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 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A comprehensive and fair comparison of two neural operators (with practical extensions) based on $\mathrm{FAIR}$ data

Neural operators can learn nonlinear mappings between function spaces and offer a new simulation paradigm for real-time prediction of complex dynamics for realistic diverse applications as well as for system identification in science and engineering. Herein, we investigate the performance of two neural operators, which have shown promising results so far, and we develop new practical extensions that will make them more accurate and robust and importantly more suitable for industrial-complexity applications. The first neural operator, DeepONet, was published in 2019 (Lu et al., 2019), and its original architecture was based on the universal approximation theorem of Chen & Chen (1995). The second one, named Fourier Neural Operator or FNO, was published in 2020, and it is based on parameterizing the integral kernel in the Fourier space. DeepONet is represented by a summation of products of neural networks (NNs), corresponding to the branch NN for the input function and the trunk NN for the output function; both NNs are general architectures, e.g., the branch NN can be replaced with a CNN or a ResNet. According to Kovachki et al. (2021), FNO in its continuous form can be viewed conceptually as a DeepONet with a specific architecture of the branch NN and a trunk NN represented by a trigonometric basis. In order to compare FNO with DeepONet computationally for realistic setups, we develop several extensions of FNO that can deal with complex geometric domains as well as mappings where the input and output function spaces are of different dimensions. We also develop an extended DeepONet with special features that provide inductive bias and accelerate training, and we present a faster implementation of DeepONet with cost comparable to the computational cost of FNO, which is based on the Fast Fourier Transform. Here we consider 16 different benchmarks to demonstrate the relative performance of the two neural operators, including instability wave analysis in hypersonic boundary layers, prediction of the vorticity field of a flapping airfoil, porous media simulations in complex-geometry domains, etc. We follow the guiding principles of FAIR (Findability, Accessibility, Interoperability, and Reusability) for scientific data management and stewardship. The performance of DeepONet and FNO is comparable for relatively simple settings, but for complex geometries the performance of FNO deteriorates greatly. We also compare theoretically the two neural operators and obtain similar error estimates for DeepONet and FNO under the same regularity assumptions.

42 ENGINEERING↗
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↗
DOE OSTI2022

Fed-DeepONet: Stochastic Gradient-Based Federated Training of Deep Operator Networks

The Deep Operator Network (DeepONet) framework is a different class of neural network architecture that one trains to learn nonlinear operators, i.e., mappings between infinite-dimensional spaces. Traditionally, DeepONets are trained using a centralized strategy that requires transferring the training data to a centralized location. Such a strategy, however, limits our ability to secure data privacy or use high-performance distributed/parallel computing platforms. To alleviate such limitations, in this paper, we study the federated training of DeepONets for the first time. That is, we develop a framework, which we refer to as Fed-DeepONet, that allows multiple clients to train DeepONets collaboratively under the coordination of a centralized server. To achieve Fed-DeepONets, we propose an efficient stochastic gradient-based algorithm that enables the distributed optimization of the DeepONet parameters by averaging first-order estimates of the DeepONet loss gradient. Then, to accelerate the training convergence of Fed-DeepONets, we propose a moment-enhanced (i.e., adaptive) stochastic gradient-based strategy. Finally, we verify the performance of Fed-DeepONet by learning, for different configurations of the number of clients and fractions of available clients, (i) the solution operator of a gravity pendulum and (ii) the dynamic response of a parametric library of pendulums.

Moya, Christian↗
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

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 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↗
DOE OSTI2022

Data-Driven Operator Theoretic Methods for Phase Space Learning and Analysis

This paper uses data-driven operator theoretic approaches to explore the global phase space of a dynamical system. In this work, we defined conditions for discovering new invariant subspaces in the state space of a dynamical system starting from an invariant subspace based on the spectral properties of the Koopman operator. When the system evolution is known locally in several invariant subspaces in the state space of a dynamical system, a phase space stitching result is derived that yields the global Koopman operator. Additionally, in the case of equivariant systems, a phase space stitching result is developed to identify the global Koopman operator using the symmetry properties between the invariant subspaces of the dynamical system and time-series data from any one of the invariant subspaces. Finally, these results are extended to topologically conjugate dynamical systems; in particular, the relation between the Koopman tuple of topologically conjugate systems is established. The proposed results are demonstrated on several second-order nonlinear dynamical systems including a bistable toggle switch. Our method elucidates a strategy for designing discovery experiments: experiment execution can be done in many steps, and models from different invariant subspaces can be combined to approximate the global Koopman operator.

42 ENGINEERING↗
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.↗
DOE OSTI2023

Machine learning for optimizing the manufacture and operation of intermediate temperature fuel cells

The project developed machine learning and artificial intelligence (ML/AI) methodologies for guiding and accelerating the materials design and processing of new high temperature proton conducing electrode ionomer binders and reinforced membranes for high-temperature proton exchange membrane fuel cell (HT-PEMFC; aka intermediate-temperature polymer electrolyte membrane fuel cells).

08 HYDROGEN↗
DOE OSTI2021

A machine learning degradation model for electrochemical capacitors operated at high temperature

Electrochemical capacitors (ECs) have only recently been considered as an alternative power source for telemetry sensors of drilling equipment for geothermal or oil and gas exploration. The lifecycle analysis and modelling of ECs is underrepresented in literature in comparison to other storage devices e.g. Li-ion batteries. This paper investigates the degradation of ECs when cycled outside the manufacturer-specified operating temperature envelope and proposes a machine learning-based approach for modelling the degradation. Experimental results show that end of life, defined as a 30% decrease in capacitance, occurs at 1,000 cycles when the environmental temperature exceeds the maximum operating temperature by 30%. The life-cycle test data is then used as an input to a Gaussian process regression (GPR) algorithm to predict the capacitance fade trend. The GPR is validated on a total of nine commercial cells from two different manufacturers, achieving an average root mean squared percent error of less than 2% and a mean calibration score of 93% when referenced to a 95% confidence interval. The model can be utilized to determine the EC degradation rate at a range of operating temperature values.

42 ENGINEERING↗
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.↗
DOE OSTI2021

Non-intrusive nonlinear model reduction via machine learning approximations to low-dimensional operators

Abstract Although projection-based reduced-order models (ROMs) for parameterized nonlinear dynamical systems have demonstrated exciting results across a range of applications, their broad adoption has been limited by their intrusivity: implementing such a reduced-order model typically requires significant modifications to the underlying simulation code. To address this, we propose a method that enables traditionally intrusive reduced-order models to be accurately approximated in a non-intrusive manner. Specifically, the approach approximates the low-dimensional operators associated with projection-based reduced-order models (ROMs) using modern machine-learning regression techniques. The only requirement of the simulation code is the ability to export the velocity given the state and parameters; this functionality is used to train the approximated low-dimensional operators. In addition to enabling nonintrusivity, we demonstrate that the approach also leads to very low computational complexity, achieving up to $$10^3{\times }$$ 10 3 × in run time. We demonstrate the effectiveness of the proposed technique on two types of PDEs. The domain of applications include both parabolic and hyperbolic PDEs, regardless of the dimension of full-order models (FOMs).

42 ENGINEERING↗
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↗
DOE OSTI2022

Optimization of Water-Alternating-CO2 Injection Field Operations Using a Machine-Learning-Assisted Workflow

Summary This paper will present a robust workflow to address multiobjective optimization (MOO) of carbon dioxide (CO2)-enhanced oil recovery (EOR)-sequestration projects with a large number of operational control parameters. Farnsworth unit (FWU) field, a mature oil reservoir undergoing CO2 alternating water injection (CO2-WAG) EOR, will be used as a field case to validate the proposed optimization protocol. The expected outcome of this work would be a repository of Pareto-optimal solutions of multiple objective functions, including oil recovery, carbon storage volume, and project economics. FWU’s numerical model is used to demonstrate the proposed optimization workflow. Because using MOO requires computationally intensive procedures, machine-learning-based proxies are introduced to substitute for the high-fidelity model, thus reducing the total computation overhead. The vector machine regression combined with the Gaussian kernel (Gaussian-SVR) is used to construct proxies. An iterative self-adjusting process prepares the training knowledge base to develop robust proxies and minimizes computational time. The proxies’ hyperparameters will be optimally designed using Bayesian optimization to achieve better generalization performance. Trained proxies will be coupled with multiobjective particle swarm Optimization (MOPSO) protocol to construct the Pareto-front solution repository. The outcomes of this workflow will be a repository containing Pareto-optimal solutions of multiple objectives considered in the CO2-WAG project. The proposed optimization workflow will be compared with another established methodology using a multilayer neural network (MLNN) to validate its feasibility in handling MOO with a large number of parameters to control. Optimization parameters used include operational variables that might be used to control the CO2-WAG process, such as the duration of the water/gas injection period, producer bottomhole pressure (BHP) control, and water injection rate of each well included in the numerical model. It is proved that the workflow coupling Gaussian-SVR proxies and the iterative self-adjusting protocol is more computationally efficient. The MOO process is made more rapid by squeezing the size of the required training knowledge base while maintaining the high accuracy of the optimized results. The outcomes of the optimization study show promising results in successfully establishing the solution repository considering multiple objective functions. Results are also verified by validating the Pareto fronts with simulation results using obtained optimized control parameters. The outcome from this work could provide field operators an opportunity to design a CO2-WAG project using as many inputs as possible from the reservoir models. The proposed work introduces a novel concept that couples Gaussian-SVR proxies with a self-adjusting protocol to increase the computational efficiency of the proposed workflow and to guarantee the high accuracy of the obtained optimized results. More importantly, the workflow can optimize a large number of control parameters used in a complex CO2-WAG process, which greatly extends its utility in solving large-scale MOO problems in various projects with similar desired outcomes.

Energy & Fuels↗