Search NASA⌕ Search

SEARCH · Search NASA

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.

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

At least 955 records · Page 53
All sourcesNASA NTRSDOE OSTI
NASA NTRS1992

An expert system for monitoring dynamic aspects of RCS

An expert system (ARC) based on the MIMIC(2) framework is being developed for assistance in monitoring the Space Shuttle reaction control system (RCS) and in training RCS mission controllers. ARC has four components: a hypothesis generator, a model-constructor, a model-simulator and a matcher. The hypothesis generator examines current readings of sensors to generate a set of hypotheses. The model constructor generates models from these hypotheses. The simulator predicts future behaviors of the system. The matcher validates hypotheses by testing the predicted states against real data. The hypothesis generator postulates faults using model-based reasoning (MBR), learned rules from real data, and expert-defined rules. The simulator uses a qualitative QSIM model of the RCS which can handle both nominal modes as well as a variety of fault models. This allows the simulator to simulate the system even when one or more components have degraded. Finally, the matcher is responsible for comparing readings against predictions and calculating confidence in a particular hypothesis.

Kulkarni, Deepak↗
DOE OSTI2017

Thermal Modeling and Cryogenic Design of a Helical Superconducting Undulator Cryostat

A conceptual design for a helical superconducting undulator (HSCU) for the Advanced Photon Source (APS) at Argonne National Laboratory (ANL) has been completed. The device differs sufficiently from the existing APS planar superconducting undulator (SCU) design to warrant development of a new cryostat based on value engineering and lessons learned from the existing planar SCU. Changes include optimization of the existing cryocooler-based refrigeration system and thermal shield as well as cost reduction through the use of standard vacuum hardware. The end result is a design that provides significantly larger 4.2 K refrigeration margin in a smaller package for greater installation flexibility in the APS storage ring. This paper presents ANSYS-based thermal analysis of the cryostat, including estimated static and dynamic

Shiroyanagi, Y.↗
DOE OSTI2026

Automating Detection and Diagnosis of Faults, Failures, and Underperformance in PV Plants

The project developed hybrid physics-based and machine-learning methods for near-real-time detection of balance-of-system faults (e.g., string, combiner, and tracker outages) in utility-scale Photovoltaic plants, achieving over 50% true positive rates with under 10% false positives and significantly reducing engineering setup time. In the extended phase, the scope expanded to plant-level underperformance analysis and industry benchmarking through the SUPER.epri.com platform. SUPER standardizes data processing and performance metrics across more than 9 GWac and 120+ plants, enabling robust comparisons and insights into loss rates, inverter downtime, and capacity degradation.

14 SOLAR ENERGY↗
DOE OSTI2024

Predictive Modeling of NOx Emissions from Lean Direct Injection of Hydrogen and Hydrogen/Natural Gas Blends Using Flame Imaging and Machine Learning

This research paper explores the use of machine learning to relate images of flame structure and luminosity to measured NOx emissions. Images of reactions produced by 16 aero-engine derived injectors for a ground-based turbine operated on a range of fuel compositions, air pressure drops, preheat temperatures and adiabatic flame temperatures were captured and postprocessed. The experimental investigations were conducted under atmospheric conditions, capturing CO, NO and NOx emissions data and OH* chemiluminescence images from 27 test conditions. The injector geometry and test conditions were based on a statistically designed test plan. These results were first analyzed using the traditional analysis approach of analysis of variance (ANOVA). The statistically based test plan yielded 432 data points, leading to a correlation for NOx emissions as a function of injector geometry, test conditions and imaging responses, with 70.2% accuracy. As an alternative approach to predicting emissions using imaging diagnostics as well as injector geometry and test conditions, a random forest machine learning algorithm was also applied to the data and was able to achieve an accuracy of 82.6%. This study offers insights into the factors influencing emissions in ground-based turbines while emphasizing the potential of machine learning algorithms in constructing predictive models for complex systems.

08 HYDROGEN↗
NASA NTRS1976

NASA philosophy concerning space stations as operations centers for construction and maintenance of large orbiting energy systems

Future United States plans for manned space-flight activities are summarized, emphasizing the long-term goals of achieving permanent occupancy and limited self-sufficiency in space. NASA-sponsored studies of earth-orbiting Space Station concepts are reviewed along with lessons learned from the Skylab missions. Descriptions are presented of the Space Transportation System, the Space Construction Base, and the concept of space industrialization (the processing and manufacturing of goods in space). Future plans for communications satellites, solar-power satellites, terrestrial observations from space stations, and manned orbital-transfer vehicles are discussed.

Freitag, R. F.↗
NASA NTRS1988

Issues on the use of meta-knowledge in expert systems

Meta knowledge is knowledge about knowledge; knowledge that is not domain specific but is concerned instead with its own internal structure. Several past systems have used meta-knowledge to improve the nature of the user interface, to maintain the knowledge base, and to control the inference engine. More extensive use of meta-knowledge is probable for the future as larger scale problems are considered. A proposed system architecture is presented and discussed in terms of meta-knowledge applications. The principle components of this system: the user support subsystem, the control structure, the knowledge base, the inference engine, and a learning facility are all outlined and discussed in light of the use of meta-knowledge. Problems with meta-constructs are also mentioned but it is concluded that the use of meta-knowledge is crucial for increasingly autonomous operations.

Facemire, Jon↗
NASA NTRS1996

A Cost Comparison of Alternative Approaches to Distance Education in Developing Countries

This paper presents a cost comparison of three approaches to two-way interactive distance learning systems for developing countries. Included are costs for distance learning hardware, terrestrial and satellite communication links, and designing instruction for two-way interactive courses. As part of this project, FSEC is developing a 30-hour course in photovoltaic system design that will be used in a variety of experiments using the Advanced Communications Technology Satellite (ACTS). A primary goal of the project is to develop an instructional design and delivery model that can be used for other education and training programs. Over two-thirds of the world photovoltaics market is in developing countries. One of the objectives of this NASA-sponsored project was to develop new and better energy education programs that take advantage of advances in telecommunications and computer technology. The combination of desktop video systems and the sharing of computer applications software is of special interest. Research is being performed to evaluate the effectiveness of some of these technologies as part of this project. The design of the distance learning origination and receive sites discussed in this paper were influenced by the educational community's growing interest in distance education. The following approach was used to develop comparative costs for delivering interactive distance education to developing countries: (1) Representative target locations for receive sites were chosen. The originating site was assumed to be Cocoa, Florida, where FSEC is located; (2) A range of course development costs were determined; (3) The cost of equipment for three alternative two-way interactive distance learning system configurations was determined or estimated. The types of system configurations ranged from a PC-based system that allows instructors to originate instruction from their office using desktop video and shared application software, to a high cost system that uses a electronic classroom; (4) A range of costs for both satellite and terrestrial communications was investigated; (5) The costs of equipment and operation of the alternative configurations for the origination and receive sites were determined; (6) A range of costs for several alternative delivery scenarios (i.e., a mix of live-interactive; asynchronous interactive;use of videotapes) was determined; and (7) A preferred delivery scenario, including cost estimate, was developed.

Ventre, Gerard G.↗
NASA NTRS2006

Incident Involving 30-Ah Li-ion Cell at NASA Glenn Research Center

The key lesson learned from the February 17, 2006 cell explosion incident is that PC-based test-systems, even those having built-in watchdog monitors, can lose control and malfunction. In the case of lithiumion cell/battery testing, the stored energy can be released explosively causing considerable injury and damage to facilities. The investigation showed that although the Arbin system has a built-in watchdog monitor, the circumstances of the incident defeated the action of the watchdog and allowed the cycler to continue operation without control. An upgrade to the most recent version of Arbin software (version 4) was provided as a fix to the presumed control problem. This upgrade included newer EPROM s for the cycler microprocessor. Investigation revealed that similar incidents have occurred at other NASA centers with a variety of PC-based test instruments. JPL suffered an incident with Maccor testers and the GRC fuel cell group observed similar problems with LabView software. This is not exclusively an Arbin problem, but an issue with all PC-based systems. In this incident, it was fortunate that the event occurred after-hours with no-one in the room. The facility arrangement placed control consoles adjacent to the test chamber doors. Had someone been in the room during the event, they would have been exposed to hot debris and toxic combustion products. It was also fortunate that the exploded cell stayed inside the chamber after the door was forced open. If the cell had been ejected into the room it could have caused serious facility damage by impact and possibly caused a fire in the facility.

Bennett, William↗
DOE OSTI2021

Prediction of social media postings as trusted news or as types of suspicious news

Disclosed are systems, techniques, and non-transitory storage media for predicting social media postings as being trusted news or a type of suspicious news. The systems, techniques, and non-transitory storage media are based on unique neural network architectures that learn from a combined representation including at least representations of social media posting content and a vector representation of communications among connected users.

Volkova, Svitlana↗
DOE OSTI2022

Deep reinforcement learning with online data augmentation to improve sample efficiency for intelligent HVAC control

Deep Reinforcement Learning (DRL) has started showing success in real-world applications such as building energy optimization. Much of the research in this space utilized simulated environments to train RL-agent in an offline mode. Very few research have used DRL-based control in real-world systems due to two main reasons: 1) sample efficiency challenge---DRL approaches need to perform a lot of interactions with the environment to collect sufficient experiences to learn from, which is difficult in real systems, and 2) comfort or safety related constraints---user's comfort must never or at least rarely be violated. In this work, we propose a novel deep Reinforcement Learning framework with online Data Augmentation (RLDA) to address the sample efficiency challenge of real-world RL. We used a time series Generative Adversarial Network (TimeGAN) architecture as a data generator. We further evaluated the proposed RLDA framework using a case study of an intelligent HVAC control. With a ≈28% improvement in the sample efficiency, RLDA framework lays the way towards increased adoption of DRL-based intelligent control in real-world building energy management systems.

Kurte, Kuldeep↗
DOE OSTI2021

Exploratory analysis and performance prediction of big data transfer in High-performance Networks

Big data transfer in large-scale scientific and business applications is increasingly carried out over connections with guaranteed bandwidth provisioned in High-performance Networks (HPNs) via advance bandwidth reservation. Provisioning agents need to carefully schedule data transfer requests, compute network paths, and allocate appropriate bandwidths. Such reserved bandwidths, if not fully utilized, could be simply wasted due to the exclusive access during the approved time window, and cause extra overhead and complexity for resource management. This calls for accurate performance prediction to reserve bandwidths that match actual needs and avoid over-provisioning. We employ machine learning algorithms to predict big data transfer performance based on extensive performance measurements collected in the past several years from data transfer tests using different protocols and toolkits between various end sites on several real-life physical or emulated testbeds. We first analyze the performance patterns in response to a comprehensive list of parameters in end-host systems, network connections, and data transfer applications, which motivate the use of machine learning and also help us identify the effects of latent factors. We then propose threshold- and clustering-based methods to eliminate negative effects of latent factors in data preprocessing and build a robust performance predictor based on customized domain-oriented loss functions. The performance of the proposed methods is verified by extensive experiments using SVR and RFR as well as theoretical analysis of the general performance bound.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

BioADAPT-MRC: adversarial learning-based domain adaptation improves biomedical machine reading comprehension task

ABSTRACT Motivation Biomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them. The high performance of modern neural network-based MRC systems depends on high-quality, large-scale, human-annotated training datasets. In the biomedical domain, a crucial challenge in creating such datasets is the requirement for domain knowledge, inducing the scarcity of labeled data and the need for transfer learning from the labeled general-purpose (source) domain to the biomedical (target) domain. However, there is a discrepancy in marginal distributions between the general-purpose and biomedical domains due to the variances in topics. Therefore, direct-transferring of learned representations from a model trained on a general-purpose domain to the biomedical domain can hurt the model’s performance. Results We present an adversarial learning-based domain adaptation framework for the biomedical machine reading comprehension task (BioADAPT-MRC), a neural network-based method to address the discrepancies in the marginal distributions between the general and biomedical domain datasets. BioADAPT-MRC relaxes the need for generating pseudo labels for training a well-performing biomedical-MRC model. We extensively evaluate the performance of BioADAPT-MRC by comparing it with the best existing methods on three widely used benchmark biomedical-MRC datasets—BioASQ-7b, BioASQ-8b and BioASQ-9b. Our results suggest that without using any synthetic or human-annotated data from the biomedical domain, BioADAPT-MRC can achieve state-of-the-art performance on these datasets. Availability and implementation BioADAPT-MRC is freely available as an open-source project at https://github.com/mmahbub/BioADAPT-MRC. Supplementary information Supplementary data are available at Bioinformatics online.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗
DOE OSTI2023

Tournament-Based Pretraining to Accelerate Federated Learning

Advances in hardware, proliferation of compute at the edge, and data creation at unprecedented scales have made federated learning (FL) necessary for the next leap forward in pervasive machine learning. For privacy and network reasons, large volumes of data remain stranded on endpoints located in geographically austere (or at least austere network-wise) locations. However, challenges exist to the effective use of these data. To solve the system and functional level challenges, we present an three novel variants of a serverless federated learning framework. We also present tournament-based pretraining, which we demonstrate significantly improves model performance in some experiments. Overall, these extensions to FL and our novel training method enable greater focus on science rather than ML development.

Baughman, Matt↗
DOE OSTI2020

Probabilistic learning and updating of a digital twin for composite material systems

This paper presents an approach for characterizing and estimating statistical dependence between a large number of observables in a composite material system. Conditional regression is carried out using the estimated joint density function, permitting a systematic exploration of interdependence between fine scale and coarse observables that can be used for both prognosis and design of complex material systems. An example demonstrates the integration of experimental data with a computational database. The statistical approach is based on the probabilistic learning on manifolds recently developed by the authors. This approach leverages intrinsic structure detected through diffusion on graphs with projected stochastic differential equations to generate samples constrained to that structure.

42 ENGINEERING↗
NASA NTRS1990

Learning receptor positions from imperfectly known motions

An algorithm is described for learning image interpolation functions for sensor arrays whose sensor positions are somewhat disordered. The learning is based on failures of translation invariance, so it does not require knowledge of the images being presented to the visual system. Previously reported implementations of the method assumed the visual system to have precise knowledge of the translations. It is demonstrated that translation estimates computed from the imperfectly interpolated images can have enough accuracy to allow the learning process to converge to a correct interpolation.

Ahumada, Albert J., Jr.↗
DOE OSTI2024

Development and Validation of Home Comfort System for Total Performance Deficiency/Fault Detection and Optimal Comfort Control

In this project, we developed and tested a learning-based home thermal model that facilitates the operation of a model predictive control (MPC)-based optimization agent and an automated fault detection and diagnosis (AFDD) agent. The home thermal model was constructed using a two-node resistor-capacitor model. Moreover, two accompanying parameter identification methods were introduced, least-squares and optimization. Based on the home thermal model, the MPC-based optimization agent was developed to optimize residential HVAC operation. Using two FDD methods, the AFDD agent was constructed to detect and diagnose two prevalent residential AC faults, airflow reduction and refrigerant undercharge. The home thermal model, along with the MPC-based optimization agent and AFDD agent, were tested at the Norman Test House, Miami Test House, Pacific Northwest National Laboratory (PNNL) Test House A, and PNNL Test House B. Finally, they were also field tested in nine demonstration homes with real occupants.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS1997

Efficiently Ranking Hyphotheses in Machine Learning

This paper considers the problem of learning the ranking of a set of alternatives based upon incomplete information (e.g. a limited number of observations). At each decision cycle, the system can output a complete ordering on the hypotheses or decide to gather additional information (e.g. observation) at some cost.

Machine Learning algorithm parametric ranking↗