Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning control”

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 1,567 records · Page 87

Autonomous convergence of STM control parameters using Bayesian optimization

Scanning tunneling microscopy (STM) is a widely used tool for atomic imaging of novel materials and their surface energetics. However, the optimization of the imaging conditions is a tedious process due to the extremely sensitive tip–surface interaction, thus limiting the throughput efficiency. In this paper, we deploy a machine learning (ML)-based framework to achieve optimal atomically resolved imaging conditions in real time. The experimental workflow leverages the Bayesian optimization (BO) method to rapidly improve the image quality, defined by the peak intensity in the Fourier space. The outcome of the BO prediction is incorporated into the microscope controls, i.e., the current setpoint and the tip bias, to dynamically improve the STM scan conditions. We present strategies to either selectively explore or exploit across the parameter space. As a result, suitable policies are developed for autonomous convergence of the control parameters. The ML-based framework serves as a general workflow methodology across a wide range of materials.

97 MATHEMATICS AND COMPUTING↗

On the Performance of Detecting Injection of Fabricated Messages into the CAN Bus

There have been several public demonstrations of attacks on connected vehicles showing the ability of an attacker to take control of a targeted vehicle by injecting messages into their Controller Area Network (CAN) bus. In this article, using injected speed reading and Revolutions Per Minute (RPM) reading messages in in-motion vehicle, we examine the ability of the Pearson correlation and the unsupervised learning methods k-means clustering and Hidden Markov Model (HMM) to differentiate ’no-attack’ and ’under-attack’ states of the given vehicle. We found that the Pearson correlation distinguishes the two states, the k-means clustering method has an acceptable accuracy but high false positive rate and HMM detects attacks with acceptable detection rate but has a high false positive in detecting attacks from speed readings when there is no attack. The accuracy of these unsupervised learning methods are comparable to the ones of the supervised learning methods used by CAN bus Intrusion Detection System (IDS) suppliers. In addition, the article shows that studying CAN anomaly detection techniques using off-vehicle test facilities may not properly evaluate the performance of the detection techniques. Finally, the results suggest using other features besides the data content of the CAN messages and integrate knowledge about how the Electronic Control Units (ECUs) collaborate in building effective techniques for the detection of injection of fabricated message attacks.

97 MATHEMATICS AND COMPUTING↗

LED Lighting in a Performing Arts Building at the University of Florida

The U.S. DOE GATEWAY Demonstration Program supports demonstrations of high-performance solid-state lighting (SSL) products in order to develop empirical data and experience with the in-the-field applications of this advanced lighting technology. This report describes the process and results of the 2013 - 2014 GATEWAY demonstration of SSL technology in the Nadine McGuire Theatre and Dance Pavilion at the University of Florida, Gainesville, FL. The LED solutions combined with dimming controls utilized in four interior spaces - the Acting Studio, Dance Studio, Scene Shop, and Dressing Room - received high marks from instructors, students/performers, and reduced energy use in all cases. The report discusses in depth and detail of each project area including specifications, energy savings, and user observations. The report concludes with lessons learned during the demonstration.

Demonstration↗

Data-driven based coordinated smart inverter control for distributed energy resources

Smart inverters (SI) for distributed energy resources (DER) are becoming popular since they have the ability to stabilize as well as restore the voltage and frequency of power systems. Aiming at establishing the mathematical models combined with SI control methods, multiple optimization methods are developed. However, the computational complexity of solving such a mathematical model with various uncertainties limits the real-time application of the SI control. To conquer this challenge, a data-driven-based SI control approach is developed to achieve coordinated control in the high penetration DER system. First, an optimization problem for maximizing the active power generation and minimizing the power loss is designed using the Volt/VAR control. To reduce the time consumption, the recurrent neural network (RNN) is proposed to model the relationship between the uncertainties and control actions during the offline site. The RNN with different sub-structures such as the long short-term memory cell and gated recurrent unit cell are included to enrich the diversity of features. In the last stage, different experiment comparisons, including multiple uncertainties maps and stateof- art machine learning methods, are conducted to verify the effectiveness of the proposed method based on the IEEE 123 bus power system. The results demonstrate that the proposed method can effectively achieve a rapid and coordinated control with a lower error rate.

Qiu, Wei↗

Commissioning and Operation of a Robotic Arm for Waste Retrieval at Trawsfynydd NPP, North Wales - 12091

Trawsfynydd is one of the UK's first generation Magnox nuclear power plants. It started operation in 1965 and ceased generation in 1991. Before the site can enter the 'care and maintenance' phase a number of wet and dry waste stores around the site must be emptied and their contents made safe. Wet wastes include sludges and resins produced during the operating life of the NPP. The sludges and resins are stored in a number of different tanks that vary significantly in terms of size, shape, internal features and access. A dexterous long reach manipulator arm has been designed and built to facilitate tank clearance. Commissioning of the arm was carried out in parallel with Factory Acceptance Testing (FAT) at the manufacturer's site in Colorado, USA. In addition to basic functional testing this work included a full range of task based testing to ensure that the arm, tools, control system and support equipment were thoroughly exercised in representative conditions. Trawsfynydd is one of the lead sites in the UK's program for nuclear plant decommissioning. As such the lessons learned, both in terms of technology and process, will be applicable across the remainder of the fleet. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Transferable dispersion-aware machine learning interatomic potentials for multilayer transition metal dichalcogenide heterostructures

Stacking atomically thin transition metal dichalcogenides (TMDs) into heterostructures enables exploration of exotic quantum phases, particularly through twist-angle-controlled moiré superlattices. These structures exhibit novel electronic and optical behaviors driven by atomic-scale structural reconstruction. However, studying such systems with DFT is computationally demanding due to their large unit cells and van der Waals (vdW) interactions between layers. To address this, we develop a transferable neural network potential (NNP) that includes long-range vdW corrections up to 12Å with minimal overhead. Trained on vdW-corrected DFT data for Mo- and W-based TMDs with S, Se, and Te, the NNP accurately models monolayers, bilayers, heterostructures, and their interaction with h-BN substrates. It reproduces equilibrium structures, energy landscapes, phonon dispersions, and matches experimental atomic reconstructions in twisted WS2 and MoS2/WSe2 systems. We demonstrate that our NNP achieves DFT-level accuracy and high computational efficiency, enabling large-scale simulations of TMD-based moiré superlattices both with and without substrates.

materials for energy and catalysis↗

Multiomics and deep learning dissect regulatory syntax in human development

Transcription factors establish cell identity during development by binding regulatory DNA in a sequence-specific manner, often promoting local chromatin accessibility and regulating gene expression1. Mapping accessible chromatin offers critical insights into transcriptional control, but available datasets for human development are restricted to bulk tissue, single organs or single modalities2. Here we present the Human Development Multiomic Atlas, a single-cell atlas of chromatin accessibility and gene expression from 817,740 fetal cells across 12 organs, spanning 203 cell types and more than 1 million candidate cis-regulatory elements, many of which exhibit organ-specific in vivo enhancer activity. Deep learning models trained to predict accessibility from local DNA sequence unravel a comprehensive lexicon of motifs that influence accessibility, including composite motifs exhibiting distinct syntactic constraints that are predicted to mediate transcription factor cooperativity. We identify ‘hard’ syntactic rules requiring precise motif spacing and orientation, ‘soft’ rules allowing flexible motif arrangements, and ubiquitous motifs inhibiting accessibility. Model-based interpretation of genetic variants reveals that disruption of motifs with positive and negative effects is associated with concordant effects on gene expression. Our work delineates how motif syntax governs cell-type-specific chromatin accessibility and provides a foundational resource for decoding cis-regulatory logic and interpreting genetic variation during human development.

59 BASIC BIOLOGICAL SCIENCES↗

SRF cavity instability detection with machine learning at CEBAF

During the operation of the Continuous Electron Beam Accelerator Facility (CEBAF), one or more unstable superconducting radio-frequency (SRF) cavities often cause beam loss trips while the unstable cavities themselves do not necessarily trip off. The present RF controls for the legacy cavities report at only 1 Hz, which is too slow to detectfast transient instabilities during these trip events. These challenges make the identification of an unstable cavity out of the hundreds installed at CEBAF a difficult and time-consuming task. To tackle these issues, a fast data acquisition system (DAQ) for the legacy SRF cavities has been developed, which records the sample at 5 kHz. An unsupervised learning framework has been developed to identify anomalous SRF cavity behavior. We will discuss the present status of the DAQ system and our framework, along with recent successes in detecting anomalous cavity behavior. Overall, our method offers a practical solution for identifying unstable SRF cavities, contributing to increased beam availability and machine reliability.

Accelerator Physics↗

Multitask Machine Learning of Collective Variables for Enhanced Sampling of Rare Events

Computing accurate reaction rates is a central challenge in computational chemistry and biology because of the high cost of free energy estimation with unbiased molecular dynamics. In this work, a data-driven machine learning algorithm is devised to learn collective variables with a multitask neural network, where a common upstream part reduces the high dimensionality of atomic configurations to a low dimensional latent space and separate downstream parts map the latent space to predictions of basin class labels and potential energies. Here, the resulting latent space is shown to be an effective low-dimensional representation, capturing the reaction progress and guiding effective umbrella sampling to obtain accurate free energy landscapes. This approach is successfully applied to model systems including a 5D Müller Brown model, a 5D three-well model, the alanine dipeptide in vacuum, and an Au(110) surface reconstruction unit reaction. It enables automated dimensionality reduction for energy controlled reactions in complex systems, offers a unified and data-efficient framework that can be trained with limited data, and outperforms single-task learning approaches, including autoencoders.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

TH-C-12A-12: Veritas: An Open Source Tool to Facilitate User Interaction with TrueBeam Developer Mode

Purpose: To address the challenges of creating delivery trajectories and imaging sequences with TrueBeam Developer Mode, a new open-source graphical XML builder, Veritas, has been developed, tested and made freely available. Veritas eliminates most of the need to understand the underlying schema and write XML scripts, by providing a graphical menu for each control point specifying the state of 30 mechanical/dose axes. All capabilities of Developer Mode are accessible in Veritas. Methods: Veritas was designed using QT Designer, a ‘what-you-is-what-you-get’ (WYSIWIG) tool for building graphical user interfaces (GUI). Different components of the GUI are integrated using QT's signals and slots mechanism. Functionalities are added using PySide, an open source, cross platform Python binding for the QT framework. The XML code generated is immediately visible, making it an interactive learning tool. A user starts from an anonymized DICOM file or XML example and introduces delivery modifications, or begins their experiment from scratch, then uses the GUI to modify control points as desired. The software automatically generates XML plans following the appropriate schema. Results: Veritas was tested by generating and delivering two XML plans at Brigham and Women's Hospital. The first example was created to irradiate the letter ‘B’ with a narrow MV beam using dynamic couch movements. The second was created to acquire 4D CBCT projections for four minutes. The delivery of the letter ‘B’ was observed using a 2D array of ionization chambers. Both deliveries were generated quickly in Veritas by non-expert Developer Mode users. Conclusion: We introduced a new open source tool Veritas for generating XML plans (delivery trajectories and imaging sequences). Veritas makes Developer Mode more accessible by reducing the learning curve for quick translation of research ideas into XML plans. Veritas is an open source initiative, creating the possibility for future developments and collaboration with other researchers. I am an employee of Varian Medical Systems.

07 ISOTOPE AND RADIATION SOURCES↗

Mucin 4 is a cellular biomarker of necrotizing bronchiolitis in influenza A virus infection

Influenza A virus (IAV) in the human and swine host infects epithelial cells lining the respiratory tract causing a necrotizing bronchitis and bronchiolitis. These epithelial surfaces are protected by large glycoproteins called mucins. Mucin 4 (MUC4) is a transmembrane mucin that consists of an alpha subunit responsible for surface protection and intracellular beta subunit involved in signal transduction which repress apoptosis and stimulate epithelial proliferation. This study was designed to determine the expression and potential role of MUC4 during IAV infection. We used immunohistochemistry in combination with machine learning image analysis to quantify differential protein expression of MUC4 subunits in IAV-infected and uninfected lung in a porcine model. MUC4 protein basal expression in control animals varied significantly by litter. MUC4 protein expression was significantly increased in bronchioles with necrotizing bronchiolitis compared to histologically normal bronchioles, likely representing a regenerative response to restore mucosal integrity of conducting airways. Understanding the impact of differential MUC4 expression among healthy individuals and during IAV infection will facilitate control strategies by elucidating mechanisms associated with susceptibility to IAV that can be therapeutically or genetically regulated and may be extended to other respiratory diseases.

60 APPLIED LIFE SCIENCES↗

Estimating vehicle fuel economy from overhead camera imagery and application for traffic control

In this work, we explore the ability to estimate vehicle fuel consumption using imagery from overhead fisheye lens cameras deployed as traffic sensors. We utilize this information to simulate vision-based control of a traffic intersection, with a goal of improving fuel economy with minimal impact to mobility. We introduce the ORNL Overhead Vehicle Dataset (OOVD), consisting of a data set of paired, labeled vehicle images from a ground-based camera and an overhead fisheye lens traffic camera. The data set includes segmentation masks based on Gaussian mixture models for vehicle detection. We show the dataset utility through three applications: the estimate of fuel consumption based on segmentation bounding boxes, vehicle discrimination for those vehicles with largest bounding boxes, and a fine-grained classification on a limited number of vehicle makes and models using a pre-trained set of convolutional neural network models. We compare these results with estimates based on a large open-source data set based on web-scraped imagery. Finally, we show the utility of the approach using reinforcement learning in a traffic simulator using the open source Simulation of Urban Mobility (SUMO) package. Our results show the feasibility of the approach for controlling traffic lights for better fuel efficiency based solely on visual vehicle estimates from commercial, fisheye lens cameras.

Karnowski, Thomas↗

A real-time machine learning-based disruption predictor in DIII-D

A disruption prediction algorithm, named DPRF (Disruption Prediction using Random Forests), has run in real-time in the DIII-D plasma control system (PCS) over more than 900 discharges. DPRF naturally provides a probability mapping associated to its predictions, i.e. the disruptivity signal, now incorporated in the DIII-D PCS. Here, we report on disruption prediction accomplishments in terms of shot-by-shot performances, by simulating alarms on each discharge as in the PCS framework. Due to the optimised performance metric chosen to evaluate DPRF, we find that almost all disruptive discharges are detected in average with few hundred of milliseconds of warning time, but this comes at a high cost of false alarms produced. Performances are not satisfying ITER requirements, where the success rate has to be higher than 95%, but this is not completely unexpected. DPRF is trained on many years of major disruptions occurring during the flattop phase of the plasma current on DIII-D, but without any differentiation by cause. Furthermore, we find that DPRF is affected by a relatively high fraction of false alarms occurring during the first 500 milliseconds from the flattop onset. This subtle effect, more evident on the discharges where DPRF ran in real-time, can be marginalized by taking specific precautions on the validity range of the predictions, and performances do improve. Even if presently burdened by some limitations, DPRF provides an incredible and novel advantage. Thanks to the feature contribution analysis (e.g., the identification of which signals contributed to triggering an alarm), it is possible to interpret and explain DPRF predictions. It is the first time that such interpretability features is exploited by a disruption predictor: by uncovering the disruption events' causes, a better understanding of disruption dynamics is achieved, and a clear path toward the design of disruption avoidance strategies can be provided.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Appraising the value of independent EIA follow-up verifiers

Independent Environmental Impact Assessment (EIA) follow-up verifiers such as monitoring agencies, checkers, supervisors and control officers are active on various construction sites across the world. There are, however, differing views on the value that these verifiers add and very limited learning in EIA has been drawn from independent verifiers. This paper aims to appraise how and to what extent independent EIA follow-up verifiers add value in major construction projects in the developing country context of South Africa. A framework for appraising the role of independent verifiers was established and four South African case studies were examined through a mixture of site visits, project document analysis, and interviews. Appraisal results were documented in the performance areas of: planning, doing, checking, acting, public participating and integration with other programs. The results indicate that independent verifiers add most value to major construction projects when involved with screening EIA requirements of new projects, allocation of financial and human resources, checking legal compliance, influencing implementation, reporting conformance results, community and stakeholder engagement, integration with self-responsibility programs such as environmental management systems (EMS), and controlling records. It was apparent that verifiers could be more creatively utilized in pre-construction preparation, providing feedback of knowledge into assessment of new projects, giving input to the planning and design phase of projects, and performance evaluation. The study confirms the benefits of proponent and regulator follow-up, specifically in having independent verifiers that disclose information, facilitate discussion among stakeholders, are adaptable and proactive, aid in the integration of EIA with other programs, and instill trust in EIA enforcement by conformance evaluation. Overall, the study provides insight on how to harness the learning opportunities arising from EIA follow-up through the appointment of independent verifiers. - Highlights: • A framework for appraising the role of independent verifiers is established. • The value added to EIA follow-up by independent verifiers in South Africa is documented. • Verifiers add most value when involved with screening, checking compliance, influencing decisions and community engagement. • Verifiers could be more creatively utilized in pre-construction preparation, giving feedback, and performance evaluation.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

The Continuously Evolving Land Use Control Climate in FUSRAP - 12285

In recent years the topic of Land Use Controls (LUCs) has become much more prevalent in the Formerly Utilized Sites Remedial Action Program (FUSRAP) for a number of reasons. Some regulatory agencies have been placing much more emphasis on this topic than they historically did. Also as the FUSRAP has matured, more sites are approaching a point in the project lifecycle that LUCs are needed to be implemented. There are many issues, some site specific, some agency specific, and some programmatic, that may arise when addressing LUCs on a FUSRAP site. These issues can span the life of a project from planning to implementation. As the emphasis on LUCs increases at a fast pace, USACE is faced with the task of developing consistency in how we respond, and at the same time leaving enough latitude for projects to accomplish their individual missions while taking into consideration the site specific concerns. The Land Use Controls arena encompasses a large number of tools to address the matter at hand. There are numerous mechanisms that can accomplish Land Use Control goals, some of which include administrative controls and engineering controls. This paper will discuss some of the mechanisms being utilized by USACE at our FUSRAP projects. Having a better understanding of how LUCs are currently being handled in the FUSRAP will be beneficial to project delivery teams in order to make the best decisions moving through the project lifecycle. Being aware of LUC requirements and options at an early stage in a project will help a team effectively plan for and execute the chosen alternative for remedial action. There are a number of guidance tools from various other agencies that exist for consideration during Land Use Control planning and implementation. The USACE is currently evaluating these guidance tools to determine applicability and impact to FUSRAP projects. Some of these tools are under review at Army and the Department of Defense. Critical to this evaluation is internal team coordination as well as coordination and input from stakeholders. With guidance on LUCs available from a number of entities, the USACE now has the opportunity to develop consistency in determining how LUCs are handled on FUSRAP projects. The FUSRAP ER, ER 200-1-4, is currently being revised and will broadly touch on LUCs. This broad approach was a result of recognizing the magnitude of variances and site specific components that come into play when applying LUCs to our FUSRAP sites. As land use controls scenarios continue to arise on our FUSRAP sites, the methods for how our project teams address those will continue to evolve. The Program is continuing to develop guidance on how to address LUCs. In the interim, our FUSRAP projects can share lessons learned on the LUCs they are implementing. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗