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.

SourceResearch connectionFrom yearThrough year

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

At least 181 records · Page 10

All sources NASA NTRS DOE OSTI

DOE OSTI2024

A data-driven framework for predicting machining stability: employing simulated data, operational modal analysis, and enhanced transfer learning

Chatter, a self-excited vibration phenomenon, presents a significant challenge in machining operations, particularly in high-speed milling, where it can degrade tool life, reduce material removal efficiency, and compromise workpiece quality. Addressing this challenge requires a reliable predictive model that can accommodate the complex dynamics of various machining scenarios. This study introduces a novel, data-driven approach to predicting machining stability, leveraging over 140,000 simulated datasets and employing advanced techniques such as operational modal analysis (OMA), enhanced transfer learning (TL), and receptance coupling substructure analysis (RCSA). By integrating these methodologies, the framework effectively classifies and predicts chatter across diverse operational modes, achieving robust and accurate outcomes. Our model utilizes a Random Forest (RF) classifier trained with the comprehensive dataset, which demonstrates substantial improvements in both predictive accuracy and robustness. Specifically, the RF model achieved an accuracy rate of 85%, an area under the curve (AUC) of 0.90, and an F1 score of 0.88, underscoring its capability to adapt to varying machining configurations. These results highlight the framework’s potential to enhance operational efficiency and machining quality by providing reliable chatter predictions across a broad range of machining parameters. In conclusion, this research thus offers a significant advancement in predictive maintenance for machining processes, enabling more stable and efficient manufacturing operations.

42 ENGINEERING↗

NASA NTRSDate not supplied

Data-Centric Operational Design Domain Characterization for Machine Learning-Based Aeronautical Products

We give for Machine Learning (ML)-based aeronautical products, a first rigorous characterization of Operational Design Domains (ODDs). Unlike in other application sectors (such as self-driving road vehicles) where ODD development is scenario-based, our approach is data-centric: we propose the dimensions along which the parameters that define an ODD can be explicitly captured, using a top-down approach starting from system specifications, and a bottom-up approach starting from detailed ML Model (MLM) designs. Then we give a categorization of the data that ML-based applications can encounter in operation, identifying their system-level relevance and impact. Specifically, we discuss how those data categories are useful to determine: (1) the requirements necessary to drive the design of MLMs; (2) the potential effects on the MLM and higher levels of the system hierarchy; (3) the learning assurance processes that may be needed, and (4) system architectural considerations. We illustrate the underlying concepts with an example of an aircraft flight envelope. The approach in this paper is one of the cornerstones of a future process guidance for development and certification/approval of safety-related aeronautical products implementing Artificial Intelligence (AI), currently being developed through aviation industry-based consensus, jointly by the SAE G-34 Committee for AI in aviation, and EUROCAE WG-114 for AI.

Aeronautical products↗

NASA NTRS2006

Spitzer Space Telescope Sequencing Operations Software, Strategies, and Lessons Learned

The Space Infrared Telescope Facility (SIRTF) was launched in August, 2003, and renamed to the Spitzer Space Telescope in 2004. Two years of observing the universe in the wavelength range from 3 to 180 microns has yielded enormous scientific discoveries. Since this magnificent observatory has a limited lifetime, maximizing science viewing efficiency (ie, maximizing time spent executing activities directly related to science observations) was the key operational objective. The strategy employed for maximizing science viewing efficiency was to optimize spacecraft flexibility, adaptability, and use of observation time. The selected approach involved implementation of a multi-engine sequencing architecture coupled with nondeterministic spacecraft and science execution times. This approach, though effective, added much complexity to uplink operations and sequence development. The Jet Propulsion Laboratory (JPL) manages Spitzer s operations. As part of the uplink process, Spitzer s Mission Sequence Team (MST) was tasked with processing observatory inputs from the Spitzer Science Center (SSC) into efficiently integrated, constraint-checked, and modeled review and command products which accommodated the complexity of non-deterministic spacecraft and science event executions without increasing operations costs. The MST developed processes, scripts, and participated in the adaptation of multi-mission core software to enable rapid processing of complex sequences. The MST was also tasked with developing a Downlink Keyword File (DKF) which could instruct Deep Space Network (DSN) stations on how and when to configure themselves to receive Spitzer science data. As MST and uplink operations developed, important lessons were learned that should be applied to future missions, especially those missions which employ command-intensive operations via a multi-engine sequence architecture.

missions operations↗

NASA NTRS2019

Simulation-to-Flight 1 (STF-1): Automating the Planning, Scheduling, Assessment and Data Processing/Reduction for a Small Satellite

On December 16, 2019, a 3-U CubeSat named STF-1 launched as West Virginia's first spacecraft. This event marked the culmination of a run-up to launch involving the production of the spacecraft, creation/configuration of command and control infrastructure, and the evolution of its co-creation, the NASA Operational Simulator for Small Satellites (NOS3). This event also marked the beginning of a new phase: operations. While plans, procedures, and infrastructure were already in place or started for operations, many lessons were learned during the operations phase, especially during early operations (first month/commissioning phase). Additional plans, procedures, and infrastructure, especially related to communication planning and automated data processing, were created and developed to fill needs for the operation of the STF-1 mission.This paper and presentation will overview the STF-1 operations team's solutions to addressing the many needs of operating a low-earth orbiting CubeSat mission with a single ground antenna that is shared and scheduled with several other missions. The STF-1 operations team deployed a combination of virtualization technologies, ground station technology solutions, collaboration software, custom planning software solutions, and existing ground antenna scheduling solutions to create an effective and efficient CubeSat operations environment. The end-solution satisfied the operations stakeholders, which include NASA, its industry partner TMC Technologies, and four independent professor-student teams at West Virginia University.

CubeSat↗

NASA NTRS2019

STF-1 Ground Operations - Automating the Planning, Scheduling, Assessment and Data Processing/Reduction for a Small Satellite

On December 16, 2018, a 3-U CubeSat named STF-1 launched as West Virginia's first spacecraft. This event marked the culmination of a run-up to launch involving the production of the spacecraft, creation/configuration of command and control infrastructure, and the evolution of its co-creation, the NASA Operational Simulator for Small Satellites (NOS3). This event also marked the beginning of a new phase: operations. While plans, procedures, and infrastructure were already in place or started for operations, many lessons were learned during the operations phase, especially during early operations (first month/commissioning phase). Additional plans, procedures, and infrastructure, especially related to communication planning and automated data processing, were created and developed to fill needs for the operation of the STF-1 mission.This paper and presentation will overview the STF-1 operations team's solutions to addressing the many needs of operating a low-earth orbiting CubeSat mission with a single ground antenna that is shared and scheduled with several other missions. The STF-1 operations team deployed a combination of virtualization technologies, ground station technology solutions, collaboration software, custom planning software solutions, and existing ground antenna scheduling solutions to create an effective and efficient CubeSat operations environment. The end-solution satisfied the operations stakeholders, which include NASA, its industry partner TMC2 Technologies, and four independent professor-student teams at West Virginia University.

Suder, Mark↗

NASA NTRS2013

Lessons Learned for Improving Spacecraft Ground Operations

NASA policy requires each Program or Project to develop a plan for how they will address Lessons Learned. Projects have the flexibility to determine how best to promote and implement lessons learned. A large project might budget for a lessons learned position to coordinate elicitation, documentation and archival of the project lessons. The lessons learned process crosses all NASA Centers and includes the contactor community. o The Office of The Chief Engineer at NASA Headquarters in Washington D.C., is the overall process owner, and field locations manage the local implementation. One tool used to transfer knowledge between program and projects is the Lessons Learned Information System (LLIS). Most lessons come from NASA in partnership with support contractors. A search for lessons that might impact a new design is often performed by a contractor team member. Knowledge is not found with only one person, one project team, or one organization. Sometimes, another project team, or person, knows something that can help your project or your task. Knowledge sharing is an everyday activity at the Kennedy Space Center through storytelling, Kennedy Engineering Academy presentations and through searching the Lessons Learned Information system. o Project teams search the lessons repository to ensure the best possible results are delivered. o The ideas from the past are not always directly applicable but usually spark new ideas and innovations. Teams have a great responsibility to collect and disseminate these lessons so that they are shared with future generations of space systems designers. o Leaders should set a goal for themselves to host a set numbers of lesson learned events each year and do more to promote multiple methods of lessons learned activities. o High performing employees are expected to share their lessons, however formal knowledge sharing presentation are not the norm for many employees.

Bell, Michael↗

NASA NTRSDate not supplied

A Cognitive Walkthrough of Multiple Drone Delivery Operations

Advances of early twenty-first century aviation and transportation technologies provide opportunities for enhanced aerial projects, and the overall integration of unmanned aircraft systems (UAS) into the National Airspace System (NAS) has applications across a wide range of operations. Through these, remote operators have learned to manage several UAS at the same time in a variety of operational environments. The present work details a component piece of an ongoing body of research into multi-UAS operations. Beginning in early 2020, NASA has collaborated with Uber Technologies to design and develop concepts of operations, roles and responsibilities, and ground control station (GCS) concepts to enable food delivery operations via multiple, small UAS (sUAS). A cognitive walkthrough was chosen as the method for data collection. This allowed information to be gathered from UAS subject matter experts (SMEs) that could further mature designs for future human-in-the-loop (HITL) simulations; in addition, it allowed information to be collected remotely during the stringent restrictions of the COVID-19 pandemic. Consequently, the described cognitive walkthrough activity utilized remote data collection protocols mediated through the usage of programs designed for presentation and telecommunications. Scenarios were designed, complete with airspace, contingencies, and remedial actions, to be presented to the SMEs. Information was collected using a combination of rating scales and open-ended questions. Results received from the SMEs revealed expected hazards, workloads, and information concerns inherent in the contingency scenarios. SMEs also provided insight into the design of GCS tools and displays as well as the duties and relationships of human operators (i.e., monitors) and automation (i.e., informers and flight managers). Implications of these findings are discussed.

unmanned aircraft systems↗

NASA NTRS2021

A Cognitive Walkthrough of Multiple Drone Delivery Operations

unmanned aircraft systems↗

NASA NTRSDate not supplied

International Space Station Space Environments Performance and Anomaly Resolution

The International Space Station is the largest and most complex on-orbit platform for space science utilization in low Earth orbit. The Space Environments Team addresses natural and induced environments for the ISS Program including external contamination, ionizing radiation, neutral atmosphere and solar ultraviolet radiation, plasma effects, and acoustics. For the ISS to fulfill its mission as a long-duration science platform, space environments effects are assessed, monitored, and controlled through design or operational mitigation. Interactions of ISS hardware with the natural and induced space environments, and the assessment and mitigation of those effects play a critical role in ISS mission operations. The Space Environments Team has complete system integration responsibility in these area for U.S./International Partner/Russian hardware, visiting vehicles, ISS payloads and operation. Lessons learned and processes developed for ISS are applicable to the design, assembly, and operations of long-duration space systems.

space environments↗

NASA NTRS1996

Fuzzy Q-Learning for Generalization of Reinforcement Learning

Fuzzy Q-Learning, introduced earlier by the author, is an extension of Q-Learning into fuzzy environments. GARIC is a methodology for fuzzy reinforcement learning. In this paper, we introduce GARIC-Q, a new method for doing incremental Dynamic Programming using a society of intelligent agents which are controlled at the top level by Fuzzy Q-Learning and at the local level, each agent learns and operates based on GARIC. GARIC-Q improves the speed and applicability of Fuzzy Q-Learning through generalization of input space by using fuzzy rules and bridges the gap between Q-Learning and rule based intelligent systems.

Berenji, Hamid R.↗

NASA NTRS2012

Lessons Learned for Improving Spacecraft Ground Operations

NASA has a unique history in processing the Space Shuttle fleet for launches. Some of this experience has been captured in the NASA Lessons Learned Information System (LLIS). This tool provides a convenient way for design engineers to review lessons from the past to prevent problems from reoccurring and incorporate positive lessons in new designs. At the Kennedy Space Center, the LLIS is being used to design ground support equipment for the next generation of launch and crewed vehicles. This paper describes the LLIS process and offers some examples.

Bell, Michael A.↗

NASA NTRS2005

Engineering Lessons Learned and Systems Engineering Applications

Systems Engineering is fundamental to good engineering, which in turn depends on the integration and application of engineering lessons learned and technical standards. Thus, good Systems Engineering also depends on systems engineering lessons learned from within the aerospace industry being documented and applied. About ten percent of the engineering lessons learned documented in the NASA Lessons Learned Information System are directly related to Systems Engineering. A key issue associated with lessons learned datasets is the communication and incorporation of this information into engineering processes. Systems Engineering has been defined (EINIS-632) as "an interdisciplinary approach encompassing the entire technical effort to evolve and verify an integrated and life-cycle balanced set of system people, product, and process solutions that satisfy customer needs". Designing reliable space-based systems has always been a goal for NASA, and many painful lessons have been learned along the way. One of the continuing functions of a system engineer is to compile development and operations "lessons learned" documents and ensure their integration into future systems development activities. They can produce insights and information for risk identification identification and characterization. on a new project. Lessons learned files from previous projects are especially valuable in risk

Gill, Paul S.↗

NASA NTRS1999

Lesson Learned During Implementation and Early Operations of the DS1 Beacon Monitor Experiment

A new approach to mission operations will be flight validated on NASA's New Millennium Program Deep Space One (DS1) mission which launched in October 1998.

becon↗

NASA NTRS2003

Drinking from the Fire Hose: Why the Flight Management System Can Be Hard to Train and Difficult to Use

The Flight Management Computer (FMC) and its interface, the Multi-function Control and Display Unit (MCDU) have been identified by researchers and airlines as difficult to train and use. Specifically, airline pilots have described the "drinking from the fire-hose" effect during training. Previous research has identified memorized action sequences as a major factor in a user s ability to learn and operate complex devices. This paper discusses the use of a method to examine the quantity of memorized action sequences required to perform a sample of 102 tasks, using features of the Boeing 777 Flight Management Computer Interface. The analysis identified a large number of memorized action sequences that must be learned during training and then recalled during line operations. Seventy-five percent of the tasks examined require recall of at least one memorized action sequence. Forty-five percent of the tasks require recall of a memorized action sequence and occur infrequently. The large number of memorized action sequences may provide an explanation for the difficulties in training and usage of the automation. Based on these findings, implications for training and the design of new user-interfaces are discussed.

Sherry, Lance↗

NASA NTRS2011

Lessons Learned from the Design, Certification, and Operation of the Space Shuttle Integrated Main Propulsion System (IMPS)

The Space Shuttle Integrated Main Propulsion System (IMPS) consists of the External Tank (ET), Orbiter Main Propulsion System (MPS), and Space Shuttle Main Engines (SSMEs). The IMPS is tasked with the storage, conditioning, distribution, and combustion of cryogenic liquid hydrogen (LH2) and liquid oxygen (LO2) propellants to provide first and second stage thrust for achieving orbital velocity. The design, certification, and operation of the associated IMPS hardware have produced many lessons learned over the course of the Space Shuttle Program (SSP). A subset of these items will be discussed in this paper for consideration when designing, building, and operating future spacecraft propulsion systems. This paper will focus on lessons learned related to Orbiter MPS and is the first of a planned series to address the subject matter.

Martinez, Hugo E.↗

DOE OSTI2025

A Neural Optimizer With Decision-Focused Learning for Optimal Energy Storage Operation

Here, this article introduces a neural optimizer-based framework for optimizing battery energy storage system (BESS) control for grid services, including demand charge and energy cost reduction. By leveraging decision-focused learning (DFL), the proposed framework ensures seamless integration and adaptation, significantly enhancing control performance. A patch time-series transformer is employed for peak load forecasting, incorporating aleatoric uncertainty quantification to account for forecasting uncertainties within the decision-making process. The framework utilizes a solver-in-the-loop approach to generate optimal BESS actions, which are then used to train the neural optimizer-based agent. By co-optimizing both BESS operational modes and output power within the NN, the system achieves improved performance and robustness. After initial training, the forecasting and control models are jointly fine-tuned to account for forecasting errors, further improving decision precision and efficiency through DFL. Case studies are performed to validate the performance of the framework using multiple real-world datasets, demonstrating superior performance in monthly peak load forecasting compared to state-of-the-art models. In addition, the results are compared against existing decision-making approaches. The results demonstrate a reduction in monthly peak forecasting error by approximately 15% across various performance measures and achieve an optimization gap for BESS operation that is about three times smaller compared to existing methods.

Kim, Hyeonjin [Pacific Northwest National Laborato↗

NASA NTRS1993

Application of hardness testing in foundry processing operations: A university and industry partnership

The objectives are the following: (1) to plan a tour of local manufacturing facility to observe hardness testing methods used and how they support the manufacturing process today; (2) to learn the operation of Brinell Hardness Testing and equipment set up with samples of accessory equipment for testing of various materials; (3) to use a Brinell scope (hand magnifier) to measure the diameter of the test indentation (in millimeters); (4) to use the hardness equation to determine the spherical area of the indentation and the calculation of the Brinell Hardness Number; (5) to use standard charts for ASTM standard size indenters to find the hardness number; and (6) to learn a method of conversion of the Brinell number to other hardness scales, their common usage, and also to convert the hardness number to the approximate tensile strength.

Martin, Donald H.↗

DOE OSTI2024

Learning Nonlinear Reduced Models from Data with Operator Inference

This review discusses Operator Inference, a nonintrusive reduced modeling approach that incorporates physical governing equations by defining a structured polynomial form for the reduced model, and then learns the corresponding reduced operators from simulated training data. The polynomial model form of Operator Inference is sufficiently expressive to cover a wide range of nonlinear dynamics found in fluid mechanics and other fields of science and engineering, while still providing efficient reduced model computations. The learning steps of Operator Inference are rooted in classical projection-based model reduction; thus, some of the rich theory of model reduction can be applied to models learned with Operator Inference. This connection to projection-based model reduction theory offers a pathway toward deriving error estimates and gaining insights to improve predictions. Furthermore, through formulations of Operator Inference that preserve Hamiltonian and other structures, important physical properties such as energy conservation can be guaranteed in the predictions of the reduced model beyond the training horizon. This review illustrates key computational steps of Operator Inference through a large-scale combustion example.

Mechanics↗