Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “adaptive 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 1,801 records · Page 100

Wynkoop Building Performance Measurement: Water

This report is a summary of the water analysis performance for the Denver, Colorado Wynkoop Building. The Wynkoop Building (Figure 1) was built in 2006 as the Environmental Protection Agency (EPA) Region 8 Headquarters intended to house over 900 occupants in the 301,292 gross square feet (248,849 rentable square feet). The building was built on a brownfield in the Lower Downtown Historic District as part of an urban redevelopment effort. The building was designed and constructed through a public-private partnership with the sustainable design elements developed jointly by General Services Administration (GSA) and EPA. That partnership is still active with all parties still engaged to optimize building operations and use the building as a Learning Laboratory. The building design achieved U.S. Green Building Council Leadership in Energy and Environmental Design for New Construction (LEED-NC) Gold Certification in 2008 (Figure 2) and a 2008 EPA Energy Star Rating of 96 with design highlights that include: (1) Water use was designed to use 40% less than a typical design baseline. The design included low flow fixtures, waterless urinals and dual flush toilets; (2) Native and adaptive vegetation were selected to minimize the need for irrigation water for landscaping; and (3) Energy use intensity was modeled at 66.1 kBtus/gross square foot, which is 39% better than ASHRAE 90.1 1999. The Wynkoop Building water use (10 gallons/square foot) was measured at lower than industry average (15 gallons/square foot) and GSA goals (13 gallons/square foot), however, it was higher than building management expected it would be. The type of occupants and number of occupants can have a significant impact on fixture water use. The occupancy per floor varied significantly over the study time period, which added uncertainty to the data analysis. Investigation of the fixture use on the 2nd, 5th, and 7th floors identified potential for water use reduction if the flush direction of the dual-flush toilet handles was reversed. The building management retrofitted the building's toilets with handles that operated on reduced flush when pushed down (0.8 gallons) and full flush when pulled up (1.1 gallons). The water pressure on the 5th floor (< 30 psi) is less than half the pressure on the 7th floor (>80 psi). The measured water savings post-retrofit was lower on the 5th floor than the 7th floor. The differences in water pressure may have had an impact on the quantity of water used per floor. The second floor water use was examined prior to and following the toilet fixture retrofit. This floor is where conference rooms for non-building occupants are available for use, thus occupancy is highly variable. The 3-day average volume per flush event was higher post-retrofit (0.79 gallons per event), in contrast to pre-retrofit (0.57 gallons per event). There were 40% more flush events post retrofit, which impacted the findings. Water use in the third floor fitness center was also measured for a limited number of days. Because of water line accessibility, only water use on the men's side of the fitness center was measured and from that the total fitness center water use was estimated. Using the limited data collected, the fitness center shower water use is approximately 2% of the whole building water use. Overall water use in the Wynkoop Building is below the industry baseline and GSA expectations. The dual flush fixture replacement appears to have resulted in additional water savings that are expected to show a savings in the total annual water use.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

High-performance data management for whole slide image analysis in digital pathology

When dealing with giga-pixel digital pathology in whole-slide imaging, a notable proportion of data records holds relevance during each analysis operation. For instance, when deploying an image analysis algorithm on whole-slide images (WSI), the computational bottleneck often lies in the input-output (I/O) system. This is particularly notable as patch-level processing introduces a considerable I/O load onto the computer system. However, this data management process could be further paralleled, given the typical independence of patch-level image processes across different patches. This paper details our endeavors in tackling this data access challenge by implementing the Adaptable IO System version 2 (ADIOS2). Our focus has been constructing and releasing a digital pathology-centric pipeline using ADIOS2, which facilitates streamlined data management across WSIs. Additionally, we’ve developed strategies aimed at curtailing data retrieval times. The performance evaluation encompasses two key scenarios: (1) a pure CPU-based image analysis scenario (“CPU scenario”), and (2) a GPU-based deep learning framework scenario (“GPU scenario”). Our findings reveal noteworthy outcomes. Under the CPU scenario, ADIOS2 showcases an impressive two-fold speed-up compared to the brute-force approach. In the GPU scenario, its performance stands on par with the cutting-edge GPU I/O acceleration framework, NVIDIA Magnum IO GPU Direct Storage (GDS). From what we know, this appears to be among the initial instances, if any, of utilizing ADIOS2 within the field of digital pathology. The source code has been made publicly available at https://github.com/hrlblab/adios.

Wang, Xiao↗

Optimal Control by Transfer-Learning

Through the project, a transfer-learning based optimal control methodology was developed. This can significantly reduce the time and data required for model learning and increase operation robustness and resilience via data-driven controller optimization. This methodology includes three major elements: 1) extraction of control knowledge or knowledge of tuning control parameter from a source feedback control task; 2) transferring of control knowledge from the source control task to a target control task (initialization of control parameters for the target control task); and 3) fast-adaptation of control parameters for the target task to achieve optimized performance.

42 ENGINEERING↗

Energy Prediction under Changed Demand Conditions: Robust Machine Learning Models and Input Feature Combinations

Deciding on a suitable algorithm for energy demand prediction in a building is non-trivial and depends on the availability of data. In this paper we compare four machine learning models, commonly found in the literature, in terms of their generalization performance and in terms of how using different sets of input features affects accuracy. This is tested on a data set where consumption patterns differ significantly between training and evaluation because of the Covid-19 pandemic. We provide a hands-on guide and supply a Python framework for building operators to adapt and use in their applications.

Schranz, Thomas↗

Missing data in multi-omics integration: Recent advances through artificial intelligence

Biological systems function through complex interactions between various ‘omics (biomolecules), and a more complete understanding of these systems is only possible through an integrated, multi-omic perspective. This has presented the need for the development of integration approaches that are able to capture the complex, often non-linear, interactions that define these biological systems and are adapted to the challenges of combining the heterogenous data across ‘omic views. A principal challenge to multi-omic integration is missing data because all biomolecules are not measured in all samples. Due to either cost, instrument sensitivity, or other experimental factors, data for a biological sample may be missing for one or more ‘omic techologies. Recent methodological developments in artificial intelligence and statistical learning have greatly facilitated the analyses of multi-omics data, however many of these techniques assume access to completely observed data. A subset of these methods incorporate mechanisms for handling partially observed samples, and these methods are the focus of this review. We describe recently developed approaches, noting their primary use cases and highlighting each method's approach to handling missing data. We additionally provide an overview of the more traditional missing data workflows and their limitations; and we discuss potential avenues for further developments as well as how the missing data issue and its current solutions may generalize beyond the multi-omics context.

97 MATHEMATICS AND COMPUTING↗

Polynomial chaos expansions on principal geodesic Grassmannian submanifolds for surrogate modeling and uncertainty quantification

In this work we introduce a manifold learning-based surrogate modeling framework for uncertainty quantification in high-dimensional stochastic systems. Our first goal is to perform data mining on the available simulation data to identify a set of low-dimensional (latent) descriptors that efficiently parameterize the response of the high-dimensional computational model. To this end, we employ Principal Geodesic Analysis on the Grassmann manifold of the response to identify a set of disjoint principal geodesic submanifolds, of possibly different dimension, that captures the variation in the data. Since operations on the Grassmann require the data to be concentrated, we propose an adaptive algorithm based on Riemannian K-means and the minimization of the sample Fréchet variance on the Grassmann manifold to identify “local” principal geodesic submanifolds that represent different system behavior across the parameter space. Polynomial chaos expansion is then used to construct a mapping between the random input parameters and the projection of the response on these local principal geodesic submanifolds. Here, the method is demonstrated on four test cases, a toy-example that involves points on a hypersphere, a Lotka-Volterra dynamical system, a continuous-flow stirred-tank chemical reactor system, and a two-dimensional Rayleigh-Bénard convection problem.

42 ENGINEERING↗

Effects of soiling and weathering on the albedo of building envelope materials: Lessons learned from natural exposure in two European cities and tuning of a laboratory simulation practice

Chemical and physical stress, weathering, organic and inorganic matter deposition, and microbial growth over time, or “aging”, affect the optical-radiative performance of building envelope materials. Natural exposure helps to quantify these effects, but it usually requires several years. Further, the contribution of the different degradation agents cannot be isolated, and results from different campaigns cannot be easily compared because of the variability in the boundary conditions producing aging. Here in this paper we present an adaptation of the protocol implemented by ASTM as D7897-18 “Standard Practice for Laboratory Soiling and Weathering of Roofing Materials to Simulate Effects of Natural Exposure on Solar Reflectance and Thermal Emittance”. The aim is to reproduce in the laboratory the changes in albedo (solar reflectance) and thermal emittance experienced by building envelope materials in European urban areas rather than in the United States. We tuned the spraying duration and weathering cycles, and we compared the UV–vis–NIR reflectances of naturally-aged specimens (48 months in Rome and Milan) of roofing and wall finish materials to those exposed to laboratory weathering and soiling. Excluding those materials that show early physical-chemical degradation, the mean absolute deviation between natural and laboratory exposure of roofing products is equal to 0.027 in albedo. This is a lower value than the differences between two natural exposure campaigns at the same site. We clearly defined the limits of application of the protocol, providing an appraisal of the repeatability of natural aging. Moreover, we identified possible improvements in the methodology to conduct both natural and laboratory exposure.

36 MATERIALS SCIENCE↗

On the Formalization of Development and Assessment Process for Digital Twins in the Nearly Autonomous Management and Control System

In recent years, the autonomous control system has been encouraged in advanced reactors for restoring economic viability, simplifying the operation and maintenance, and enabling remote-site power generations [1]. Since the reactor is expected to be operated for a long period of time with a limited number of individuals onsite, it is recommended that the autonomous control system should have access to very realistic models of the state of processes in the whole lifecycle, together with these process behaviors in interaction with their environment in the real world. As a result, digital twin (DT) technology is suggested in autonomous control systems. DT is defined as a digital representation of a physical object or system, which contains a record for the histories of loads, operation and maintenance status, predictions for the near-term transient of important state variables, and decision-making process [2]. Since machine learning (ML) can recognize patterns within a complex system in real-time applications, it has been used to build DTs in the autonomous control systems for advanced reactors. Meanwhile, due to the rareness of operation data in accident scenarios, the development and assessment of DTs is expected to be mainly driven by simulations. Although the capability and feasibility of ML-based DTs are recognized in improving the safety and efficiency of reactor control, a major concern from the regulatory commission and the nuclear industry is whether the information from a DT is developed and assessed in accordance with expectation and requirements by the target decision. Such concerns not only affect the acceptance criteria for DTs, but also values that can be extracted from DTs and autonomous control system during operations. Inspired by the success of formal methods in improving the reliability and robustness of computer programming and software development, it is suggested that the development and assessment process (DAP) for both separate DTs and integral control system should be formalized in a transparent, consistent, and improvable manner. In this study, a digital-twin development and assessment process (DT-DAP) is proposed by adapting the evaluation model development and assessment process (EMDAP) [3] to requirements by the autonomous control system, ML algorithms, and DT technology. To demonstrate the framework, a baseline nearly autonomous management and control (NAMAC) system with ML-based DTs for diagnosis and prognosis is developed and assessed based on the framework. It is found that with selected testing methods and techniques, the DT-DAP can help identify errors in DTs and NAMAC which would otherwise be left unverified. Meanwhile, it is found that the DT-DAP can improve the DTs and NAMAC by continuously learning and iterating through different elements.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Mars Exobiology: The Principles Behind The Plan For Exploration

The search for evidence of life on Mars is a highly interdisciplinary enterprise which extends beyond the traditional life sciences. Mars conceivably had a pervasive ancient biosphere which may have persisted even to the present, but only in subsurface environments. Understanding the history of Mars' global environment, including its inventory of volatile elements, is a crucial part of the search strategy. Those deposits (minerals, sediments, etc.) which could have and retained a record of earlier biological activity must be identified and examined. While the importance of. seeking another biosphere has not diminished during the years since the Viking mission, the strategy for Mars exploration certainly has been modified by later discoveries. The Viking mission itself demonstrated that the present day surface environment of Mars is hostile to life as we know it. Thus, to search effectively for life on Mars, be it extant or extinct, we now must greatly improve our understanding of Mars the planet. Such an understanding will help us broaden our search beyond the Viking lander sites, both back in time to earlier epochs and elsewhere to other sites and beneath the surface. Exobiology involves much more than simply a search for extant life beyond Earth. It addresses the prospect of long-extinct biospheres and also the chemistry, organic and otherwise, which either led to life or which occurred on rocky planets that remained lifeless. Even a Mars without a biosphere would reveal much about life. How better to understand the origin and impact of a biosphere than to compare Earth with another similar but lifeless planet? Still, several relatively recent discoveries offer encouragement that a Martian biosphere indeed might have existed. The ancient Martian surface was extensively sculptured by volcanism and the activity of liquid water. Such observations invoke impressions of an ancient martian atmosphere and environment that resembled ancient Earth more than present-day Mars. Since Viking, we have learned that our own biosphere began prior to 3.5 billion years ago, during an early period when our solar system apparently was sustaining clement conditions on at least two of its planets. Also, we have found that microorganisms can survive, even flourish, in environments more extreme in temperature and water availability than had been previously recognized. The common ancestor of life on Earth probably was adapted to elevated temperatures, raising the possibility that hydrothermal systems played a central role in sustaining our early biosphere. If a biosphere ever arose on Mars, at least some of its constituents probably dwelled in the subsurface. Even today, conditions on Mars and Earth become more similar with increasing depth beneath their surfaces. For example, under the martian permafrost, the geothermal gradient very likely maintains liquid water in environments which resemble aquifers on Earth. Indigenous bacteria have recently been recovered from deep aquifers on Earth. Liquid groundwater very likely persisted throughout Mars' history. Thus, martian biota, if they ever existed, indeed might have survived in subsurface environments.

DesMarais, D. J.↗

Human orientation and movement control in weightless and artificial gravity environments

Our goal is to summarize what has been learned from studies of human movement and orientation control in weightless conditions. An understanding of the physics of weightlessness is essential to appreciate the dramatic consequences of the absence of continuous contact forces on orientation and posture. Eye, head, arm, leg, and whole body movements are discussed, but only experiments whose results seem relatively incontrovertible are included. Emphasis is placed on distinguishing between virtually immediate adaptive compensations to weightlessness and those with longer time courses. The limitations and difficulties of performing experiments in weightless conditions are highlighted. We stress that when astronauts and cosmonauts return from extended space flight they do so with both physical "plant" and neural "controller" structurally and functionally altered. Recent developments in adapting humans to artificial gravity conditions are discussed as a way of maintaining sensory-motor and structural integrity in extended missions involving transitions between different force environments.

NASA Discipline Neuroscience↗

NASA Tech Briefs, August 2012

Topics covered include: Mars Science Laboratory Drill; Ultra-Compact Motor Controller; A Reversible Thermally Driven Pump for Use in a Sub-Kelvin Magnetic Refrigerator; Shape Memory Composite Hybrid Hinge; Binding Causes of Printed Wiring Assemblies with Card-Loks; Coring Sample Acquisition Tool; Joining and Assembly of Bulk Metallic Glass Composites Through Capacitive Discharge; 670-GHz Schottky Diode-Based Subharmonic Mixer with CPW Circuits and 70-GHz IF; Self-Nulling Lock-in Detection Electronics for Capacitance Probe Electrometer; Discontinuous Mode Power Supply; Optimal Dynamic Sub-Threshold Technique for Extreme Low Power Consumption for VLSI; Hardware for Accelerating N-Modular Redundant Systems for High-Reliability Computing; Blocking Filters with Enhanced Throughput for X-Ray Microcalorimetry; High-Thermal-Conductivity Fabrics; Imidazolium-Based Polymeric Materials as Alkaline Anion-Exchange Fuel Cell Membranes; Electrospun Nanofiber Coating of Fiber Materials: A Composite Toughening Approach; Experimental Modeling of Sterilization Effects for Atmospheric Entry Heating on Microorganisms; Saliva Preservative for Diagnostic Purposes; Hands-Free Transcranial Color Doppler Probe; Aerosol and Surface Parameter Retrievals for a Multi-Angle, Multiband Spectrometer LogScope; TraceContract; AIRS Maps from Space Processing Software; POSTMAN: Point of Sail Tacking for Maritime Autonomous Navigation; Space Operations Learning Center; OVERSMART Reporting Tool for Flow Computations Over Large Grid Systems; Large Eddy Simulation (LES) of Particle-Laden Temporal Mixing Layers; Projection of Stabilized Aerial Imagery Onto Digital Elevation Maps for Geo-Rectified and Jitter-Free Viewing; Iterative Transform Phase Diversity: An Image-Based Object and Wavefront Recovery; 3D Drop Size Distribution Extrapolation Algorithm Using a Single Disdrometer; Social Networking Adapted for Distributed Scientific Collaboration; General Methodology for Designing Spacecraft Trajectories; Hemispherical Field-of-View Above-Water Surface Imager for Submarines; and Quantum-Well Infrared Photodetector (QWIP) Focal Plane Assembly.

Source record↗

Quantitative Approach for the Accurate CFD Simulation of Hover in Turbulent Flow

Time-dependent Navier-Stokes simulations have been carried out for a V22 rotor in hover using an improved, low-diffusion, HLLE++ upwind algorithm in the OVERFLOW code. Emphasis is placed on lessons learned over the past decade regarding the effects of high-order spatial accuracy, grid resolution, and the use of detached eddy simulation in predicting the rotor performance, i.e., figure-of-merit (FM). A quick-start procedure is described together with a statistical measure of FM convergence that reduces hover computations by 5 times, similar in computational work for forward flight. Furthermore, Cartesian adaptive mesh refinement in the rotor wake revealed a complex turbulent flow with worm-like structures of various scales. These turbulent worms, found computationally more than a decade ago, have recently been observed in a separate German Aerospace Center (DLR) experiment. Moreover, adaptive mesh refinement has been used to resolve the tip-vortex to its correct physical size.

Neal M. Chaderjian↗

Adaptive model training system and method

An adaptive model training system and method for filtering asset operating data values acquired from a monitored asset for selectively choosing asset operating data values that meet at least one predefined criterion of good data quality while rejecting asset operating data values that fail to meet at least the one predefined criterion of good data quality; and recalibrating a previously trained or calibrated model having a learned scope of normal operation of the asset by utilizing the asset operating data values that meet at least the one predefined criterion of good data quality for adjusting the learned scope of normal operation of the asset for defining a recalibrated model having the adjusted learned scope of normal operation of the asset.

97 MATHEMATICS AND COMPUTING↗

Adaptive model training system and method

An adaptive model training system and method for filtering asset operating data values acquired from a monitored asset for selectively choosing asset operating data values that meet at least one predefined criterion of good data quality while rejecting asset operating data values that fail to meet at least the one predefined criterion of good data quality; and recalibrating a previously trained or calibrated model having a learned scope of normal operation of the asset by utilizing the asset operating data values that meet at least the one predefined criterion of good data quality for adjusting the learned scope of normal operation of the asset for defining a recalibrated model having the adjusted learned scope of normal operation of the asset.

97 MATHEMATICS AND COMPUTING↗

Assessing Development Impacts Associated with Low Emission Development Strategies: Lessons Learned from Pilot Efforts in Kenya and Montenegro

Low emission development strategies (LEDS) articulate economy-wide policies and implementation plans designed to enable a country to meet its long-term development objectives while reducing greenhouse gas emissions. A development impact assessment tool was developed to inform an analytically robust and transparent prioritization of LEDS actions based on their economic, social, and environmental impacts. The graphical tool helps policymakers communicate the development impacts of LEDS options and identify actions that help meet both emissions reduction and development goals. This paper summarizes the adaptation and piloting of the tool in Kenya and Montenegro. The paper highlights strengths of the tool and discusses key needs for improving it.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

EngineSim: Turbojet Engine Simulator Adapted for High School Classroom Use

EngineSim is an interactive educational computer program that allows users to explore the effect of engine operation on total aircraft performance. The software is supported by a basic propulsion web site called the Beginner's Guide to Propulsion, which includes educator-created, web-based activities for the classroom use of EngineSim. In addition, educators can schedule videoconferencing workshops in which EngineSim's creator demonstrates the software and discusses its use in the educational setting. This software is a product of NASA Glenn Research Center's Learning Technologies Project, an educational outreach initiative within the High Performance Computing and Communications Program.

Petersen, Ruth A.↗

Survey of Machine Learning-Based Rotating Detonation Engine Diagnostics: Evaluation for Broad Application in Experimental Facilities

This work evaluates and compares various convolutional neural networks (CNNs) trained in previous NETL studies according to metrics effecting diagnostic feasibility, external applicability, and performance. Each CNN surveyed, including image classification, object detection, and time series classification, is used to develop total RDE diagnostics and evaluated alongside conventional techniques with respect to real-time capabilities. Real-time capable diagnostics are deployed and evaluated in the laboratory environment using an altered experimental setup, which is outlined herein for possible adaptations in external experimental facilities.

Johnson, Kristyn↗

Survey of Machine Learning-Based Rotating Detonation Engine Diagnostics: Evaluation for Broad Application in Experimental Facilities

This work evaluates and compares various convolutional neural networks (CNNs) trained in previous NETL studies according to metrics effecting diagnostic feasibility, external applicability, and performance. Each CNN surveyed, including image classification, object detection, and time series classification, is used to develop total RDE diagnostics and evaluated alongside conventional techniques with respect to real-time capabilities. Real-time capable diagnostics are deployed and evaluated in the laboratory environment using an altered experimental setup, which is outlined herein for possible adaptations in external experimental facilities.

Johnson, Kristyn↗

Refine your search to explore more results.