Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Active learning”

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 973 records · Page 54
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Overcoming sparse datasets with multi-task learning as applied to high entropy alloys

Abstract The design of novel High Entropy Alloys for use in high-temperature applications is an area of active interest due to their potential to provide exceptional properties compared to conventional alloys. Since the increased popularity of machine learning, an important cog in the design process has been training surrogate models on alloy properties. However, these Single-Task models are trained on individual mechanical properties and do not take advantage of the relatedness between properties. Multi-Task models can capture the interdependencies between tasks, leading to potentially more accurate predictions for all tasks. In this paper, we investigate if Multi-Task models can show improvement over Single-Task models when used for predicting the mechanical properties of these alloys. To ensure fair evaluation between the models, we apply L 0 regularization and skip connections to the models, which allows them to adjust the number of model parameters and depth for optimal performance. We find that the Multi-Task models can leverage task relationships to perform better than Single-Task models, especially for high amounts of missing data in the tasks. Furthermore, adding simple auxiliary targets can boost Multi-Task performance even further despite not being effective as input descriptors to single-task models themselves. We anticipate that the proposed strategies can achieve more accurate predictions and consequently enable better design capabilities for such data-constrained domains without incurring much additional computational cost.

Debnath, Arindam (ORCID:0000000194274499)↗
NASA NTRS2005

Artificial Gravity Research Project

Protecting the health, safety, and performance of exploration-class mission crews against the physiological deconditioning resulting from long-term weightlessness during transit and long-term hypogravity during surface operations will require effective, multi-system countermeasures. Artificial gravity (AG), which would replace terrestrial gravity with inertial forces generated by rotating the transit vehicle or by a human centrifuge device within the transit vehicle or surface habitat, has long been considered a potential solution. However, despite its attractiveness as an efficient, multi-system countermeasure and its potential for improving the environment and simplifying operational activities (e.g., WCS, galley, etc.), much still needs to be learned regarding the human response to rotating environments before AG can be successfully implemented. This paper will describe our approach for developing and implementing a rigorous AG Research Project to address the key biomedical research questions that must be answered before developing effective AG countermeasure implementation strategies for exploration-class missions. The AG Research Project will be performed at JSC, ARC, extramural academic and government research venues, and international partner facilities maintained by DLR and IMBP. The Project includes three major ground-based human research subprojects that will lead to flight testing of intermittent short-radius AG in ISS crewmembers after 201 0, continuous long-radius AG in CEV crews transiting to and from the Moon, and intermittent short-radius AG plus exercise in lunar habitats. These human ground-based subprojects include: 1) a directed, managed international short-radius project to investigate the multi-system effectiveness of intermittent AG in human subjects deconditioned by bed rest, 2) a directed, managed long-radius project to investigate the capacity of humans to live and work for extended periods in rotating environments, and 3) a focused, investigator-initiated project to investigate system-specific adaptation to and from rotating environments. The AG Research Project also includes two major animal research subprojects: 1) a directed, managed ground-based subproject using rodents and, possibly, sub-human primates, to address mechanistic issues that cannot be studied in humans, to rapidly develop higher sample numbers than can be achieved in the human subprojects, and to establish feasible parameter operating bands to reduce the breadth of the human subprojects, and 2) a flight subproject using rodents to estimate the physiological effects of long term exposure to hypogravity and to investigate the effects of contamination by terrestrial gravity in estimating AG effectiveness. The animal flight subproject would be performed aboard ISS using the CAM module in approximately the 2008-201 1 timeframe. The paper will first present an overview of the key biomedical research questions to be answered. It will then describe the overall approaches to be utilized in developing and implementing the AG Research Project, including definition of the intended scientific research, management and development approaches, identification of roles and responsibilities, risk management, and definition of project deliverables. The primary focus of the paper will be on the first of the three ground-based human research subprojects, since it is the only one currently in development and is scheduled to start active subject investigations in April of 2005.

Kamman, Michelle R.↗
NASA NTRS2011

Space Shuttle Guidance, Navigation, and Rendezvous Knowledge Capture Reports

This document is a catalog and readers guide to lessons learned, experience, and technical history reports, as well as compilation volumes prepared by United Space Alliance personnel for the NASA/Johnson Space Center (JSC) Flight Dynamics Division.1 It is intended to make it easier for future generations of engineers to locate knowledge capture documentation from the Shuttle Program. The first chapter covers observations on documentation quality and research challenges encountered during the Space Shuttle and Orion programs. The second chapter covers the knowledge capture approach used to create many of the reports covered in this document. These chapters are intended to provide future flight programs with insight that could be used to formulate knowledge capture and management strategies. The following chapters contain descriptions of each knowledge capture report. The majority of the reports concern the Space Shuttle. Three are included that were written in support of the Orion Program. Most of the reports were written from the years 2001 to 2011. Lessons learned reports concern primarily the shuttle Global Positioning System (GPS) upgrade and the knowledge capture process. Experience reports on navigation and rendezvous provide examples of how challenges were overcome and how best practices were identified and applied. Some reports are of a more technical history nature covering navigation and rendezvous. They provide an overview of mission activities and the evolution of operations concepts and trajectory design. The lessons learned, experience, and history reports would be considered secondary sources by historians and archivists.

John L Goodman↗
DOE OSTI2025

Backpropagation-based learning with local derivative approximation and memory replay in biologically plausible neural systems

When learning, the brain modifies individual synaptic connections to reach a desired behavior. Animal and human brains have been shown to be incredibly capable of learning complex and varied functions across a wide variety of tasks. In recent years, artificial neural networks, inspired by human and animal brains, have shown great capabilities in learning a wide variety of difficult tasks. However, artificial neural networks primarily teach themselves through the use of backpropagation, a learning method which has no clear analogue within the brain. Additionally, Artificial Neural Networks primarily use continuous activation functions, which differ significantly from the spiking neuronal behavior present in the brain. In this paper, we discuss and demonstrate a biologically plausible learning method that approximates backpropagation through two techniques on Spiking Neural Networks. First, we show that the local temporal derivatives that are necessary for backpropagation can be approximately recovered through reconstruction using spike timings. Second, we show that through learning during a sleep phase, inspired by neuroscience research into memory replay, the localized parallel feedback path can learn to approximate the derivative through the forward path weight matrix, thus solving the weight transport problem. Lastly, we demonstrate that the combination of these two methods can approach or exceed the accuracy of backpropagation-based methods for a variety of neuromorphic vision tasks while maintaining biological plausibility.

42 ENGINEERING↗
DOE OSTI2023

Gating interactions steer loop conformational changes in the active site of the L1 metallo-β-lactamase

β-Lactam antibiotics are the most important and widely used antibacterial agents across the world. However, the widespread dissemination of β-lactamases among pathogenic bacteria limits the efficacy of β-lactam antibiotics. This has created a major public health crisis. The use of β-lactamase inhibitors has proven useful in restoring the activity of β-lactam antibiotics, yet, effective clinically approved inhibitors against class B metallo-β-lactamases are not available. L1, a class B3 enzyme expressed by Stenotrophomonas maltophilia , is a significant contributor to the β-lactam resistance displayed by this opportunistic pathogen. Structurally, L1 is a tetramer with two elongated loops, α3-β7 and β12-α5, present around the active site of each monomer. Residues in these two loops influence substrate/inhibitor binding. To study how the conformational changes of the elongated loops affect the active site in each monomer, enhanced sampling molecular dynamics simulations were performed, Markov State Models were built, and convolutional variational autoencoder-based deep learning was applied. The key identified residues (D150a, H151, P225, Y227, and R236) were mutated and the activity of the generated L1 variants was evaluated in cell-based experiments. The results demonstrate that there are extremely significant gating interactions between α3-β7 and β12-α5 loops. Taken together, the gating interactions with the conformational changes of the key residues play an important role in the structural remodeling of the active site. These observations offer insights into the potential for novel drug development exploiting these gating interactions.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Multireference Methods are Realistic and Useful Tools for Modeling Catalysis

Abstract Highly correlated systems, in particular those that include transition metals, are ubiquitous in catalysis. The significant static correlation found in such systems is often poorly accounted for using Kohn Sham density functional theory methods, as they are single determinantal in nature. Applications to catalysis of more rigorous and appropriate multiconfigurational methods have been reported in select instances, but their use remains rare. We discuss obstacles that hinder the routine application of multireference (MR) wave function theoretical calculations to catalytic systems and the current state of the art with respect to removing those obstacles.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Hallucination of closed repeat proteins containing central pockets

In pseudocyclic proteins, such as TIM barrels, β barrels, and some helical transmembrane channels, a single subunit is repeated in a cyclic pattern, giving rise to a central cavity that can serve as a pocket for ligand binding or enzymatic activity. Inspired by these proteins, we devised a deep-learning-based approach to broadly exploring the space of closed repeat proteins starting from only a specification of the repeat number and length. Biophysical data for 38 structurally diverse pseudocyclic designs produced in Escherichia coli are consistent with the design models, and the three crystal structures we were able to obtain are very close to the designed structures. Docking studies suggest the diversity of folds and central pockets provide effective starting points for designing small-molecule binders and enzymes.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Reductive catalytic fractionation of agricultural residue and energy crop lignin and application of lignin oil as antimicrobials

Cheap and abundant waste from bioethanol and agricultural processing industries are an alluring alternative feedstock for biorefineries. In this work, we employ reductive catalytic fractionation (RCF) to depolymerize, over Ru/C powder and Ru/Al 2 O 3 pellets, five herbaceous biomass feedstocks, namely corn stover, miscanthus, switchgrass, sugarcane bagasse, and wheat straw into phenolic monomers with high yields (~40 wt.% based on total (Klason + acid soluble) lignin and > 50 wt.% when stabilized using aldehydes), leaving behind a carbohydrate pulp residue. Interestingly, a polar solvent is sufficient to solubilize and fragment the lignin polymer into monomers without any catalyst. Here, contrary to woody biomass, where the monomer yields are positively correlated with the S-content of lignin, principal component analysis indicates that the monomer yields from herbaceous biomass depend on the content of lignin crosslinker – ferulate. Using NMR, we further identify α – 6 C-C linked oligomers formed from condensation reactions, explaining the unexpected low monomer yields of high β-O-4 herbaceous biomass. Recyclability experiments indicate that catalyst deactivation occurs through sintering, leaching, and fouling. Lignin oil from herbaceous biomass exhibits bacteriostatic effects against Staphylococcus aureus, highlighting a potential application in functional food development and as food or feed preservative.

09 BIOMASS FUELS↗
DOE OSTI2025

AI for nuclear physics: the EXCLAIM project

An overview of the recent activity of the newly funded EXCLusives with AI and Machine learning (EXCLAIM) collaboration is presented. The main goal of the collaboration is to develop a framework to implement AI and machine learning techniques in problems emerging from the phenomenology of high energy exclusive scattering processes from nucleons and nuclei, maximizing the information that can be extracted from various sets of experimental data, while implementing theoretical constraints from lattice QCD. A specific perspective embraced by EXCLAIM is to use the methods of theoretical physics to understand the working of ML, beyond its standardized applications to physics analyses which most often rely on industrially provided tools, in an automated way.

Analysis and statistical methods↗
DOE OSTI2023

Hpc Natural Language Understanding (nlu) Dataset

This code provides natural language annotation and labels for multiple activities in high performance. The purpose is to enable machine learning for natural language processing algorithms with high performance computing systems.

Biggs, BrandonS↗
DOE OSTI2025

Intelligent Triggers for Rare Event Detection in Liquid Argon Detectors

Next-generation neutrino experiments like SBND and DUNE rely on Liquid Argon Time Projection Chambers (LArTPCs), which produce exceptionally detailed data at high volume. Capturing rare or unexpected events in real-time is a major challenge. Our project explores the use of machine learning, specifically autoencoder-based anomaly detection, to identify unusual activity directly from raw detector signals. Inspired by successes at the CMS experiment, we demonstrate that such methods can be adapted to LArTPCs and show promising results in both simulated studies and early steps toward real-time hardware deployment. This approach could open new avenues for detecting signals from physics beyond the Standard Model.

Chung, Seokju [Columbia U. (main)]↗
NASA NTRS1981

Parameter estimation of large flexible aerospace structures with application to the control of the Maypole Deployable Reflector

Systems such as the Maypole deployable reflector have a distributed parameter nature. The flexible column and hoop structure and the circular antenna of 30-100 meter diameter which it supports are described by partial, rather than ordinary, differential equations. Progress completed in reduced order modelling andd controller design and digital parameter estimation and control is summarized. Topics covered include depolyment and on-orbit operation; quasi-static (steady state) operation; dynamic distributed parameter system; autoregressive moving average identification; frequency domain procedures; direct or implicit active control; adaptive observers; parameter estimation using a linear reinforcement learning factor; feedback control; and reduced order modeling for nonlinear systems.

Balas, M. J.↗
NASA NTRS1985

Computer architectures for computational physics work done by Computational Research and Technology Branch and Advanced Computational Concepts Group

Slides are reproduced that describe the importance of having high performance number crunching and graphics capability. They also indicate the types of research and development underway at Ames Research Center to ensure that, in the near term, Ames is a smart buyer and user, and in the long-term that Ames knows the best possible solutions for number crunching and graphics needs. The drivers for this research are real computational physics applications of interest to Ames and NASA. They are concerned with how to map the applications, and how to maximize the physics learned from the results of the calculations. The computer graphics activities are aimed at getting maximum information from the three-dimensional calculations by using the real time manipulation of three-dimensional data on the Silicon Graphics workstation. Work is underway on new algorithms that will permit the display of experimental results that are sparse and random, the same way that the dense and regular computed results are displayed.

Source record↗
NASA NTRS1989

A comparison of two neural network schemes for navigation

Neural networks have been applied to tasks in several areas of artificial intelligence, including vision, speech, and language. Relatively little work has been done in the area of problem solving. Two approaches to path-finding are presented, both using neural network techniques. Both techniques require a training period. Training under the back propagation (BPL) method was accomplished by presenting representations of (current position, goal position) pairs as input and appropriate actions as output. The Hebbian/interactive activation (HIA) method uses the Hebbian rule to associate points that are nearby. A path to a goal is found by activating a representation of the goal in the network and processing until the current position is activated above some threshold level. BPL, using back-propagation learning, failed to learn, except in a very trivial fashion, that is equivalent to table lookup techniques. HIA, performed much better, and required storage of fewer weights. In drawing a comparison, it is important to note that back propagation techniques depend critically upon the forms of representation used, and can be sensitive to parameters in the simulations; hence the BPL technique may yet yield strong results.

Munro, Paul W.↗
NASA NTRS1990

A comparison of two neural network schemes for navigation

Neural networks have been applied to tasks in several areas of artificial intelligence, including vision, speech, and language. Relatively little work has been done in the area of problem solving. Two approaches to path-finding are presented, both using neural network techniques. Both techniques require a training period. Training under the back propagation (BPL) method was accomplished by presenting representations of current position, goal position pairs as input and appropriate actions as output. The Hebbian/interactive activation (HIA) method uses the Hebbian rule to associate points that are nearby. A path to a goal is found by activating a representation of the goal in the network and processing until the current position is activated above some threshold level. BPL, using back-propagation learning, failed to learn, except in a very trivial fashion, that is equivalent to table lookup techniques. HIA, performed much better, and required storage of fewer weights. In drawing a comparison, it is important to note that back propagation techniques depend critically upon the forms of representation used, and can be sensitive to parameters in the simulations; hence the BPL technique may yet yield strong results.

Munro, Paul↗
NASA NTRS1992

Sound transmission reduction with intelligent panel systems

Experimental and theoretical investigations are performed of the use of intelligent panel systems to control the sound transmission and radiation. An intelligent structure is defined as a structural system with integrated actuators and sensors under the guidance of an adaptive, learning type controller. The system configuration is based on the Active Structural Acoustic Control (ASAC) concept where control inputs are applied directly to the structure to minimize an error quantity related to the radiated sound field. In this case multiple piezoelectric elements are employed as sensors. The importance of optimal shape and location is demonstrated to be of the same order of influence as increasing the number of channels of control.

Fuller, Chris R.↗
NASA NTRS1993

Architecture for Adaptive Intelligent Systems

We identify a class of niches to be occupied by 'adaptive intelligent systems (AISs)'. In contrast with niches occupied by typical AI agents, AIS niches present situations that vary dynamically along several key dimensions: different combinations of required tasks, different configurations of available resources, contextual conditions ranging from benign to stressful, and different performance criteria. We present a small class hierarchy of AIS niches that exhibit these dimensions of variability and describe a particular AIS niche, ICU (intensive care unit) patient monitoring, which we use for illustration throughout the paper. We have designed and implemented an agent architecture that supports all of different kinds of adaptation by exploiting a single underlying theoretical concept: An agent dynamically constructs explicit control plans to guide its choices among situation-triggered behaviors. We illustrate the architecture and its support for adaptation with examples from Guardian, an experimental agent for ICU monitoring.

ACTIVE CONTROL↗