Search NASA⌕ Search

SEARCH · Search NASA

Results for “REINFORCEMENT”

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 217 records · Page 12

The influence of exposure to early-life adversity on agency-modulated reinforcement learning

Agency beliefs influence how humans learn from different contexts and outcomes. Research demonstrates that stressors, such as exposure to early-life adversity (ELA), are associated with both agency beliefs and learning, but how these processes interact remains unclear. The current study investigated whether exposure to ELA influences agency and interacts with reinforcement learning in adults. Replicating prior behavioral and computational work, ELA resulted in decreased learning, while increased adversity severity was associated with decreased latent agency beliefs. These findings suggest that exposure to adversity in childhood has a nuanced impact on reinforcement learning and agency beliefs in adulthood.

Neurosciences & Neurology↗

Integrated Routing and Traffic Signal Control for CAVs via Reinforcement Learning Approach

Incorporating Connected and Automated Vehicles (CAVs) into urban traffic networks presents opportunities and challenges for traffic management systems. This paper aims to develop an integrated routing and traffic signal control system designed explicitly for CAVs, utilizing a Reinforcement Learning (RL) approach. The objective is to enhance traffic flow and improve overall transportation efficiency in the controlled areas. We propose an innovative framework that employs the Deep Reinforcement Learning (DRL) algorithm, especially the Deep Q-network (DQN), to dynamically adjust the number of vehicles in the routes and the duration of traffic signals. Our simulation results demonstrate that a DQN agent successfully optimizes the number of vehicles in the routes and traffic signal timings of traffic signal controllers, eventually reducing total travel time. The study illustrates the potential usage of RL-based systems in managing routing and traffic signals for CAVs, offering a promising opportunity for future urban traffic management strategies.

Park, Jiho [New York University]↗

Federated Deep Reinforcement Learning for Decentralized VVO of BTM DERs

The future of grid control requires a hybrid approach combining centralized and decentralized methods to fully utilize the potential of smart edge devices with artificial intelligence (AI) capabilities. This paper aims to develop and evaluate a federated deep reinforcement learning (FDRL) framework for decentralized adaptive volt-var optimization (VVO) of behind-the-meter (BTM) distributed energy resources (DERs). First, this paper models a single deep reinforcement learning (DRL) agent using the Markov Decision Process (MDP) framework for decentralized adaptive VVO of BTM DERs. Two DRL algorithms, soft actor-critic (SAC) and twin-delayed deep deterministic policy gradient (TD3), are compared for their effectiveness in optimizing VVO. Results show that TD3 outperforms SAC, achieving a 71.3% improvement in mean reward. Finally, the DRL agent is deployed within the FDRL framework, using the Flower platform, to enhance learning, provide adaptive control, and ensure data privacy for BTM DERs.

Ravi, Abhijith↗

Quantum Reinforcement Learning for Volt-VAR Control in Power Distribution Systems

Volt-VAR control (VVC) is crucial in active distribution networks for optimizing voltage profiles and minimizing network losses. While traditional deep reinforcement learning (DRL) algorithms exhibit promise for VVC, they often require extensive computational resources to handle such a high-dimensional problem. As a potential solution, quantum reinforcement learning (QRL) algorithms integrate the computational capabilities of quantum computing into the DRL framework. However, existing QRL algorithms struggle with complex VVC problems due to the limitations of current quantum hardware. To bridge this gap, this paper proposes an innovative QRL algorithm featuring an end-to-end architecture that integrates a classical autoencoder, variational quantum circuits (VQCs), and classical post-processing layers. This design efficiently compresses high-dimensional grid states, enabling VQCs to leverage quantum advantages while producing multiple control device outputs tailored for VVC tasks. Numerical studies on three representative distribution systems verify the effectiveness and scalability of the proposed QRL algorithm, and demonstrate its enhanced performance over classical approaches with only approximately 1% of the parameters. Additionally, the robustness of our developed algorithm is validated through noisy quantum environments.

97 MATHEMATICS AND COMPUTING↗

Deep Reinforcement Learning Based Control of Wind Turbines for Fast Frequency Response

In order to fulfill vital auxiliary grid services, such as load regulation, spin and non-spin reserve provision, and frequency support during emergencies, there is often a requirement for certain wind farms to operate in de-loaded modes. Leveraging the swift response capabilities of wind farms, this study demonstrates that reserving power in de-loaded modes can significantly enhance power grid stability and reliability during system contingencies. Controlling wind farms optimally for frequency support is intricate due to the nonlinearity of models and controllers and the complexity of wind farm interactions with power systems. Here, to address this challenge, this paper introduces a novel approach that integrates wind turbines into reinforcement learning-based solutions for frequency response. This innovative methodology utilizes the state-of-the-art reinforcement learning algorithm known as the surrogate-gradient-based evolutionary strategy. The proposed learning-based algorithm provides continuous control of wind farm output to rapidly stabilize system frequency and prevent unnecessary trips of under-frequency load shedding relays. To facilitate efficient training, parallel computing techniques are employed. The proposed methodology is evaluated on a modified IEEE-39 bus system, and simulation results reveal its efficacy in reliably supporting power system frequency and preventing the need for unnecessary load shedding.

Gao, Wei [Argonne National Laboratory (ANL), Argon↗

A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching

Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.

99 GENERAL AND MISCELLANEOUS↗

Flax fiber-reinforced fatty acid vitrimer biocomposite with enhanced chemical recyclability

Here, this study unveils a sustainable, easily recyclable biocomposite, leveraging the dynamic nature of covalently adaptive bonds in a vitrimer matrix. The fabrication involved a fatty acid-derived vitrimer as the polymer matrix and multi-layered, nonwoven flax mat as reinforcing scaffold. The incorporation of these fibers significantly improved the mechanical performance of the vitrimer matrix uniformly. The ester-based covalently adaptive network plays a crucial role in enabling exceptional fiber-matrix bonding, as well as recyclability. The vitrimer matrix dissolves in ethylene glycol through transesterification, facilitating complete material recovery and biocomposite recycling without compromising the original properties of the matrix and reinforcing fibers.

36 MATERIALS SCIENCE↗

Overview of Elastic Orthotropic Fiber Reinforced Polymer Modular Damage Model for Library of Advanced Materials for Engineering (LAMÉ)

This memo includes the documentation sections for the Library of Advanced Materials for Engineering (LAMÉ) manual for a fiber reinforced polymer composite damage model (Elastic_Orthotropic_FRP_Modular_Damage) in advance of the next Sierra/SM and LAMÉ release consistent with the transition of the model from development to a production capability. This new model capability provides both a set of physically based orthotropic damage criteria as well as orthotropic material softening for woven fiber reinforced polymer composite materials. The documentation sections include short sections on theory, implementation, verification, and user guidance to prescribe the model in a Sierra/SM input file.

36 MATERIALS SCIENCE↗

Tailored Silicone Network Architecture for Ultimate Mechanical Reinforcement

Hydrosilylation cured silicone elastomers are subject to reaction inefficiency, leading to incomplete and non-uniform crosslink networks, restricting the potential of mechanical reinforcement. This work investigates pre-synthesized, functional PDMS architectures as additives to improve ultimate mechanical performance relative to conventional single-step curing. Three custom, functional structures were prepared: a partially crosslinked PDMS scaffold (Structure A), a bottle-brush PDMS (Structure B), and a star-shaped PDMS derived from an MQ resin (Structure C). Rheological characterization was used to identify the ultimate design space and proper stoichiometric ratio for Structure A, and confirm successful formation of all structures for suitable incorporation into a base silicone formulation at 30wt%. Mechanical tests indicated that all three structures increased in ultimate tensile strength relative to their single-step counterparts, with Structure A providing additional improvements to toughness (432 vs. 258 kJ/m3) and ultimate elongation (158 vs. 115%). Furthermore, Structure B remained very soft in the unfilled state, while Structure C provided hardness (23 vs. 18 Shore A) and stiffness (780 vs. 420 kPa Young’s modulus) increases. In silica filled systems, Structure A retained increased strength but reduced elongation, while Structure B indicated strong reinforcement in terms of strength, toughness, and stiffness. Thermal analysis on the cure profiles of these materials suggested that pre-formation of network architectures enable a more complete reaction than a single-step process (15.9 vs. 15.1 J/g). Ultimately, these results indicate that tailoring PDMS architecture before the final cure can improve ultimate mechanical properties via improved network development in silicone elastomers. Furthermore, this work offers a promising strategy for designing higher-performance, more tunable silicone formulations.

36 MATERIALS SCIENCE↗

Post-Deployment Characterization of Glass Fiber-Reinforced Thermoset and Thermoplastic Composite Tidal Turbine Blades

In 2021, the National Renewable Energy Laboratory (NREL) supported Verdant Power with the most successful tidal energy deployment in U.S. history. Three of their Gen5d 5 m turbines were deployed as part of the Roosevelt Island Tidal Energy project. Initially, the three rotors initially deployed were manufactured from glass fiber-reinforced epoxy composites. Midway through the deployment, one rotor was replaced with one manufactured at NREL. The new rotor utilized a novel infusible thermoplastic resin system. Since the deployment, one epoxy rotor and one thermoplastic rotor were returned to NREL for continued materials and manufacturing research. The two rotors underwent full-scale structural testing before being sectioned and cut into specimens for a variety of manufacturing quality tests, thermomechanical characterization, and evaluation of material performance in marine environments to understand the key differences between the fiberglass-reinforced epoxy and Elium composites used for the respective rotors. Matrix burn-off tests showed that the Elium blades had a considerably higher fiber volume fraction compared to the epoxy blades (61% vs. 49%). Environmental aging of the specimens showed that the epoxy laminates absorbed more water over the conditioning period; however, it was determined that the Elium laminates had higher diffusion coefficients, so they initially absorbed water faster. Finally, one full epoxy blade and one full Elium blade were conditioned at ambient temperatures for up to 11 months, while periodic mass measurements were taken. The datasets were extrapolated to assume a full 20-year operational life span, and it was determined that the blades would not reach full saturation during that time span.

composite manufacturing↗

Pipe joints reinforced in place with fitted aluminum sleeves

Installation of an aluminum sleeve, using specially designed tools, reinforces solder- sealed ferrule joints in installed small-diameter aluminum tubing. Tubing joints reinforced by this method withstand considerable torsional tensional, and vibrational stresses at moderately elevated temperatures.

Cortez, I., Jr.↗

Improved method for producing metal-reinforced ceramics

Vacuum impregnation process produces metal-reinforced ceramics with only 3 percent void space volumes. Method may be used to produce metal-reinforced ceramics for high temperature or structural applications such as furnace supports and armor.

Landingham, R. L.↗

Compressive behavior of titanium alloy skin-stiffener specimens selectively reinforced with boron-aluminum composite

A method of selectively reinforcing a conventional titanium airframe structure with unidirectional boron-aluminum composite attached by brazing was successfully demonstrated in compression tests of short skin-stiffener specimens. In a comparison with all-titanium specimens, improvements in structural performance recorded for the composite-reinforced specimens exceeded 25 percent on an equivalent-weight basis over the range from room temperature to 700 K (800 F) in terms of both initial buckling and maximum strengths. Performance at room temperature was not affected by prior exposure at 588 K (600 F) for 1000 hours in air or by 400 thermal cycles between 219 K and 588 K (-65 F and 600 F). The experimental results were generally predictable from existing analytical procedures. No evidence of failure was observed in the braze between the boron-aluminum composite and the titanium alloy.

Herring, H. W.↗

Boron epoxy reinforced structural sections.

A NASA Research program on the development of lightweight aluminum stiffening sections will be reviewed. The sections under investigation are hollowed extrusions which have been reinforced with boron epoxy by means of a fiber infiltration scheme being developed by Avco. Advantages of this type of construction are cost, environmental stability, manufacturing flexibility, and simplicity in joining. Present studies are focused on developing and verifying structural concepts for stiffener sections for compression panels. Results of analytical studies to size boron reinforcement will be discussed. Compression test results on stiffener sections will be presented and the design of a large compression panel will be reviewed. Results from compression panel efficiency studies indicate that panels with infiltrated stiffeners may be as much as 25% lighter than comparable all aluminum panels.-

Roy, P. A.↗

Design, analysis, and test of a boron/epoxy reinforced airframe.

The airframe of a large helicopter generally requires additional stiffening for dynamic tuning to prevent resonance with the rotor vibratory forces. Investigations showed that aluminum stringers reinforced with boron/epoxy offered substantial weight saving for the CH54B Skycrane helicopter to achieve the required airframe stiffness. As a result, a program has been conducted under a NASA contract to design, test, and evaluate the static and fatigue strength characteristics of the composite reinforcement. The results of this phase of the effort will be reported in this paper.

Rich, M. J.↗

Experimental and theoretical investigation of stress wave attenuation in fiber reinforced composites.

The propagation of an initialrcidrical pressure pulse through a linear elastic fiber reinforced composite medium is analysed, both experimentally and analytically. In the experiment, tests were performed on plates with single and multiple circular inclusions embedded in a matrix of lower characteristic impedance. Sharp compression pulses were generated at an edge of the plate. Strain gages were mounted on various positions of the plate to determine the attenuation of the transient stress in the fiber reinforced composite. The qualitative analytical treatment is based on the methods of propagating stress discontinuities. Computer programs were written to numerically determine the changes in the shape of the leading wave front and the stresses immediately behind it. Experimental results for the attenuation of stress wave on steel-aluminum and steel-brass fiber-matrix composites compared very well with the computed analytical results when the applied pressure is generated by small explosive charges. The results did not compare well when the applied pressure is generated by projectile impact.

Yang, J. C. S.↗

Design synthesis of a boron/epoxy reinforced metal shear web.

An advanced composite shear web design concept has been developed for the Space Shuttle Orbiter main engine thrust beam structure. Various web concepts were synthesized by a computer-aided adaptive random search procedure. A practical concept is identified having a titanium-clad, boron/epoxy plate with vertical boron/epoxy reinforced stiffeners. Baseline composite and titanium shear resistant designs are compared; the composite concept is 28% lighter than the titanium web. Element test results show the metal cladding effectively reinforces critical composite load transfer and fastener hole areas making the composite web concept practical for other shear structure applications.-

Laakso, J. H.↗

Moisture effects on the high-temperature strength of fiber-reinforced resin composites.

Under NAS 8-27435, the Convair Aerospace Division of General Dynamics and their subcontractor, Hercules Incorporated, have conducted studies on the effects of moisture on the properties of fiber-reinforced resin composites and on the epoxy resins presently used in advanced composites. Data are presented on the resins and composites subjected to varying time/temperature/humidity or time/temperature/water-boil exposures. The effects of moisture on matrix, reinforcement, and fiber/resin interface are discussed and supported by experimental test data.

Hertz, J.↗