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 1,297 records · Page 72

The Soil Moisture Acttive Passive Mission: Fault Protection Performance and Lessons Learned

Fault protection as a discipline involves a collection of flight software logic and operational processes for detecting unacceptable anomalous behavior, responding prior to reaching criticality, restricting the propagation of a failure beyond a fault containment region, and recovering the vehicle back to full or degraded functionality if possible. The System Fault Protection (SFP) design for the SMAP Earth orbiter was put to the test during its 90-day vehicle commissioning activities. During this time, the SFP software autonomously protected the vehicle from multiple faults to critical hardware, and the operations team successfully returned the observatory to its science state. The SFP also performed well in the presence of anomalous behavior below true safety limits by not taking unnecessary response actions, instead allowing the operations team time to monitor the behavior. Certain aspects of the SFP design were modified during operations via both parameter updates and a full flight software update in order to better match the vehicle behavior in the flight environment. An evaluation of the SMAP SFP performance during vehicle Commissioning will be provided in this paper, as well as a set of lessons learned largely focused on visibility, SFP mutability in operations, responses to peripheral device faults, and Safe Mode recovery and design. By capturing some of the knowledge gained during SMAP Commissioning, it is intended that this paper provide guidance for making future System Fault Protection designs more robust and supportive of operations.

Clark, Jessica↗

Taxi Time Prediction at Charlotte Airport Using Fast-Time Simulation and Machine Learning Techniques

Accurate taxi time prediction can be used for more efficient runway scheduling to increase runway throughput and reduce taxi times and fuel consumptions on the airport surface. This paper describes two different approaches to predicting taxi times, which are a data-driven analytical method using machine learning techniques and a fast-time simulation-based approach. These two taxi time prediction methods are applied to realistic flight data at Charlotte Douglas International Airport (CLT) and assessed with actual taxi time data from the human-in-the-loop simulation for CLT airport operations using various performance measurement metrics. Based on the preliminary results, we discuss how the taxi time prediction accuracy can be affected by the operational complexity at this airport and how we can improve the fast-time simulation model for implementing it with an airport scheduling algorithm in real-time operational environment.

Lee, Hanbong↗

Lessons Learned from International Space Station Crew Autonomous Scheduling Test

In 2017, our team investigated and evaluated the novel concept of operations of astronaut self-scheduling (rescheduling their own timeline without creating violations) onboard International Space Station (ISS). Five test sessions were completed for this technology demonstration called Crew Autonomous Scheduling Test (CAST). For the first time in a spaceflight operational environment, an ISS crewmember planned, rescheduled, and executed their activities in real-time on a mobile device while abiding by flight and scheduling constraints. This paper discusses the lessons learned from deployment to execution.

planning and scheduling↗

Partnering with Industry: Lessons Learned from the Wide Field Instrument on the Wide Field InfraRed Survey Telescope Mission

Through most of the project formulation prior to Phase A, the Wide Field InfraRed Survey Telescope (WFIRST) project was developed as a Goddard Space Flight Center (GSFC) in house mission with one secondary instrument developed by JPL and an existing telescope donated from elsewhere in the federal government and managed by the original industry vendor. GSFC was responsible for the spacecraft bus, the instrument supporting structure and the Wide Field Instrument (WFI), which provides the primary science for the mission. Shortly before the beginning of Phase A, NASA codified its acquisition strategy for WFIRST to explore a more substantial role for industry in the mission. The project decided to have a large portion of the WFI be co-developed by industry. This paper describes lessons learned and recommendations for bringing potential industry partners into a project at later stages of conceptual design and presents viewpoints from both the vendor and customer on the experience with WFIRST.

Peabody,Hume L.↗

Cumulus Lessons Learned: Building, Testing, and Sharing a Cloud Archive

Cumulus is a scalable, extensible cloud-based archive system which is capable of ingesting, archiving, and distributing data from both existing on-prem sources and new cloud-native missions. As we have built and evolved the system with contributions from seven NASA EOSDIS organizations, we have learned several lessons about how to build a robust, broadly-applicable, microservices-based cloud system for geospatial data which we will share in this talk.

Quinn, Patrick↗

Earthdata Search UX Lessons Learned

Crafting a great user experience is hard. Crafting a great user experience for Earth science applications is fraught with challenges. From the variability in metadata to the experience profile of various users the possible permutations of use cases introduce layer upon layer of complexities that must be designed against. In this session, the Earthdata Search team would like to highlight lessons learned over the lifespan of the application the good, the bad, and the ugly.

Earthdata Search↗

Integration and Test (I&T) Horror Stories and the Lessons Learned

I've been asked to be a presenter along with a panel of fellow NASA Electromagnetic Compatibility (EMC) engineers at this year's IEEE EMC & Signal and Power Integrity (SIPI) 2019 symposium. The topic I am asked to cover is in regards to I&T horror stories because of my 15 years of personal experience as an EMC test engineer with Code 549. I am planning on only having slides with photos of test methods we no longer use as well as cover some mishaps that have happened over the years both within my organization and throughout the space industry. Highlighting the mistakes that were made, the lessons learned from those incidents and how they've effected how we test today.

EMI↗

Automated Cardiovascular Pathology Assessment using Semantic Segmentation and Ensemble Learning

Cardiac magnetic resonance imaging provides high spatial resolution, enabling improved extraction of important functional and morphological features for cardiovascular disease staging. Segmentation of ventricular cavities and myocardium in cardiac cine sequencing provides a basis to quantify cardiac measures such as ejection fraction. A method is presented that curtails the expense and observer bias of manual cardiac evaluation by combining semantic segmentation and disease classification into a fully automatic processing pipeline. The initial processing element consists of a robust dilated convolutional neural network architecture for voxel-wise segmentation of the myocardium and ventricular cavities. The resulting comprehensive volumetric feature matrix captures diagnostic clinical procedure data and is utilized by the final processing element to model a cardiac pathology classifier. Our approach evaluated anonymized cardiac images from a training data set of 100 patients (4 pathology groups, 1 healthy group, 20 patients per group) examined at the University Hospital of Dijon. The top average Dice index scores achieved were 0.940, 0.886, 0.849 for structure segmentation of the left ventricle (LV), myocardium and right ventricle (RV) respectively. A 5-ary pathology classification accuracy of 90% was recorded on an independent test set using the trained model. Performance results demonstrate potential for advanced machine learning methods to deliver accurate, efficient and reproducible cardiac pathological assessment.

Semantic Segmentation↗

Measuring Pilot Eye Fixations: What Have We Learned About Monitoring?

There is a substantial literature on eye-tracking measurement for pilots. These measures offer one method for studying pilot visual attention. This presentation reviews this literature to identify the range of eye-tracking measures used; the primary findings from eye tracking as it relates to commercial transport pilots; and whether we can learn anything from these studies about pilot monitoring. We identify gaps between the process of pilot monitoring and what we can know from studying eye tracking. This is a brief presentation.

Commercial Aviation↗

Machine Learning Lifecycle for Earth Science Application: A Practical Insight into Production Deployment

Earth science domain presents unique sets of problems that are increasingly being solved using data driven approaches. The availability of big Earth science data offers immense potential for Machine learning (ML) as evident from numerous research publications lately. However, many of these publications are not ending up as production applications mainly because the data scientists who develop the ML models are now expected to complete the ML lifecycle by deploying and scaling the models in production. We introduce ML lifecycle to the Earth science community including the opportunities and challenges that lie ahead in each phase of the lifecycle. We demonstrate the lifecycle using an Earth science problem that we used ML to address and transitioned to production.

Maskey, Manil↗

Lessons Learned from the Flight Unit Testing of the Near Earth Asteroid Scout Flight System

The Near Earth Asteroid Scout flight mission is set to launch on the maiden voyage of the Space Launch System as a secondary payload. The spacecraft will be jettisoned in cis-lunar space and embark on an ambitious 2.5 year mission to image an asteroid. The spacecraft is uniquely equipped with an 85m2 solar sail as the main propulsion system. The monolithic sail system is designed to package within a 6U volume for launch and then deploy during flight. The NEA Scout team has presented in the past to the International Symposium on Solar Sailing topics related to the engineering development unit and design efforts to achieve flight hardware build. This paper will focus on the lessons learned from building and testing the NEA Scout flight system. Focus will be on the mechanical, software, and electrical interfaces as well as preparation for subsystem environmental tests, including thermal vacuum. Due to the unique design of the spacecraft, the solar sail subsystem was required to be located in the center of the spacecraft. This requirement lead to design challenges such as designing and accommodating critical cable harnesses to run through the center of the sail subsystem, packaging and deployment design of the sail subsystem, and integrated testing efforts through an avionics test bed to verify and validate a complete system architecture.

Lockett, Tiffany Russell↗

Ramp Traffic Console (RTC) Lessons Learned

This presentation provides lessons learned for use of ramp traffic control (RTC) and ramp manager traffic console (RMTC) features of the ATD-2 (Airspace Technology Demonstration 2) Integrated Arrival, Departure, and Surface (IADS) system in an operational environment.

Jung, Yoon↗

Application of Machine Learning Techniques to Aviation Operations: Promises and Challenges

There is an increasing interest in applying methods based on Machine Learning Techniques (MLT) to problems in aviation operations. The current interest is based on developments in Cloud Computing, the availability of open software and the success of MLT in automation, consumer behavior and finance involving large database. This paper reviews the current-state-of-the art in applying MLT to aviation operations, its promises and challenges. Historically aviation operations have been analyzed using physics-based models and provide information for making operational decisions. This paper compares the methodology used in and issues to be addressed in applying either model-driven or data-driven methods. Some aviation operations involving many decision makers, multiple objectives, poor or unavailable physics-based models and a rich historical database are prime candidates for data-driven methods. The application of MLT to aviation operations falls into three categories: (a) based on the lack of a physics-based model, MLT is the favored approach, (b) marginal difference between regression methods using physics-based models and MLT and (c) better results using a blend of physics-based methods combined with MLT. As always, the best approach depends on the task, the physical understanding of the problem and the quality and quantity of the available data.

Sridhar, Banavar↗

Forming Aggregations using Virtual Sharding: Lessons Learned from Simple Scalable Storage (S3)

Data aggregation is the ability to combine separate datasets to form a single new logical dataset provides users with a powerful abstraction. The advantage of an aggregate dataset is that the users are freed from having to understand, and incorporate into their workflow, knowledge about the (ad hoc) organization of the constituent datasets. However, aggregating large numbers of files can be computationally complex with data server systems performing many repetitive operations. As part of the authors work on subsetting data stored on Amazon Web Service (AWS) Simple Storage Service (S3), we developed technology to read portions of otherwise monolithic data files. This enables the formation of virtual shards for user in subsetting data stored in HDF5 (hierarchical data format, version 5) files. This same tool can be used to form aggregations that combine data stored in many HDF5 files when those files are stored on S3. The nature of the virtual sharding and the algorithm that exploits it for subsetting is such that it can also be used for aggregation with the need for many of the repetitive operations required by the per file aggregation techniques. We will present timing information that demonstrates the flexibility of this approach. However, the lessons learned is that while this is a useful result in and of itself, these very same techniques can be applied in other contexts where data are stored in services and on media other than S3. For example, this same technique can be applied to data stored on spinning disk. Pushing the envelope for S3 forced a reexamination of our data access techniques which lead to unexpected positive benefits.

Gallagher, James↗

Towards Autonomous Aviation Operations: What Can We Learn from Other Areas of Automation?

Rapid advances in automation has disrupted and transformed several industries in the past 25 years. Automation has evolved from regulation and control of simple systems like controlling the temperature in a room to the autonomous control of complex systems involving network of systems. The reason for automation varies from industry to industry depending on the complexity and benefits resulting from increased levels of automation. Automation may be needed to either reduce costs or deal with hazardous environment or make real-time decisions without the availability of humans. Space autonomy, Internet, robotic vehicles, intelligent systems, wireless networks and power systems provide successful examples of various levels of automation. NASA is conducting research in autonomy and developing plans to increase the levels of automation in aviation operations. This paper provides a brief review of levels of automation, previous efforts to increase levels of automation in aviation operations and current level of automation in the various tasks involved in aviation operations. It develops a methodology to assess the research and development in modeling, sensing and actuation needed to advance the level of automation and the benefits associated with higher levels of automation. Section II describes provides an overview of automation and previous attempts at automation in aviation. Section III provides the role of automation and lessons learned in Space Autonomy. Section IV describes the success of automation in Intelligent Transportation Systems. Section V provides a comparison between the development of automation in other areas and the needs of aviation. Section VI provides an approach to achieve increased automation in aviation operations based on the progress in other areas. The final paper will provide a detailed analysis of the benefits of increased automation for the Traffic Flow Management (TFM) function in aviation operations.

Sridhar, Banavar↗

A Landslide Climate Indicator from Machine Learning

In order to create a Landslide Hazard Index, we accessed rain, snow, and a dozen other variables from the National Climate Assessment Land Data Assimilation System. These predictors were converted to probabilities of landslide occurrence with XGBoost, a major machine-learning tool. The model was fitted with thousands of historical landslides from the Pacific Northwest Landslide Inventory (PNLI).

Stanley, T. A.↗

X-56A Structural Dynamics Ground Testing Overview and Lessons Learned

The X-56A Multi-Utility Technology Testbed (MUTT) is a subscale, fixed-wing aircraft designed for high-risk aeroelastic flight demonstration and research. Structural dynamics ground testing for model validation was especially important for this vehicle because the structural model was directly used in the development of a flight control system with active flutter suppression capabilities. Structural dynamics ground tests of the X-56A MUTT with coupled rigid-body and structural modes provided a unique set of challenges. An overview of the ground vibration test (GVT) and moment of inertia (MOI) test setup and execution is presented. The series of GVTs included the wing by itself attached to a strongback and complete vehicle at two mass conditions: empty and full fuel. Two boundary conditions for the complete-vehicle test were studied: on landing gear and suspended free-free. Pitch MOI tests were performed using a compound pendulum method and repeated with two different pendulum lengths for independent verification. The original soft-support test configuration for the GVT used multiple bungees, resulting in unforeseen coupling interactions between the soft-support bungees and the vehicle structural modes. To resolve this problem, the soft-support test setup underwent multiple iterations. The various GVT configurations and boundary-condition modifications are highlighted and explained. Lessons learned are captured for future consideration when performing structural dynamics testing with similar vehicles.

Chin, Alexander W.↗