated controls tend to be more highly organized than those in either horizontally or vertically rotated Clinostat samples.

Young, Ronald B.↗
NASA NTRS1992

A composite self tuning strategy for fuzzy control of dynamic systems

The feature of self learning makes fuzzy logic controllers attractive in control applications. This paper proposes a strategy to tune the fuzzy logic controller on-line by tuning the data base as well as the rule base. The structure of the controller is outlined and preliminary results are presented using simulation studies.

Shieh, C.-Y.↗
NASA NTRS1994

An integrated strategy for the planetary sciences: 1995 - 2010

In 1992, the National Research Council's Space Studies Board charged its Committee on Planetary and Lunar Exploration (COMPLEX) to: (1) summarize current understanding of the planets and the solar system; (2) pose the most significant scientific questions that remain; and (3) establish the priorities for scientific exploration of the planets for the period from 1995 to 2010. The broad scientific goals of solar system exploration include: (1) understanding how physical and chemical processes determine the major characteristics of the planets, and thereby help us to understand the operation of Earth; (2) learning about how planetary systems originate and evolve; (3) determining how life developed in the solar system, particularly on Earth, and in what ways life modifies planetary environments; and (4) discovering how relatively simple, basic laws of physics and chemistry can lead to the diverse phenomena observed in complex systems. COMPLEX maintains that the most useful new programs to emphasize in the period from 1995 to 2010 are detailed investigations of comets, Mars, and Jupiter and an intensive search for, and characterization of, extrasolar planets.

Source record↗
NASA NTRS2016

Development of a Multi-Band Shared Aperture Reflectarray/Reflector Antenna Design for NASA

A dual-band (Ka/W) shared-aperture antenna system design has been developed as a proposed solution to meet the needs of NASA's planned Aerosol, Clouds, and Ecosystem (ACE) mission. The design is comprised of a compact Cassegrain reflector/reflect array with a fixed W-band feed and a cross track scanned Ka-band Active Electronically Scanned Array (AESA). Critical Sub-scale prototype testing and flight tests have validated some of the key aspects of this innovative antenna design, including the low loss reflector/reflect array surface. More recently the science community has expressed interest in a mission that offers the ability to measure precipitation (Ku- band with scanning) in addition to clouds and aerosols. In this paper we present findings from a design study that explores options for realizing a tri-frequency (Ku/Ka/W), shared-aperture antenna system to meet these science objectives. Design considerations included meeting performance requirements while striving to minimize payload size, weight, prime power, and cost. The extensive trades and lessons learned from the ACE system development were utilized as the foundation for this work.

doppler↗
NASA NTRS2017

What Machines Need to Learn to Support Human Problem-Solving

In the development of intelligent systems that interact with humans, there is often confusion between how the system functions with respect to the humans it interacts with and how it interfaces with those humans. The former is a much deeper challenge than the latter it requires a system-level understanding of evolving human roles as well as an understanding of what humans need to know (and when) in order to perform their tasks. This talk will focus on some of the challenges in getting this right as well as on the type of research and development that results in successful human-autonomy teaming. Brief Bio: Dr. Alonso Vera is Chief of the Human Systems Integration Division at NASA Ames Research Center. His expertise is in human-computer interaction, information systems, artificial intelligence, and computational human performance modeling. He has led the design, development and deployment of mission software systems across NASA robotic and human space flight missions, including Mars Exploration Rovers, Phoenix Mars Lander, ISS, Constellation, and Exploration Systems. Dr. Vera received a Bachelor of Science with First Class Honors from McGill University in 1985 and a Ph.D. from Cornell University in 1991. He went on to a Post-Doctoral Fellowship in the School of Computer Science at Carnegie Mellon University from 1990-93.

intelligent systems↗
DOE OSTI2023

mergedsmpsapsml

Merged aerosol particle size distributions for the Aerodynamic Particle Sizer (APS) and Scanning Mobility Particle Sizer (SMPS) instruments with Machine Learning Quality Checks Applied

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Role of reinforcement learning for risk-based robust control of cyber-physical energy systems

Critical infrastructures such as cyber-physical energy systems (CPS-E) integrate information flow and physical operations that are vulnerable to natural and targeted failures. Safe, secure, and reliable operation and control of CPS-E is critical to ensure societal well-being and economic prosperity. Automated control is key for real-time operations and may be mathematically cast as a sequential decision-making problem under uncertainty. Emergence of data-driven techniques for decision making under uncertainty, such as reinforcement learning (RL), have led to promising advances for addressing sequential decision-making problems for risk-based robust CPS-E control. However, existing research challenges include understanding the applicability of RL methods across diverse CPS-E applications, addressing the effect of risk preferences across multiple RL methods, and development of open-source domain-aware simulation environments for RL experimentation within a CPS-E context. This article systematically analyzes the applicability of four types of RL methods (model-free, model-based, hybrid model-free and model-based, and hierarchical) for risk-based robust CPS-E control. Problem features and solution stability for the RL methods are also discussed. We demonstrate and compare the performance of multiple RL methods under different risk specifications (risk-averse, risk-neutral, and risk-seeking) through the development and application of an open-source simulation environment. Motivating numerical simulation examples include representative single-zone and multizone building control use cases. Finally, six key insights for future research and broader adoption of RL methods are identified, with specific emphasis on problem features, algorithmic explainability, and solution stability.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2004

Accessing FMS Functionality: The Impact of Design on Learning

In modern commercial and military aircraft, the Flight Management System (FMS) lies at the heart of the functionality of the airplane. The nature of the FMS has also caused great difficulties learning and accessing this functionality. This study examines actual Air Force pilots who were qualified on the newly introduced advanced FMS and shows that the design of the system itself is a primary source of difficulty learning the system. Twenty representative tasks were selected which the pilots could be expected to accomplish on an ' actual flight. These tasks were analyzed using the RAFIV stage model (Sherry, Polson, et al. 2002). This analysis demonstrates that a great burden is placed on remembering complex reformulation of the task to function mapping. 65% of the tasks required retaining one access steps in memory to accomplish the task, 20% required two memorized access steps, and 15% required zero memorized access steps. The probability that a participant would make an access error on the tasks was: two memorized access steps - 74%, one memorized access step - 13%, and zero memorized access steps - 6%. Other factors were analyzed as well, including experience with the system and frequency of use. This completed the picture of a system with many memorized steps causing difficulty with the new system, especially when trying to fine where to access the correct function.

Fennell, Karl↗
DOE OSTI2017

Deep Learning-Based Data Forgery Detection in Automatic Generation Control

Automatic Generation Control (AGC) is a key control system in the power grid. It is used to calculate the Area Control Error (ACE) based on frequency and tie-line power flow between balancing areas, and then adjust power generation to maintain the power system frequency in an acceptable range. However, attackers might inject malicious frequency or tie-line power flow measurements to mislead AGC to do false generation correction which will harm the power grid operation. Such attacks are hard to be detected since they do not violate physical power system models. In this work, we propose algorithms based on Neural Network and Fourier Transform to detect data forgery attacks in AGC. Different from the few previous work that rely on accurate load prediction to detect data forgery, our solution only uses the ACE data already available in existing AGC systems. In particular, our solution learns the normal patterns of ACE time series and detects abnormal patterns caused by artificial attacks. Evaluations on the real ACE dataset show that our methods have high detection accuracy.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Variational multiscale reinforcement learning for discovering reduced order closure models of nonlinear spatiotemporal transport systems

Abstract A central challenge in the computational modeling and simulation of a multitude of science applications is to achieve robust and accurate closures for their coarse-grained representations due to underlying highly nonlinear multiscale interactions. These closure models are common in many nonlinear spatiotemporal systems to account for losses due to reduced order representations, including many transport phenomena in fluids. Previous data-driven closure modeling efforts have mostly focused on supervised learning approaches using high fidelity simulation data. On the other hand, reinforcement learning (RL) is a powerful yet relatively uncharted method in spatiotemporally extended systems. In this study, we put forth a modular dynamic closure modeling and discovery framework to stabilize the Galerkin projection based reduced order models that may arise in many nonlinear spatiotemporal dynamical systems with quadratic nonlinearity. However, a key element in creating a robust RL agent is to introduce a feasible reward function, which can be constituted of any difference metrics between the RL model and high fidelity simulation data. First, we introduce a multi-modal RL to discover mode-dependant closure policies that utilize the high fidelity data in rewarding our RL agent. We then formulate a variational multiscale RL (VMRL) approach to discover closure models without requiring access to the high fidelity data in designing the reward function. Specifically, our chief innovation is to leverage variational multiscale formalism to quantify the difference between modal interactions in Galerkin systems. Our results in simulating the viscous Burgers equation indicate that the proposed VMRL method leads to robust and accurate closure parameterizations, and it may potentially be used to discover scale-aware closure models for complex dynamical systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

PhotonIDs: ML-Powered Photon Identification System for Dark Count Elimination

Reliable single photon detection is the foundation for practical quantum communication and networking. However, today's superconducting nanowire single photon detector(SNSPD) inherently fails to distinguish between genuine photon events and dark counts, leading to degraded fidelity in long-distance quantum communication. In this work, we introduce PhotonIDs, a machine learning-powered photon identification system that is the first end-to-end solution for real-time discrimination between photons and dark count based on full SNSPD readout signal waveform analysis. PhotonIDs ~demonstrates: 1) an FPGA-based high-speed data acquisition platform that selectively captures the full waveform of signal only while filtering out the background data in real time; 2) an efficient signal preprocessing pipeline, and a novel pseudo-position metric that is derived from the physical temporal-spatial features of each detected event; 3) a hybrid machine learning model with near 98% accuracy achieved on photon/dark count classification. Additionally, proposed PhotonIDs ~ is evaluated on the dark count elimination performance with two real-world case studies: (1) 20 km quantum link, and (2) Erbium ion-based photon emission system. Our result demonstrates that PhotonIDs ~could improve more than 31.2 times of signal-noise-ratio~(SNR) on dark count elimination. PhotonIDs ~ marks a step forward in noise-resilient quantum communication infrastructure.

Linne, Karl C. [Chicago U.] (ORCID:000900091870358↗
DOE OSTI2024

Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks

Abstract Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to its reliance on single systems. This constrains output dimensionality and dynamic range, limiting performance to a narrow range of tasks. Here, we engineer a suite of nanomagnetic array physical reservoirs and interconnect them in parallel and series to create a multilayer neural network architecture. The output of one reservoir is recorded, scaled and virtually fed as input to the next reservoir. This networked approach increases output dimensionality, internal dynamics and computational performance. We demonstrate that a physical neuromorphic system can achieve an overparameterised state, facilitating meta-learning on small training sets and yielding strong performance across a wide range of tasks. Our approach’s efficacy is further demonstrated through few-shot learning, where the system rapidly adapts to new tasks.

Science & Technology - Other Topics↗
DOE OSTI2023

Learning continuous models for continuous physics

Abstract Dynamical systems that evolve continuously over time are ubiquitous throughout science and engineering. Machine learning (ML) provides data-driven approaches to model and predict the dynamics of such systems. A core issue with this approach is that ML models are typically trained on discrete data, using ML methodologies that are not aware of underlying continuity properties. This results in models that often do not capture any underlying continuous dynamics—either of the system of interest, or indeed of any related system. To address this challenge, we develop a convergence test based on numerical analysis theory. Our test verifies whether a model has learned a function that accurately approximates an underlying continuous dynamics. Models that fail this test fail to capture relevant dynamics, rendering them of limited utility for many scientific prediction tasks; while models that pass this test enable both better interpolation and better extrapolation in multiple ways. Our results illustrate how principled numerical analysis methods can be coupled with existing ML training/testing methodologies to validate models for science and engineering applications.

97 MATHEMATICS AND COMPUTING↗