SEARCH · Engineering Papers

Results for “learned priors”

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 595 records · Page 33

All sources NASA NTRS DOE OSTI

NASA NTRS2023

Designing Learning Experiences With A Low-Cost Robotic Arm

Robots have gained immense popularity in Hollywood and growth globally in both industrial manufacturing and non-manufacturing environments and applications such as healthcare, service sector, and space exploration. To date, there are several examples of simple and low-cost educational robotic platforms and commercially available platforms (e.g., Lego Mindstorms, VEX Robotics) for incorporation into existing curriculum. However, most low-cost examples require access to rapid-prototyping tools, such as 3D printers to manufacture the structure of the robot, while commercially available platforms are relatively expensive (> $1,000). Although the low-cost, open-source examples provide increased access, these examples require design and manufacturing tasks that would be considered outside the learning objectives of an upper-level robotics course and are better suited for other introductory courses. Thus, we asked, how can a robotic platform be incorporated into existing robotics curriculum to enhance students' learning experiences? To explore this research question, we introduce a low-cost (<$200), untethered, and transportable robotic platform that is easy to assemble using off-the-shelf components. This kit can be powered from a laptop computer and does not rely on access to rapid-prototyping tools such as 3D printers or laser cutters, making this a more accessible option in undergraduate engineering courses. Specifically, we aimed to investigate the design of experiential learning experiences for the mathematical modeling of the forward and inverse kinematics of a serial robotic arm that complements existing robotics curriculum. The experiential learning experience focuses on traditional written answer, simulation in MATLAB, and finally implementation on a robotic platform. Few studies examined this accessible option when evaluating experiential learning experiences that complement existing robotics curricula. To assess the impact of this robotic arm kit in an undergraduate course, we implemented an educational intervention that allowed us insight into student perceptions, takeaways on the course and activities involving the robotic arm, and the impact of the course on their career outlook when comparing activities that involved use of the robotic arm and those that did not. Details on the design, development and implementation of the learning activities is provided. Both quantitative and qualitative data were collected and analyzed. The results presented in this paper discuss students finding the learning activities on the robotic arms more helpful than those without, and that students found high value in the hands-on experiences and real-world scenarios offered by the activities using the robotic arm. Challenges to implementation of the robotic arms are discussed, including students’ prior knowledge of using robotic arms.

Eric J. Markvicka↗

DOE OSTI2025

Gradient flow based phase-field modeling using separable neural networks

Allen–Cahn equation is a reaction–diffusion equation and is widely used for modeling phase separation. Machine learning methods for solving the Allen–Cahn equation in its strong form suffer from inaccuracies in collocation techniques, errors in computing higher-order spatial derivatives, and the large system size required by the space–time approach. To overcome these challenges, we propose solving the gradient flow of the Ginzburg–Landau free energy functional, which is equivalent to the Allen–Cahn equation, thereby avoiding the second-order spatial derivatives associated with the Allen–Cahn equation. A minimizing movement scheme is employed to solve the gradient flow problem, eliminating the complexities of a space–time approach. We utilize a separable neural network that efficiently represents the phase field through low-rank tensor decomposition. As we use the minimizing movement scheme to numerically solve the gradient flow problem, we thus, refer to the proposed method as the Separable Deep Minimizing Movement (SDMM) method. The evaluation of the functional in the minimizing movement scheme using the Gauss quadrature technique bypasses the inaccuracies associated with collocation techniques traditionally used to solve partial differential equations. A hyperbolic tangent transformation is introduced on the phase field prior to the evaluation of the functional to ensure that it remains strictly bounded within the values of the two phases. For this transformation, theoretical guarantee for energy stability of the minimizing movement scheme is established. Our results suggest that this transformation helps to improve the accuracy and efficiency significantly. The proposed method resolves the challenges faced by state-of-the-art machine learning techniques, outperforming them in both accuracy and efficiency. It is also the first machine learning method to achieve an order of magnitude speed improvement over the finite element method. In addition to its formulation and computational implementation, several case studies illustrate the applicability of the proposed method.

42 ENGINEERING↗

DOE OSTI2024

Coincident learning for unsupervised anomaly detection of scientific instruments

Abstract Anomaly detection is an important task for complex scientific experiments and other complex systems (e.g. industrial facilities, manufacturing), where failures in a sub-system can lead to lost data, poor performance, or even damage to components. While scientific facilities generate a wealth of data, labeled anomalies may be rare (or even nonexistent), and expensive to acquire. Unsupervised approaches are therefore common and typically search for anomalies either by distance or density of examples in the input feature space (or some associated low-dimensional representation). This paper presents a novel approach called coincident learning for anomaly detection (CoAD), which is specifically designed for multi-modal tasks and identifies anomalies based on coincident behavior across two different slices of the feature space. We define an unsupervised metric, F ^ β , out of analogy to the supervised classification F β statistic. CoAD uses F ^ β to train an anomaly detection algorithm on unlabeled data , based on the expectation that anomalous behavior in one feature slice is coincident with anomalous behavior in the other. The method is illustrated using a synthetic outlier data set and a MNIST-based image data set, and is compared to prior state-of-the-art on two real-world tasks: a metal milling data set and our motivating task of identifying RF station anomalies in a particle accelerator.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Neural lumped parameter differential equations with application in friction-stir processing

Lumped parameter methods aim to simplify the evolution of spatially-extended or continuous physical systems to that of a “lumped” element representative of the physical scales of the modeled system. For systems where the definition of a lumped element or its associated physics may be unknown, modeling tasks may be restricted to full-fidelity physics simulations. Here, in this work, we consider data-driven modeling tasks with limited point-wise measurements of otherwise continuous systems. We build upon the notion of the Universal Differential Equation (UDE) to construct data-driven models for reducing dynamics to that of a lumped parameter and inferring its properties. The flexibility of UDEs allow for composing various known physical priors suitable for application-specific modeling tasks, including lumped parameter methods. The motivating example for this work is the plunge and dwell stages for friction-stir welding; specifically, (i) mapping power input into the tool to a point-measurement of temperature and (ii) using this learned mapping for process control.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Unraveling complex causal processes that affect sustainability requires more integration between empirical and modeling approaches

Scientists seek to understand the causal processes that generate sustainability problems and determine effective solutions. Yet, causal inquiry in nature–society systems is hampered by conceptual and methodological challenges that arise from nature–society interdependencies and the complex dynamics they create. Here, we demonstrate how sustainability scientists can address these challenges and make more robust causal claims through better integration between empirical analyses and process- or agent-based modeling. To illustrate how these different epistemological traditions can be integrated, we present four studies of air pollution regulation, natural resource management, and the spread of COVID-19. The studies show how integration can improve empirical estimates of causal effects, inform future research designs and data collection, enhance understanding of the complex dynamics that underlie observed temporal patterns, and elucidate causal mechanisms and the contexts in which they operate. These advances in causal understanding can help sustainability scientists develop better theories of phenomena where social and ecological processes are dynamically intertwined and prior causal knowledge and data are limited. The improved causal understanding also enhances governance by helping scientists and practitioners choose among potential interventions, decide when and how the timing of an intervention matters, and anticipate unexpected outcomes. Methodological integration, however, requires skills and efforts of all involved to learn how members of the respective other tradition think and analyze nature–society systems.

42 ENGINEERING↗

NASA NTRS2004

Immunity-Based Aircraft Fault Detection System

In the study reported in this paper, we have developed and applied an Artificial Immune System (AIS) algorithm for aircraft fault detection, as an extension to a previous work on intelligent flight control (IFC). Though the prior studies had established the benefits of IFC, one area of weakness that needed to be strengthened was the control dead band induced by commanding a failed surface. Since the IFC approach uses fault accommodation with no detection, the dead band, although it reduces over time due to learning, is present and causes degradation in handling qualities. If the failure can be identified, this dead band can be further A ed to ensure rapid fault accommodation and better handling qualities. The paper describes the application of an immunity-based approach that can detect a broad spectrum of known and unforeseen failures. The approach incorporates the knowledge of the normal operational behavior of the aircraft from sensory data, and probabilistically generates a set of pattern detectors that can detect any abnormalities (including faults) in the behavior pattern indicating unsafe in-flight operation. We developed a tool called MILD (Multi-level Immune Learning Detection) based on a real-valued negative selection algorithm that can generate a small number of specialized detectors (as signatures of known failure conditions) and a larger set of generalized detectors for unknown (or possible) fault conditions. Once the fault is detected and identified, an adaptive control system would use this detection information to stabilize the aircraft by utilizing available resources (control surfaces). We experimented with data sets collected under normal and various simulated failure conditions using a piloted motion-base simulation facility. The reported results are from a collection of test cases that reflect the performance of the proposed immunity-based fault detection algorithm.

Dasgupta, D.↗

NASA NTRS2014

LADEE Multi-Domain Simulation

The Lunar Atmosphere Dust Environment Explorer (LADEE) was a small explorer class spacecraft that was launched on Sept 7, 2013 and that was de-orbited and successfully impacted the Moons surface on April 17, 2014 after completing all of the mission objectives. The low-cost rapidly prototyped hardware design used for the spacecraft was extend to the development of the software base. To achieve this goal, a Model Based Design approach was utilized to develop the onboard flight software, and out of this development a model based multipurpose simulator was created of the LADEE spacecraft and its mission environment. This simulator extended the traditional function of propagating the vehicle's kinematic and rotational states and included the electrical and thermal states propagation. Traditionally, these domains are handled by domain specific high fidelity simulations that use the states histories from other domains as input. By reducing the fidelity and abstracting the relevant features being monitored and controlled by the flight software, it was possible to model the coupling across these domains resulting in more accurate overall system behavior. A faster than real-time workstation (WSIM) version of the LADEE simulator was used to develop and test the software control algorithms in the Simulink environment. To maximize the performance of the simulation, modeling knobs were introduced to reduce the resolution of the some of the domains models when the effects of that domain were not significant for the scope of that simulation. The automatic code generation feature in Simulink was used to port the simulation to several real-time environments to support Processor-in-the-Loop (PIL) and Hardware-in-the-Loop (HIL) testing, verification and validation. The real-time environment required that the design of each of the domain models be deterministic as possible in the time required to perform all of the calculations to update its states. The simulation interface was designed to be compatible with the command interface employed by the LADEE mission operation team. The WSIM, PIL, and HIL simulators thus used a common interface and thus were used for flight software testing, for mission operations personnel training (nominal and off-nominal operations) prior to the mission and to perform command sequence verification during the mission. This presentation will look at the modeling strategies used to create a common interface to the simulator and to model and couple multiple domains within the simulation, the results of those strategies, and the lessons learned.

Multi-Domain↗

DOE OSTI2021

Nuclear Deactivation and Downgrade of Enriched Uranium Facilities at the Y-12 National Security Complex

Buildings 9206 and 9212 at the Y-12 National Security Complex are both Hazard Category 2 nuclear facilities from the Manhattan Project era that supported various missions over the decades, including the processing of enriched uranium. The production mission for Building 9206 ended in the 1990s, while Building 9212 is still an active production facility. The disposition process for contaminated excess facilities is generally described in the U.S. Department of Energy (DOE) Guide DOE O 430.1A, Life Cycle Asset Management, which provides guidance on facility surveillance and maintenance, deactivation, decommissioning, and transition in supplemental guides DOE G 430.1-2 through 430.1-5. Historically, production facilities similar to Buildings 9206 and 9212 have not always been cleaned out and deactivated prior to being excessed, which significantly complicates the decommissioning phase. Many legacy facilities were shut down before the formal DOE guidance was established. This paper presents the practical application and implementation of the DOE guidance for the nuclear deactivation of Buildings 9206 and 9212, and summarizes the lessons learned for application across the DOE enterprise.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2021

Nuclear Deactivation and Downgrade of Enriched Uranium Facilities at the Y-12 National Security Complex

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

NASA NTRS2005

Lessons Learned From Developing Three Generations of Remote Sensing Science Data Processing Systems

The Biospheric Information Systems Branch at NASA s Goddard Space Flight Center has developed three generations of Science Investigator-led Processing Systems for use with various remote sensing instruments. The first system is used for data from the MODIS instruments flown on NASA s Earth Observing Systems @OS) Terra and Aqua Spacecraft launched in 1999 and 2002 respectively. The second generation is for the Ozone Measuring Instrument flying on the EOS Aura spacecraft launched in 2004. We are now developing a third generation of the system for evaluation science data processing for the Ozone Mapping and Profiler Suite (OMPS) to be flown by the NPOESS Preparatory Project (NPP) in 2006. The initial system was based on large scale proprietary hardware, operating and database systems. The current OMI system and the OMPS system being developed are based on commodity hardware, the LINUX Operating System and on PostgreSQL, an Open Source RDBMS. The new system distributes its data archive across multiple server hosts and processes jobs on multiple processor boxes. We have created several instances of this system, including one for operational processing, one for testing and reprocessing and one for applications development and scientific analysis. Prior to receiving the first data from OMI we applied the system to reprocessing information from the Solar Backscatter Ultraviolet (SBUV) and Total Ozone Mapping Spectrometer (TOMS) instruments flown from 1978 until now. The system was able to process 25 years (108,000 orbits) of data and produce 800,000 files (400 GiB) of level 2 and level 3 products in less than a week. We will describe the lessons we have learned and tradeoffs between system design, hardware, operating systems, operational staffing, user support and operational procedures. During each generational phase, the system has become more generic and reusable. While the system is not currently shrink wrapped we believe it is to the point where it could be readily adopted, with substantial cost savings, for other similar tasks.

Tilmes, Curt↗

DOE OSTI2025

Baseflow Identification via Explainable AI With Kolmogorov‐Arnold Networks

Abstract Hydrological models often involve constitutive laws that may not be optimal in every application. We propose to replace such laws with the Kolmogorov‐Arnold networks (KANs), a class of neural networks designed to identify symbolic expressions. We demonstrate KAN's potential on the problem of baseflow identification, a notoriously challenging task plagued by significant uncertainty. KAN‐derived functional dependencies of the baseflow components on the aridity index outperform their original counterparts; they demonstrate that water availability, rather than potential evapotranspiration, drives baseflow by constraining actual evapotranspiration under arid conditions. On a test set, they increase the Nash‐Sutcliffe efficiency (NSE) by 65%, decrease the root mean squared error by 29%, and increase the Kling‐Gupta efficiency by 34%. This superior performance is achieved while reducing the number of fitting parameters from three to two. Next, we use data from 378 catchments across the continental United States to refine the water‐balance equation at the mean‐annual scale. The KAN‐derived equations based on the refined water balance outperform both the current aridity index model, with up to a 105% increase in NSE, and the KAN‐derived equations based on the original water balance. While the performance of our model and tree‐based machine learning methods is similar, KANs offer the advantage of simplicity and transparency and require no specific software or computational tools. This case study focuses on the aridity index formulation, but the approach is flexible and transferable to other hydrological processes. Plain Language Summary Equations used in hydrologic model are often suboptimal, resulting in reduced prediction accuracy and efficiency. We implemented Kolmogorov‐Arnold networks (KAN), a machine learning algorithm for deriving symbolic formulations, to estimate groundwater recharge and showed that it outperforms an existing state‐of‐the‐art semi‐empirical formulation. In hydrology, Nash‐Sutcliffe efficiency (NSE), root mean squared error (RMSE), and Kling‐Gupta efficiency (KGE) are commonly used to evaluate model performance. Higher NSE and KGE values indicate better performance, while lower RMSE values are preferable. Our results show that NSE increased by 71%, RMSE decreased by 32%, and KGE improved by 25%. In addition, KAN identifies an optimal functional form and can be used to derive new analytical formulas using the prior knowledge. The KAN‐inspired equation outperformed the original formulation and reduced the fitting parameters. Furthermore, we refined the water‐balance equation at the mean‐annual scale and showed that, based on the new water‐balance equation, KAN can derive new formulations that are superior to the original aridity index formulations (up to 105% increase in NSE) and KAN‐derived equations based on the original water balance. These findings highlight the significant potential of KAN to advance the scientific understanding of a wide range of hydrologic processes. Key Points Kolmogorov‐Arnold networks (KANs) enhance interpretability of machine‐learned hydrological models KAN‐derived symbolic formulations outperform state‐of‐the‐art semi‐empirical aridity indices KAN‐identified functional form yields an analytical index with fewer fitting parameters and improved performance

baseflow↗

DOE OSTI2020

On the Convergence of Physics Informed Neural Networks for Linear Second-Order Elliptic and Parabolic Type PDEs

Physics informed neural networks (PINNs) are deep learning based techniques for solving partial differential equations (PDEs) encountered in computational science and engineering. Guided by data and physical laws, PINNs find a neural network that approximates the solution to a system of PDEs. Such a neural network is obtained by minimizing a loss function in which any prior knowledge of PDEs and data are encoded. Despite its remarkable empirical success in one, two or three dimensional problems, there is little theoretical justification for PINNs. As the number of data grows, PINNs generate a sequence of minimizers which correspond to a sequence of neural networks. We want to answer the question: Does the sequence of minimizers converge to the solution to the PDE? We consider two classes of PDEs: linear second-order elliptic and parabolic. By adapting the Schauder approach and the maximum principle, we show that the sequence of minimizers strongly converges to the PDE solution in C 0 . Furthermore, we show that if each minimizer satisfies the initial/boundary conditions, the convergence mode becomes H 1 . Computational examples are provided to illustrate our theoretical findings. To the best of our knowledge, this is the first theoretical work that shows the consistency of PINNs.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1986

Thin-sectioning and microanalysis of individual extraterrestrial particles

A long standing constraint on the study of micrometeorites has centered on difficulties in preparing them for analysis. This is due largely to their small dimensions and consequent practical limitations on sample manipulation. Chondritic micrometeorites provide a good example; although much has been learned about their chemistry and mineralogy almost nothing was known about such basic properties as texture and petrographic associations. The only way to assess such properties is to examine microstructure indigenous to the particles. Unfortunately, almost all micrometeorites, out of necessity, have been crushed and dispersed onto appropriate substances prior to analysis, and most information about texture and petrography was lost. Recently, thin-sections of individual extraterrestrial particles have been prepared using an ultramicrotome equipped with a diamond knife. This procedure has been applied to stratospheric micrometeorites and Solar Max impact debris. In both cases the sections have enabled observation of a variety of internal particle features, including textures, porosity, and petrographic associations. The sectioning procedure is described and analysis results for chondritic micrometeoroids and select particles from Solar Max are presented.

Bradley, J. P.↗

NASA NTRS2000

Partners in Freedom: Contributions of the Langley Research Center to U.S. Military Aircraft of the 1990's

Established in 1917 as the nation#s first civil aeronautics research laboratory under the National Advisory Commit-tee for Aeronautics (NACA), Langley was a small laboratory that solved the problems of flight for military and civil aviation. Throughout history, Langley has maintained a working partnership with the Department of Defense, U.S. industry, universities, and other government agencies to support the defense of the nation with research. During World War II, Langley directed virtually all of its workforce and facilities to research for military aircraft. Following the war, a balanced program of military and civil projects was undertaken. In some instances Langley research from one aircraft program helped solve a problem in another. At the conclusion of some programs, Langley obtained the research models for additional tests to learn more about previously unknown phenomena. The data also proved useful in later developmental programs. Many of the military aircraft in the U.S. inventory as of late 1999 were over 20 years old. Langley activities that contributed to the development of some of these aircraft began over 50 years prior. This publication documents the role, from early concept stages to problem solving for fleet aircraft, that Langley played in the military aircraft fleet of the United States for the 1990's.

Chambers, Joseph R.↗

NASA NTRS2008

Orbital Express AVGS Validation and Calibration for Automated Rendezvous

From March to July of 2007, the DARPA Orbital Express mission achieved a number of firsts in autonomous spacecraft operations. The NASA Advanced Video Guidance Sensor (AVGS) was the primary docking sensor during the first two dockings and was used in a blended mode three other automated captures. The AVGS performance exceeded its specification by approximately an order of magnitude. One reason that the AVGS functioned so well during the mission was that the validation and calibration of the sensor prior to the mission advanced the state-of-the-art for proximity sensors. Some factors in this success were improvements in ground test equipment and truth data, the capability for ILOAD corrections for optical and other effects, and the development of a bias correction procedure. Several valuable lessons learned have applications to future proximity sensors.

Heaton, Andrew F.↗

NASA NTRSDate not supplied

Medical Lessons Learned from the Exploration Atmospheres Study

Background: The National Aeronautics and Space Administration’s (NASA) Exploration Atmospheres study (EA) was done to evaluate alternative cabin atmospheres for future spacecraft designs and planetary surface exploration of the Moon, Mars and beyond. Deep space exploration involves creating habitats and environments safe for human occupancy and means to explore the outside environment (extravehicular activities, EVA). In order to validate alternative atmospheres and pre-spacewalk procedures, the EA study was conducted to evaluate factors such as hypoxia risks, denitrogenation protocols, food limitations, medications, and the impact of other factors on human performance. Overview: Space travel is constrained by mass, volume, power and the cost of vehicle development, which creates tradeoffs in various capabilities, including breathing gasses. Higher atmospheric pressure in a vehicle means more gas, and a stronger containment vessel/habitat; while lower pressure requires higher oxygen partial pressure, which may increase fire risk. NASA’s EA study evaluated a proposed alternative cabin environment (8.2 psia, 34% Oxygen), for future spacecraft habitat, and planetary EVAs. EA included both a 3-day and a 11-day trial. These trials included a depressurization and saturation to 8.2psi at 34% O2 with additional depresses to 4.3 psia at 85% O2 for simulated EVAs, (1 EVA during the 3-day and 5 during the 11-day trials). Discussion: Planning for and executing the medical monitoring and response plan for a trial of this scope was a huge undertaking with no prior practice to fall back on. Food obstacles, sleeping issues, medications, joint injury, equipment limitations, medical privacy, multiple cases of decompression sickness, and even a COVID outbreak among the support team proved challenging. Conclusion: Testing of this nature is an essential part NASA’s preparation for the upcoming Lunar Artemis missions. As spaceflight transitions beyond low earth orbit, to planetary, even more trials of this nature will be required to learn what are the optimal atmospheric and associated operational constraints to maintain the optimal health of the crew and achieve mission objectives.

R Sanders↗

NASA NTRS2021

Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications

The exceptional progress in the field of machine learning (ML) in recent years has attracted a lot of interest in using this technology in aviation. Possible airborne applications of ML include safety-critical functions, which must be developed in compliance with rigorous certification standards of the aviation industry. Current certification standards for the aviation industry were developed prior to the ML renaissance without taking specifics of ML technology into account. There are some fundamental incompatibilities between traditional design assurance approaches and certain aspects of ML-based systems. In this paper, we analyze the current airborne certification standards and show that all objectives of the standards can be achieved for a low-criticality ML-based system if certain assumptions about ML development workflow are applied.

Avionics↗

NASA NTRSDate not supplied

Flight Dynamics and Navigation Performance of the BioSentinel Mission

BioSentinel was one of the ten 6U CubeSats launched by the Space Launch System (SLS) as part of the Artemis-I mission on November 16th, 2022. The spacecraft was deployed after the trans-lunar injection imparted by the upper stage of SLS, and performed a lunar flyby that provided the necessary energy to escape the Earth-Moon system into heliocentric space. The BioSentinel mission required flight dynamics support prior to flight to assess the deployment conditions and the trajectory design, as well as navigation support during flight, to provide orbit determination solutions for the mission and the Deep Space Network (DSN). This paper discusses the BioSentinel mission flight dynamics campaign, from mission design to the challenges and lessons learned encountered during flight.

Astrodynamics↗