Search NASA⌕ Search

SEARCH · Search NASA

Results for “Operator 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 505 records · Page 28

DeepONet-Assisted Optimization of Surface Topography for Transition Delay in A Mach 4.5 Boundary Layer

We use deep learning, an ensemble variationaltechnique (EnVar), and direct numerical simulations(DNS) to design an optimal topography for a two-dimensional roughness element that delays the on-set of laminar-turbulent transition in a Mach 4.5 flat-plate boundary layer. Deep operator networks (Deep-ONets), which have the known ability to learn com-plex nonlinear operators within dynamical systems,are used for machine learning. For the baseline config-uration of a smooth flat plate, the second-mode wavesat the DNS inflow cause a quick nonlinear breakdownof the high-speed boundary layer within the computa-tional domain. Results reported in the present studyvalidate the ability of DeepONets to model the tran-sition delay via a given topography of the roughnesselement. The computing cost to optimize the rough-ness element for minimal skin-friction drag is substan-tially lowered by the DeepONets-based reduced-ordermodel. In comparison to the baseline method of EnVaroptimization based on DNS alone, the DeepONets-based EnVar optimizer is able to delay transition pastthe outflow boundary of the computational domainwhile utilizing almost 5–6 times fewer DNS.

Machine Learning↗

CATIA V5 Virtual Environment Support for Constellation Ground Operations

This summer internship primarily involved using CATIA V5 modeling software to design and model parts to support ground operations for the Constellation program. I learned several new CATIA features, including the Imagine and Shape workbench and the Tubing Design workbench, and presented brief workbench lessons to my co-workers. Most modeling tasks involved visualizing design options for Launch Pad 39B operations, including Mobile Launcher Platform (MLP) access and internal access to the Ares I rocket. Other ground support equipment, including a hydrazine servicing cart, a mobile fuel vapor scrubber, a hypergolic propellant tank cart, and a SCAPE (Self Contained Atmospheric Protective Ensemble) suit, was created to aid in the visualization of pad operations.

Kelley, Andrew↗

Time series comparisons in Deep Space Network

The Deep Space Network (DSN) is NASA’s international array of antennas that support interplanetary spacecraft missions. DSN provides radar and radio astronomy observations that enhance our understanding of the solar system and the larger universe. A track is a block of continuous multi-dimensional time series from the beginning to end of DSN communication with the target spacecraft, containing 129 monitor data items lasting several hours at a frequency of 0.2-1Hz. Monitor data on each track reports on the performance of specific spacecraft operations and the DSN itself. DSN is receiving signals from 32 spacecraft across the solar system. DSN has pressure to reduce costs while maintaining the quality of support for DSN mission users. DSN operators need to simultaneously monitor multiple tracks and identify anomalies in real time. DSN has seen that as the number of missions increases, the data that needs to be processed increases over time. In this project, we look at the last 8 years of data for analysis. Any anomaly in the track indicates a problem with either the spacecraft, DSN equipment, or weather conditions. DSN operators typically write “discrepancy reports” for further analysis. It is recognized that it would be quite helpful to identify 10 similar historical tracks out of the huge database to quickly find/match anomalies. This tool has three functions: (1) identification of the top 10 similar historical tracks, (2) detection of anomalies compared to the reference normal track, and (3) comparison of statistical differences between two given tracks. The requirements for these features were confirmed by survey responses from 21 DSN operators and engineers. The preliminary machine learning model has shown promising performance (AUC=0.92). We plan to increase the number of data sets and perform additional testing to improve performance further before its planned integration into the Track Visualizer to assist DSN field operators and engineers.

Rebbapragada, Umaa↗

Transient Optimization of a Gas Turbine Engine

Gas turbine engines are the primary power plants for modern commercial aircraft. Transients prompted by significant changes in thrust or power demand are common and unavoidable. Extreme transient scenarios such as those associated with a go-around during a landing attempt are possible and must be accounted for in the design of the engine and its controller. Engine transients tend to cause a reduction in compressor operability margin, which must be addressed by the engine control system and accounted for in the engine design to prevent events such as compressor stall/surge and combustor blow out. Transient operability concerns typically lead to compromises in the engine design that sacrifice efficiency and/or limit responsiveness. Transient operability is typically managed by logic that limits the fuel flow command. If this logic is not optimized, then the potential for valuable performance could be lost. This study presents a strategy for optimizing the transient limit logic and proposes a strategy for updating the control logic over the lifespan of the engine. The results demonstrate significant improvements in transient operability. For example, of the results at sea level static conditions demonstrated a 31% reduction in the usage of the high pressure compressor operability stack during a snap acceleration transient. Furthermore, a reinforcement learning algorithm is demonstrated to modify the transient logic as the engine degrades to minimize response time while respecting a prescribed compressor operability margin limit. A simple demonstration of the reinforcement learning algorithm resulted in a thrust response time reduction of ~11.8%.

transient↗

Transient Optimization of a Gas Turbine Engine

Gas turbine engines are the primary power plants for modern commercial aircraft. Transients prompted by significant changes in thrust or power demand are common and unavoidable. Extreme transient scenarios such as those associated with a go-around during a landing attempt are possible and must be accounted for in the design of the engine and its controller. Engine transients tend to cause a reduction in compressor operability margin, which must be addressed by the engine control system and accounted for in the engine design to prevent events such as compressor stall/surge and combustor blow out. Transient operability concerns typically lead to compromises in the engine design that sacrifice efficiency and/or limit responsiveness. Transient operability is typically managed by logic that limits the fuel flow command. If this logic is not optimized, then the potential for valuable performance could be lost. This study presents a strategy for optimizing the transient limit logic and proposes a strategy for updating the control logic over the lifespan of the engine. The results demonstrate significant improvements in transient operability. For example, of the results at sea level static conditions demonstrated a 31% reduction in the usage of the high pressure compressor operability stack during a snap acceleration transient. Furthermore, a reinforcement learning algorithm is demonstrated to modify the transient logic as the engine degrades to minimize response time while respecting a prescribed compressor operability margin limit. A simple demonstration of the reinforcement learning algorithm resulted in a thrust response time reduction of ~11.8%.

transient↗

Adaptive/learning control of large space structures - System identification techniques

Techniques developed for the control of aircraft under changing operating conditions are used to develop a learning control system structure for a multi-configuration, flexible space vehicle. A configuration identification subsystem that is to be used with a learning algorithm and a memory and control process subsystem is developed. Adaptive gain adjustments can be achieved by this learning approach without prestoring of large blocks of parameter data and without dither signal inputs which will be suppressed during operations for which they are not compatible. The Space Shuttle Solar Electric Propulsion (SEP) experiment is used as a sample problem for the testing of adaptive/learning control system algorithms.

Thau, F. E.↗

Transient Optimization of a Gas Turbine Engine

Gas turbine engines are the primary power plants for modern commercial aircraft. Transients prompted by significant changes in thrust or power demand are common and unavoidable. Extreme transient scenarios such as those associated with a go-around during a landing attempt are possible and must be accounted for in the design of the engine and its controller. Engine transients tend to cause a reduction in compressor operability margin, which must be addressed by the engine control system and accounted for in the engine design to prevent events such as compressor stall/surge and combustor blow out. Transient operability concerns typically lead to compromises in the engine design that sacrifice efficiency and/or limit responsiveness. Transient operability is typically managed by logic that limits the fuel flow command. If this logic is not optimized, then the potential for valuable performance could be lost. This study presents a strategy for optimizing the transient limit logic and proposes a strategy for updating the control logic over the lifespan of the engine. The results demonstrate significant improvements in transient operability. For example, of the results at sea level static conditions demonstrated a 31% reduction in the usage of the high pressure compressor operability stack during a snap acceleration transient. Furthermore, a reinforcement learning algorithm is demonstrated to modify the transient logic as the engine degrades to minimize response time while respecting a prescribed compressor operability margin limit. A simple demonstration of the reinforcement learning algorithm resulted in a thrust response time reduction of ~11.8%.

transient↗

How Do Different Knowledge Frameworks Help Us Learn From Aviation Line Observations?

Human performance includes actions that increase safety, as well as actions that can reduce safety. Ensuring safety in complex dynamic operations like commercial aviation depends on the ability to institute appropriate responses based on what is learned from flightcrew performance and the contexts in which it occurs. To do this systemically at the organization level requires collecting data on flightcrew performance, developing effective approaches to analyzing those data, and understanding how to translate what has been learned into policies, procedures, and practice. Systematic observation of front-line operators is a vital source of human performance data. Much has been learned from such observations, including methodological principles. Most observations have been based on a framework focused on managing safety challenges and the ensuing unsafe events. A complementary perspective focuses on flexibility and actions that promote continued safe and effective operation. We consider lessons learned about observational methods from an established framework focused on undesired actions and how these might be extended for a framework focused on desired actions.

safety↗

The Right Stuff: A Look Back at Three Decades of Flight Controller Training for Space Shuttle Mission Operations

Operations of human spaceflight systems is extremely complex, therefore the training and certification of operations personnel is a critical piece of ensuring mission success. Mission Control Center (MCC-H), at the Lyndon B. Johnson Space Center, in Houston, Texas manages mission operations for the Space Shuttle Program, including the training and certification of the astronauts and flight control teams. This paper will give an overview of a flight control team s makeup and responsibilities during a flight, and details on how those teams are trained and certified. The training methodology for developing flight controllers has evolved significantly over the last thirty years, while the core goals and competencies have remained the same. In addition, the facilities and tools used in the control center have evolved. These changes have been driven by many factors including lessons learned, technology, shuttle accidents, shifts in risk posture, and generational differences. Flight controllers will share their experiences in training and operating the Space Shuttle throughout the Program s history. A primary method used for training Space Shuttle flight control teams is by running mission simulations of the orbit, ascent, and entry phases, to truly "train like you fly." The reader will learn what it is like to perform a simulation as a shuttle flight controller. Finally, the paper will reflect on the lessons learned in training for the shuttle program, and how those could be applied to future human spaceflight endeavors. These endeavors could range from going to the moon or to Mars. The lessons learned from operating the space shuttle for over thirty years will help the space industry build the next human transport space vehicle and inspire the next generation of space explorers.

Dittemore, Gary D.↗

Predictive Model for Workload in Remote Operators During sUAS Contingency Scenarios

The increase in automated capabilities of small Uncrewed Aerial Systems (sUAS) has enabled the human operators to manage larger numbers of vehicles simultaneously. As this happens, the operational paradigm shifts to an m:N configuration where multiple operators (m) are managing multiple vehicles (N) together. However, many questions about how operators will interact with each other and share interaction across the vehicle pool are yet unanswered. Therefore, stakeholders from government and industry have partnered to develop ground control station concepts for such operations. The work presented in this paper aims to identify factors that contribute to operator workload. A supervised machine learning-based method built using Support Vector Machines and K-fold cross-validation was used to create workload prediction models for various NASA TLX subscales by leveraging features related to interactions and their relative timings during m:N operations. Results show that the models yielded fairly high predictive accuracies ranging from ~60-75%.

workload prediction↗

Pavlovian, Skinner, and Other Behaviourists' Contributions to AI

A version of the definition of intelligent behaviour will be supplied in the context of real and artificial systems. Short presentation of principles of learning, starting with Pavlovian s classical conditioning through reinforced response and operant conditioning of Thorndike and Skinner and finishing with cognitive learning of Tolman and Bandura will be given. The most important figures within behaviourism, especially those with contribution to AI, will be described. Some tools of artificial intelligence that act according to those principles will be presented. An attempt will be made to show when some simple rules for behaviour modifications can lead to a complex intelligent behaviour.

Kosinski, Withold↗

Real-Time Science Operations to Support a Lunar Polar Volatiles Rover Mission

Future human exploration of the Moon will likely rely on in situ resource utilization (ISRU) to enable long duration lunar missions. Prior to utilizing ISRU on the Moon, the natural resources (in this case lunar volatiles) must be identified and characterized, and ISRU demonstrated on the lunar surface. To enable future uses of ISRU, NASA and the CSA are developing a lunar rover payload that can (1) locate near subsurface volatiles, (2) excavate and analyze samples of the volatile-bearing regolith, and (3) demonstrate the form, extractability and usefulness of the materials. Such investigations are important both for ISRU purposes and for understanding the scientific nature of these intriguing lunar volatile deposits. Temperature models and orbital data suggest near surface volatile concentrations may exist at briefly lit lunar polar locations outside persistently shadowed regions. A lunar rover could be remotely operated at some of these locations for the approx. 2-14 days of expected sunlight at relatively low cost. Due to the limited operational time available, both science and rover operations decisions must be made in real time, requiring immediate situational awareness, data analysis, and decision support tools. Given these constraints, such a mission requires a new concept of operations. In this paper we outline the results and lessons learned from an analog field campaign in July 2012 which tested operations for a lunar polar rover concept. A rover was operated in the analog environment of Hawaii by an off-site Flight Control Center, a rover navigation center in Canada, a Science Backroom at NASA Ames Research Center in California, and support teams at NASA Johnson Space Center in Texas and NASA Kennedy Space Center in Florida. We find that this type of mission requires highly efficient, real time, remotely operated rover operations to enable low cost, scientifically relevant exploration of the distribution and nature of lunar polar volatiles. The field demonstration illustrated the need for science operations personnel in constant communications with the flight mission operators and the Science Backroom to provide immediate and continual science support and validation throughout the mission. Specific data analysis tools are also required to enable immediate data monitoring, visualization, and decision making. The field campaign demonstrated that this novel methodology of real-time science operations is possible and applicable to providing important new insights regarding lunar polar volatiles for both science and exploration.

Moon; Volatiles; Rover; Missions↗

Interoperability Trends in Extravehicular Activity (EVA) Space Operations for the 21st Century

No other space operations in the 21 st century more comprehensively embody the challenges and dependencies of interoperability than EVA. This discipline is already functioning at an W1paralleled level of interagency, inter-organizational and international cooperation. This trend will only increase as space programs endeavor to expand in the face of shrinking budgets. Among the topics examined in this paper are hardware-oriented issues. Differences in design standards among various space participants dictate differences in the EVA tools that must be manufactured, flown and maintained on-orbit. Presently only two types of functional space suits exist in the world. However, three versions of functional airlocks are in operation. Of the three airlocks, only the International Space Station (ISS) Joint Airlock can accommodate both types of suits. Due to functional differences in the suits, completely different operating protocols are required for each. Should additional space suit or airlock designs become available, the complexity will increase. The lessons learned as a result of designing and operating within such a system are explored. This paper also examines the non-hardware challenges presented by interoperability for a discipline that is as uniquely dependent upon the individual as EVA. Operation of space suits (essentially single-person spacecrafts) by persons whose native language is not that of the suits' designers is explored. The intricacies of shared mission planning, shared control and shared execution of joint EVA's are explained. For example, once ISS is fully functional, the potential exists for two crewmembers of different nationality to be wearing suits manufactured and controlled by a third nation, while operating within an airlock manufactured and controlled by a fourth nation, in an effort to perform tasks upon hardware belonging to a fifth nation. Everything from training issues, to procedures development and writing, to real-time operations is addressed. Finally, this paper looks to the management challenges presented by interoperability in general. With budgets being reduced among all space-faring nations, the need to expand cooperation in the highly expensive field of human space operations is only going to intensify. The question facing management is not if the trend toward interoperation will continue, but how to best facilitate its doing so. Real-world EVA interoperability experience throughout the ShuttlelMir and ISS Programs is discussed to illustrate the challenges and

Miller, Gerald E.↗

Anomaly Detection, Active Learning, Precursor Identification,and Human Knowledge for Autonomous System Safety

The project Autonomy Teaming and TRajectories for ComplexTrusted Operational Reliability (ATTRACTOR) researched and developed Artificial Intelligence with application to multi-Unmanned Aerial Systems (UAS) missions. Such missions, like other complex systems-of-systems, are likely to have previously-unknown, safety relevant anomalies occur due to many possible factors including system failures or degradations, emergent behavior, changes in the environment in which the systems operate, changes in the way the systems are operated. We discuss the application of anomaly detection, active learning, and precursor identification to identify such anomalies and the conditions under which they are more likely to appear. We demonstrate results on simulated multi-UAS missions that show promise to be applied to real missions.

machine learning↗

A Flight Research Overview of WSPR, a Pilot Project for Sonic Boom Community Response

In support of the ongoing effort by the National Aeronautics and Space Administration (NASA) to bring supersonic commercial travel to the public, the NASA Armstrong Flight Research Center and the NASA Langley Research Center, in cooperation with other industry organizations, conducted a flight research experiment to identify the methods, tools, and best practices for a large-scale quiet (or low) sonic boom community human response test. The name of the effort was Waveforms and Sonic boom Perception and Response (WSPR). Such tests will be applied to building a dataset that governing agencies such as the Federal Aviation Administration and the International Civil Aviation Organization will use to establish regulations for acceptable sound levels of overland sonic booms. The WSPR test was the first such effort that studied responses to non-traditional low sonic booms while the subject persons were in their own homes and performing daily activities.The WSPR test was a NASA collaborative effort with several industry partners, in response to a NASA Aeronautics Research Mission Directorate Research Opportunities in Aeronautics. The primary contractor was Wyle (El Segundo, California). Other partners included Gulfstream Aerospace Corporation (Savannah, Georgia); Pennsylvania State University (University Park, Pennsylvania); Tetra Tech, Inc. (Pasadena, California); and Fidell Associates, Inc. (Woodland Hills, California).A major objective of the effort included exposing a community to the sonic boom magnitudes and occurrences that would be expected to occur in high-air traffic regions having a network of supersonic commercial aircraft in place. Low-level sonic booms designed to simulate those produced by the next generation of commercial supersonic aircraft were generated over a small residential community. The sonic boom footprint was recorded with an autonomous wireless microphone array that spanned the entire community. Human response data were collected using multiple survey methods. The research focused on essential elements of community response testing including subject recruitment, survey methods, instrumentation systems, flight planning and operations, and data analysis methods.This paper focuses on the NASA role in the logistics and operations of the effort, including human response subject recruitment, the operational processes involved in implementing the surveys throughout the community, instrumentation systems, logistics, flight planning, and flight operations. Findings discussed in this paper include critical lessons learned in all of the above-mentioned areas, as well as flight operations results. Analysis of the accuracy and repeatability of planning and executing the unique aircraft maneuver used to generate low sonic booms concluded that the sonic booms had overpressures within 0.15 lbft2 of the planned values for 76 percent of the attempts. Similarly, 90 percent of the attempts to generate low sonic booms within the community were successful.

community response↗

System Administrator for LCS Development Sets

The Spaceport Command and Control System Project is creating a Checkout and Control System that will eventually launch the next generation of vehicles from Kennedy Space Center. KSC has a large set of Development and Operational equipment already deployed in several facilities, including the Launch Control Center, which requires support. The position of System Administrator will complete tasks across multiple platforms (Linux/Windows), many of them virtual. The Hardware Branch of the Control and Data Systems Division at the Kennedy Space Center uses system administrators for a variety of tasks. The position of system administrator comes with many responsibilities which include maintaining computer systems, repair or set up hardware, install software, create backups and recover drive images are a sample of jobs which one must complete. Other duties may include working with clients in person or over the phone and resolving their computer system needs. Training is a major part of learning how an organization functions and operates. Taking that into consideration, NASA is no exception. Training on how to better protect the NASA computer infrastructure will be a topic to learn, followed by NASA work polices. Attending meetings and discussing progress will be expected. A system administrator will have an account with root access. Root access gives a user full access to a computer system and or network. System admins can remove critical system files and recover files using a tape backup. Problem solving will be an important skill to develop in order to complete the many tasks.

Virtualizing in Linux↗