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 343 records · Page 19

Reinforcement Learning Applied to Cognitive Space Communications

The future of space exploration depends on robust, reliable communication systems. As the number of such communication systems increase, automation is fast becoming a requirement to achieve this goal. A reinforcement learning solution can be employed as a possible automation method for such systems. The goal of this study is to build a reinforcement learning algorithm which optimizes data throughput of a single actor. A training environment was created to simulate a link within the NASA Space Communication and Navigation (SCaN) infrastructure, using state of the art simulation tools developed by the SCaN Center for Engineering, Networks, Integration, and Communications (SCENIC) laboratory at NASA Glenn Research Center to obtain the closest possible representation of the real operating environment. Reinforcement learning was then used to train an agent inside this environment to maximize data throughput. The simulation environment contained a single actor in low earth orbit capable of communicating with twenty-five ground stations that compose the Near-Earth Network (NEN). Initial experiments showed promising training results, so additional complexity was added by augmenting simulation data with link fading profiles obtained from real communication events with the International Space Station. A grid search was performed to find the optimal hyperparameters and model architecture for the agent. Using the results of the grid search, an agent was trained on the augmented training data. Testing shows that the agent performs well inside the training environment and can be used as a foundation for future studies with added complexity and eventually tested in the real space environment.

Schubert, Carson D.↗

Exceptional Thermal Properties of Polymer-Derived Ceramic Composites Reinforced with High Volume Fractions of Boron Nitride Nanotube at Elevated Temperature

We report for the first time the synthesis of boron nitride nanotube (BNNT) reinforced ceramic composites using the polymer derived ceramic (PDC) processing route. The nanocomposites had a BNNT loading of up to 35.4 vol.%. TGA results showed that the nanocomposites have good thermal stability up to 900 oC in air. BNNTs in the nanocomposites survived in an oxidizing environment up to 900 oC, revealing that the nanocomposites can be used for high temperature applications. Thermal conductivity of PDC reinforced with 35.4 vol.% BNNT was measured as 4.123 W/(m·K) at room temperature, which is a 2100 % increase compared to that of pristine PDC. The thermal conductivity value increases with the increase of BNNT content. A thermal conductivity percolation phenomenon appeared when the BNNT content increased to 36±5 vol.%. The results of this study showed that BNNTs could effectively improve the thermal conductivity of PDC materials. BNNT reinforced PDC could be used as thermal structural materials in a harsh environment at the temperature up to 900 deg C.

Yujun Jia↗

Method of producing particulate-reinforced composites and composties produced thereby

A process for producing particle-reinforced composite materials through utilization of an in situ reaction to produce a uniform dispersion of a fine particulate reinforcement phase. The process includes forming a melt of a first material, and then introducing particles of a second material into the melt and subjecting the melt to high-intenisty acoustic vibration. A chemical reaction initiates between the first and second materials to produce reaction products in the melt. The reaciton products comprise a solide particulate phase, and the high-intensity acoustic vibration fragments and/or separates the reaction products into solid particles that are dispersed in the melt and are smaller than the particles of the second material. Also encompassed are particles-reinforced composite materials produced by such a process.

36 MATERIALS SCIENCE↗

Method of producing particulate-reinforced composites and composites produced thereby

A process for producing particle-reinforced composite materials through utilization of an in situ reaction to produce a uniform dispersion of a fine particulate reinforcement phase. The process includes forming a melt of a first material, and then introducing particles of a second material into the melt and subjecting the melt to high-intensity acoustic vibration. A chemical reaction initiates between the first and second materials to produce reaction products in the melt. The reaction products comprise a solid particulate phase, and the high-intensity acoustic vibration fragments and/or separates the reaction products into solid particles that are dispersed in the melt and are smaller than the particles of the second material. Also encompassed are particle-reinforced composite materials produced by such a process.

36 MATERIALS SCIENCE↗

Method of producing particulate-reinforced composites and composites produced thereby

A process for producing particle-reinforced composite materials through utilization of an in situ reaction to produce a uniform dispersion of a fine particulate reinforcement phase. The process includes forming a melt of a first material, and then introducing particles of a second material into the melt and subjecting the melt to high-intensity acoustic vibration. A chemical reaction initiates between the first and second materials to produce reaction products in the melt. The reaction products comprise a solid particulate phase, and the high-intensity acoustic vibration fragments and/or separates the reaction products into solid particles that are dispersed in the melt and are smaller than the particles of the second material. Also encompassed are particle-reinforced composite materials produced by such a process.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Additive manufacturing of short and mixed fibre-reinforced polymer

Additive manufacturing of a fiber-reinforced polymer (FRP) product using an additive manufacturing print head; a reservoir in the additive manufacturing print head; short carbon fibers in the reservoir, wherein the short carbon fibers are randomly aligned in the reservoir; an acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin in the reservoir, wherein the short carbon fibers are dispersed in the acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin; a tapered nozzle in the additive manufacturing print head operatively connected to the reservoir, the tapered nozzle produces an extruded material that forms the fiber-reinforced polymer product; baffles in the tapered nozzle that receive the acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin with the short carbon fibers dispersed in the acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin; and a system for driving the acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin with the short carbon fibers dispersed in the acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin from the reservoir through the tapered nozzle wherein the randomly aligned short carbon fibers in the acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin are aligned by the baffles and wherein the extruded material has the short carbon fibers aligned in the acrylate, methacrylate, epoxy, cyanate ester or isocyanate resin that forms the fiber-reinforced polymer product.

36 MATERIALS SCIENCE↗

Graphene reinforced materials and related methods of manufacture

Graphene reinforced materials and related methods of manufacture are provided. The graphene reinforced materials include graphene sheet or scroll, graphene-polymer sheet or scroll, and graphene-carbon sheet or scroll, each having material properties that are attractive across a broad range of applications and industries. The graphene reinforced materials generally include monolayer or multilayer graphene that is synthesized by annealing a catalyst substrate within a CVD chamber, introducing a hydrocarbon gas as a carbon source with the CVD chamber to form a layer of graphene on the catalyst substrate, detaching the catalyst substrate from the layer of graphene, and rolling the layer of graphene onto itself to form a scroll, optionally with the addition of a polymer layer or carbonized layer on the graphene layer.

36 MATERIALS SCIENCE↗

Enforcing constraints for time series prediction in supervised, unsupervised and reinforcement learning

We assume that we are given a time series of data from a dynamical system and our task is to learn the flow map of the dynamical system. We present a collection of results on how to enforce constraints coming from the dynamical system in order to accelerate the training of deep neural networks to represent the flow map of the system as well as increase their predictive ability. In particular, we provide ways to enforce constraints during training for all three major modes of learning, namely supervised, unsupervised and reinforcement learning. In general, the dynamic constraints need to include terms which are analogous to memory terms in model reduction formalisms. Such memory terms act as a restoring force which corrects the errors committed by the learned flow map during prediction. For supervised learning, the constraints are added to the objective function. For the case of unsupervised learning, in particular generative adversarial networks, the constraints are introduced by augmenting the input of the discriminator. Finally, for the case of reinforcement learning and in particular actor-critic methods, the constraints are added to the reward function. In addition, for the reinforcement learning case, we present a novel approach based on homotopy of the action-value function in order to stabilize and accelerate training. We use numerical results for the Lorenz system to illustrate the various constructions.

Stinis, Panagiotis↗

Study on Fracture of Fiber-Reinforced Polymeric Composites Using Spiral Notch Torsion Test

Fiber-reinforced polymer-matrix composites have been widely applied in various areas due to their excellent mechanical properties. In this study, carbon fiber-reinforced polymer-matrix composites and glass fiber-reinforced polymer-matrix composites failure tests under quasi static torsion have been demonstrated by using spiral notch torsion test methodology. Three types of cylindrical specimens with different fiber orientations were prepared and tested. For both composites, after increase stage, A type exhibited limited stress variations before the sudden failure, whereas B type showed gradual failure with torque drops. Displacement contours, stress contours and energy release rates were acquired using the anisotropic elastic finite element models. Microscopic characterization exhibited that the failure of A type occurred along interfaces between fibers and matrices, whereas circular cracks in B type propagated alternatively between polymeric matrices and interfaces. Type C failure is similar to type A whereas with a curvature observed on the fracture surface.

Du, Fen↗

Graphene reinforced materials and related methods of manufacture

Graphene reinforced materials and related methods of manufacture are provided. The graphene reinforced materials include graphene sheet or scroll, graphene-polymer sheet or scroll, and graphene-carbon sheet or scroll, each having material properties that are attractive across a broad range of applications and industries. The graphene reinforced materials generally include monolayer or multilayer graphene that is synthesized by annealing a catalyst substrate within a CVD chamber, introducing a hydrocarbon gas as a carbon source with the CVD chamber to form a layer of graphene on the catalyst substrate, detaching the catalyst substrate from the layer of graphene, and rolling the layer of graphene onto itself to form a scroll, optionally with the addition of a polymer layer or carbonized layer on the graphene layer.

Vlassiouk, Ivan V.↗

Integrating Overhead Camera Imagery with Reinforcement Learning to Improve Fuel Economy Through Adaptive Traffic Control

Overhead cameras have been deployed for some time as a sensor for traffic control, with many advantages over conventional inductive loop sensors in terms of robustness, ease of installation, and simplicity with respect to maintenance. We explore the utility of such imagery (in particular, fisheye lens cameras) for intelligent traffic control in real-time using reinforcement learning, with a goal of improving fuel economy for the overall intersection and grid of intersections. We summarize our initial work in data collection and approach to ascertain the ability to visually sense vehicular fuel consumption using real-world data. We then describe our deep reinforcement learning topology to test adaptive control informed by the camera capabilities. Next, we tested the proof-of-concept through a variety of simulation scenarios using the Simulation of Urban Mobility (SUMO) traffic simulator, which included different estimates on vehicle classifications, different traffic distributions, and different traffic densities. Six different control policies were tested ranging from simple timing, to heuristic visual-based methods, to actual policies learned via the reinforcement learning approach. Our results demonstrate the feasibility of the approach for controlling traffic lights for better fuel efficiency based on visual vehicle estimates from commercial, fisheye lens cameras.

Karnowski, Thomas↗

Reinforced preform and method for molding

A reinforced preform includes a sheet of reinforced material having opposed first and second edges, with each edge having a respective first connection point located therealong. The preform also includes first and second tethers, with each tether being attached at a respective first end thereof to a respective one of the first connection points and having a respective second end thereof terminating in at least one of: a respective loop tied at the respective second end, a respective knot tied at the respective second end, a respective graspable member to which the respective second end is connected, and an attachment to a respective second connection point located along a perimeter of the sheet. A method and mold for molding a reinforced preform are also disclosed.

36 MATERIALS SCIENCE↗

The trends and challenges of fiber reinforced additive manufacturing

In the last few years, utilizing fiber reinforced additive manufacturing (FRAM)-based components in several industries has become quite popular. Compared to conventional AM technologies, FRAM offered complementary solutions to their needs. In general, fibers have been traditionally used in many manufacturing processes for various reasons. However, using conventional methods, there are obstacles in obtaining the desired complex geometries and low setup costs. AM offers possible avoidance of these limitations. Shape complexity, infill density, and manufacturing lead times are no longer barriers. Bridging AM with fiber reinforced materials offers a vast opportunity for lightweight and strong parts. Depending on the affinity, fibers with different structures can be mixed with different matrix materials and, thus, create stronger parts with improved mechanical properties. Process parameters like raster angle, infill speed, layer thickness, and nozzle temperature also strongly impact physical properties of FRAM products and are considered carefully. FRAM-based components are used in many industries such as aerospace, motorsports, and biomedicine, where the weight, strength, and complexity of parts are critical. Hence, numerous industrial companies and research facilities are investigating the implementation and adaptation of FRAM to their requirements. Studies are generally conducted on new materials, new FRAM technologies, the effect of fiber orientations and fraction on the performance of parts, improving the printing parameters, and other subjects. Furthermore, this study reports the current trends and challenges that FRAM is bringing to AM ecosystem.

36 MATERIALS SCIENCE↗

A micromechanical approach to elastic and viscoelastic properties of fiber reinforced concrete

Some aspects of the constitutive behavior of fiber reinforced concrete (FRC) are investigated within a micromechanical framework. Special emphasis is put on the prediction of creep of such materials. The linear elastic behavior is first examined by implementation of a Mori-Tanaka homogenization scheme. The micromechanical predictions for the overall stiffness prove to be very close to finite element solutions obtained from the numerical analysis of a representative elementary volume of FRC modeled as a randomly heterogeneous medium. The validation of the micromechanical concepts based on comparison with a set of experiments, shows remarkable predictive capabilities of the micromechanical representation. The second part of the paper is devoted to non-ageing viscoelasticity of FRC. Adopting a Zener model for the behavior of the concrete matrix and making use of the correspondence principle, the homogenized relaxation moduli are derived analytically. The validity of the model is established by mean of comparison with available experiment measurements of creep strain of steel fiber reinforced concrete under compressive load. Finally, the model predictions are compared to those derived from analytical models formulated within a one-dimensional setting.

36 MATERIALS SCIENCE↗

Orientation factor and number of fibers at failure plane in ring-type steel fiber reinforced concrete

Considering the probabilistic distributions of fibers in ring-type steel fiber reinforced concrete, the orientation factor and the number of ring-type steel fibers crossing the failure plane were theoretically derived as a function of fiber geometry, specimen dimensions, and fiber volume fraction. A total number of 24 specimens were tested incorporating different fiber types, specimen geometry, and fiber volume fractions of 0.2% and 0.4%: 5 beams and 5 panels containing straight steel fibers; and 6 beams and 8 panels containing ring-type steel fibers. Measurements were made to assess the number of fibers at fractured surfaces of steel fiber reinforced concrete. The developed theoretical expressions reasonably predicted the orientation factor and the number of ring-type steel fibers at failure plane: the average and the standard deviation for the ratios of the test to theory were 1.03 and 0.26, respectively. Theoretical investigations and comparisons were made for the values of orientation factor and the number of fibers at failure plane for straight steel fibers and ring-type steel fibers.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Inverse reinforcement learning control for building energy management

Reinforcement learning (RL) based control is widely considered a promising approach in building automation and control as it has demonstrated the potential to deal with complex objectives in adjacent domains like robotics, autonomous vehicles, gaming applications, and advertisement recommendations. When applied to any environment, model-free RL learns to improve its control performance over time without requiring a control model, by receiving and then analyzing feedback from the building environment after each control action. Operational objectives are becoming increasingly complex through the simultaneous consideration of thermal comfort, carbon emissions, grid services, and indoor air quality. In this context, conventional rule-based control approaches are proving sub-optimal, mostly heuristic, and inadequate. The model-free and self learning nature of RL appears promising and attractive as it may address the scalability issues associated with advanced control approaches. However, it suffers from long training times and unstable control behavior during the early stages of its learning process, which makes it unsuitable to be applied directly to buildings. This paper addresses these issues using an inverse reinforcement learning approach (IRL), a technique utilized to learn the objective of a controller agent which is considered an expert in its respective domain. Here, we consider a rule-based control as the expert demonstrator. IRL is different from a direct imitation (i.e., direct mapping of states to actions) of control actions as it tries to find the underlying intent of an expert's policy, providing the controller with a better-generalized policy for unseen states or environments with slightly different dynamics. This approach propels the RL controller's policy to levels similar to or better than that of a rule-based policy before it starts learning by interacting with the building. This makes RL for building energy management applications more practical as it prevents the erratic and exploratory behavior in the initial training period, simultaneously speeding up the learning process when compared to applying an untrained RL agent directly to a building environment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Effects of processing temperature, pressure, and fiber volume fraction on mechanical and morphological behaviors of fully-recyclable uni-directional thermoplastic polymer-fiber-reinforced polymers

This work explores a type of composite called thermoplastic polymer-fiber-reinforced polymers (PFRPs), often referred to as self-reinforced composites (SRCs). A representative PFRP was exemplified using unidirectional (UD) ultra-high-molecular-weight polyethylene (UHMWPE) fibers embedded in a high-density polyethylene (HDPE) matrix. The effects of compression molding temperature and pressure on the mechanical and morphological behaviors of the filament-wound PFRPs with various fiber volume fractions (V f ) were experimentally investigated. The results elucidate the evolution of morphologies and tensile properties of the PFRPs due to thermal melting, fiber misalignment from pressure, and (V f )-induced structural variance, which has not been comprehensively reported yet. The highest specific tensile strength and modulus of the PFRP laminae reach 600 MPa/(g/cm 3 ) and 31 GPa/(g/cm 3 ), respectively. These properties are comparable to glass-/aramid-fiber-reinforced polymers (GFRPs, GFRTPs, AFRPs, and AFRTPs), with PFRPs exhibiting better ductility (specific strain at peak load ≈ 4%/(g/cm 3 )) than other common polymer composites. The motivation for this work was the high recyclability of PFRPs, which can be recycled by melting both the fibers and the matrix, and then reshaped them for re-manufacturing composites to maximize the efficiency in material reuse. This process simplifies the implementation of closed-loop recycling, re-manufacturing, and reuse to support sustainability in composites. This work aims to contribute to advancing thermoplastic PFRPs for their potential applications in various industries.

36 MATERIALS SCIENCE↗

Numerical Study on Mixed-mode Fracture in Reinforced Concrete

The object of this work is to model the propagation of fracture in mixed-mode in lightly reinforced concrete beams. When a notched beam does not have enough shear reinforcement, fracture can initiate and propagate unstably and lead to failure through diagonal tension. In order to study this phenomenon numerically, a model capable of dealing with both static and dynamic crack propagation as well as the natural transition of those two regimes is necessary. We adopt a cohesive model for concrete fracture and an interface model for the deterioration between concrete and steel re-bar, both combined with an insertion algorithm. The static process is solved by dynamic relaxation (DR) method together with a modified technique to enhance convergence rate. The same DR method is used to detect a dynamic process and switch to a dynamic calculation. The numerically obtained load-displacement curves, load-CMOD curves and crack patterns fit reasonably well with their experimental counterparts, having in mind that we fed the calculations only with parameters measured experimentally.

36 MATERIALS SCIENCE↗