Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning dynamics”

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 1,297 records · Page 72
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Neural network approaches for parameterized optimal control

Here, we consider numerical approaches for deterministic, finite-dimensional optimal control problems whose dynamics depend on unknown or uncertain parameters. We seek to amortize the solution over a set of relevant parameters in an offline stage to enable rapid decision-making and be able to react to changes in the parameter in the online stage. To tackle the curse of dimensionality arising when the state and/or parameter are high-dimensional, we represent the policy using neural networks. We compare two training paradigms: First, our model-based approach leverages the dynamics and definition of the objective function to learn the value function of the parameterized optimal control problem and obtain the policy using a feedback form. Second, we use actor-critic reinforcement learning to approximate the policy in a data-driven way. Using an example involving a two-dimensional convection-diffusion equation, which features high-dimensional state and parameter spaces, we investigate the accuracy and efficiency of both training paradigms. While both paradigms lead to a reasonable approximation of the policy, the model-based approach is more accurate and considerably reduces the number of PDE solves.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1992

Adding dynamic rules to self-organizing fuzzy systems

This paper develops a Dynamic Self-Organizing Fuzzy System (DSOFS) capable of adding, removing, and/or adapting the fuzzy rules and the fuzzy reference sets. The DSOFS background consists of a self-organizing neural structure with neuron relocation features which will develop a map of the input-output behavior. The relocation algorithm extends the topological ordering concept. Fuzzy rules (neurons) are dynamically added or released while the neural structure learns the pattern. The DSOFS advantages are the automatic synthesis and the possibility of parallel implementation. A high adaptation speed and a reduced number of neurons is needed in order to keep errors under some limits. The computer simulation results are presented in a nonlinear systems modelling application.

Buhusi, Catalin V.↗
NASA NTRS1992

Cooperative intelligent robotics in space III; Proceedings of the Meeting, Boston, MA, Nov. 16-18, 1992

The present volume on cooperative intelligent robotics in space discusses sensing and perception, Space Station Freedom robotics, cooperative human/intelligent robot teams, and intelligent space robotics. Attention is given to space robotics reasoning and control, ground-based space applications, intelligent space robotics architectures, free-flying orbital space robotics, and cooperative intelligent robotics in space exploration. Topics addressed include proportional proximity sensing for telerobots using coherent lasar radar, ground operation of the mobile servicing system on Space Station Freedom, teleprogramming a cooperative space robotic workcell for space stations, and knowledge-based task planning for the special-purpose dextrous manipulator. Also discussed are dimensions of complexity in learning from interactive instruction, an overview of the dynamic predictive architecture for robotic assistants, recent developments at the Goddard engineering testbed, and parallel fault-tolerant robot control.

Erickson, Jon D.↗
NASA NTRS1992

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms and a supervised computational neural network, a dynamic multilayered perception trained with the cascade correlation learning algorithm. Initial clinical results are presented on both normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. However, for a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed.

Hall, Lawrence O.↗
NASA NTRS1996

Overview of HATP Experimental Aerodynamics Data for the Baseline F/A-18 Configuration

Determining the baseline aerodynamics of the F/A-18 was one of the major objectives of the High-Angle-of-Attack Technology Program (HATP). This paper will review the key data bases that have contributed to our knowledge of the baseline aerodynamics and the improvements in test techniques that have resulted from the experimental program. Photographs are given highlighting the forebody and leading-edge-extension (LEX) vortices. Other data representing the impact of Mach and Reynolds numbers on the forebody and LEX vortices will also be detailed. The level of agreement between different tunnels and between tunnels and flight will be illustrated using pressures, forces, and moments measured on a 0.06-scale model tested in the Langley 7- by 10-Foot High Speed Tunnel, a 0.16-scale model in the Langley 30- by 60-Foot Tunnel, a full-scale vehicle in the Ames 80- by 120-Foot Wind Tunnel, and the flight F/A-18 High Alpha Research Vehicle (HARV). Next, creative use of wind tunnel resources that accelerated the validation of the computational fluid dynamics (CFD) codes will be described. Lastly, lessons learned, deliverables, and program conclusions are presented.

Hall, Robert M.↗
NASA NTRS2003

Free-Flowing Solutions for CFD

Licensed to over 1,500 customers worldwide, an advanced computational fluid dynamics (CFD) post-processor with a quick learning curve is consistently providing engineering solutions, with just the right balance of visual insight and hard data. FIELDVIEW is the premier product of JMSI, Inc., d.b.a. Intelligent Light, a woman-owned, small business founded in 1994 and located in Lyndhurst, New Jersey. In the early 1990s, Intelligent Light entered into a joint development contract with a research based company to commercialize the post-processing FIELDVIEW code. As Intelligent Light established itself, it purchased the exclusive rights to the code, and structured its business solely around the software technology. As a result, it is enjoying profits and growing at a rate of 25 to 30 percent per year. Advancements made from the earliest commercial launch of FIELDVIEW, all the way up to the recently released versions 8 and 8.2 of the program, have been backed by research collaboration with NASA's Langley Research Center, where some of the world's most progressive work in transient (also known as time-varying) CFD takes place.

Source record↗
DOE OSTI2018

The Effects of Market Concentration on Residential Solar PV Prices: Competition, Installer Scale, and Soft Costs

Competition among residential solar photovoltaic (PV) installers may reduce PV price markups and yield lower prices. At the same time, competition may reduce installer experience and opportunities for cost reductions through learning-by-doing and economies of scale. These dynamics suggest that PV non-hardware or 'soft' costs and installed prices depend on the distribution of market shares among installers, also known as market structure. This study leverages a rich data set of 226,769 residential PV systems to examine the relationship between market structure, soft costs, and PV prices. The results show that PV prices are lower, on average, in more concentrated markets, i.e., markets with fewer installers or where a subset of installers holds a large market share. The study provides evidence that this relationship is non-linear, such that prices are minimized in markets with an optimal balance of the benefits of market concentration and the benefits of competition.

14 SOLAR ENERGY↗
DOE OSTI2021

DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology

Abstract The proper biogenesis, morphogenesis, and dynamics of subcellular organelles are essential to their metabolic functions. Conventional techniques for identifying, classifying, and quantifying abnormalities in organelle morphology are largely manual and time-consuming, and require specific expertise. Deep learning has the potential to revolutionize image-based screens by greatly improving their scope, speed, and efficiency. Here, we used transfer learning and a convolutional neural network (CNN) to analyze over 47,000 confocal microscopy images from Arabidopsis wild-type and mutant plants with abnormal division of one of three essential energy organelles: chloroplasts, mitochondria, or peroxisomes. We have built a deep-learning framework, DeepLearnMOR (Deep Learning of the Morphology of Organelles), which can rapidly classify image categories and identify abnormalities in organelle morphology with over 97% accuracy. Feature visualization analysis identified important features used by the CNN to predict morphological abnormalities, and visual clues helped to better understand the decision-making process, thereby validating the reliability and interpretability of the neural network. This framework establishes a foundation for future larger-scale research with broader scopes and greater data set diversity and heterogeneity.

Plant Sciences↗
DOE OSTI2018

Memristive Ion Channel-Doped Biomembranes as Synaptic Mimics

Solid-state neuromorphic systems based on transistors or memristors have yet to achieve the interconnectivity, performance, and energy efficiency of the brain due to excessive noise, undesirable material properties, and nonbiological switching mechanisms. Here in this work, we demonstrate that an alamethicin-doped, synthetic biomembrane exhibits memristive behavior, emulates key synaptic functions including paired-pulse facilitation and depression, and enables learning and computing. Unlike state-of-the-art devices, our two-terminal, biomolecular memristor features similar structure (biomembrane), switching mechanism (ion channels), and ionic transport modality as biological synapses while operating at considerably lower power. The reversible and volatile voltage-driven insertion of alamethicin peptides into an insulating lipid bilayer creates conductive pathways that exhibit pinched current–voltage hysteresis at potentials above their insertion threshold. Moreover, the synapse-like dynamic properties of the biomolecular memristor allow for simplified learning circuit implementations. Finally, low-power memristive devices based on stimuli-responsive biomolecules represent a major advance toward implementation of full synaptic functionality in neuromorphic hardware.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Exploration of Electrochemical Reactions at Organic–Inorganic Halide Perovskite Interfaces via Machine Learning in In Situ Time-of-Flight Secondary Ion Mass Spectrometry

The instability of hybrid organic–inorganic perovskite (HOIP) devices is one of the significant challenges preventing commercialization. Exploring these phenomena is severely limited by the complexity of the intrinsic electrochemistry of HOIPs, the presence of multiple volatile and mobile ionic species, and the possible role of environmentally induced reactions at surfaces and triple-phase junctions. Here, in situ studies of the electrochemistry of methylammonium lead bromide perovskite with the Au electrode interface are reported via light- and voltage-dependent time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging of lateral perovskite heterostructures. While ToF-SIMS allows for the visualization of the chemical composition along the surface and its evolution with light and electrical bias, the interpretation of the multidimensional data obtained is often limited due to strong correlations between chemical signatures and the need to track multiple peaks at once. Here, a machine learning workflow combining the Hough transform and non-negative matrix factorization and no-negative tensor decomposition is developed to avoid this limitation and extract salient features of associated chemical changes and to separate the light- and voltage-dependent dynamics. Finally, combining these in situ characterizations and the machine learning workflow provides comprehensive information on the chemical nature of moving species, ion accumulation, and interfacial electrochemical reactions in HOIP devices.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Small Modular Reactor and Microreactor Security-by-Design Lessons Learned: Integrated PPS Designs

U.S. nuclear power facilities face increasing challenges in meeting dynamic security requirements caused by evolving and expanding threats while keeping costs reasonable to make nuclear energy competitive. The past approach has often included implementing security features after a facility has been designed and without attention to optimization, which can lead to cost overruns. Incorporating security into the design process can provide robust, cost-effective, and sufficient physical protection systems. The purpose of this report is to capture lessons learned by the Advanced Reactor Safeguards and Security (ARSS) program that may be beneficial for other advanced and small modular reactor (SMR) vendors to use when developing security systems and postures. This report will capture relevant information that can be used in the security-by-design (SeBD) process for SMR and microreactor vendors.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning

Adversary emulation is an offensive exercise that provides a comprehensive assessment of a system’s resilience against cyber attacks. However, adversary emulation is typically a manual process, making it costly and hard to deploy in cyber-physical systems (CPS) with complex dynamics, vulnerabilities, and operational uncertainties. In this paper, we develop an automated, domain-aware approach to adversary emulation for CPS. We formulate a Markov Decision Process (MDP) model to determine an optimal attack sequence over a hybrid attack graph with cyber (discrete) and physical (continuous) components and related physical dynamics. We apply model-based and model-free reinforcement learning (RL) methods to solve the discrete-continuous MDP in a tractable fashion. As a baseline, we also develop a greedy attack algorithm and compare it with the RL procedures. We summarize our findings through a numerical study on sensor deception attacks in buildings to compare the performance and solution quality of the proposed algorithms.

Bhattacharya, Arnab↗
DOE OSTI2022

Enabling Predictive Scale-Bridging Simulations through Active Learning (Institutional Computing Annual Report (Project w20_alscalebridging)) [Slides]

The goal of this project was to develop, demonstrate, and provide a new capability to achieve greater physical fidelity in large-scale simulations, rather than the usual brute-force increases in the number of mesh elements or particles. This was done by using machine learning (ML) techniques to develop emulators for subscale physics that can be used in coarse-scale continuum simulations, trained on fine-scale molecular dynamics (MD) simulations that are launched on-the-fly via active learning. raditional inertial confinement fusion (ICF) simulations rely on numerical diffusion to simulate molecular effects such as non-local transport and mixing without truly accounting for molecular interactions; our approach directly accounts for this physics.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2026

Introduction to and comparison of deep learning and optimization approaches to analytical wake modeling of a tilted wind turbine

This paper introduces innovative optimization and deep learning techniques to enhance the prediction of complex wake dynamics in the downstream wind velocity of tilted wind turbines. Traditional methods for calibrating the Bastankhah wake model often lead to increased errors in wind velocity distribution due to overfitting of the local wake characteristics. To address this issue, we propose an additional global optimization step to reduce errors in wind velocity predictions with respect to various wake parameters. Despite this improvement, the Bastankhah model's axisymmetric Gaussian wake shape limits its accuracy for complex wake structures. Therefore, we also propose a deep learning approach, which demonstrates promising results by accurately modeling complex wake shapes across a broader range of tilt angles with minimal computational cost. The deep learning approach achieves near-identical predictions to high-fidelity large-eddy simulations, representing a promising advancement in wake modeling.

17 WIND ENERGY↗
DOE OSTI2026

Recurrent convolutional neural networks for modeling nonadiabatic dynamics of quantum-classical systems

Recurrent neural networks (RNNs) have recently been extensively applied to model the time evolution in fluid dynamics, weather predictions, and even chaotic systems due to their ability to capture temporal dependencies and sequential patterns in data. Here we present an RNN model based on convolutional neural networks for modeling the nonlinear nonadiabatic dynamics of hybrid quantum-classical systems. The dynamical evolution of the hybrid systems is governed by equations of motion for classical degrees of freedom and von Neumann equation for electrons. The Physics-Aware Recurrent Convolution (PARC) neural network structure incorporates a differentiator-integrator architecture that inductively models the spatiotemporal dynamics of generic physical systems. Here, we apply our RNN approach to learn the space-time evolution of a one-dimensional semiclassical Holstein model after an interaction quench. For shallow quenches (small changes in electron-lattice coupling), the deterministic dynamics can be accurately captured using a single-CNN-based recurrent network. In contrast, deep quenches induce chaotic evolution, making long-term trajectory prediction significantly more challenging. Nonetheless, we demonstrate that the PARC-CNN architecture can effectively learn the statistical climate of the Holstein model under deep-quench conditions.

Holstein model↗
DOE OSTI2022

Machine learning-based ethylene concentration estimation, real-time optimization and feedback control of an experimental electrochemical reactor

With the increase in electricity supply from clean energy sources, electrochemical reduction of carbon dioxide (CO 2 ) has received increasing attention as an alternative source of carbon-based fuels. As CO 2 reduction is becoming a stronger alternative for the clean production of chemicals, the need to model, optimize and control the electrochemical reduction of the CO 2 process becomes inevitable. However, on one hand, a first-principles model to represent the electrochemical CO 2 reduction has not been fully developed yet because of the complexity of its reaction mechanism, which makes it challenging to define a precise state-space model for the control system. On the other hand, the unavailability of efficient concentration measurement sensors continues to challenge our ability to develop feedback control systems. Gas chromatography (GC) is the most common equipment for monitoring the gas product composition, but it requires a period of time to analyze the sample, which means that GC can provide only delayed measurements during the operation. Moreover, the electrochemical CO 2 reduction process is catalyzed by a fast-deactivating copper catalyst and undergoes a selectivity shift from the product-of-interest at the later stages of experiments, which can pose a challenge for conventional control methods. To this end, machine learning (ML) techniques provide a potential approach to overcome those difficulties due to their demonstrated ability to capture the dynamic behavior of a chemical process from data. Motivated by the above considerations, we propose a machine learning-based modeling methodology that integrates support vector regression and first-principles modeling to capture the dynamic behavior of an experimental electrochemical reactor; this model, together with limited gas chromatography measurements, is employed to predict the evolution of gas-phase ethylene concentration. The model prediction is directly used in a proportional-integral (PI) controller that manipulates the applied potential to regulate the gas-phase ethylene concentration at energy-optimal set-point values computed by a real-time process optimizer (RTO). Specifically, the RTO calculates the operation set-point by solving an optimization problem to maximize the economic benefit of the reactor. Finally, suitable compensation methods are introduced to further account for the experimental uncertainties and handle catalyst deactivation. The proposed modeling, optimization, and control approaches are the first demonstration of active control for a CO 2 electrolyzer and contribute to the automation and scale-up efforts for electrified manufacturing of fuels and chemicals starting from CO 2 .

42 ENGINEERING↗
DOE OSTI2024

Deep reinforcement learning for optimal control of induction welding process

Optimizing induction welding (IW) process parameters for the application of joining thermoplastic composites is challenging as it requires achieving complex spatiotemporal thermal characteristics along the weld-line to obtain desired weld quality. We formulate an optimal control problem which captures these requirements and seeks to optimize the IW coil speed using a fast-acting dynamic IW process model. We develop a novel Deep Reinforcement Learning (DRL) framework to solve this computationally challenging control problem and demonstrate via simulation study that the learned DRL feedback control policy results in better spatiotemporal thermal characteristics as compared to the current state-of-the-art.

36 MATERIALS SCIENCE↗