Results for “Operator learning” — Page 56

NASA NTRS2014

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↗

DOE OSTI2026

Autonomous monitoring of algal biomass: Success stories and lessons learned from long-term field deployment

Autonomous, high-frequency monitoring of outdoor algal ponds is needed to quantify biomass productivity and detect culture decline in environments prone to contamination, grazers, and variable operating conditions. We report successes and lessons learned in translating a laboratory spectroradiometric monitoring approach to a multi-year autonomous field deployment at the Arizona Center for Algae Technology and Innovation (AzCATI). The system measures spectrally resolved pond reflectance by ratioing upwelling radiance from each raceway to simultaneous downwelling sky irradiance using fiber-coupled spectrometers. A physics-based reflectance model (ASHARP) is fit to each spectrum pair to estimate optical parameters, including a biomass-proxy coefficient (C a ) which enables near-real-time tracking of biomass accumulation and culture state at 2–5 min intervals. From May 2022 through September 2025 the platform operated continuously while scaling from two to six raceway ponds. Several strains of algae were monitored successfully, including the high productivity Tetraselmis striata and Picochlorum celeri. Transitioning data acquisition from a Windows laptop to a Raspberry Pi improved uptime from 57% (2022) to ~89% (2024–2025) and enabled routine real-time analysis. Further, we converted relative biomass estimates to absolute ash-free dry weight (AFDW) using experimentally-derived calibrations, providing field-relevant biomass predictions with conservative confidence bounds. These results demonstrate the feasibility of long-term, autonomous optical monitoring for well-mixed open-raceway algal cultivation and provide practical guidance for reliable field operation and scaling.

Katinas, Christopher Michael [Sandia National Labo↗

DOE OSTI2022

Identifying chemically similar multiphase nanoprecipitates in compositionally complex non-equilibrium oxides via machine learning

Abstract Characterizing oxide nuclear fuels is difficult due to complex fission products, which result from time-evolving system chemistry and extreme operating environments. Here, we report a machine learning-enhanced approach that accelerates the characterization of spent nuclear fuels and improves the accuracy of identifying nanophase fission products and bubbles. We apply this approach to commercial, high-burnup, irradiated light-water reactor fuels, demonstrating relationships between fission product precipitates and gases. We also gain understanding of the fission versus decay pathways of precipitates across the radius of a fuel pellet. An algorithm is provided for quantifying the chemical segregation of the fission products with respect to the high-burnup structure, which enhances our ability to process large amounts of microscopy data, including approaching the atomistic-scale. This may provide a faster route for achieving physics-based fuel performance modeling.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Machine Learning-Based PV Reserve Determination Strategy for Frequency Control on the WECC System: Preprint

Frequency control from Photovoltaic (PV) plants has great potential to address the frequency response challenge of the power system with high renewable penetration. However, using model-based approaches to determine the optimal PV headroom reserve requires significant online computation and is intractable for an interconnection level system. This paper proposes a machine learning based strategy, that is suitable for real-time operation, to determine the optimal PV reserve for frequency control. The proposed machine learning algorithm is trained and tested on 1,987 offline simulations of a 60% renewable penetration Western Electricity Coordinating Council (WECC) system. Furthermore, the proposed reserve determination strategy is applied on a realistic one-day operation profile of the WECC system and demonstrates over 40% PV headroom saving compared to a conservative approach. It is evident that the proposed strategy can efficiently and effectively determine the optimal PV frequency control reserve for realistic interconnection systems.

41 EE - Solar Energy Technologies Office (EE-4S)↗

DOE OSTI2025

Solid oxide electrolysis cell and stack testing best practices

Solid oxide electrolyzer (SOE) technology is an emerging method for hydrogen production, noted for its superior electrical efficiency. Despite the significant progress made in recent years, the broad development of SOE technology is often constrained by the necessary and extensive "skill of the craft" required to successfully test simple single cell test articles. This may be linked to the dearth of practical and pragmatic guidance within the literature for safe, reliable, and performant test equipment and test procedures. Researchers at the Idaho National Laboratory (INL) have been actively testing SOEs ranging from button cells to stacks up to 500 kW, in collaboration with industry and other national laboratories. Based on operational experience, INL has developed system design procedures that ensure safe and reliable operation of SOE systems with the level of support required for each test. This paper presents key aspects of SOE stack and system testing, including safe design procedures, balance of plant components design, and specific implementations at INL. Practical design details of reactants, heat, and power management are presented along with lessons learned from the SOE test facility operations at INL.

08 HYDROGEN↗

NASA NTRS2013

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↗

DOE OSTI2025

From clutter to clarity: Emergent neural operators via questionnaire metrics

Real-world datasets in chemical engineering and bioengineering processes—such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials—can often be unlabeled or disorganized, rendering the training of existing supervised learning models ineffective at learning the underlying dynamics. To salvage these datasets for decision-making, we first seek to obtain clarity from the cluttered data. Here, we present a framework for developing “structural” generative models, discovering emergent equations, and constructing efficient emulators from scrambled datasets by integrating unsupervised organizational learning techniques (Questionnaires) with advanced deep learning architectures (Deep Hidden Physics Models and Deep Operator Networks). Our approach is demonstrated on two illustrative model systems: (a) a 1D advection–diffusion partial differential equation representing a winding underground pipe and (b) an ensemble of Stuart–Landau oscillators, an agent-based system of coupled ordinary differential equations. In both cases, we successfully reconstruct meaningful spatial, temporal, and parameter embeddings from scrambled data, enabling good predictions of system dynamics. As a result, we highlight the framework’s potential for broader applications, enabling data-driven system identification in fields with inherently disorganized or hidden parameter spaces.

42 ENGINEERING↗

DOE OSTI2025

Nuclear microreactor transient and load-following control with deep reinforcement learning

The economic feasibility of nuclear microreactors will depend on minimizing operating costs through advancements in autonomous control, especially when these microreactors are operating alongside other types of energy systems (e.g., renewable energy). This study explores the application of deep reinforcement learning (RL) for real-time drum control in microreactors, exploring performance in regard to load-following scenarios. By leveraging a point kinetics model with thermal and xenon feedback, we first establish a baseline using a single-output RL agent, then compare it against a traditional proportional–integral–derivative (PID) controller. This study demonstrates that RL controllers, including both single- and multi-agent RL (MARL) frameworks, can achieve similar or even superior load-following performance as traditional PID control across a range of load-following scenarios. In short transients, the RL agent was able to reduce the tracking error rate in comparison to PID by one half to one third. Over extended 300-minute load-following scenarios in which xenon feedback becomes a dominant factor, PID maintained better accuracy, but RL still remained within a 1% error margin despite being trained only on short-duration scenarios. This highlights RL’s strong ability to generalize and extrapolate to longer, more complex transients, affording substantial reductions in training costs and reduced overfitting. Furthermore, when control was extended to multiple drums, MARL enabled independent drum control as well as maintained reactor symmetry constraints without sacrificing performance---an objective that standard single-agent RL could not learn. We also found that, as increasing levels of Gaussian noise were added to the power measurements, the RL controllers were able to maintain lower error rates than PID, and to do so with at least 10% and upwards of 150% less control effort. These findings illustrate RL's potential for autonomous nuclear reactor control, laying the groundwork for future integration into high-fidelity simulations and experimental validation efforts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS2022

Sustainable Aviation Operations and the Role of Information Technology and Data Science: Background, Current Status and Future Directions

This paper reviews the achievements of the international community towards environmentally friendly aviation operations, also referred to as Sustainable Aviation Operations in the last 25 years and the aspirations and goals to limit the impact of aviation and climate in the future. The framework for achieving global progress is provided by the International Civil Aviation Organization. NASA and FAA supported research and development to advance ATM concepts, and implemented the technology, concepts, and procedures that were responsible for creating fuel efficient flights. Historically aviation operations have been analyzed using physics-based models and provide information for making operational decisions. Future developments in aviation operations require new concepts, procedure, modeling, and analysis techniques. There is an increasing interest in applying methods based on Machine Learning Techniques to problems in Air Traffic Management. Aviation operations involving many decision makers, multiple objectives, poor or unavailable physics-based models and the availability of a rich historical database provide opportunities to exploit the richness of data-driven methods. The promises and challenges in applying Machine Learning Techniques to Air Traffic Management are discussed in the paper along with the testing and trustworthiness required for adoption of the techniques in operations.

Sustainable Aviation, Data Science, Machine Learni↗

NASA NTRS2022

Sustainable Aviation Operations and the Role of Information Technology and Data Science: Background, Current Status and Future Directions

This paper reviews the achievements of the international community towards environmentally friendly aviation operations, also referred to as Sustainable Aviation Operations in the last 25 years and the aspirations and goals to limit the impact of aviation and climate in the future. The framework for achieving global progress is provided by the International Civil Aviation Organization. NASA and FAA supported research and development to advance ATM concepts, and implemented the technology, concepts, and procedures that were responsible for creating fuel efficient flights. Historically aviation operations have been analyzed using physics-based models and provide information for making operational decisions. Future developments in aviation operations require new concepts, procedure, modeling, and analysis techniques. There is an increasing interest in applying methods based on Machine Learning Techniques to problems in Air Traffic Management. Aviation operations involving many decision makers, multiple objectives, poor or unavailable physics-based models and the availability of a rich historical database provide opportunities to exploit the richness of data-driven methods. The promises and challenges in applying Machine Learning Techniques to Air Traffic Management are discussed in the paper along with the testing and trustworthiness required for adoption of the techniques in operations.

Sustainable Aviation, Data Science, Machine Learni↗

NASA NTRS2000

Multimodality Instrument for Tissue Characterization

A system with multimodality instrument for tissue identification includes a computer-controlled motor driven heuristic probe with a multisensory tip is discussed. For neurosurgical applications, the instrument is mounted on a stereotactic frame for the probe to penetrate the brain in a precisely controlled fashion. The resistance of the brain tissue being penetrated is continually monitored by a miniaturized strain gauge attached to the probe tip. Other modality sensors may be mounted near the probe tip to provide real-time tissue characterizations and the ability to detect the proximity of blood vessels, thus eliminating errors normally associated with registration of pre-operative scans, tissue swelling, elastic tissue deformation, human judgement, etc., and rendering surgical procedures safer, more accurate, and efficient. A neural network, program adaptively learns the information on resistance and other characteristic features of normal brain tissue during the surgery and provides near real-time modeling. A fuzzy logic interface to the neural network program incorporates expert medical knowledge in the learning process. Identification of abnormal brain tissue is determined by the detection of change and comparison with previously learned models of abnormal brain tissues. The operation of the instrument is controlled through a user friendly graphical interface. Patient data is presented in a 3D stereographics display. Acoustic feedback of selected information may optionally be provided. Upon detection of the close proximity to blood vessels or abnormal brain tissue, the computer-controlled motor immediately stops probe penetration.

Mah, Robert W.↗

NASA NTRS2004

Multimodality instrument for tissue characterization

A system with multimodality instrument for tissue identification includes a computer-controlled motor driven heuristic probe with a multisensory tip. For neurosurgical applications, the instrument is mounted on a stereotactic frame for the probe to penetrate the brain in a precisely controlled fashion. The resistance of the brain tissue being penetrated is continually monitored by a miniaturized strain gauge attached to the probe tip. Other modality sensors may be mounted near the probe tip to provide real-time tissue characterizations and the ability to detect the proximity of blood vessels, thus eliminating errors normally associated with registration of pre-operative scans, tissue swelling, elastic tissue deformation, human judgement, etc., and rendering surgical procedures safer, more accurate, and efficient. A neural network program adaptively learns the information on resistance and other characteristic features of normal brain tissue during the surgery and provides near real-time modeling. A fuzzy logic interface to the neural network program incorporates expert medical knowledge in the learning process. Identification of abnormal brain tissue is determined by the detection of change and comparison with previously learned models of abnormal brain tissues. The operation of the instrument is controlled through a user friendly graphical interface. Patient data is presented in a 3D stereographics display. Acoustic feedback of selected information may optionally be provided. Upon detection of the close proximity to blood vessels or abnormal brain tissue, the computer-controlled motor immediately stops probe penetration. The use of this system will make surgical procedures safer, more accurate, and more efficient. Other applications of this system include the detection, prognosis and treatment of breast cancer, prostate cancer, spinal diseases, and use in general exploratory surgery.

Mah, Robert W.↗

NASA NTRS2011

Handling Qualities Flight Testing of the Stratospheric Observatory for Infrared Astronomy (SOFIA)

Airborne infrared astronomy has a long successful history, albeit relatively unknown outside of the astronomy community. A major problem with ground based infrared astronomy is the absorption and scatter of infrared energy by water in the atmosphere. Observing the universe from above 40,000 ft puts the observation platform above 99% of the water vapor in the atmosphere, thereby addressing this problem at a fraction of the cost of space based systems. The Stratospheric Observatory For Infrared Astronomy (SOFIA) aircraft is the most ambitious foray into the field of airborne infrared astronomy in history. Using a 747SP (The Boeing Company, Chicago, Illinois) aircraft modified with a 2.5m telescope located in the aft section of the fuselage, the SOFIA endeavors to provide views of the universe never before possible and at a fraction of the cost of space based systems. The modification to the airplane includes moveable doors and aperture that expose the telescope assembly. The telescope assembly is aimed and stabilized using a multitude of on board systems. This modification has the potential to cause aerodynamic anomalies that could induce undesired forces either at the cavity itself or indirectly due to interference with the empennage, both of which could cause handling qualities issues. As a result, an extensive analysis and flight test program was conducted from December 2009 through March 2011. Several methods, including a Lower Order Equivalent Systems analysis and pilot assessment, were used to ascertain the effects of the modification. The SOFIA modification was found to cause no adverse handling qualities effects and the aircraft was cleared for operational use. This paper discusses the history and modification to the aircraft, development of test procedures and analysis, results of testing and analysis, lessons learned for future projects and justification for operational certification.

Glaser, Scott T.↗

NASA NTRSDate not supplied

Transient Optimization of an Electrified Gas Turbine Engine Using Machine Learning

Gas turbine engines are designed with sufficient margin to prevent stall under normal operating conditions throughout their life. This compromise ensures that during rapid accelerations, compressor operation remains stable, but at the cost of efficiency and thrust responsiveness. The design margin encompasses multiple sources of uncertainty and systematic deviances from the operating line, the largest of which is the transient allowance. This set-aside accounts for the temporary incoordination of the engine spools during an acceleration while still enabling it to meet the certification requirement to accelerate from low to high power within a specified time, and without experiencing overtemperature, surge, stall, or other detrimental factors. Electrification of the powertrain provides the opportunity to address this reserve and truly optimize the design. The addition of electric machines inherent in hybrid propulsion concepts offers a means to interact with the engine shafts such that the necessary margin can be reduced, which can positively impact the engine design. By adjusting the amount of power extracted from or injected to the engine spools by the electric machines during transient operation, excursions from the operating line can be minimized. Past work using a dynamic engine model has shown that optimization of the fuel flow schedule during acceleration can reduce the required margin while still meeting the time requirement, and results are further improved when combined with power injection and extraction. The current work uses machine learning through a genetic algorithm to address the problem holistically by concurrently optimizing the electric machine power command and fuel flow acceleration schedule using an updated, higher fidelity version of the original engine model.

Stall Margin↗

NASA NTRSDate not supplied

Transient Optimization of an Electrified Gas Turbine Engine Using Machine Learning

Gas turbine engines are designed with sufficient margin to prevent stall under normal operating conditions throughout their life. This compromise ensures that during rapid accelerations, compressor operation remains stable, but at the cost of efficiency and thrust responsiveness. The design margin encompasses multiple sources of uncertainty and systematic deviances from the operating line, the largest of which is the transient allowance. This set-aside accounts for the temporary incoordination of the engine spools during an acceleration while still enabling it to meet the certification requirement to accelerate from low to high power within a specified time, and without experiencing overtemperature, surge, stall, or other detrimental factors. Electrification of the powertrain provides the opportunity to address this reserve and truly optimize the design. The addition of electric machines inherent in hybrid propulsion concepts offers a means to interact with the engine shafts such that the necessary margin can be reduced, which can positively impact the engine design. By adjusting the amount of power extracted from or injected to the engine spools by the electric machines during transient operation, excursions from the operating line can be minimized. Past work using a dynamic engine model has shown that optimization of the fuel flow schedule during acceleration can reduce the required margin while still meeting the time requirement, and results are further improved when combined with power injection and extraction. The current work uses machine learning through a genetic algorithm to address the problem holistically by concurrently optimizing the electric machine power command and fuel flow acceleration schedule using an updated, higher fidelity version of the original engine model.

Stall Margin↗

NASA NTRS2024

Transient Optimization of an Electrified Gas Turbine Engine Using Machine Learning

Gas turbine engines are designed with sufficient margin to prevent stall under normal operating conditions throughout their life. This compromise ensures that during rapid accelerations, compressor operation remains stable, but at the cost of efficiency and thrust responsiveness. The design margin encompasses multiple sources of uncertainty and systematic deviances from the operating line, the largest of which is the transient allowance. This set-aside accounts for the temporary incoordination of the engine spools during an acceleration while still enabling it to meet the certification requirement to accelerate from low to high power within a specified time, and without experiencing overtemperature, surge, stall, or other detrimental factors. Electrification of the powertrain provides the opportunity to address this reserve and truly optimize the design. The addition of electric machines inherent in hybrid propulsion concepts offers a means to interact with the engine shafts such that the necessary margin can be reduced, which can positively impact the engine design. By adjusting the amount of power extracted from or injected to the engine spools by the electric machines during transient operation, excursions from the operating line can be minimized. Past work using a dynamic engine model has shown that optimization of the fuel flow schedule during acceleration can reduce the required margin while still meeting the time requirement, and results are further improved when combined with power injection and extraction. The current work uses machine learning through a genetic algorithm to address the problem holistically by concurrently optimizing the electric machine power command and fuel flow acceleration schedule using an updated, higher fidelity version of the original engine model.

Stall Margin↗

DOE OSTI2024

Probabilistic machine learning for battery health diagnostics and prognostics—review and perspectives

Abstract Diagnosing lithium-ion battery health and predicting future degradation is essential for driving design improvements in the laboratory and ensuring safe and reliable operation over a product’s expected lifetime. However, accurate battery health diagnostics and prognostics is challenging due to the unavoidable influence of cell-to-cell manufacturing variability and time-varying operating circumstances experienced in the field. Machine learning approaches informed by simulation, experiment, and field data show enormous promise to predict the evolution of battery health with use; however, until recently, the research community has focused on deterministic modeling methods, largely ignoring the cell-to-cell performance and aging variability inherent to all batteries. To truly make informed decisions regarding battery design in the lab or control strategies for the field, it is critical to characterize the uncertainty in a model’s predictions. After providing an overview of lithium-ion battery degradation, this paper reviews the current state-of-the-art probabilistic machine learning models for health diagnostics and prognostics. Details of the various methods, their advantages, and limitations are discussed in detail with a primary focus on probabilistic machine learning and uncertainty quantification. Last, future trends and opportunities for research and development are discussed.

25 ENERGY STORAGE↗

DOE OSTI2026

Adaptive Reinforcement Learning Control for Power Distribution in Multi-Output Resonant Converters

This paper presents an adaptive reinforcement learning (ARL)-based control framework for efficient power distribution in a multi-output resonant converter for UAV applications. The proposed system is based on a high-frequency isolated resonant architecture, where a single energy source supplies multiple propulsion loads through independently controlled output rectifiers, addressing the need for coordinated multi-motor power management. The ARL framework dynamically allocates output power by learning optimal phase-shift control actions under varying load demands and operating conditions. The agent autonomously determines control parameters that maximize conversion efficiency while ensuring accurate power sharing among multiple outputs. In addition, the proposed approach enables adaptive operation without requiring detailed system modeling or manual tuning. Experimental results demonstrate stable and efficient performance over a wide range of operating conditions, confirming the effectiveness and robustness of the learning-based control strategy for multi-output resonant converter system.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗