Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

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↗
DOE OSTI2020

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↗
DOE OSTI2020

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↗
DOE OSTI2020

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.↗
DOE OSTI2020

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↗
DOE OSTI2022

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↗
DOE OSTI2019

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↗
DOE OSTI2023

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↗
DOE OSTI2024

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↗
DOE OSTI2020

Deep Reinforcement Learning-Based Edge Caching in Wireless Networks

With the purpose to offload data traffic in wireless networks, content caching techniques have recently been studied intensively. Using these techniques and caching a portion of the popular files at the local content servers, the users can be served with less delay. Most of the content replacement policies are based on the content popularity, that depends on the users' preferences. In practice, such information varies over time. Therefore, an approach to determine the file popularity patterns must be incorporated into caching policies. In this context, we study content caching at the wireless network edge using a deep reinforcement learning framework with Wolpertinger architecture. In particular, we propose deep actor-critic reinforcement learning based policies for both centralized and decentralized content caching. For centralized edge caching, we aim at maximizing the cache hit rate. In decentralized edge caching, we consider both the cache hit rate and transmission delay as performance metrics. These proposed frameworks are assumed to neither have any prior information on the file popularities nor know the potential variations in such information. Via simulation results, the superiority of the proposed frameworks is verified by comparing them with other policies, including least frequently used (LFU), least recently used (LRU), and first-in-first-out (FIFO) policies.

42 ENGINEERING↗
DOE OSTI2025

ARM-IRL: Adaptive Resilience Metric Quantification Using Inverse Reinforcement Learning

The resilience of safety-critical systems is gaining importance due to the rise in cyber and physical threats, especially within critical infrastructure. Traditional static resilience metrics may not capture dynamic system states, leading to inaccurate assessments and ineffective responses to cyber threats. This work aims to develop a data-driven, adaptive method for resilience metric learning. We propose a data-driven approach using inverse reinforcement learning (IRL) to learn a single, adaptive resilience metric. The method infers a reward function from expert control actions. Unlike previous approaches using static weights or fuzzy logic, this work applies adversarial inverse reinforcement learning (AIRL), training a generator and discriminator in parallel to learn the reward structure and derive an optimal policy. The proposed approach is evaluated on multiple scenarios: optimal communication network rerouting, power distribution network reconfiguration, and cyber–physical restoration of critical loads using the IEEE 123-bus system. The adaptive, learned resilience metric enables faster critical load restoration in comparison to conventional RL approaches.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Multiple‐Repeated Plasma Surface Treatments for Significantly Improving Bonding Performance of Metal‐Carbon‐Fiber‐Reinforced Thermoplastic Polymer Dissimilar Adhesive Joints

This work investigates how multiple‐repeated plasma surface treatments can significantly enhance adhesively bonded metal‐carbon‐fiber‐reinforced thermoplastic polymer (CFRTP) dissimilar joints, a topic that has been rarely investigated compared to other parameters during the plasma treatment process. By conducting double cantilever beam tests on adhesively bonded AA6061‐carbon‐fiber‐reinforced polyphthalamide (CFRPPA) dissimilar joints, it is shown that the average Mode I specific fracture energy after 20 repetitions of the same plasma treatment, using processing parameters without noticeably changing surface roughness, can be improved and saturated up to almost 2000% compared to non‐treated joints and almost 240% compared to a single plasma treatment commonly used in the literature. The improvement can be attributed to the enhanced chemical bonding at the CFRPPA‐adhesive interface. This study is important for achieving strong bonding performance of CFRTP‐related structural joints using multiple plasma treatments, a simple and effective method.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Effects of Cooling Rates on Self-Reinforced Polyethylene Composites via Multiscale Experimental Characterizations

This study investigates cooling rate effects on self-reinforced polyethylene composites (PE-SRCs), focusing on macroscopic thermal and mechanical properties, and micro- to sub-micron morphologies. Unlike conventional fiber-reinforced composites (e.g., carbon and glass fiber based), cooling rate effects on SRCs remain less studied. PE-SRCs were fabricated from ultrahigh molecular weight polyethylene (UHMWPE) fabric and high-density polyethylene (HDPE) matrix with cooling rates from 0.76°C/min to 425°C/min. Tensile properties, including modulus (~9.5 GPa), strength (~360 MPa), and ultimate elongation (~6%), showed no significant cooling rate dependence. However, thermal analysis revealed melting temperature of HDPE matrix decreased from ~130°C to ~126.5°C with total crystallinity reducing from 84% to 75%. Wide-angle X-ray scattering confirmed decreasing crystallinity but at lower values (67%–59%), as thermal analysis might overestimate crystallinity. Small-angle X-ray scattering showed long period decreased from 24.3 to 17.4 nm, attributed to thinner lamellae and closer packing, suggesting limited crystal growth and faster nucleation. While cooling rates alter melting point and crystalline structures of HDPE matrix, these changes do not translate to substantial impact on macroscale mechanical properties of PE-SRCs. This insensitivity might be related to low interfacial shear strength at PE/PE interfaces, enabling process optimization while maintaining mechanical performance.

Cooling rate↗
DOE OSTI2025

Multiphysics simulation of recent experiments on alkali‐silica reaction expansion in reinforced concrete members

Alkali‐silica reaction (ASR) is an important degradation process that causes volumetric expansion and damage in concrete, and is affected significantly by the local temperature, moisture and stress conditions that often vary across the regions of a structure. Numerical simulation is essential to predict the progression and effects of ASR on the performance of structures. Because of the interactions between thermal and moisture transport and mechanical deformation, it is important for numerical models to represent all these physical phenomena and the coupling between them. Simulations of ASR in reinforced concrete (RC) structures are further complicated by the need to capture interactions between concrete and embedded reinforcing bars. Here, this paper describes the implementation of a scalable, coupled‐physics ASR model for simulating RC structures and assesses the ability of that model to predict ASR‐induced expansion in recent laboratory tests on RC block and beam specimens. These laboratory tests and the simulation approach were selected because of their applicability to RC structural‐scale simulations. This validation study helps builds confidence the ability of this approach to model ASR expansion in large, complex RC structures, which is a current high‐priority need.

36 MATERIALS SCIENCE↗
DOE OSTI2019

Strength of Reinforced Concrete Structures of Hydroelectric Power Plants and Nuclear Power Plants

The reinforced concrete structures of hydroelectric power plants and nuclear power plants differ from civil structures by their massive nature, including high cross-sections, low reinforcement percentage, and the presence of block seams. A decrease in the safety of these structures results when these features are not taken into account. Methods of calculation that take these features into account are proposed.

42 ENGINEERING↗
DOE OSTI2018

Effects of TiB{sub 2} Particle and Short Fiber Sizes on the Microstructure and Properties of TiB{sub 2}-Reinforced Composite Coatings

In this study, particle and short fiber-reinforced titanium matrix composite coatings are prepared via laser in situ technique using (0.5 and 50 μm) TiB{sub 2} and Ti powder as cladding materials. The microstructure and properties of the composite coatings are studied, and the changing mechanism of the microstructure is discussed. The results reveal that particle agglomeration is prone to appear with using fine TiB{sub 2} particles. Decomposition of the particles preferentially occurs with using coarse TiB{sub 2} particles. The cracks and pores on the surface of the coating are formed at a lower laser energy density. With the increase in the laser energy density, cracking on the surface of the coating diminishes, but the coating exhibits depression behavior. The depression extent of the coating using fine TiB{sub 2} particle as the reinforcement is much less than that of the coating using coarse TiB{sub 2} particle. Moreover, the size of the aggregate and the tendency of cracking can be reduced with the increase in Ti addition. Meanwhile, short TiB fiber bundles are formed by the diffusion mechanism of rod aggregate, and randomly oriented TiB short fibers are formed mainly by the dissolution–precipitation mechanism of fine TiB{sub 2} particles. Moreover, the growth of short TiB fibers can be in an alternating manner between B27 and Bf structures. The micro-hardness and wear resistance of the coatings are evidently higher than that of the titanium alloy substrate. The wear resistance of the large size TiB{sub 2} coating is higher than that of the small size TiB{sub 2} coating under the condition of low load.

36 MATERIALS SCIENCE↗
DOE OSTI2024

An innovative heterogeneous transfer learning framework to enhance the scalability of deep reinforcement learning controllers in buildings with integrated energy systems

Deep Reinforcement Learning (DRL)-based control shows enhanced performance in the management of integrated energy systems when compared with Rule-Based Controllers (RBCs), but it still lacks scalability and generalisation due to the necessity of using tailored models for the training process. Transfer Learning (TL) is a potential solution to address this limitation. However, existing TL applications in building control have been mostly tested among buildings with similar features, not addressing the need to scale up advanced control in real-world scenarios with diverse energy systems. This paper assesses the performance of an online heterogeneous TL strategy, comparing it with RBC and offline and online DRL controllers in a simulation setup using EnergyPlus and Python. The study tests the transfer in both transductive and inductive settings of a DRL policy designed to manage a chiller coupled with a Thermal Energy Storage (TES). The control policy is pre-trained on a source building and transferred to various target buildings characterised by an integrated energy system including photovoltaic and battery energy storage systems, different building envelope features, occupancy schedule and boundary conditions (e.g., weather and price signal). The TL approach incorporates model slicing, imitation learning and fine-tuning to handle diverse state spaces and reward functions between source and target buildings. Results show that the proposed methodology leads to a reduction of 10% in electricity cost and between 10% and 40% in the mean value of the daily average temperature violation rate compared to RBC and online DRL controllers. Moreover, online TL maximises self-sufficiency and self-consumption by 9% and 11% with respect to RBC. Conversely, online TL achieves worse performance compared to offline DRL in either transductive or inductive settings. However, offline Deep Reinforcement Learning (DRL) agents should be trained at least for 15 episodes to reach the same level of performance as the online TL. Therefore, the proposed online TL methodology is effective, completely model-free and it can be directly implemented in real buildings with satisfying performance.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2019

Additively manufactured carbon fiber-reinforced composites: State of the art and perspective

While polymer additive manufacturing (AM) has advanced significantly over the past few decades, the limitations in material properties, speed of manufacture, and part size have relegated this technology to the space of rapid prototyping rather than the legitimate manufacture of end-use parts. Carbon fiber offers a low density, a low coefficient of thermal expansion, and high thermal conductivity and is an ideal material for bringing polymer-based AM from the realm of form and fit to that of form, fit, and function. The use of carbon fiber in AM can improve material properties, reduce the time required to manufacture functional parts compared with traditional subtractive technologies, and reduce warping, thereby enabling a larger possible build envelope. Therefore, the addition of carbon fiber to various AM technologies is of increasing interest in academic and industrial communities. This paper examines the work performed in this fast-growing area to date. Specifically, the effects of fiber reinforcement on the structure and mechanical properties of 3D printed parts are investigated within the body of literature. Upper bounds for tensile properties of carbon fiber composites are theoretically evaluated and compared with experimentally measured values. Moreover, current and potential applications of additively manufactured carbon fiber composites in the context of desktop 3D printing and big area AM are discussed. Recent innovations and industry breakthroughs in this field are also examined. This review is intended to organize and synthesize the present body of work surrounding AM of carbon fiber reinforced plastics, identify the most promising technologies, and prescribe viable research and development paths forward to advance AM from the application space of rapid prototyping to that of functional, load-bearing, end-use parts.

36 MATERIALS SCIENCE↗