Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 703 records · Page 39

Lightweight Thrust Chamber Composite Overwrap Lessons Learned

Filament winding a polymer/carbon fiber composite overwrap onto an additively manufactured copper combustion chamber will allow it to act as a light-weight structural jacket, significantly reducing weight for high pressure thrust chamber assemblies and reducing overall cost and fabrication schedules. Chamber assemblies for 2k lb. and 7k lb. of thrust have been successfully tested at NASA’s Marshall Space Flight Center. Multiple lessons were learned throughout the overwrap process development and manufacturing trials. The lessons learned on small scale hardware will guide further composite manufacturing technologies and enable a progression to larger scale assemblies with greater structural loads. Material performance requirements, manufacturing process development, and surface preparation were evaluated during the small chamber trials, with the broad thermal requirements of the resin being the primary driver for material selection and processing. Both epoxy and bismaleimide materials were evaluated with respect to both performance in the hot-fire test and ease of fabrication. Separately, surface preparation procedures were studied with the goal of providing a smooth chamber surface to promote a non-bonded overwrap. The recent testing of the 7k trust chamber has provided data in Non-Destructive Evaluation (NDE) and processing in order to continue to evaluate the performance requirements stated.

composite overwrap↗

Enabling Real-time Multi-messenger Astrophysics Discoveries with Deep Learning

Multi-messenger astrophysics is a fast-growing, interdisciplinary field that combines data, which vary in volume and speed of data processing, from many different instruments that probe the Universe using different cosmic messengers: electromagnetic waves, cosmic rays, gravitational waves and neutrinos. In this Expert Recommendation, we review the key challenges of real-time observations of gravitational wave sources and their electromagnetic and astroparticle counterparts, and make a number of recommendations to maximize their potential for scientific discovery. These recommendations refer to the design of scalable and computationally efficient machine learning algorithms; the cyber-infrastructure to numerically simulate astrophysical sources, and to process and interpret multi-messenger astrophysics data; the management of gravitational wave detections to trigger real-time alerts for electromagnetic and astroparticle follow-ups; a vision to harness future developments of machine learning and cyber-infrastructure resources to cope with the big-data requirements; and the need to build a community of experts to realize the goals of multi-messenger astrophysics.

E A Huerta↗

Advancing Methodologies for Applying Machine Learning and Evaluating Spatiotemporal Models of Fine Particulate Matter (PM 2.5 ) Using Satellite Data Over Large Regions

Reconstructing the distribution of fine particulate matter (PM 2.5 ) in space and time, even far from ground monitoring sites, is an important exposure science contribution to epidemiologic analyses of PM 2.5 health impacts. Flexible statistical methods for prediction have demonstrated the integration of satellite observations with other predictors, yet these algorithms are susceptible to overfitting the spatiotemporal structure of the training datasets. We present a new approach for predicting PM 2.5 using machine-learning methods and evaluating prediction models for the goal of making predictions where they were not previously available. We apply extreme gradient boosting (XGBoost) modeling to predict daily PM 2.5 on a 1 x 1 km 2 resolution for a 13 state region in the Northeastern USA for the years 2000–2015 using satellite-derived aerosol optical depth and implement a recursive feature selection to develop a parsimonious model. We demonstrate excellent predictions of withheld observations but also contrast an RMSE of 3.11 μg/m 3 in our spatial cross-validation withholding nearby sites versus an overfit RMSE of 2.10 μg/m 3 using a more conventional random ten-fold splitting of the dataset. As the field of exposure science moves forward with the use of advanced machine-learning approaches for spatiotemporal modeling of air pollutants, our results show the importance of addressing data leakage in training, overfitting to spatiotemporal structure, and the impact of the predominance of ground monitoring sites in dense urban sub-networks on model evaluation. The strengths of our resultant modeling approach for exposure in epidemiologic studies of PM 2.5 include improved efficiency, parsimony, and interpretability with robust validation while still accommodating complex spatiotemporal relationships.

air pollution↗

Thermal Performance Comparison and Lessons Learned for the Thermal Infrared Sensor Instruments 1 & 2

The Thermal Infrared Sensor (TIRS-1) is one of two instruments on the Landsat-8 Mission, which launched in February of 2013 and remains operational. The TIRS-2 instrument was developed for the Landsat-9 Mission, which is scheduled to launch in September of 2021. The TIRS-2 instrument design was adjusted to account for requirements changes and to include key lessons learned from its predecessor. The overall thermal subsystem design of the TIRS Sensor Unit remained comparable from mission to mission, but there were some areas that needed modifications. The general design is comprised of five thermal zones which range in temperature from less than 43 Kelvin to 320 Kelvin. Most zones are proportional heater controlled. A two-stage cryocooler provided by Ball Aerospace is used to cool the cryogenic subsystem, and excess power dissipation is rejected via ammonia transport heat pipes to a dedicated cryocooler radiator with embedded ammonia heat pipes. The cryogenic subsystem includes a series of shells used to radiatively and conductively isolate the cold stage from the warmer surroundings. The Optical System (telescope) is passively cooled to 180-195 Kelvin using a dedicated radiator with embedded dual-bore ethane heat pipes. The warmer end of the instrument includes a Scene Select Mechanism, an on-board Black Body Calibrator with a dedicated radiator, and a Focal Plane Electronics Box, all of which are attached to the Sensor Unit primary structure. The TIRS-1 thermal subsystem design was successfully verified during an extended testing campaign and during more than 8years of on-orbit operations. The TIRS-2 thermal subsystem design was successfully verified during months of ground testing prior to delivery in August of 2019and at the Observatory level in the Spring of 2021. A detailed comparison of the thermal performance of the two instruments has been made with a focus on key lessons learned during each instrument development, and with the benefit of on-orbit data acquired for the TIRS-1 instrument.

Veronica Otero↗

Lightweight Thrust Chamber Composite Overwrap Lessons Learned

The manufacturing, design, and analysis of filament wound carbon fiber/polymer composite overwraps for additively manufactured, copper combustion chambers are a critical part of NASA’s Rapid Analysis and Manufacturing Propulsion Technology (RAMPT) project. Ideally, the composite overwrap acts as a light-weight structural jacket and allows significant weight reduction of the high pressure thrust chamber assembly, reduction of overall cost, and reduced fabrication schedules. Chamber assemblies for 2000 lb. (2k) and 7000 lb. (7k) of thrust have been successfully tested at NASA’s Marshall Space Flight Center. Multiple lessons were learned throughout the overwrap process development and manufacturing trials. The lessons learned on small scale hardware, such as the 2k and 7k chambers, will guide further composite manufacturing technologies and enable a progression to larger scale assemblies with greater structural loads. Material performance requirements, manufacturing process development, and surface preparation were evaluated during the small chamber trials, with the broad thermal requirements of the resin being the primary driver for material selection and processing. Both epoxy and bismaleimide (BMI) materials were evaluated with respect to both performance in the hot-fire test and ease of fabrication. Separately, surface preparation procedures were studied with the goal of providing a smooth chamber surface to promote a non-bonded overwrap. Recent testing of the 7k trust chamber has provided data in Non-Destructive Evaluation (NDE) and processing in order to continue to evaluate the performance requirements stated.

Allison Clark↗

Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning

The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. A big challenge is that these new aerial vehicles will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe operations. In this paper, we consider an air transportation system where multiple aerial vehicles are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) requirement must be achieved to ensure flight safety. Our objective is to minimize the average mission completion time by jointly optimizing the velocity selection and spectrum allocation for all aerial vehicles. We formulate the optimization problem as a multi-stage Markov Decision Process (MDP) where the optimization variables are coupled together. A multi-agent Deep Reinforcement Learning (DRL) based solution is proposed where Value Decomposition Networks (VDN) algorithm is utilized to take discrete actions. Additionally, we propose a heuristic greedy algorithm as a baseline solution. Simulation results show that our learning based solution outperforms the heuristic greedy algorithm and another Orthogonal Multiple Access (OMA) solution in minimizing the mission completion time.

Ruixuan Han↗

Lessons Learned in Space Life Support System Testing

The earlier problems can be found and corrected, the easier and cheaper it is to fix them. Doing less testing saves cost and time but doing too little testing increases the risk of operational failures causing large costs and delays. Integrated test is necessary to determine if the subsystems work together and the overall architecture performs as intended. This report reviews the testing lessons learned from the NASA Systems Engineering Handbook, a National Research Council report, and five reviews of International Space Station (ISS) lessons learned. The five reviews all mention two important points. First, that testing should be performed on the final integrated system, one as close as possible to the intended flight system. Second, “test as you fly,” while operating as planned in an environment as close as possible to the expected flight environment. Other lessons are the need for extensive preflight ground testing, the need to establish and defend an adequate budget, the problems using protoflight hardware on ISS, and the benefit of having ISS as a zero gravity test bed. The major ISS life support systems, carbon dioxide removal, water recycling, and oxygen recovery, were protoflight systems with little testing before launch to ISS. The failure rates of these systems have been much greater than predicted and this has caused dissatisfaction with the protoflight approach. The more costly traditional approach builds qualification and test units in addition to flight units. The test units are used to find, analyze, and fix failure modes. Other work shows that there is an optimum cost-effective amount of testing when redundant systems must have a specified reliability and confidence.

Harry W. Jones↗

Assimilating Lessons Learned – From URGE to NASA's Student Airborne Science Activation (SaSa) Project

In the first half of 2021, formal and informal pods at several universities and NASA Center affiliates participated in the Unlearning Racism in Geosciences (URGE) curriculum and deliverables. As a result, several members from different URGE pods are propagating and applying the URGE lessons learned to the new 5-year NASA Student Airborne Science Activation project (SaSa). Starting in the Summer of 2022, SaSa will provide an 8-week summer Earth Science research experience focused on attracting and retaining early undergraduate students from historically underrepresented groups from minority-serving institutions (MSIs). The multicenter and field-based research experience will provide the students access to and experience with NASA airborne resources. Additionally, integrating NASA material into the MSI curricula and providing student mentorship at both MSIs and NASA Centers will enhance students' exposure to Earth Science research. The objectives of URGE and SaSa are highly compatible with one another, and the project timing allows for the integration of URGE lessons early in the SaSa curriculum design phase. As of December 2021, the first SaSa summer program application will be open and the first SaSa semester at the host MSIs will be completed. This presentation will discuss the assimilation of URGE lessons learned from our respective pods into the first SaSa academic semester and into the preparations for the first SaSa summer cohort. We will welcome additional feedback from the broader URGE community in advance of SaSa's first summer session.

Kristina Pistone↗

Dynamic Spectrum Allocation in Urban Air Transportation System via Deep Reinforcement Learning

The emerging concepts of Urban Air Mobility (UAM) and Advanced Air Mobility (AAM) open a new paradigm for urban air transportation. A big challenge is that these new aerial vehicles will quickly saturate the already crowded aviation spectrum, which is an essential resource to ensure reliable communications for safe operations. In this paper, we consider an air transportation system where multiple aerial vehicles are operated to transport passengers or cargo from different sources to destinations along their pre-defined paths. During the flight, the minimum communication Quality of Service (QoS) requirement must be achieved to ensure flight safety. Our objective is to minimize the average mission completion time by jointly optimizing the velocity selection and spectrum allocation for all aerial vehicles. We formulate the optimization problem as a multi-stage Markov Decision Process (MDP) where the optimization variables are coupled together. A multi-agent Deep Reinforcement Learning (DRL) based solution is proposed where Value Decomposition Networks (VDN) algorithm is utilized to take discrete actions. Additionally, we propose a heuristic greedy algorithm as a baseline solution. Simulation results show that our learning based solution outperforms the heuristic greedy algorithm and another Orthogonal Multiple Access (OMA) solution in minimizing the mission completion time.

Ruixuan Han↗

Communicating Metrics of Land Surface Temperature Variability Using Multi-sensor Machine Learning

Land surface temperature (LST) is a key climate observable used to detect changes in the Earth’s surface energy budget that influence carbon and water cycles. Land surface temperature exhibits strong diurnal variability, which geostationary satellites can observe at scale thanks to their temporal resolution. Due to anthropogenic climate and land use changes, the surface energy balance has been considerably modified and may be described by changes in diurnal temperature range and extremes. Using high performance computing and datasets from the NASA Earth Exchange, we exploit co-located, co-temporal observations from low-earth orbit (LEO) and geostationary (GEO) sensors to develop a deep learning-based method for LEO-to-GEO algorithm emulation. Our model is trained to predict MODIS Terra LST from GOES-16 thermal bands and achieves validation error <2K. Application of the model to unseen times of day (observed by MODIS Aqua) and a new GEO sensor (Himawari-8) observing an unseen spatial domain, demonstrate the generalization of the deep learning model across space, time and spectra. Further, time series clustering approaches are examined with the objective of identifying key indicators of change in diurnal cycling and extremes on a continental scale. Communicating LST variability observed by geostationary satellites can have impacts in multiple disciplines, from understanding of snow, vegetation and soil dynamics, to recognizing trends in heat events relevant to human health.

Kate Duffy↗

A generalizable machine learning approach to predict land surface temperature

Monitoring of land surface and atmospheric states is highly reliant on satellite data. Traditionally, data products are generated using carefully tuned and validated algorithms for low-earth orbit (LEO) sensors. However, the emerging constellation of geostationary (GEO) sensors contributes global, high temporal resolution observations which can better capture the diurnal variability of key observables like land surface temperature (LST). Using high performance computing and datasets from the NASA Earth Exchange, we exploit co-located, co-temporal observations from LEO and GEO satellites to develop a deep learning-based method for sensor-to-sensor algorithm emulation. Our model is trained on GOES-16 thermal bands to predict MODIS Terra LST and achieves a validation error <2K. Further, application of the model to unseen times of day and a second GEO sensor observing an unseen spatial domain demonstrate the generalization of the deep learning model across space, time and spectra. We anticipate that the synergies between a variety of active orbit configurations can be used to accelerate application of existing algorithms to new datasets.

Kate Marie Duffy↗

Learning Based Edge Computing in Air-to-Air Communication Network

This paper studies learning-based edge computing and communication in a dynamic Air-to-Air Ad-hoc Network (AAAN). Due to spectrum scarcity, we assume the number of Air-to-Air (A2A) communication links is greater than that of the available frequency channels, such that some communication links have to share the same channel, causing co-channel interference. We formulate the joint channel selection and power control optimization problem to maximize the aggregate spectrum utilization efficiency under resource and fairness constraints. A distributed deep Q learning-based edge computing and communication algorithm is proposed to find the optimal solution. In particular, we design two different neural network structures and each communication link can converge to the optimal operation by exploiting only the local information from its neighbors, making it scalable to large networks. Finally, experimental results demonstrate the effectiveness of the proposed solution in various AAAN scenarios.

Zhe Wang↗

Machine-learning Solution for Automatic Spacesuit Motion Recognition and Measurement from Conventional Video

Extravehicular Activity (EVA) spacesuits exhibit unique movement patterns due to their design characteristics. Mobility assessments using traditional motion capture systems are cost prohibitive and not feasible for some training conditions (e.g., simulated lunar outdoor terrain). This paper aims to present the ongoing development of machine learning solutions to quantify suit motions from conventional videos without special sensors or hardware. Given the fast growth in deep/machine learning technologies, external expertise was sought from open-source communities. This was expected to accelerate development and provide more cost-effective, time-saving solutions. This work was selected for a NASA Crowdsourcing project through an agency-wide solicitation. Partnerships were formed with the NASA JSC Center of Excellence for Collaborative Innovation and an execution crowdsourcing platform partner to solicit framework developments from external contenders. NASA provided contenders with video clips of spacesuits and simultaneously measured motion capture data during EVA simulation tasks. The contenders used this data to train and develop generalized algorithms to predict motions. At the end of the crowdsourcing event, five solutions were selected from 250 submissions. Each submission was tested and scored using video clips not previously disclosed to the contenders. The scoring metrics measured how well the algorithm detected the suit shape, the 2D suit joint detection accuracy, and 3D joint detection accuracy. The winning solution was able to achieve roughly 85% prediction accuracy (weighted combination of scoring metrics). Overall, the algorithms could efficiently detect various types of spacesuits and motions across different EVA simulation environments such as the Neutral Buoyancy Lab (NBL). However, 3D joint identification is less reliable when parts of the suit were obstructed in the image. After continued improvements and validation, the fully developed system will enable EVA stakeholders to quantify suit kinematic patterns, which can help optimize suit, hardware, and task designs.

Linh Vu↗

DEVELOP’s Approach to Experiential Learning

The NASA DEVELOP Program addresses environmental decision making needs and geoscience workforce development through 10-week feasibility studies that apply Earth observations to environmental issues at hand. The program builds capacity to use geospatial information in both its participants (students, recent graduates, early career professionals, and transitioning career professionals) and partner organizations (federal agencies, state & local governments, non-profits, and private industry). This is accomplished through a structured project execution model that provides opportunities for participants to have autonomy, learn “on the job,” and gain new skillsets for working with remote sensing data. A pipeline of leadership positions enhances opportunities for individuals engaged in the program to get hands-on experience conducting data analyses, communicating their work, leading technical projects, and building their knowledge bank of Earth-observing satellite capabilities. These skillsets and knowledge are then transferred to partners through the projects. This panel contribution will introduce the DEVELOP model, highlight experiences of participants, and share the program’s insights into good practices for effective experiential learning.

Capacity Building↗

Supervised Machine Learning Approach for Classifying Earth Science Publications

The data collections archived and distributed by the GES DISC NASA data center are widely utilized for various Earth Science studies. As these collections are created, many research works are published regarding these collections' algorithms, their validation, and their applications. As NASA data centers collect these publications for public use, it is helpful to categorize them based on how they relate to their associated datasets. Specifically, whether the publication linked to the GES DISC dataset is using it for applicational research, describing the algorithm used for the dataset creation, validating the dataset, or providing a general overview of the data collection. Currently, this process requires simple manual labeling, and as such, it may be possible to solve via automation. To approach this problem, machine learning classifiers were developed to predict a publication's category. Manually labeled publications were used as the training data for the supervised machine learning algorithms, specifically Random Forest and Multinomial Naïve Bayes. After balancing the dataset and implementing the Multinomial Naïve Bayes algorithm, the classification accuracy achieved was substantially higher than the baseline accuracy, thus significantly improving the efficiency of publication labeling.

Rohan Dayal↗

A Reinforcement Learning Framework for Space Missions in Unknown Environments

A land-and-traverse mission to icy worlds such as Europa and Enceladus is challenging due to lack of prior knowledge regarding the terrain conditions. Previous work [1] showed that rovers with high degrees of freedom (DoF) can achieve robust traversal by leveraging redundant modes for mobility to counter terrain uncertainty (e.g. walking, driving, or inch-worming). This paper presents a generic and scalable reinforcement learning scheme for enabling on-board decision making on rovers to automatically switch between modes of traversal based on online performance feedback. The objective is to maximize energy efficiency, minimize operator input and successfully negotiate unstructured terrain conditions without relying on exhaustive prior knowledge. The proposed methodology is well grounded in the literature on reinforcement learning and has been adapted to address conformance to validation and verification requirements and JPL flight operations history of using per-sol prescribed sequences for a space mission.

Tavallali, Peyman↗

Lessons Learned in Remote Participant Concurrent Engineering Concept Development Studies

Team-X was born from a need to perform rapid space mission design for principal investigator-led competed proposals in the mid-1990s. Throughout the last 25 years, Team-X at the Jet Propulsion Laboratory has expanded its application of the collaborative, concurrent study approach into every facet necessary to win competed proposals. The COVID-19 pandemic of 2020 created an immediate and new constraint on these studies – the need to conduct them with remote participants, both on the client side requesting the study, but also on the provider side producing the study. This paper provides lessons learned from dozens of design studies run by Team-X at the Jet Propulsion Laboratory during the COVID-19 pandemic. These lessons span all aspects of the information infrastructure: the people, processes, procedures, methods, tools, and “facilities”. These lessons learned will have applicability post-pandemic, as they have shown how best to incorporate participants, both on the provider side, and on the client side, who cannot travel or otherwise be co-located during collaborative, concurrent study sessions.

Nash, Alfred↗

Learning from Past Missions for Today’s Case Studies

As interest in small spacecraft and its community continue to grow, the extensive selection of subsystem parts and service providers can present as many opportunities as unique challenges for mission design and implementation. These challenges often include inadequate trade studies, missing lessons learned, and unknown solutions to common pitfalls. Trade studies frequently fall short if products and services ultimately do not meet customer expectations, especially if the actual performance of a particular service or technology is not shared with others seeking similar products or services. It is difficult to quantify the viability and robustness of desired products and services, truly understand what solutions exist, and account for unique failures from previous SmallSat missions when experiences are not shared and captured. This noted, one reason for the lack of information as input for trade studies is that it is problematic to capture and disseminate the relevant lessons learned, experienced anomalies, and programmatic issues in both the laboratory and on-orbit setting, as these types of information can be extremely sensitive and are specific to each unique mission. Often, they are not made publicly available. The adoption and use of existing tools and databases, as well as contributions toward and sharing of information available in literature can help distribute useful information for future SmallSat missions to help avoid these common pitfalls. This paper will provide the required framework for current and future SmallSat mission implementation by providing best practices and identifying helpful resources to assist with subsystem parts and services as part of trade study selections.

Bruce Yost↗