SEARCH · Engineering Papers

Results for “learning based systems”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,801 records · Page 100

All sources NASA NTRS DOE OSTI

NASA NTRS2001

Description of Selected Algorithms and Implementation Details of a Concept-Demonstration Aircraft VOrtex Spacing System (AVOSS)

A ground-based system has been developed to demonstrate the feasibility of automating the process of collecting relevant weather data, predicting wake vortex behavior from a data base of aircraft, prescribing safe wake vortex spacing criteria, estimating system benefit, and comparing predicted and observed wake vortex behavior. This report describes many of the system algorithms, features, limitations, and lessons learned, as well as suggested system improvements. The system has demonstrated concept feasibility and the potential for airport benefit. Significant opportunities exist however for improved system robustness and optimization. A condensed version of the development lab book is provided along with samples of key input and output file types. This report is intended to document the technical development process and system architecture, and to augment archived internal documents that provide detailed descriptions of software and file formats.

Hinton, David A.↗

NASA NTRS2005

Designing Agent Utilities for Coordinated, Scalable and Robust Multi-Agent Systems

Coordinating the behavior of a large number of agents to achieve a system level goal poses unique design challenges. In particular, problems of scaling (number of agents in the thousands to tens of thousands), observability (agents have limited sensing capabilities), and robustness (the agents are unreliable) make it impossible to simply apply methods developed for small multi-agent systems composed of reliable agents. To address these problems, we present an approach based on deriving agent goals that are aligned with the overall system goal, and can be computed using information readily available to the agents. Then, each agent uses a simple reinforcement learning algorithm to pursue its own goals. Because of the way in which those goals are derived, there is no need to use difficult to scale external mechanisms to force collaboration or coordination among the agents, or to ensure that agents actively attempt to appropriate the tasks of agents that suffered failures. To present these results in a concrete setting, we focus on the problem of finding the sub-set of a set of imperfect devices that results in the best aggregate device. This is a large distributed agent coordination problem where each agent (e.g., device) needs to determine whether to be part of the aggregate device. Our results show that the approach proposed in this work provides improvements of over an order of magnitude over both traditional search methods and traditional multi-agent methods. Furthermore, the results show that even in extreme cases of agent failures (i.e., half the agents failed midway through the simulation) the system's performance degrades gracefully and still outperforms a failure-free and centralized search algorithm. The results also show that the gains increase as the size of the system (e.g., number of agents) increases. This latter result is particularly encouraging and suggests that this method is ideally suited for domains where the number of agents is currently in the thousands and will reach tens or hundreds of thousands in the near future.

Tumer, Kagan↗

NASA NTRS2017

Exploiting Dark Information Resources to Create New Value Added Services to Study Earth Science Phenomena

This paper presents two research applications exploiting unused metadata resources in novel ways to aid data discovery and exploration capabilities. The results based on the experiments are encouraging and each application has the potential to serve as a useful standalone component or service in a data system. There were also some interesting lessons learned while designing the two applications and these are presented next.

Earth Science Informatics↗

NASA NTRS2017

The Challenges of Human-Autonomy Teaming

Machine intelligence is improving rapidly based on advances in big data analytics, deep learning algorithms, networked operations, and continuing exponential growth in computing power (Moores Law). This growth in the power and applicability of increasingly intelligent systems will change the roles humans, shifting them to tasks where adaptive problem solving, reasoning and decision-making is required. This talk will address the challenges involved in engineering autonomous systems that function effectively with humans in aeronautics domains.

artificial intelligence↗

NASA NTRS2017

The Challenges of Human-Autonomy Teaming

Human-Autonomy teaming↗

NASA NTRSDate not supplied

Machine Learning Algorithms for Alignment Verification of the Roman Space Telescope

The Nancy Grace Roman Telescope is a NASA observatory designed to unravel the secrets of dark energy and dark matter, search for and image exoplanets, and explore many topics in infrared optics. Scheduled to launch no earlier than October 2026, this 2.4 meter aperture telescope has a field of view 100 times greater than the Hubble Space Telescope. The mission is currently in its construction phase, where the telescope and its two instruments will soon be aligned together to ensure proper pupil matching. To help verify this alignment, multiple point sources above the entrance pupil of the telescope will illuminate the optical path through the telescope-instrument system, and shadows of various obstructions in the system will be analyzed using machine learning algorithms to determine the pupil matching error. This presentation discusses the test approach and the machine learning algorithms employed, as well as our uncertainty predictions based on a modeled Monte-Carlo analysis of the test.

Telescope↗

DOE OSTI2017

Simplified Interface to Complex Memory Hierarchies 1.x

Memory systems are expected to get evermore complicated in the coming years, and it isn't clear exactly what form that complexity will take. On the software side, a simple, flexible way of identifying and working with memory pools is needed. Additionally, most developers seek code portability and do not want to learn the intricacies of complex memory. Hence, we believe that a library for interacting with complex memory systems should expose two kinds of abstraction: First, a low-level, mechanism-based interface designed for the runtime or advanced user that wants complete control, with its focus on simplified representation but with all decisions left to the caller. Second, a high-level, policy-based interface designed for ease of use for the application developer, in which we aim for best-practice decisions based on application intent. We have developed such a library, called SICM: Simplified Interface to Complex Memory.

Lang, Michael↗

DOE OSTI2015

An integrated equipment for massive segmentation and packaging of control Rod Guide Tubes - 15161

Over time, some utilities have decided to undergo safety upgrades that include replacement of some ageing components like control rod guide tubes (GT's). GT's are safety related components because they control the path of the control rods into and out of the core. These components are usually stored underwater in interim storage pools to decay their radioactivity. When the interim storage facility reaches saturation, treatment and final disposal of the retired Guide Tubes needs to be performed. Based on more than 30 years of experience and lessons learned in the development of segmentation and packaging technologies for nuclear components, Westinghouse has designed, commissioned and will operate a dedicated system for cutting and packaging retired GT's from 900 MW plants, currently stored in a EDF maintenance facility located in the south of France. The first main technical challenge was the waste volume optimization. Two separate waste streams had to be considered for coping with the highly irradiated portion of the GT's (lower part) and the very low level waste sections (upper part). The segmentation plan has been designed to minimize the waste volume of the highly irradiated waste and therefore develop a process which could be adapted to the container size specified by EDF. Metallic baskets have been designed to optimize the packaging and storage density in the containers. All cutting techniques previously used by Westinghouse in similar applications were assessed and underwater mechanical cutting with a band saw was selected as the preferred method. A turning stand positions the GT in front of the band saw. When the cut is completed, the remnant GT is inserted into the next turning stand for the next cut. Each cell of the turning stand positions the GT at the pre-defined cutting height. An integrated water filtration system is used to ensure good visibility during the cutting operations and to minimize water volume and limit the final liquid effluents. The whole process of GT insertion, cutting, packaging and waste conditioning is carried out in a hot cell and controlled remotely. The operator can therefore follow the packaging plan accurately and safely by using a four axis pick and place unit, while keeping personal radiation exposure low. This innovative process allows cutting and packaging large quantities of GT's in a safe and efficient manner. The pilot project covers the segmentation of 93 GT's but it can be further used for cutting larger quantities of retired GT's resulting from the upcoming GT replacement campaigns. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2021

GANpiler

Focal Area(s): Rather than augment or replace physical models with machine learning, we instead preserve the existing models and augment the underlying code with faster surrogate models created by generative adversarial networks (GAN). To leverage the performance optimization, we also propose a runtime system and user interfaces that allow prediction and tracking of accumulated error as well as dynamic, per-process decision making as to which model (if any) to use for each iteration. Science Challenge: This proposal sits at the nexus of two hard problems. First, climate models based on machine learning will be, by their nature, difficult to trust once their predictions begin diverging from the consensus. Second, compilers and hardware have been making only incremental performance gains for decades. GPGPUs have provided a welcome performance boost for codes that can take advantage of them, but there is no similar technology on the horizon to provide the next performance leap.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Benchmarking machine learning interatomic potentials via phonon anharmonicity

Abstract Machine learning approaches have recently emerged as powerful tools to probe structure-property relationships in crystals and molecules. Specifically, machine learning interatomic potentials (MLIPs) can accurately reproduce first-principles data at a cost similar to that of conventional interatomic potential approaches. While MLIPs have been extensively tested across various classes of materials and molecules, a clear characterization of the anharmonic terms encoded in the MLIPs is lacking. Here, we benchmark popular MLIPs using the anharmonic vibrational Hamiltonian of ThO 2 in the fluorite crystal structure, which was constructed from density functional theory (DFT) using our highly accurate and efficient irreducible derivative methods. The anharmonic Hamiltonian was used to generate molecular dynamics (MD) trajectories, which were used to train three classes of MLIPs: Gaussian approximation potentials, artificial neural networks (ANN), and graph neural networks (GNN). The results were assessed by directly comparing phonons and their interactions, as well as phonon linewidths, phonon lineshifts, and thermal conductivity. The models were also trained on a DFT MD dataset, demonstrating good agreement up to fifth-order for the ANN and GNN. Our analysis demonstrates that MLIPs have great potential for accurately characterizing anharmonicity in materials systems at a fraction of the cost of conventional first principles-based approaches.

interatomic potentials↗

DOE OSTI2019

Reinforcement Learning-based Traffic Control to Optimize Energy Usage and Throughput (CRADA report)

The US roadways are critical to meeting the mobility and economic needs of the nation. The United States uses 28% of its energy in moving goods and people, with approximately 60% of that utilized by cars, light trucks, and motorcycles. Thus, improved transportation efficiency is vital to America’s economic progress. The increasing congestion and energy resource requirements of transportation systems for metropolitan areas require research in methods to improve and optimize control methods. Coordinating and optimizing traffic in urban areas may introduce hundreds of thousands of vehicles and traffic management systems, which can require high performance computing (HPC) resources to model and manage. In this work, we seek to use machine learning, computer vision, and HPC to improve the energy efficiency aspects of traffic control by leveraging GRIDSMART traffic cameras as sensors for adaptive traffic control, with a sensitivity to the fuel consumption characteristics of the traffic in the camera’s visual field. Traffic control use cases using reinforcement learning have been published and achieved good results. Surveys from DOE national laboratories estimate that the fuel cost of idling is 6 billion gallons wasted annually [Argonne National Laboratory, 2019]. GRIDSMART cameras—an existing, fielded commercial product—sense the presence of vehicles at intersections and replace more conventional sensors (such as inductive loops) to issue calls to traffic control. These cameras, which have horizon-to-horizon view, offer the potential for an improved view of the traffic environment which can be used to generate better control algorithms.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2026

Low-latency Jet Tagging for HL-LHC Using Transformer Architectures

Transformers are the state-of-the-art model architectures and widely used in application areas of machine learning. However the performance of such architectures is less well explored in the ultra-low latency domains where deployment on FPGAs or ASICs is required. Such domains include the trigger and data acquisition systems of the LHC experiments. We present a transformer-based algorithm for jet tagging built with the HGQ2 framework, which is able to produce a model with heterogeneous bitwidths for fast inference on FPGAs, as required in the trigger systems at the LHC experiments. The bitwidths are acquired during training by minimizing the total bit operations as an additional parameter. By allowing a bitwidth of zero, the model is pruned in-situ during training. Using this quantization-aware approach, our algorithm achieves state-of-the-art performance while also retaining permutation invariance which is a key property for particle physics applications. Due to the strength of transformers in representation learning, our work also serves as a stepping stone for the development of a larger foundation model for trigger applications.

Laatu, Lauri [Imperial Coll., London]↗

DOE OSTI2025

Accelerating Discovery of Solid‐State Thin‐Film Metal Dealloying for 3D Nanoarchitecture Materials Design through Laser Thermal Gradient Treatment

Thin‐film solid‐state metal dealloying (thin‐film SSMD) is a promising method for fabricating nanostructures with controlled morphology and efficiency, offering advantages over conventional bulk materials processing methods for integration into practical applications. Although machine learning (ML) has facilitated the design of dealloying systems, the selection of key thermal treatment parameters for nanostructure formation remains largely unknown and dependent on experimental trial and error. To overcome this challenge, a workflow enabling high‐throughput characterization of thermal treatment parameters is demonstrated using a laser‐based thermal treatment to create temperature gradients on single thin‐film samples of Nb‐Al/Sc and Nb‐Al/Cu. This continuous thermal space enables observation of dealloying transitions and the resulting nanostructures of interest. Through synchrotron X‐ray multimodal and high‐throughput characterization, critical transitions and nanostructures can be rapidly captured and subsequently verified using electron microscopy. The key temperatures driving chemical reactions and morphological evolutions are clearly identified. While the oxidation may influence nanostructure formation during thin‐film treatment, the dealloying process at the dealloying front involves interactions solely between the dealloying elements, highlighting the availability and viability of the selected systems. Further, this approach enables efficient exploration of the dealloying process and validation of ML predictions, thereby accelerating the discovery of thin‐film SSMD systems with targeted nanostructures.

36 MATERIALS SCIENCE↗

DOE OSTI2015

Collective I/O Tuning Using Analytical and Machine-Learning Models

The ever larger demand of scientific applications for computation and data is currently driving a continuous increase in scale of parallel computers. The inherent complexity of scaling up a computing systems in terms of both hardware and software stack exposes an increasing number of factors impacting the performance and complicating the process of optimization. In particular, the optimization of parallel I/O has become increasingly challenging due to increasing storage hierarchy and well known performance variability of shared storage systems. This paper focuses on model-based autotuning of the two-phase collective I/O algorithm from a popular MPI distribution on the Blue Gene/Q architecture. We propose a novel hybrid model, constructed as a composition of analytical models for communication and storage operations and black-box models for the performance of the individual operations. We perform an in-depth study of the complexity involved in performance modeling including architecture, software stack and noise. In particular we address this challenges of modeling the performance of shared storage systems by building a benchmark that helps synthesizing factors such as topology, file caching, and noise. The experimental results show that the hybrid approach produces significantly better results than state-of-the-art machine learning approaches and shows a higher robustness to noise, at the cost of a higher modeling complexity

I/O performance modeling↗

DOE OSTI2025

Generative AI models for learning flow maps of stochastic dynamical systems in bounded domains

Simulating stochastic differential equations (SDEs) in bounded domains, presents significant computational challenges due to particle exit phenomena, which requires accurate modeling of interior stochastic dynamics and boundary interactions. Despite the success of machine learning-based methods in learning SDEs, existing learning methods are not applicable to SDEs in bounded domains because they cannot accurately capture the particle exit dynamics. We present a unified hybrid data-driven approach that combines a conditional diffusion model with an exit prediction neural network to capture both interior stochastic dynamics and boundary exit phenomena. Our ML model consists of two major components: a neural network that learns exit probabilities using binary cross-entropy loss with rigorous convergence guarantees, and a training-free diffusion model that generates state transitions for non-exiting particles using closed-form score functions. The two components are integrated through a probabilistic sampling algorithm that determines particle exit at each time step and generates appropriate state transitions. Here, the performance of the proposed approach is demonstrated via three test cases: a one-dimensional simplified problem for theoretical verification, a two-dimensional advection-diffusion problem in a bounded domain, and a three-dimensional problem of interest to magnetically confined fusion plasmas.

Bounded domains↗

DOE OSTI2014

MO-G-BRD-01: Point/Counterpoint Debate: Arc Based Techniques Will Make Conventional IMRT Obsolete

A variety of intensity modulated radiation therapy (IMRT) delivery techniques have been developed that have provided clinicians with the ability to deliver highly conformal dose distributions. The delivery techniques include compensators, step-and-shoot IMRT, sliding window IMRT, volumetric modulated arc therapy (VMAT), and tomotherapy. A key development in the field of IMRT was the introduction of new planning algorithms and delivery control systems in 2007 that made it possible to coordinate the gantry rotation speed, dose rate, and multileaf collimator leaf positions during the delivery of arc therapy. With these developments, VMAT became a routine clinical tool. The use of VMAT has continued to grow in recent years and some would argue that this will soon make conventional IMRT obsolete, and this is the premise of this debate. To introduce the debate, David Shepard, Ph.D. will provide an overview of IMRT delivery techniques including historical context and how they are being used today. The debate will follow with Richard Popple, Ph.D. arguing FOR the Proposition and Peter Balter, Ph.D. arguing AGAINST it. Learning Objectives: Understand the different delivery techniques for IMRT. Understand the potential benefits of conventional IMRT. Understand the potential benefits of arc-based IMRT delivery.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2014

Biomass District Heat System for Interior Rural Alaska Villages

Alaska Village Initiatives (AVI) from the outset of the project had a goal of developing an integrated village approach to biomass in Rural Alaskan villages. A successful biomass project had to be ecologically, socially/culturally and economically viable and sustainable. Although many agencies were supportive of biomass programs in villages none had the capacity to deal effectively with developing all of the tools necessary to build a complete integrated program. AVI had a sharp learning curve as well. By the end of the project with all the completed tasks, AVI developed the tools and understanding to connect all of the dots of an integrated village based program. These included initially developing a feasibility model that created the capacity to optimize a biomass system in a village. AVI intent was to develop all aspects or components of a fully integrated biomass program for a village. This meant understand the forest resource and developing a sustainable harvest system that included the “right sized” harvest equipment for the scale of the project. Developing a training program for harvesting and managing the forest for regeneration. Making sure the type, quality, and delivery system matched the needs of the type of boiler or boilers to be installed. AVI intended for each biomass program to be of the scale that would create jobs and a sustainable business.

09 BIOMASS FUELS↗

DOE OSTI2025

Federated Learning for Efficient Condition Monitoring and Anomaly Detection in Industrial Cyber-Physical Systems

Detecting and localizing anomalies in cyber-physical systems (CPS) has become increasingly challenging as systems grow in complexity, particularly due to varying sensor reliability and node failures in distributed environments. While federated learning (FL) offers a foundation for distributed model training, existing approaches lack mechanisms to handle these CPS-specific challenges. This paper presents an enhanced FL framework that introduces three key innovations: adaptive model aggregation based on sensor reliability, dynamic node selection for resource optimization, and Weibull-based checkpointing for fault tolerance. Our framework enables reliable condition monitoring while addressing the computational and reliability challenges of industrial CPS deployments. Experiments on NASA Bearing and Hydraulic System Datasets demonstrate superior performance over state-of-the-art FL methods, achieving 99.5% AUC-ROC in anomaly detection and maintaining accuracy under node failures. Statistical validation using Mann-Whitney (U) test confirms significant improvements (p < 0.05) in both detection accuracy and computational efficiency across diverse operational scenarios.1

Marfo, William [University of Texas at El Paso,Dep↗

Refine your search to explore more results.