SEARCH · Search NASA

Results for “Active learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 991 records · Page 55

All sources NASA NTRS DOE OSTI

DOE OSTI2023

A Revised International Standard for Gearboxes in Wind Turbine Systems

Gearbox and wind turbine design and application standards have contributed significantly to improvements in reliability over the past two decades. The International Electrotechnical Commission (IEC) 61400-4 standard of wind turbine gearbox design is currently being revised by a joint working group (JWG) of experts in IEC TC 88 (wind energy) and International Organization for Standardization (ISO) TC60 (gears) to further that effort. Experts from ISO TC4 (rolling bearings) and ISO TC28 (lubricants) have actively participated. This revision has implemented lessons learned from industry use of edition 1 since its publication in 2012. The main document, IEC 61400-4, was pared down to essential design requirements and application-specific recommendations along with a design verification framework. The JWG leveraged concurrent development of other standards, such as IEC 61400-8 on wind turbine structures, to replace edition 1 content. These are described along with how this works with the IEC Renewable Energy certification scheme for wind turbines (IECRE-WE). The JWG recognized the interest in maintaining informative parts of edition 1 including annexes on wind turbine architecture and loads, bearing and gear arrangements, bearing selection, lubrication system descriptions and lubricant performance recommendations. This information was retained in two technical reports: IEC/TR 61400-4-2 Lubrication and IEC/TR 61400-4-3 Explanatory Notes. Additionally, a technical specification, IEC/TS 61400-4-1, was drafted to provide a reliability calculation method for comparing different design options or conditions. Salient elements of these documents are described. All four documents were recently distributed for IEC/ISO review, ballot, and comment. Publication is expected in 2023.

gearbox↗

DOE OSTI2023

A Revised International Standard for Gearboxes in Wind Turbine Systems: Preprint

ENGINEERING,WIND ENERGY↗

DOE OSTI2022

Sourcing thermotolerant poly(ethylene terephthalate) hydrolase scaffolds from natural diversity

Enzymatic deconstruction of poly(ethylene terephthalate) (PET) is under intense investigation, given the ability of hydrolase enzymes to depolymerize PET to its constituent monomers near the polymer glass transition temperature. To date, reported PET hydrolases have been sourced from a relatively narrow sequence space. Here, we identify additional PET-active biocatalysts from natural diversity by using bioinformatics and machine learning to mine 74 putative thermotolerant PET hydrolases. We successfully express, purify, and assay 51 enzymes from seven distinct phylogenetic groups; observing PET hydrolysis activity on amorphous PET film from 37 enzymes in reactions spanning pH from 4.5–9.0 and temperatures from 30–70 °C. We conduct PET hydrolysis time-course reactions with the best-performing enzymes, where we observe differences in substrate selectivity as function of PET morphology. We employed X-ray crystallography and AlphaFold to examine the enzyme architectures of all 74 candidates, revealing protein folds and accessory domains not previously associated with PET deconstruction. Overall, this study expands the number and diversity of thermotolerant scaffolds for enzymatic PET deconstruction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Machine Learning for Anomaly Detection in Neural Network Security and SRF Cavities

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.

Ferguson, Hal [Old Dominion University]↗

DOE OSTI2025

A Weakly Supervised Machine Learning Procedure for Magnet Quench Diagnostics

Voltage taps remain the standard and reliable diagnostic tool for detecting quenches in superconducting magnets. However, they identify a quench only at the time of voltage rise and do not provide information on earlier physical precursors. In this work, we investigate whether acoustic emission data can reveal precursor activity that occurs before conventional voltage detection using machine learning techniques. We introduce an event selection method and a weakly supervised machine learning procedure to learn data-driven criteria for identifying potential acoustic precursors to quenches. Two Convolutional Neural Network (CNN) architectures are trained: one on acoustic sensor events from our selection procedure and one on the Fast Fourier Transforms (FFTs) of these events. Both networks are trained iteratively using confidence-weighted loss functions to associate certain subsets of training data with a precursor label. We evaluate the performance of these models by examining the time distribution of events classified as potential precursors relative to the quench onset. Results indicate that the proposed approach can possibly distinguish acoustic emission events occurring closer to the quench from earlier acoustic activity during ramping, suggesting the potential for flagging quench precursors in acoustic data.

Khan, Maira [Fermilab] (ORCID:0009000891602387)↗

DOE OSTI2019

Learning nonlinear level sets for dimensionality reduction in function approximation

We developed a Nonlinear Level-set Learning (NLL) method for dimensionality reduction in high-dimensional function approximation with small data. This work is motivated by a variety of design tasks in real-world engineering applications, where practitioners would replace their computationally intensive physical models (e.g., high-resolution fluid simulators) with fast-to-evaluate predictive machine learning models, so as to accelerate the engineering design processes. There are two major challenges in constructing such predictive models: (a) high-dimensional inputs (e.g., many independent design parameters) and (b) small training data, generated by running extremely time-consuming simulations. Thus, reducing the input dimension is critical to alleviate the over-fitting issue caused by data insufficiency. Existing methods, including sliced inverse regression and active subspace approaches, reduce the input dimension by learning a linear coordinate transformation; our main contribution is to extend the transformation approach to a nonlinear regime. Specifically, we exploit reversible networks (RevNets) to learn nonlinear level sets of a high-dimensional function and parameterize its level sets in low-dimensional spaces. A new loss function was designed to utilize samples of the target functions' gradient to encourage the transformed function to be sensitive to only a few transformed coordinates. The NLL approach is demonstrated by applying it to three 2D functions and two 20D functions for showing the improved approximation accuracy with the use of nonlinear transformation, as well as to an 8D composite material design problem for optimizing the buckling-resistance performance of composite shells of rocket inter-stages.

Zhang, Guannan↗

NASA NTRS2010

Things That Work: Roles and Services of SPDF

The current Heliophysics Science Data Management Policy (HpSDMP) defines the roles of the Space Physics Data Facility (SPDF) project as a heliophysics active Final Archive (aFA), a focus for critical data infrastructure services and a center of excellence for data and ancillary information services. This presentation will highlight (1) select current SPDF activities, (2) the lessons we are continuing to learn in how to usefully serve the the heliophysics science community and (3)SPDF's programmatic emphasis in the coming year. In cooperation with the Heliophysics Virtual discipline Observatories (VxOs), we are working closely with current, and with upcoming missions such as RBSP and MMS, to define effective approaches to ensure the long-term availability and archiving of mission data, as well as how SPDF services can complement active mission capabilities. We are working to make the Virtual Space Physics Observatory (VSPO) service comprehensive in all significant and NASA relevant heliophysics data. We will highlight a new CDAWeb interface, a faster SSCWeb, availability of our data through VxO services such as Autoplot, a new capability to easily access our data from within IDL and continuing improvements to CDF including better handling of leap seconds.

McGuire, R. E.↗

DOE OSTI2018

Deep Learning for Unsupervised Insider Threat Detection in Structured Cyber Security Data Streams

Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective filter for the human analyst, we present an online unsupervised deep learning approach to detect anomalous network activity from system logs in real time. Our models decompose anomaly scores into the contributions of individual user behavior features for increased interpretability to aid analysts reviewing potential cases of insider threat. Using the CERT Insider Threat Dataset v6.2 and threat detection recall as our performance metric, our novel deep and recurrent neural network models outperform Principal Component Analysis, Support Vector Machine and Isolation Forest based anomaly detection baselines. For our best model, the events labeled as insider threat activity in our dataset had an average anomaly score in the 95.53 percentile, demonstrating our approach's potential to greatly reduce analyst workloads.

Deep Learning, Insider Threat↗

DOE OSTI2017

Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams

Analysis of an organization’s computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective filter for the human analyst, we present an online unsupervised deep learning approach to detect anomalous network activity from system logs in real time. Our models decompose anomaly scores into the contributions of individual user behavior features for increased interpretability to aid analysts reviewing potential cases of insider threat. Using the CERT Insider Threat Dataset v6.2 and threat detection recall as our performance metric, our novel deep and recurrent neural network models outperform Principal Component Analysis, Support Vector Machine and Isolation Forest based anomaly detection baselines. For our best model, the events labeled as insider threat activity in our dataset had an average anomaly score in the 95.53 percentile, demonstrating our approach’s potential to greatly reduce analyst workloads.

Tuor, Aaron R.↗

DOE OSTI2025

Bioremediation of Chlorinated Volatile Organic Compounds: DOE Experiences and Lessons Learned

From the mid-1980s to the present, the Department of Energy (DOE) has developed, tested, and deployed diverse bioremediation strategies for chlorinated volatile organic compounds (cVOCs). A systematic review of these projects after decades of activity provides an opportunity to identify crosscutting themes and lessons learned. The knowledge provided by a DOE bioremediation retrospective represents a resource to support current and future bioremediation operations, and future decisions related to cVOC bioremediation. This systematic review examined the design, objectives, performance and outcomes for remediation projects at DOE sites including Savannah River, Hanford, Idaho, Mound and Pinellas. The results were used to identify emergent themes to provide actionable insights. The bioremediation retrospective technical team first developed standardized criteria to support the systematic review. Then, the evaluation was performed using a sequential process that was informed by local technical experts who identified and provided the structured information that served as the basis for the evaluation. The participation of these experts was invaluable to the effort. Importantly, DOE cVOC bioremediation efforts were implemented based on the foundational knowledge developed by U.S. Department of Defense (DoD) strategic and applied environmental technology development and certification programs, as well as technical, policy and regulatory guidance from the U.S. Environmental Protection Agency (EPA), Interstate Technology and Regulatory Council (ITRC), U.S. Geological Survey (USGS), industry, and universities. To maximize the value of the DOE cVOC bioremediation retrospective, the systematic review strategy focused on identifying important DOE-specific experiences, trends and lessons learned that would extend the knowledge available from these other key entities.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2021

Evaluating Automated Face Identity-Masking Methods with Human Perception and a Deep Convolutional Neural Network

Face de-identification (or “masking”) algorithms have been developed in response to the prevalent use of video recordings in public places. Here, we evaluated the success of face identity masking for human perceivers and a deep convolutional neural network (DCNN). Eight de-identification algorithms were applied to videos of drivers’ faces, while they actively operated a motor vehicle. These masks were pre-selected to be applicable to low-quality video and to maintain coarse information about facial actions. Humans studied high-resolution images to learn driver identities and were tested on their recognition of active drivers in low-resolution videos. Faces in the videos were either unmasked or were masked by one of the eight algorithms. When participants were tested immediately after learning (Experiment 1), all masks reduced identification, with six of eight masks reducing identification to extremely poor performance. In a second experiment, two of the most effective masks were tested after a delay of 7 or 28 days. The delay did not further reduce identification of the masked faces. In all masked conditions, participants maintained stringent decision criteria, with low confidence in recognition, further indicating the effectiveness of the masks. Next, the DCNN performed an identity-matching task between high-resolution images and masked videos—a task analogous to that done by humans. The pattern of accuracy for the DCNN mirrored some, but not all, aspects of human performance, highlighting the need to test the effectiveness of identity masking for both humans and machines. The DCNN was also tested on its ability to match identity between masked and unmasked versions of the same video, based only on the face. DCNN performance for the eight masks offers insight into the nature of the information in faces that is coded in these networks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Promoting Physical Activity During Pregnancy and the Postpartum Period

Introduction Physical activity is important for improving and maintaining overall health across the life span, including during and after pregnancy. Achieving recommended levels of physical activity can be challenging during pregnancy and the postpartum period. The US Office of Disease Prevention and Health Promotion sought to promote physical activity during and after pregnancy through the development of health education materials for the Move Your Way campaign. Research was conducted with pregnant and postpartum people to learn what types of messages and materials would encourage physical activity in these populations. Methods Participants were recruited from 3 regions of the United States to participate in 90‐minute virtual focus groups. Eligible participants were aged 18 years or older and either pregnant or 6 weeks to 1 year postpartum. Participants were asked questions about their beliefs, attitudes, and perceptions about physical activity and prompted to provide feedback on health promotion messages and images. Sessions were recorded, transcribed, and analyzed for key themes. Results Twenty‐four focus groups were conducted with 48 pregnant participants and 52 postpartum participants. Sixteen sessions were conducted in English and 8 were conducted in Spanish. Most participants had questions about how much physical activity is recommended, and many cited their health care provider as a trusted source of information. Participants responded positively to materials that acknowledged the uniqueness of each pregnant or postpartum experience, referenced gradually increasing physical activity levels, highlighted the benefits of physical activity, focused on safety, addressed common barriers, and displayed realistic representations of physical activity. Discussion There is an opportunity to improve messaging about physical activity during and after pregnancy. To better promote physical activity, perinatal health care providers and other health professionals can share information about recommended amounts of physical activity, communicate the benefits, and promote realistic and achievable physical activity messages that address common barriers in these populations.

Nursing↗

NASA NTRS2011

The Application of Lean Thinking Principles and Kaizen Practices for the Successful Development and Implementation of the Ares I-X Flight Test Rocket and Mission

On October 28, 2009 the Ares I-X flight test rocket launched from Kennedy Space Center and flew its suborbital trajectory as designed. The mission was successfully completed as data from the test, and associated development activities were analyzed, transferred to stakeholders, and well documented. Positive lessons learned from Ares I-X were that the application of lean thinking principles and kaizen practices are effective in streamlining development activities. Ares I-X, like other historical rocket development projects, was hampered by technical, cost, and schedule challenges and if not addressed boldly could have resulted in cancellation of the test. The mission management team conducted nine major meetings, referred to as lean events, across its elements to assess plans, procedures, processes, requirements, controls, culture, organization, use of resources, and anything that could be changed to optimize schedule or reduce risk. The preeminent aspect of the lean events was the focus on value added activities and the removal or at least reduction in non-value activities. Trained Lean Six Sigma facilitators assisted the Ares I-X developers in conducting the lean events. They indirectly helped formulate the mission s own unique methodology for assessing schedule. A core team was selected to lead the events and report to the mission manager. Each activity leveraged specialized participants to analyze the subject matter and its related processes and then recommended alternatives and solutions. Stakeholders were the event champions. They empowered and encouraged the team to succeed. The keys to success were thorough preparation, honest dialog, small groups, adherence to the Ares I-X ground rules, and accountability through disciplined reporting and tracking of actions. This lean event formula was game-changing as demonstrated by the success of Ares I-X. It is highly recommended as a management tool to help develop other complex systems efficiently. The key benefits for Ares I-X were obtaining unambiguous schedule margin, defining enabling options for risk reduction, and most importantly a stronger more unified team.

Askins, B. R.↗

DOE OSTI2022

Emulation Modeling for Development of Cyber-Defense Capabilities for Satellite Systems

The objective of this project was to develop a novel capability to generate synthetic data sets for the purpose of training Machine Learning (ML) algorithms for the detection of malicious activities on satellite systems. The approach experimented with was to a) generate sparse data sets using emulation modeling and b) enlarge the sparse data using Generative Adversarial Networks (GANs). We based our emulation modeling on the Open Source NASA Operational Simulator for Small Satellites (NOS3) developed by the Katherine Johnson Independent Verification and Validation (IV&V) program in West Virginia. Significant new capabilities on NOS3 had to be developed for our data set generation needs. To expand these data sets for the purpose of training ML, we experimented with a) Extreme Learning Machines (ELMs) and b) Wasserstein-GANs (WGAN-GP).

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

NASA NTRS1993

Profile of NASA software engineering: Lessons learned from building the baseline

It is critically important in any improvement activity to first understand the organization's current status, strengths, and weaknesses and, only after that understanding is achieved, examine and implement promising improvements. This fundamental rule is certainly true for an organization seeking to further its software viability and effectiveness. This paper addresses the role of the organizational process baseline in a software improvement effort and the lessons we learned assembling such an understanding for NASA overall and for the NASA Goddard Space Flight Center in particular. We discuss important, core data that must be captured and contrast that with our experience in actually finding such information. Our baselining efforts have evolved into a set of data gathering, analysis, and crosschecking techniques and information presentation formats that may prove useful to others seeking to establish similar baselines for their organization.

Hall, Dana↗

NASA NTRS2016

Proving Ground Potential Mission and Flight Test Objectives and Near Term Architectures

NASA is developing a Pioneering Space Strategy to expand human and robotic presence further into the solar system, not just to explore and visit, but to stay. NASA's strategy is designed to meet technical and non-technical challenges, leverage current and near-term activities, and lead to a future where humans can work, learn, operate, and thrive safely in space for an extended, and eventually indefinite, period of time. An important aspect of this strategy is the implementation of proving ground activities needed to ensure confidence in both Mars systems and deep space operations prior to embarking on the journey to the Mars. As part of the proving ground development, NASA is assessing potential mission concepts that could validate the required capabilities needed to expand human presence into the solar system. The first step identified in the proving ground is to establish human presence in the cis-lunar vicinity to enable development and testing of systems and operations required to land humans on Mars and to reach other deep space destinations. These capabilities may also be leveraged to support potential commercial and international objectives for Lunar Surface missions. This paper will discuss a series of potential proving ground mission and flight test objectives that support NASA's journey to Mars and can be leveraged for commercial and international goals. The paper will discuss how early missions will begin to satisfy these objectives, including extensibility and applicability to Mars. The initial capability provided by the launch vehicle will be described as well as planned upgrades required to support longer and more complex missions. Potential architectures and mission concepts will be examined as options to satisfy proving ground objectives. In addition, these architectures will be assessed on commercial and international participation opportunities and on how well they develop capabilities and operations applicable to Mars vicinity missions.

Smith, R. Marshall↗

NASA NTRS2011

International Space Station (ISS) Risk Reduction Activities

As the assembly of the ISS nears completion, it is worthwhile to step back and review some of the actions pursued by the Program in recent years to reduce risk and enhance the safety and health of ISS crewmembers, visitors, and space flight participants. While the ISS requirements and initial design were intended to provide the best practicable levels of safety, it is always possible to reduce risk -- given the determination and commitment to do so. The following is a summary of some of the steps taken by the ISS Program Manager, by our International Partners, by hardware and software designers, by operational specialists, and by safety personnel to continuously enhance the safety of the ISS. While decades of work went into developing the ISS requirements, there are many things in a Program like the ISS that can only be learned through actual operational experience. These risk reduction activities can be divided into roughly three categories: (1) Areas that were initially noncompliant which have subsequently been brought into compliance or near compliance (i.e., Micrometeoroid and Orbital Debris [MMOD] protection, acoustics) (2) Areas where initial design requirements were eventually considered inadequate and were subsequently augmented (i.e., Toxicity Level 4 materials, emergency hardware and procedures) (3) Areas where risks were initially underestimated, and have subsequently been addressed through additional mitigation (i.e., Extravehicular Activity [EVA] sharp edges, plasma shock hazards) Due to the hard work and cooperation of many parties working together across the span of nearly a decade, the ISS is now a safer and healthier environment for our crew, in many cases exceeding the risk reduction targets inherent in the intent of the original design. It will provide a safe and stable platform for utilization and discovery.

Fodroci, Michael↗

DOE OSTI2022

Contextual Active Online Model Selection with Expert Advice

How can we collect the most useful labels to learn a model selection policy, when presented with arbitrary heterogeneous data streams? In this paper, we formulate this task as a contextual active model selection problem, where at each round the learner receives an unlabeled data point along with a context. The goal is to output the best model for any given context without obtaining an excessive amount of labels. In particular, we focus on the task of selecting pre-trained classifiers, and propose a contextual active model selection algorithm (CAMS), which relies on a novel uncertainty sampling query criterion defined on a given policy class for adaptive model selection. In comparison to prior art, our algorithm does not assume a globally optimal model. We provide rigorous theoretical analysis for the regret and query complexity under both adversarial and stochastic settings. Our experiments on several benchmark classification datasets demonstrate the algorithm’s effectiveness in terms of both regret and query complexity. Notably, to achieve the same accuracy, CAMS incurs less than 10% of the label cost when compared to the best online model selection baselines on CIFAR10.

Liu, Xuefeng↗