Engineering Papers⌕ Search

SEARCH · Engineering Papers

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.

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

At least 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Improving Self-Driving Labs: Quantifying System-Level Experiment Repeatability and Broadening Instrument-Level Compatibility

Modular Autonomous Research System (MARS) is a self-driving laboratory (SDL) which performs wet-lab science with peptide-lanthanide combinations in an automated and, ultimately, an autonomous manner to aid in soil analysis for domestic lithium mining. Autonomous experimentation involves automated experimentation, experiment planning, and active learning. MARS consists of a 6-axis robotic arm (UR5e) on a linear rail, pipette robots (Opentrons 2), and microplate readers. These components transport, operate on, and collect data with chemical solutions in standard labware. For effective autonomy, MARS must perform system-level labware operations repeatably, plan experiments autonomously, and be portable between research-domains. Repeatability is evaluated by labware placement precision, such that future operations can properly locate labware, as well as the elapsed time, so that low variance mean estimates of experiment duration can inform high-level researcher decision making. Autonomous experiment planning is the next step to decouple experimentation from human management; however, there is a conflict between the ideal system-level experiment goals and the constraints imposed by instruments’ limitations. Sub-domain portability is a long-term goal to extend MARS’ research beyond the chemistry of peptide-lanthanide binding to other sub-domains without having to invest significant overhead to system retrofitting. To address these goals, we manually trained the robotic arm labware placement and modelled statistical failurerate and uncertainty Additionally, we benchmarked the duration and variance of each experiment sub-operation as a heuristic for research decision making. Next, we use a parameterized geometric program (PGP) approach to design experiments that optimize system-level objectives and satisfy instrument-level constraints. Lastly, we proposed a Python framework to maximize MARS’ extensibility to other scientific sub-domains through a JSON-based experiment specification.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Fermilab Booster loss modelling and rebalancing using Bayesian methods

Fermilab Booster is being upgraded for the PIP-II project to support 20Hz ramp rate at higher intensities. Loss trip limits determine the achievable peak power. To meet PIP-II requirements, losses need to be halved as compared to current levels. Losses primarily occur at injection and transition crossing, with both gradually increasing and threshold-like intensity-dependent behaviors. The existing simulation models are not yet good enough for quantitative loss predictions. In practice, it will be necessary to tune up the Booster using iterative methods and operator intuition. In this paper we present an effort to systematically model Booster losses using active learning (Bayesian exploration) techniques, and subsequently to rebalance them for higher trip limit margins. We first created several sets of spatially and temporally isolated orbit and optics knobs, and trained Gaussian process models for each beam loss monitor as well as beam current. This is a complex task due to safety and timing requirements – we discuss mitigations such as uncertainty constraints and approximate fitting. Once models are stable, we perform large-scale single and multi-objective tuning using scalarized objectives made up of critical beam loss locations. Our results demonstrate significant rebalancing of losses, increasing trip margins, as well as an overall improvement in beam transmission efficiency. We are exploring how to combine existing simulations with experimental data and automate the collection procedure so that more advanced surrogate models can be created over time.

Kuklev, Nikita [Fermilab]↗
NASA NTRS1987

Tutoring electronic troubleshooting in a simulated maintenance work environment

A series of intelligent tutoring systems, or intelligent maintenance simulators, is being developed based on expert and novice problem solving data. A graded series of authentic troubleshooting problems provides the curriculum, and adaptive instructional treatments foster active learning in trainees who engage in extensive fault isolation practice and thus in conditionalizing what they know. A proof of concept training study involving human tutoring was conducted as a precursor to the computer tutors to assess this integrated, problem based approach to task analysis and instruction. Statistically significant improvements in apprentice technicians' troubleshooting efficiency were achieved after approximately six hours of training.

Gott, Sherrie P.↗
NASA NTRS1993

Schools of the Pacific rainfall climate experiment

The SPaRCE program is a cooperative rainfall climate field project involving high school and college level students and teachers from various Pacific island and atoll nations. The goals of the SPaRCE program are: (1) to foster interest and increase understanding among Pacific-area students and teachers of climate and climate change; (2) to educate the students and teachers as to the importance of rainfall in the Pacific area to climate studies; (3) to provide the students and teachers an opportunity of making a major contribution to the global climate research effort by collecting and analyzing Pacific rainfall data; and (4) to incorporate collected rainfall observations into a comprehensive Pacific daily rainfall data base to be used for climate research purposes. Schools participating in SPaRCE have received standard raingauges with which to measure rainfall at their sites. Students learned to site and use their raingauges by viewing a video produced at the University of Oklahoma. Four more videos will be produced which will include information on Earth's atmosphere, global climate and climate change, regional climate and implications of climate change, and how to analyze and use the rainfall data they are collecting. The videos are accompanied by workbooks which summarize the main points of each video, and contain concrete learning activities to help the student better understand climate and climate change. Following each video, interactive sessions are held with the students using the PEACESAT (Pan-Pacific Education And Communication Experiments by Satellite) satellite radio communication system.

Postawko, S. E.↗
NASA NTRS1993

Toward lowering the cost of mission operations

The mission operations system is one of the more significant drivers of the cost of the mission operations and data analysis segment of missions. In large or long-lived projects, the MOS can also be a driver in total mission cost. Larger numbers of missions, together with an increasingly cost-conscious environment, dictate that future missions must more strictly control costs as they perform to their requirements. It is therefore prudent to examine the conduct of past missions for ways to conserve resources. In this paper we review inputs made to past projects' 'lessons-learned' activities, in which personnel from past projects (among other things) identified major cost drivers of MOS's and considered how economies were or might have been realized in both design and performance of their MOS. Common themes among four such reviews are summarized in an attempt to provide suggestions for cost reduction in future missions.

Wall, S. D.↗
NASA NTRS1999

Launch Vehicle Design Process Description and Training Formulation

A primary NASA priority is to reduce the cost and improve the effectiveness of launching payloads into space. As a consequence, significant improvements are being sought in the effectiveness, cost, and schedule of the launch vehicle design process. In order to provide a basis for understanding and improving the current design process, a model has been developed for this complex, interactive process, as reported in the references. This model requires further expansion in some specific design functions. Also, a training course for less-experienced engineers is needed to provide understanding of the process, to provide guidance for its effective implementation, and to provide a basis for major improvements in launch vehicle design process technology. The objective of this activity is to expand the description of the design process to include all pertinent design functions, and to develop a detailed outline of a training course on the design process for launch vehicles for use in educating engineers whose experience with the process has been minimal. Building on a previously-developed partial design process description, parallel sections have been written for the Avionics Design Function, the Materials Design Function, and the Manufacturing Design Function. Upon inclusion of these results, the total process description will be released as a NASA TP. The design function sections herein include descriptions of the design function responsibilities, interfaces, interactive processes, decisions (gates), and tasks. Associated figures include design function planes, gates, and tasks, along with other pertinent graphics. Also included is an expanded discussion of how the design process is divided, or compartmentalized, into manageable parts to achieve efficient and effective design. A detailed outline for an intensive two-day course on the launch vehicle design process has been developed herein, and is available for further expansion. The course is in an interactive lecture/workshop format to engage the participants in active learning. The course addresses the breadth and depth of the process, requirements, phases, participants, multidisciplinary aspects, tasks, critical elements,as well as providing guidance from previous lessons learned. The participants are led to develop their own understanding of the current process and how it can be improved. Included are course objectives and a session-by-session outline of course content. Also included is an initial identification of visual aid requirements.

Atherton, James↗
NASA NTRS2007

Family Science Night: Changing Perceptions One Family at a Time

If students are not encouraged to succeed in science, mathematics, and technology classes at school, efforts to improve the quality of content and teaching in these subjects may be futile. Parents and families are in a unique position to encourage children to enroll and achieve in these classes. The NASA Goddard Space Flight Center Family Science Night program invites middle school students and their families to explore the importance of science and technology in our daily lives by providing a venue for families to comfortably engage in learning activities that change their perception and understanding of science - making it more practical and approachable for participants of all ages. Family Science Night strives to change the way that students and their families participate in science, within the program and beyond.

Pesnell, W. D.↗
NASA NTRS2009

NASA Tech Briefs, November 2009

Topics covered include: Cryogenic Chamber for Servo-Hydraulic Materials Testing; Apparatus Measures Thermal Conductance Through a Thin Sample from Cryogenic to Room Temperature; Rover Attitude and Pointing System Simulation Testbed; Desktop Application Program to Simulate Cargo-Air-Drop Tests; Multimodal Friction Ignition Tester; Small-Bolt Torque-Tension Tester; Integrated Spacesuit Audio System Enhances Speech Quality and Reduces Noise; Hardware Implementation of a Bilateral Subtraction Filter; Simple Optoelectronic Feedback in Microwave Oscillators; Small X-Band Oscillator Antennas; Free-Space Optical Interconnect Employing VCSEL Diodes; Discrete Fourier Transform Analysis in a Complex Vector Space; Miniature Scroll Pumps Fabricated by LIGA; Self-Assembling, Flexible, Pre-Ceramic Composite Preforms; Flight-speed Integral Image Analysis Toolkit; Work Coordination Engine; Multi-Mission Automated Task Invocation Subsystem; Autonomously Calibrating a Quadrupole Mass Spectrometer; Determining Spacecraft Reaction Wheel Friction Parameters; Composite Silica Aerogels Opacified with Titania; Multiplexed Colorimetric Solid-Phase Extraction; Detecting Airborne Mercury by Use of Polymer/Carbon Films; Lattice-Matched Semiconductor Layers on Single Crystalline Sapphire Substrate; Pressure-Energized Seal Rings to Better Withstand Flows; Rollerjaw Rock Crusher; Microwave Sterilization and Depyrogenation System; Quantifying Therapeutic and Diagnostic Efficacy in 2D Microvascular Images; NiF2/NaF:CaF2/Ca Solid-State High-Temperature Battery Cells; Critical Coupling Between Optical Fibers and WGM Resonators; Microwave Temperature Profiler Mounted in a Standard Airborne Research Canister; Alternative Determination of Density of the Titan Atmosphere; Solar Rejection Filter for Large Telescopes; Automated CFD for Generation of Airfoil Performance Tables; Progressive Classification Using Support Vector Machines; Active Learning with Irrelevant Examples; A Data Matrix Method for Improving the Quantification of Element Percentages of SEM/EDX Analysis; Deployable Shroud for the International X-Ray Observatory; Improved Model of a Mercury Ring Damper; Optoelectronic pH Meter: Further Details; X-38 Advanced Sublimator; and Solar Simulator Represents the Mars Surface Solar Environment.

Source record↗
NASA NTRS2012

Adaptive Sampling of Time Series During Remote Exploration

This work deals with the challenge of online adaptive data collection in a time series. A remote sensor or explorer agent adapts its rate of data collection in order to track anomalous events while obeying constraints on time and power. This problem is challenging because the agent has limited visibility (all its datapoints lie in the past) and limited control (it can only decide when to collect its next datapoint). This problem is treated from an information-theoretic perspective, fitting a probabilistic model to collected data and optimizing the future sampling strategy to maximize information gain. The performance characteristics of stationary and nonstationary Gaussian process models are compared. Self-throttling sensors could benefit environmental sensor networks and monitoring as well as robotic exploration. Explorer agents can improve performance by adjusting their data collection rate, preserving scarce power or bandwidth resources during uninteresting times while fully covering anomalous events of interest. For example, a remote earthquake sensor could conserve power by limiting its measurements during normal conditions and increasing its cadence during rare earthquake events. A similar capability could improve sensor platforms traversing a fixed trajectory, such as an exploration rover transect or a deep space flyby. These agents can adapt observation times to improve sample coverage during moments of rapid change. An adaptive sampling approach couples sensor autonomy, instrument interpretation, and sampling. The challenge is addressed as an active learning problem, which already has extensive theoretical treatment in the statistics and machine learning literature. A statistical Gaussian process (GP) model is employed to guide sample decisions that maximize information gain. Nonsta tion - ary (e.g., time-varying) covariance relationships permit the system to represent and track local anomalies, in contrast with current GP approaches. Most common GP models are stationary, e.g., the covariance relationships are time-invariant. In such cases, information gain is independent of previously collected data, and the optimal solution can always be computed in advance. Information-optimal sampling of a stationary GP time series thus reduces to even spacing, and such models are not appropriate for tracking localized anomalies. Additionally, GP model inference can be computationally expensive.

Thompson, David R.↗
NASA NTRS2015

Online Dectection and Modeling of Safety Boundaries for Aerospace Application Using Bayesian Statistics

The behavior of complex aerospace systems is governed by numerous parameters. For safety analysis it is important to understand how the system behaves with respect to these parameter values. In particular, understanding the boundaries between safe and unsafe regions is of major importance. In this paper, we describe a hierarchical Bayesian statistical modeling approach for the online detection and characterization of such boundaries. Our method for classification with active learning uses a particle filter-based model and a boundary-aware metric for best performance. From a library of candidate shapes incorporated with domain expert knowledge, the location and parameters of the boundaries are estimated using advanced Bayesian modeling techniques. The results of our boundary analysis are then provided in a form understandable by the domain expert. We illustrate our approach using a simulation model of a NASA neuro-adaptive flight control system, as well as a system for the detection of separation violations in the terminal airspace.

Statistics↗
NASA NTRSDate not supplied

A Framework for the Analysis of Deep Neural Networks in Autonomous Aerospace Applications using Bayesian Statistics

Deep Neural Networks (DNNs) are considered to be key components in many autonomous systems. Applications range from vision-based obstacle avoidance to intelligent/learning control and planning. Safety-critical applications as found in the aerospace domain require that the behavior of the DNN is validated and tested rigorously for safety of the autonomous system (AUS). In this paper, we present a framework to support testing of DNNs and the analysis of the network structure. Our framework employs techniques from statistical modeling and active learning to effectively generate test cases for DNN safety testing and performance analysis. We will present results of a case study on a physics-based Deep recurrent residual neural network (DR-RNN), which has been trained to emulate the aerodynamics behavior of a fixed-wing aircraft.

Deep Neural networks↗
NASA NTRSDate not supplied

A Framework for Software Health Management Using Bayesian Statistics

Software Health Management (SWHM) must make sure that the software always remains in safe and healthy regions of the state space. Boundaries between healthy and unhealthy regions are important for the detection of violations and health management.In this position paper, we present a framework, which employs techniques from Bayesian statistical modeling and active learning to efficiently characterize health boundaries in high-dimensional spaces. We will discuss, how this framework supports SWHM during design time and during operation of learning/adapting software systems

software health management↗
NASA NTRSDate not supplied

NASA GLOBE Clouds: Matching your sky observations to multiple satellite data

Have you ever wondered how your view of the sky compares to satellite data? The NASA GLOBE Clouds team at NASA Langley Research Center in Hampton, VA, matches ground-cloud observations taken by citizen scientists through the GLOBE Program to geostationary satellites as well as to Terra, Aqua, and CALIPSO satellites. The result is the NASA GLOBE Clouds satellite match table sent in a NASA personalized email summarizing both ground-cloud and satellite observations. The table contains ground-cloud and satellite values of total cloud cover and cloud cover by height (low, mid, high), cloud opacity and cloud phase. The satellite match table also includes images from the respective satellites centered on the latitude and longitude of the ground-cloud report entered through the GLOBE Program. Participants can receive satellite flyover notifications for their location through the GLOBE Observer app or through the satellite flyover schedule. This presentation will engage the audience through a live demonstration showing how to access GLOBE Clouds data visualization tools and view corresponding satellite imagery and data. We will also discuss best practices suggested by classroom teachers and undergraduate professors in incorporating active learning and satellite data analysis.

Marilé Colón Robles↗
NASA NTRS2024

Artificial Intelligence Medical Support for Long-Duration Space Missions

We envision an artificial intelligence (AI) based system that will provide support and recommendations to the crew medical officer (CMO) and ground flight surgeon during long-duration space missions. Such a system would be pretrained on the knowledgebase of clinical knowledge on Earth, minimizing the amount of Earth data that needs to be transferred into space. Then during deployment, the system would be constantly refined through active learning from diverse streams of data from sensors in the spacecraft, data collected daily from individual astronauts, and human-in-the-loop feedback from the crew. The model could be interrogated for predictions and recommendations on personalized crew health based on the overall status of the spacecraft, medicinal stores, and status of other crew members. Adaptation techniques would be used to incorporate spaceflight data that have very different distributions from the training data due to the extreme environment. Edge computing and the most advanced neuromorphic processing would enable computation in scenarios with low power and bandwidth, while dimensionality reduction would be employed to ensure that the input data streams from spaceflight are as small as possible. In order to realize this long-term vision, several hardware and software aspects need to be developed and assembled. First, models pretrained on Earth biomedical data would need to be evaluated for predictive accuracy, and the best one selected. That model would need to be adapted to learn from diverse, sparse, and inconsistently measured data streams, as well as human-in-the-loop feedback. A data integration, standardization, and dimensionality reduction methodology would need to be developed to handle all data types and feed them into the model. Once the software and data infrastructure is developed, it would need to be integrated with small footprint compute processors and tested in high-radiation, high-vibration, unregulated temperature situations. As a short-term goal, we recommend to focus on the development of the data and model software structure. Several large language models (LLM) already exist that have been trained on Earth biomedical and clinical knowledgebases, including BioMedLLM, Med-PaLM, SPOKE LLM, and Foresight. These models need to be evaluated for accuracy and the best one chosen for a proof-of-concept structure, while maintaining awareness of the accelerating AI field and incorporating any newly improved model architectures as needed. Then, we recommend to develop a database of synthetic data types to mimic the diverse data streams that are expected in a long-duration space mission. This should include environmental and microbial data from the spacecraft, non-invasive data from wearables and point-of-care devices employed by astronauts, and more invasive molecular and physiological monitoring of clinical and biomarker data from astronauts. The data standardization methodology should be developed, and these data streams used to refine the clinical LLM. Several scenarios should be developed that could plausibly come up in a long-duration space mission, and changes or aberrations introduced to the data at specific times to mimic these scenarios. Then, question and answer tasks should be designed to interrogate the model for predictions and recommendations, with acceptable answers already identified.

Artificial Intelligence↗
DOE OSTI2024

Accelerating Thermochemical Equilibrium Calculations for Nuclear Reactor Applications

Thermochemical properties play a key role in modeling and simulation of several key phenomena in nuclear reactors. There has been an increasing interest in incorporating CALPHAD-based formulations in multiphysics simulations including for Molten Salt Reactors where knowledge of phase evolution of the salt and the chemical potentials of various elements are of utmost importance in source term analyses and redox control. However, the size of such simulations is often limited by the high computational cost of full thermodynamic equilibrium calculations. This work discusses the current efforts aimed at accelerating thermochemical equilibrium calculations for multiphysics simulations performed using the open-source finite element / finite volume code Multiphysics Object Oriented Simulation Environment (MOOSE) [1]. While several methods have been proposed for accelerating phase equilibrium calculations [2], most focus on relatively small systems and often rely on a- priori knowledge of the state-space of the system. Nuclear materials, however, are often multi-component systems owing to the evolution of composition under irradiation and an approach based on a-priori mapping of phase diagram is often not enough. This work is aimed at demonstrating an on-the-fly surrogate modeling framework that uses active learning to reduce the number of full equilibrium calculations that must be performed. By combining with efficient coupling approaches, the surrogate framework helps in reducing the computational cost of thermodynamic equilibrium informed multiphysics simulations of nuclear materials. The performance is benchmarked against full coupling with the thermochemistry library Thermochimica [3]. This work uses a machine learning based approach for constructing surrogate models to predict the stable phases in a multicomponent system. The surrogates were constructed using neural networks and Gaussian process classification. In this work, we compare the relative performance of the two methods. We also demonstrate the use of caching previous calculations by interpolating the values from nearest neighbors. References [1] Lindsay, A.D., et al. "2.0 – MOOSE: Enabling massively parallel multiphysics simulation", SoftwareX, 20 (2022): 101202. [2] Roos, W.A. and Zietsman J.H. "Accelerating complex chemical equilibrium calculations – A Review", Calphad, 77 (2022): 102380. [3] Piro, M.H.A., et al. "The thermochemistry library Thermochimica", Computational Materials Science, 67 (2013): 266-272.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Surrogate Model Guided Optimization of Expensive Black-Box Multi-Objective Problems: A Posteriori Methods

Many engineering applications require the simultaneous optimization of multiple conflicting objective functions. Often, these objective functions are evaluated using highly accurate computer simulations that are computationally too expensive to be evaluated hundreds or thousands of times during optimization. Thus, the goal is to find good approximations of the Pareto front using as few of these expensive simulations as possible. Here, we describe an optimization approach based on surrogate models and diverse sampling strategies to accelerate the search for the Pareto solutions. We use a separate surrogate model for approximating each objective function and then we use the surrogate models to inform where additional expensive simulations should be run. The surrogate models are updated in an active learning framework whenever new information from the expensive simulations becomes available. The sampling strategies aim at balancing local improvements of the approximate Pareto front and global exploration to identify the extrema and fill in large gaps of the approximate Pareto front. We demonstrate on a large set of benchmark problems the effectiveness of the method for finding good approximations of the Pareto front.

MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Ligand-Based Compound Activity Prediction via Few-Shot Learning

Predicting the activities of new compounds against biophysical or phenotypic assays based on the known activities of one or a few existing compounds is a common goal in early stage drug discovery. This problem can be cast as a “few-shot learning” challenge, and prior studies have developed few-shot learning methods to classify compounds as active versus inactive. However, the ability to go beyond classification and rank compounds by expected affinity is more valuable. We describe Few-Shot Compound Activity Prediction (FS-CAP), a novel neural architecture trained on a large bioactivity data set to predict compound activities against an assay outside the training set, based on only the activities of a few known compounds against the same assay. Our model aggregates encodings generated from the known compounds and their activities to capture assay information and uses a separate encoder for the new compound whose activity is to be predicted. The new method provides encouraging results relative to traditional chemical-similarity-based techniques as well as other state-of-the-art few-shot learning methods in tests on a variety of ligand-based drug discovery settings and data sets.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗