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 1,207 records · Page 67
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Postdisaster Routing of Movable Energy Resources for Enhanced Distribution System Resilience: A Deep Reinforcement Learning-Based Approach

The deployment of movable energy resources (MERs) can be an effective strategy to restore critical loads to enhance power system resilience when no other energy sources are available after the occurrence of an extreme event. Since the optimal locations of MERs following an extreme event are dependent on system operating states (e.g., the loads at each node, on/off status of system branches, and so on), existing analytical and population-based approaches must repeat the entire analysis and calculation when the system operating states change. On the contrary, if deep reinforcement learning (DRL)-based algorithms are sufficiently trained with a wide range of scenarios, they can quickly find optimal or near-optimal locations irrespective of changes in system states. A deep Q-learning-based approach is proposed for optimal MER deployment to enhance power system resilience. MERs can be also utilized to complement other types of resources, if available. The proposed approach operates in two stages after the occurrence of extreme events. In the first stage, the distribution network is represented as a graph, and the network is then reconfigured using tie switches by using Kruskal’s spanning forest search algorithm (KSFSA). To maximize critical load recovery, the optimal or near-optimal locations of MERs are chosen in the second stage. Further, case studies on a 33-node distribution system and a modified IEEE 123-node system demonstrate the effectiveness of the proposed approach for postdisaster routing of MERs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Frequency-domain computing using nonlinear acoustic-wave device on lithium niobate

Abstract Multiply-accumulation are crucial computing operations in signal processing, numerical simulations, and machine learning. In recent years, optical analog approaches have demonstrated higher computing performance and better power efficiency than their digital counterparts. However, analog computing chips usually need large areas and complex structures for parallel computing, as a single device element only executes one computing operation at a single time. Here, we demonstrate frequency-domain computing using the nonlinear acoustic-wave devices on lithium niobate, featuring a normalized external second-harmonic generation conversion efficiency of ~ 5.7 × 10-4 W-1. The second-order sum-frequency nonlinear process of lithium niobate enables multiplication of inputs encoded in the frequency domain. Compared to the analog schemes, our device features a notably simpler design, and nanofabrication requires only one lift-off. Using a single acoustic-wave device within an area of 0.03 mm2, we can simultaneously conduct over 130,000 multiply-accumulation operations. Our acoustic-wave device shows applications in real and complex vector convolutions and image processing. This demonstration sets the stage for experimental realizations into frequency-domain integrated nonlinear acoustic computing systems, potentially shaping future developments in acoustic neural networks and quantum computing.

chai, mingzhao (ORCID:0009000466226341)↗
DOE OSTI2025

Accelerating Hamiltonian Monte Carlo for Bayesian inference in neural networks and neural operators

Hamiltonian Monte Carlo (HMC) is a powerful and accurate method to sample from the posterior distribution in Bayesian inference. However, HMC techniques are computationally demanding for Bayesian neural networks due to the high dimensionality of the network’s parameter space and the non-convexity of their posterior distributions. Therefore, various approximation techniques, such as variational inference (VI) or stochastic gradient MCMC, are often employed to infer the posterior distribution of the network parameters. Such approximations introduce inaccuracies in the inferred distributions, resulting in unreliable uncertainty estimates. In this work, we propose a hybrid approach that combines inexpensive VI and accurate HMC methods to efficiently and accurately quantify uncertainties in neural networks and neural operators. The proposed approach leverages an initial VI training on the full network. We examine the influence of individual parameters on the prediction uncertainty, which shows that a large proportion of the parameters do not contribute substantially to uncertainty in the network predictions. This information is then used to significantly reduce the dimension of the parameter space, and HMC is performed only for the subset of network parameters that strongly influence prediction uncertainties. This yields a framework for accelerating the full batch HMC for posterior inference in neural networks. We demonstrate the efficiency and accuracy of the proposed framework on deep neural networks and operator networks, showing that inference can be performed for large networks with tens to hundreds of thousands of parameters. Finally, we show that this method can effectively learn surrogates for complex physical systems by modeling the operator that maps from upstream conditions to wall-pressure data on a cone in hypersonic flow.

Bayesian inference↗
DOE OSTI2022

DSO+T: Transactive Energy Coordination Framework (DSO+T Study: Volume 3)

This report describes a transactive energy coordination scheme designed to integrate into existing day-ahead and real-time wholesale energy markets. This scheme was evaluated in the Distribution System Operator with Transactive (DSO+T) study to assess the engineering and economic performance of the transactive energy coordination of a large-scale deployment of distributed energy resources (DER). Transactive agents were developed for a range of DERs (heating, ventilation, and air conditioning units, water heaters, batteries, and electric vehicles) that optimize flexibility over a 48-hour horizon and adjust their strategy in response to changes in real-time prices. A transactive energy coordination scheme, executed by a DSO retail market operator, aggregates these DER bids from participating customers and clears them against a DSO supply curve using a double auction market mechanism. The process of constructing the price-quantity DSO supply curve includes distribution-level transportation constraints (for example, substation congestion limits) and forecast locational marginal price of the DSO’s connected transmission node. The resulting day-ahead and real-time quantities are then bid into a competitive wholesale market operated by an independent system operator. This report also details additional capabilities for proper marketplace simulation such as wholesale price, weather, and load forecasting. The report concludes with a discussion of lessons learned and key design features required to ensure successful operation.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Demonstration and Evaluation of the Human-Technology Integration Guidance for Plant Modernization

The significance of nuclear power in its role producing carbon-free electricity to the U.S. cannot be overstated. However, with changes in the energy market coupled with changes in incentives given to certain resources like solar and wind, the operating and maintenance costs for these sources have seen a significant reduction, which has consequently negatively impacted the economic viability of the existing U.S. nuclear power plant fleet. Digital instrumentation and control (I&C) and control room modernization is a major critical work domain to reduce operating and maintenance costs. Existing nuclear power plants are commonly configured with mostly legacy analog I&C as well as isolated pockets of digital I&C (a plant process computer, digital recorders, etc.). One challenge with this analog I&C is that replacement parts are becoming prohibitively more expensive and difficult to obtain. Moreover, a significant challenge with the existing analog I&C is that the way in which plants are currently operated and maintained is no longer competitive with other electricity generating sources, like natural gas, where advanced digital I&C technologies are commonplace. This gap between the waynuclear power plants are operated compared to other electricity generating sources significantly challenges the economic viability of the nuclear industry. Indeed, digital I&C systems can fundamentally change the way the plant is operated (i.e., the concept of operation). The introduction of digital I&C technologies offers a wealth of benefits to the nuclear industry. However, it is important to emphasize that, to realize these benefits, a careful understanding of how to integrate technology in a collaborative way that leverages the capabilities of people and technologies is necessary. Human-technology integration applies human factors engineering methods and tools to ensure the safe and reliable use of these technologies while ensuring that the inherent features of the technologies that provide economic value are not missed. The scope of this work documents the demonstration of the recently developed human and technology integration methodology, as applied to developing a new vision and concept of operations for a major U.S. nuclear power plant fleet. This report focuses on the methodological aspects of developing a vision and concept of operations. This report shares the tools, activities, and lessons learned during a modernization currently underway for industry as a whole to consider when planning any significant digital modification and developing a new vision and concept of operations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS2007

Integrating Automation into a Multi-Mission Operations Center

NASA Goddard Space Flight Center's Space Science Mission Operations (SSMO) Project is currently tackling the challenge of minimizing ground operations costs for multiple satellites that have surpassed their prime mission phase and are well into extended mission. These missions are being reengineered into a multi-mission operations center built around modern information technologies and a common ground system infrastructure. The effort began with the integration of four SMEX missions into a similar architecture that provides command and control capabilities and demonstrates fleet automation and control concepts as a pathfinder for additional mission integrations. The reengineered ground system, called the Multi-Mission Operations Center (MMOC), is now undergoing a transformation to support other SSMO missions, which include SOHO, Wind, and ACE. This paper presents the automation principles and lessons learned to date for integrating automation into an existing operations environment for multiple satellites.

Surka, Derek M.↗
NASA NTRS2004

Microgravity Spray Cooling Research for High Powered Laser Applications

An extremely powerful laser is being developed at Goddard Space Flight Center for use on a satellite. This laser has several potential applications. One application is to use it for upper atmosphere weather research. In this case, the laser would reflect off aerosols in the upper atmosphere and bounce back to the satellite, where the aerosol velocities could be calculated and thus the upper atmosphere weather patterns could be monitored. A second application would be for the US. Air Force, which wants to use the laser strategically as a weapon for satellite defense. The Air Force fears that in the coming years as more and more nations gain limited space capabilities that American satellites may become targets, and the laser could protect the satellites. Regardless of the ultimate application, however, a critical step along the way to putting the laser in space is finding a way to efficiently cool it. While operating the laser becomes very hot and must be cooled to prevent overheating. On earth, this is accomplished by simply running cool tap water over the laser to keep it cool. But on a satellite, this is too inefficient. This would require too much water mass to be practical. Instead, we are investigating spray cooling as a means to cool the laser in microgravity. Spray cooling requires much less volume of fluid, and thus could be suitable for use on a satellite. We have inherited a 2.2 second Drop Tower rig to conduct our research with. In our experiments, water is pressurized with a compressed air tank and sprayed through a nozzle onto our test plate. We can vary the pressure applied to the water and the temperature of the plate before an experiment trial. The whole process takes place in simulated microgravity in the 2.2 second Drop Tower, and a high speed video camera records the spray as it hits the plate. We have made much progress in the past few weeks on these experiments. The rig originally did not have the capability to heat the test plate, but I did some heat transfer calculations and picked out a heater to order for the rig. I learned QBasic programming language to change the operating code for our drops, allowing us to rapidly cycle the spray nozzle open and closed to study the effects. We have derived an equation for flow rate vs. pressure for our experiment. We have recorded several videos of drops at different pressures, some with heated test plate and some without, and have noticed substantial differences in the liquid behavior. I have also changed the computer program to write a file with temperature vs. time profiles for the test plate, and once the necessary thermocouple comes in (it was ordered last week), we will have temperature profiles to accompany the videos. Once we have these temperature profiles to go with the videos, we will be able to see how the temperature is affected by the spray at different pressures, and how the spray changes its behavior once as the plate changes from hot to cool. With quantitative temperature data, we can then mathematically model the heat transfer from the plate to the cooling spray. Finally, we can look at the differences between trials in microgravity and those in normal earth gravity.

Zivich, Chad P.↗
DOE OSTI2019

A Supervised Machine Learning Approach to Control Energy Storage Devices

This paper introduces a supervised machine learning approach to predict and schedule the real-time operation mode of the next operation interval for residential PV/Battery systems controlled by mode-based controllers. The performance of the mode-based economic model-predictive control (EMPC) approach is used as the benchmark. The residential load and PV data used in the paper are 1-minute data downloaded from the the Pecan Street Project website. The optimal operation mode for each control interval is first derived from the historical data used as the training set. Then, four machine learning algorithms (i.e. neural network, support vector machine, logistic regression, and random forest algorithms) are applied. We compared the performance of the four algorithms when using different number of features and length of the training sets extracted from different months of the year. Simulation results show that using the machine learning approach can effectively improve the performance of the mode-based control system and reduce the computation effort of local controllers because the training can be completed on a cloud-based Machine Learning engine. Furthermore, the work presented in this paper paves the way for using a shared-learning platform to design controllers of residential PV/storage systems. This may significantly reduce the cost for implementing such systems.

25 ENERGY STORAGE↗
NASA NTRS1991

Artificial neural networks and approximate reasoning for intelligent control in space

A method is introduced for learning to refine the control rules of approximate reasoning-based controllers. A reinforcement-learning technique is used in conjunction with a multi-layer neural network model of an approximate reasoning-based controller. The model learns by updating its prediction of the physical system's behavior. The model can use the control knowledge of an experienced operator and fine-tune it through the process of learning. Some of the space domains suitable for applications of the model such as rendezvous and docking, camera tracking, and tethered systems control are discussed.

Berenji, Hamid R.↗
NASA NTRSDate not supplied

Infusion of AI/ML Technology into Operational NASA Data Systems

NASA has been developing a variety of Artificial Intelligence / Machine Learning technologies related to Earth Observations. In most cases, the full value of such a technology is realized when it is infused into an operational system. NASA’s Earth Science Data Systems program has been formulating repeatable methods to execute technology infusion. These efforts include the Advancing Collaborative Connections for Earth System Science (ACCESS) program, a Technology Infusion Playbook, and an assemblage of working groups investigating methods for infusion collaboration, community development, and capacity building. ESDS has also been executing a pathfinder activity to infuse a machine-learning-driven recommender of science keywords for Earth Observation datasets, which is intended to be used for metadata curation in the Earth Observation System Data and Information System.

C Lynnes↗
DOE OSTI2025

From disorganized data to emergent dynamic models: Questionnaires to partial differential equations

Starting with sets of disorganized observations of spatially varying and temporally evolving systems, obtained at different (also disorganized) sets of parameters, we demonstrate the data-driven derivation of parameter dependent, evolutionary partial differential equation (PDE) models capable of generating the data. This tensor type of data is reminiscent of shuffled (multidimensional) puzzle tiles. The independent variables for the evolution equations (their “space” and “time”) as well as their effective parameters are all emergent , i.e. determined in a data-driven way from our disorganized observations of behavior in them. We use a diffusion map based questionnaire approach to build a smooth parametrization of our emergent space/time/parameter space for the data. This approach iteratively processes the data by successively observing them on the “space,” the “time” and the “parameter” axes of a tensor. Once the data become organized, we use machine learning (here, neural networks) to approximate the operators governing the evolution equations in this emergent space. Our illustrative examples are based (i) on a simple advection–diffusion model; (ii) on a previously developed vertex-plus-signaling model of Drosophila embryonic development; and (iii) on two complex dynamic network models (one neuronal and one coupled oscillator model) for which no obvious smooth embedding geometry is known a priori. This allows us to discuss features of the process like symmetry breaking, translational invariance, and autonomousness of the emergent PDE model, as well as its interpretability.

generative models↗
DOE OSTI2025

A quantitative risk assessment framework for fault reactivation in underground hydrogen storage: Coupled simulation and deep learning approach

Underground hydrogen storage (UHS) is emerging as a critical solution for large-scale energy storage. However, like all subsurface fluid injection activities, UHS poses the risk of injection-induced fault reactivation. Accurate risk assessment is essential to ensuring the safety and efficiency of UHS operations. This study presents the development of deep-learning surrogate models for fault reactivation prediction in UHS, trained on a comprehensive database of fully coupled fluid flow-geomechanics simulations. Our findings reveal that analytical models often yield unreliable estimates, with errors up to 54% in the allowable injection pressure, potentially leading to a 40% reduction in UHS operational capacity. The developed surrogate models were incorporated into a quantitative risk assessment (QRA) framework, enabling probabilistic evaluation of fault reactivation risk while accounting for uncertainties in the input variables. Site-specific features, such as horizontal stress gradients, fault’s dip and strike angles, and operational parameters like bottom-hole injection pressure and well-fault distance, were identified as the primary drivers of fault reactivation across various stress regimes. Whereas other hydraulic, geological, and poroelastic reservoir properties were found to have a secondary impact. Notably, we observed that the risk of fault reactivation for a critically oriented fault with a static friction coefficient greater than 0.55 remains below 10% in a normal faulting stress regime. However, the risk significantly increases as the stress regime transitions from normal to strike-slip and ultimately to reverse faulting conditions. These findings underscore the importance of rigorous site characterization and comprehensive QRA evaluations to optimize UHS performance and minimize geomechanical risks.

25 ENERGY STORAGE↗
DOE OSTI2020

The CYBER security – Competency Health and Maturity Progression (CYBER-CHAMP) model: Extending the National Initiative for Cybersecurity Education (NICE) Framework Across Organizational Security

Problem Statement: There is a pervasive talent deficit in the cybersecurity industry that prevents employers from being able to fill their open positions efficiently. A holistic approach to security is required to ensure organizations have adequate prevention and response capabilities in case of a cyberattack. Specifically, industrial control systems (ICS’s) and their operational technology (OT) components have become a constant target for cyberattacks. Research Questions: It is proposed that the NICE Framework should be extended in the following areas: 1) Include guidance regarding the job roles and competencies for both IT and OT professionals. 2) Offer step-by-step solutions, based on the work role mappings from the NICE Framework, to increase cybersecurity through employee training and education. 3) Provide a streamlined, lifecycle approach to building a cybersecurity program. Contribution: The CYBER security – Competency Health and Maturity Progression (CYBER-CHAMP©) model provides a customized solution for businesses to understand their education gaps in organizational security and target areas for improvement. Rationale: The Framework for Improving Critical Infrastructure Cybersecurity v1.1 addresses ICS but does not offer a measurement of cybersecurity maturity or clear methods to ascertain an organization’s current risk profile. In Phases 1 and 5 of the model, measurements are provided to help an organization build their current and target risk profiles. The NICE framework provides a structure for planning an IT cybersecurity workforce, but the OT aspects of cybersecurity are only briefly discussed. The model uses Phases 2-3 to examine the competencies of an organization’s workforce, which includes both IT and OT roles. Current frameworks do not offer next steps to increase an organization’s cybersecurity. During Phase 4, employees’ roles are mapped to training, education, and/or certifications from common vendors. Investigative Approach: The model provides measurements and metrics for both an organization’s status and continual improvement. This improvement methodology includes guidance for creating an overall strategic plan for security improvement via products designed to increase an organization’s operational readiness through workforce competency health. Lessons Learned: Depending on who was participating, there were contradicting answers given in Phase 1 due to different security cultures in the organization. This revelation has influenced the steps listed in the User’s Guide, where Phase 1’s first recommended step is to assemble a team that champions the facilitation and implementation of the model in the organization. During Phase 2, the discovery was made that organizations may be missing roles that are necessary to perform critical cybersecurity functions. By understanding the functional roles and competencies needed, they can contract or hire cybersecurity help to fill these gaps. Implications: Using the model, organizations can discuss quantitative measures for improvement as a business case for advancing their security program. Future research can validate and extend the present theory and model to a variety of environments. It is of interest to investigate additional security roles and knowledge domains that are used to build standardized cybersecurity curriculum.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Tokamak divertor plasma emulation with machine learning

Abstract Future tokamak devices that aim to create conditions relevant to power plant operations must consider strategies for mitigating damage to plasma facing components in the divertor. One of the goals of MAST-U tokamak operations is to inform these considerations by researching advanced divertor configurations that aid stable plasma detachment. Machine design, scenario planning and detachment control would all greatly benefit from tools that enable rapid calculation of scenario-relevant quantities given some input parameters. This paper presents a method for generating large, simulated scrape-off layer data sets, which was applied to generate a data set of steady-state Hermes-3 simulations of the MAST-U tokamak. A machine learning model was constructed using a Bayesian approach to hyperparameter optimisation to predict diagnosable output quantities given control-relevant input features. The resulting best-performing model, which is based on a feedforward neural network, achieves high accuracy when predicting electron temperature at the divertor target and carbon impurity radiation front position and runs in around 1 ms in inference mode. Techniques for interpreting the predictions made by the model were applied, and a high-resolution parameter scan of upstream conditions was performed to demonstrate the utility of rapidly generating accurate predictions using the emulator. This work represents a step forward in the design of machine learning-driven emulators of tokamak exhaust simulation codes in operational modes relevant to divertor detachment control and plasma scenario design.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Energy and Emission Prediction for Mixed-Vehicle Transit Fleets Using Multi-task and Inductive Transfer Learning

Public transit agencies are focused on making their fixed-line bus systems more energy efficient by introducing electric (EV) and hybrid (HV) vehicles to their fleets. However, because of the high upfront cost of these vehicles, most agencies are tasked with managing a mixed-fleet of internal combustion vehicles (ICEVs), EVs, and HVs. In managing mixed-fleets, agencies require accurate predictions of energy use for optimizing the assignment of vehicles to transit routes, scheduling charging, and ensuring that emission standards are met. The current state-of-the-art is to develop separate neural network models to predict energy consumption for each vehicle class. Although different vehicle classes’ energy consumption depends on a varied set of covariates, we hypothesize that there are broader generalizable patterns that govern energy consumption and emissions. In this paper, we seek to extract these patterns to aid learning to address two problems faced by transit agencies. First, in the case of a transit agency which operates many ICEVs, HVs, and EVs, we use multi-task learning (MTL) to improve accuracy of forecasting energy consumption. Second, in the case where there is a significant variation in vehicles in each category, we use inductive transfer learning (ITL) to improve predictive accuracy for vehicle class models with insufficient data. As this work is to be deployed by our partner agency, we also provide an online pipeline for joining the various sensor streams for fixed-line transit energy prediction. Here, we find that our approach outperforms vehicle-specific baselines in both the MTL and ITL settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Machine Learning 5G Attack Detection in Programmable Logic

Machine learning-assisted network security may significantly contribute to securing 5G components. However, machine learning network security inference speeds generally require tens to hundreds of milliseconds thereby introducing significant latency in 5G operations. The inference latency can be reduced by deploying the machine learning model to programmable logic in a field programmable gate array (FPGA) at the cost of a small loss in accuracy. In order to quantify this loss, as well as to establish baseline performance inference speeds for programmable logic implementations, this work explores an autoencoder and a ß-variational autoencoder deployed on two different FPGA evaluation boards and compares accuracy and performance against an NVIDIA A100 GPU implementation. A publicly available 5G dataset containing 10 types of attacks along with normal traffic is introduced as part of the evaluation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Learning Behavior of Distribution System Discrete Control Devices for Cyber-Physical Security

Conventional cyber-security intrusion detection systems monitor network traffic for malicious activity and indications that an adversary has gained access to the system. The approach discussed here expands the idea of a traditional intrusion detection system within electrical power systems, specifically power distribution networks, by monitoring the physical behavior of the grid. This is achieved through the use of high-rate distribution Phasor Measurement Units (PMUs), alongside SCADA packets analysis, for the purpose of monitoring the behavior of discrete control devices. In this work we present a set of algorithms for passively learning the control logic of voltage regulators and switched capacitor banks. Upon detection of an abnormal operation, the operator is alerted and further action can be taken. Finally, the proposed learning algorithms are validated on both simulated data and on measured PMU data from a utility pilot deployment site.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗