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 793 records · Page 44
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Machine Learning for Real-time Fusion Plasma Behavior Prediction and Manipulation

This project set out with an ambitious goal: to develop and apply machine learning-based methods of discovering new controllers and operating regimes for achieving better performing plasmas in tokamaks. As summarized in the dozens of papers below, the project was a huge success. It developed several machine learning components and integrated them into a single ML system that was added to the DIII-D PCS. That functionality was demonstrated over a series of experiments on DIII-D. A summary of these results is given here with the details in the published papers below.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems

This work presents a data-driven method for learning low-dimensional time-dependent physics-based surrogate models whose predictions are endowed with uncertainty estimates. We use the operator inference approach to model reduction that poses the problem of learning low-dimensional model terms as a regression of state space data and corresponding time derivatives by minimizing the residual of reduced system equations. Standard operator inference models perform well with accurate training data that are dense in time, but producing stable and accurate models when the state data are noisy and/or sparse in time remains a challenge. Another challenge is the lack of uncertainty estimation for the predictions from the operator inference models. Our approach addresses these challenges by incorporating Gaussian process surrogates into the operator inference framework to (1) probabilistically describe uncertainties in the state predictions and (2) procure analytical time derivative estimates with quantified uncertainties. The formulation leads to a generalized least-squares regression and, ultimately, reduced-order models that are described probabilistically with a closed-form expression for the posterior distribution of the operators. The resulting probabilistic surrogate model propagates uncertainties from the observed state data to reduced-order predictions. Furthermore, we demonstrate the method is effective for constructing low-dimensional models of two nonlinear partial differential equations representing a compressible flow and a nonlinear diffusion–reaction process, as well as for estimating the parameters of a low-dimensional system of nonlinear ordinary differential equations representing compartmental models in epidemiology.

Data-driven model reduction↗
NASA NTRS2005

Attitude and position estimation on the Mars Exploration Rovers

NASA/JPL 's Mars Exploration Rovers acquire their attitude upon command and autonomously propagate their attitude and position. The rovers use accelerometers and images of the sun to acquire attitude, autonomously searching the sky for the sun with a pointable camera. To propagate the attitude and position the rovers use either accelerometer and gyro readings or gyro readings and wheel odometiy, depending on the nature of the movement ground operators are commanding. Where necessary, visual odometry is performed on images to fine tune the position updates, particularly in high slip environments. The capability also exists for visual odometry attitude updates. This paper describes the techniques used by the rovers to acquire and maintain attitude and position knowledge, the accuracy which is obtainable, and lessons learned after more than one year in operation.

attitude estimation↗
DOE OSTI2024

Deep Multitask Learning Models for Radiation Estimation at High Energy Accelerator Facility

Controlling the dose of radiation exposure in potential radioactive facilities is critical for ensuring the safety of staff and the public. Here, in this paper, we developed machine learning models to estimate radiation exposure efficiently at the Thomas Jefferson National Accelerator Facility (JLab), aiming to enhance safety in both accelerator facilities and public areas. Multiple sensors were deployed around the three experimental halls at JLab. Data on single-beam currents, energy levels, and radiation values at the sensor locations were collected during accelerator operation. We proposed a multi-task learning model for radiation estimation, utilizing either one-dimensional convolutional neural networks (1-D CNNs) or long short-term memory networks (LSTMs) as the backbone. The proposed model was trained to simultaneously estimate radiation levels at the sensor locations. Experimental results demonstrated that the proposed model with LSTM backbone achieved the best estimation performance, with an average R 2 score of 0.7557 for estimation within the same year and 0.7157 for estimation across different years. These results significantly surpassed those of competing models.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS2017

Transforming Satellite Data into Weather Forecasts

A NASA project spans the gap between research and operations, introducing new composites of satellite imagery to weather forecasters to prepare for the next generation of satellites. Satellite imagery has been an immense benefit to weather forecasters. With it, they can assess aviation hazards such as low clouds, monitor thunderstorms, and track the evolution of dust plumes. Satellite sensors are continually evolving to provide ever greater imaging capabilities, and researchers continue to develop advanced techniques to identify hazards in satellite imagery. However, barriers can prevent experimental products from reaching forecasters in the operational environment. A NASA project has developed an interactive process whereby weather forecasters learn to interpret the latest satellite imagery and apply it to their operations. Forecasters then provide feedback to the researchers who are developing algorithms and products to further improve future products. This effort has taken on greater importance with the anticipated launch of a new series of satellites that will provide substantially greater amounts of data than are currently available.

Emily Berndt↗
NASA NTRS2000

On-Line, Self-Learning, Predictive Tool for Determining Payload Thermal Response

This paper will present the results of a joint ManTech / Goddard R&D effort, currently under way, to develop and test a computer based, on-line, predictive simulation model for use by facility operators to predict the thermal response of a payload during thermal vacuum testing. Thermal response was identified as an area that could benefit from the algorithms developed by Dr. Jeri for complex computer simulations. Most thermal vacuum test setups are unique since no two payloads have the same thermal properties. This requires that the operators depend on their past experiences to conduct the test which requires time for them to learn how the payload responds while at the same time limiting any risk of exceeding hot or cold temperature limits. The predictive tool being developed is intended to be used with the new Thermal Vacuum Data System (TVDS) developed at Goddard for the Thermal Vacuum Test Operations group. This model can learn the thermal response of the payload by reading a few data points from the TVDS, accepting the payload's current temperature as the initial condition for prediction. The model can then be used as a predictive tool to estimate the future payload temperatures according to a predetermined shroud temperature profile. If the error of prediction is too big, the model can be asked to re-learn the new situation on-line in real-time and give a new prediction. Based on some preliminary tests, we feel this predictive model can forecast the payload temperature of the entire test cycle within 5 degrees Celsius after it has learned 3 times during the beginning of the test. The tool will allow the operator to play "what-if' experiments to decide what is his best shroud temperature set-point control strategy. This tool will save money by minimizing guess work and optimizing transitions as well as making the testing process safer and easier to conduct.

Jen, Chian-Li↗
DOE OSTI2024

WEST full tungsten operation with an ITER grade divertor

The mission of WEST (tungsten-W Environment in Steady-state Tokamak) is to explore long pulse operation in a full tungsten (W) environment for preparing next-step fusion devices (ITER and DEMO) with a focus on testing the ITER actively cooled W divertor in tokamak conditions. Following the successful completion of phase 1 (2016-2021), phase 2 started in December 2022 with the lower divertor made entirely of actively cooled ITER-grade tungsten mono-blocks. A boronization prior the first plasma attempt allowed for a smooth startup with the new divertor. Despite the reduced operating window due to tungsten, rapid progress has been made in long pulse operation, resulting in discharges with a pulse length of 100 s and an injected energy of around 300 MJ per discharge. Plasma startup studies were carried out with equatorial boron nitride limiters to compare them with tungsten limiters, while Ion Cyclotron Resonance Heating assisted startup was attempted. High fluence operation in attached regime, which was the main thrust of the first campaigns, already showed the progressive build up of deposits and appearance of dust, impacting the plasma operation as the plasma fluence increased. In total, the cumulated injected energy during the first campaigns reached 43 GJ and the cumulated plasma time exceeded 5 h. Demonstration of controlled X-Point Radiator regime is also reported, opening a promising route for investigating plasma exhaust and plasma-wall interaction issues in more detached regime. This paper summarises the lessons learned from the manufacturing and the first operation of the ITER-grade divertor, describing the progress achieved in optimising operation in a full W environment with a focus on long pulse operation and plasma wall interaction.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2011

Space Shuttle Guidance, Navigation, and Rendezvous Knowledge Capture Reports

This document is a catalog and readers guide to lessons learned, experience, and technical history reports, as well as compilation volumes prepared by United Space Alliance personnel for the NASA/Johnson Space Center (JSC) Flight Dynamics Division.1 It is intended to make it easier for future generations of engineers to locate knowledge capture documentation from the Shuttle Program. The first chapter covers observations on documentation quality and research challenges encountered during the Space Shuttle and Orion programs. The second chapter covers the knowledge capture approach used to create many of the reports covered in this document. These chapters are intended to provide future flight programs with insight that could be used to formulate knowledge capture and management strategies. The following chapters contain descriptions of each knowledge capture report. The majority of the reports concern the Space Shuttle. Three are included that were written in support of the Orion Program. Most of the reports were written from the years 2001 to 2011. Lessons learned reports concern primarily the shuttle Global Positioning System (GPS) upgrade and the knowledge capture process. Experience reports on navigation and rendezvous provide examples of how challenges were overcome and how best practices were identified and applied. Some reports are of a more technical history nature covering navigation and rendezvous. They provide an overview of mission activities and the evolution of operations concepts and trajectory design. The lessons learned, experience, and history reports would be considered secondary sources by historians and archivists.

John L Goodman↗
DOE OSTI2024

Overview of the KSTAR experiments toward fusion reactor

The Korean Superconducting Tokamak Advanced Research has been focused on exploring the key physics and engineering issues for future fusion reactors by demonstrating the long pulse operation of high beta steady-state discharge. Advanced scenarios are being developed with the goal for steady-state operation, and significant progress has been made in high ℓ i , hybrid and high beta scenarios with β N of 3. In the new operation scenario called fast ion regulated enhanced (FIRE), fast ions play an essential role in confinement enhancement. GK simulations show a significant reduction of the thermal energy flux when the thermal ion fraction decreases and the main ion density gradient is reversed by the fast ions in FIRE mode. Optimization of 3D magnetic field techniques, including adaptive control and real-time machine learning control algorithm, enabled long-pulse operation and high-performance ELM-suppressed discharge. Symmetric multiple shattered pellet injections (SPIs) and real-time disruption event characterization and forecasting are being performed to mitigate and avoid the disruptions associated with high-performance, long-pulse ITER-like scenarios. Finally, the near-term research plan will be addressed with the actively cooled tungsten divertor, a major upgrade of the NBI and helicon current drive heating, and transition to a full metallic wall.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1995

Dynamic neural networks based on-line identification and control of high performance motor drives

In the automated and high-tech industries of the future, there wil be a need for high performance motor drives both in the low-power range and in the high-power range. To meet very straight demands of tracking and regulation in the two quadrants of operation, advanced control technologies are of a considerable interest and need to be developed. In response a dynamics learning control architecture is developed with simultaneous on-line identification and control. the feature of the proposed approach, to efficiently combine the dual task of system identification (learning) and adaptive control of nonlinear motor drives into a single operation is presented. This approach, therefore, not only adapts to uncertainties of the dynamic parameters of the motor drives but also learns about their inherent nonlinearities. In fact, most of the neural networks based adaptive control approaches in use have an identification phase entirely separate from the control phase. Because these approaches separate the identification and control modes, it is not possible to cope with dynamic changes in a controlled process. Extensive simulation studies have been conducted and good performance was observed. The robustness characteristics of neuro-controllers to perform efficiently in a noisy environment is also demonstrated. With this initial success, the principal investigator believes that the proposed approach with the suggested neural structure can be used successfully for the control of high performance motor drives. Two identification and control topologies based on the model reference adaptive control technique are used in this present analysis. No prior knowledge of load dynamics is assumed in either topology while the second topology also assumes no knowledge of the motor parameters.

Rubaai, Ahmed↗
NASA NTRS2006

Spitzer Observatory Operations -- Increasing Efficiency in Mission Operations

This paper explores the how's and why's of the Spitzer Mission Operations System's (MOS) success, efficiency, and affordability in comparison to other observatory-class missions. MOS exploits today's flight, ground, and operations capabilities, embraces automation, and balances both risk and cost. With operational efficiency as the primary goal, MOS maintains a strong control process by translating lessons learned into efficiency improvements, thereby enabling the MOS processes, teams, and procedures to rapidly evolve from concept (through thorough validation) into in-flight implementation. Operational teaming, planning, and execution are designed to enable re-use. Mission changes, unforeseen events, and continuous improvement have often times forced us to learn to fly anew. Collaborative spacecraft operations and remote science and instrument teams have become well integrated, and worked together to improve and optimize each human, machine, and software-system element.

operational efficiency↗
DOE OSTI2024

Towards intelligent emergency control for large-scale power systems: Convergence of learning, physics, computing and control

Here, this paper has delved into the pressing need for intelligent emergency control in large-scale power systems, which are experiencing significant transformations and are operating closer to their limits with more uncertainties. Learning-based control methods are promising and have shown effectiveness for intelligent power system control. However, when they are applied to large-scale power systems, there are multifaceted challenges such as scalability, adaptiveness, and security posed by the complex power system landscape, which demand comprehensive solutions. The paper first proposes and instantiates a convergence framework for integrating power systems physics, machine learning, advanced computing, and grid control to realize intelligent grid control at a large scale. Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56 000 scenarios. Our work achieved a 26% reduction in load shedding on average and outperformed existing rule-based control in 99.7% of the test scenarios. The results demonstrated the potential of the proposed convergence framework and DRL-based intelligent control for the future grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Co-Simulation Meets AI: MCP-Driven Power System Analysis

GridGPT, a fine-tuned Generative AI model is designed for on-premise use in grid control rooms. This presentation will demonstrate how eGridGPT can seamlessly integrate with control room solutions to offer operators, engineers, and corporate users enhanced guidance and decision support. It is to show how this innovative AI solution can improve state estimation, boost variable energy forecasting, and optimize grid operations. By leveraging eGridGPT's unique features, audience will learn to unlock new levels of automation, predictive analytics, and reliability within their power systems, ultimately leading to reduced downtime and improved operational efficiency.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Data-Driven Modeling and Correction of Vehicle Dynamics

We develop a data-driven framework for learning and correcting nonautonomous vehicle dynamics. Physics-based vehicle models are often simplified for tractability and therefore exhibit inherent model-form uncertainty, motivating the need for data-driven correction. Moreover, nonautonomous dynamics are governed by time-dependent control inputs, which pose challenges in learning predictive models directly from temporal snapshot data. To address these, we reformulate the vehicle dynamics via a local parameterization of the time-dependent inputs, yielding a modified system composed ofa sequence of local parametric dynamical systems. Here, we approximate these parametric systems using two complementary approaches. First, we employ the dimension reduction and interpolation in parameter space (DRIPS) methodology to construct efficient linear surrogate models, equipped with lifted observable spaces and manifold-based operator interpolation. This enables data-efficient learning of vehicle models whose dynamics admit accurate linear representations in the lifted spaces. Second, for more strongly nonlinear systems, we employ flow map learning (FML), a deep neural network (DNN) approach that approximates the parametric evolution map without requiring special treatment of nonlinearities. We further extend FML with a transfer-learning-based model correction procedure, enabling the correction of misspecified prior models using only a sparse set of high-fidelity or experimental measurements, without assuming a prescribed form for the correction term. Through a suite of numerical experiments on unicycle, simplified bicycle, and slip-based bicycle models, we demonstrate that DRIPS offers robust and highly data-efficient learning of nonautonomous vehicle dynamics, while FML provides expressive nonlinear modeling and effective correction of model-form errors under severe data scarcity.

data-driven modeling↗
NASA NTRS2016

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↗
NASA NTRSDate not supplied

NASA's Biosentinel Mission: Lessons Learned and What's Next

In the last two years, two BioSentinel payloads were launched to space. The ISS mission launched in December 2021, and returned to the ground in August 2022 after successfully completing eight biological experiments while validating the different instruments. On the other hand, the deep space mission launched onboard Artemis I in November 2022, and is currently in a heliocentric orbit over 20 million kilometers away from the Earth. Even though all hardware subsystems were validated in deep space, the microfluidic subsystems experienced anomalies throughout the initial 6-month mission. The main goals of this presentation are (1) to present flight data from the deep space payload, including biology, fluidics, electronics, data processing, and mission operations, and (2) to discuss the lessons learned – what worked and what did not – from this unique complex mission, and how these lessons are aiding in the development of the Lunar Exploration Instrument for space biology Applications (LEIA) mission, launching to the lunar surface on a commercial lander in 2026. As of the writing of this abstract, the satellite continues to work nominally, communicating to Earth via the Deep Space Network (DSN) twice per week. Importantly, the mission received and extension to continue recording data on the deep space radiation environment on its way to solar maximum (i.e., higher probability of solar particle events). BioSentinel is supported by NASA Exploration Systems Development Mission Directorate (ESDMD).

BioSentinel↗
NASA NTRS1981

Using rewards and penalties to obtain desired subject performance

Operant conditioning procedures, specifically the use of negative reinforcement, in achieving stable learning behavior is described. The critical tracking test (CTT) a method of detecting human operator impairment was tested. A pass level is set for each subject, based on that subject's asymptotic skill level while sober. It is critical that complete training take place before the individualized pass level is set in order that the impairment can be detected. The results provide a more general basis for the application of reward/penalty structures in manual control research.

Cook, M.↗
NASA NTRS1990

Knowledge acquisition and representation for the Systems Test and Operations Language (STOL) Intelligent Tutoring System (ITS)

This presentation concentrates on knowledge acquisition and its application to the development of an expert module and a user interface for an Intelligent Tutoring System (ITS). The Systems Test and Operations Language (STOL) ITS is being developed to assist NASA control center personnel in learning a command and control language as it is used in mission operations rooms. The objective of the tutor is to impart knowledge and skills that will permit the trainee to solve command and control problems in the same way that the STOL expert solves those problems. The STOL ITS will achieve this object by representing the solution space in such a way that the trainee can visualize the intermediate steps, and by having the expert module production rules parallel the STOL expert's knowledge structures.

Seamster, Thomas L.↗