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 487 records · Page 27
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Potential of deep learning methods to enhance satellite-based monitoring of nuclear power plants focusing on remote operation evaluations

The anticipated expansion of the nuclear industry and the deployment of new nuclear reactors (200 + GW of new nuclear capacity by 2050) require the development of monitoring systems that align with safety and security concerns, providing enhanced evaluation capabilities. A remote monitoring system using satellites and deep learning techniques was evaluated for its ability to detect anomalies and capture various features of nuclear reactors independently of the conditions on the ground. Satellite images of current operational and under-construction nuclear power plants were collected from Google Earth Pro as a surrogate database. Subsequently, five datasets were created from the collected images. Transfer learning technique was used for several classification tasks utilizing VGG16, ResNet50V2, Xception, DenseNet121, and MobileNetV2 pre-trained models. In the first task, the capability of the monitoring system to detect abnormal conditions or processes in a nuclear power plant was investigated. In the second task, the ability to capture operational features remotely was examined. As an example, for the purposes of this study, these features included classifying reactors based on type, power range, or onsite condition. Several evaluation metrics were used to compare the performance of the pre-trained models and the overall monitoring system. Here, the evaluation results demonstrated that deep learning techniques and pre-trained models applied to satellite images have the potential to facilitate further and expand capabilities in monitoring systems to assess plant operation details.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2017

CONTROLLING ENERGY STORAGE SYSTEMS: LESSONS LEARNED FROM THE WASHINGTON CLEAN ENERGY FUND DEMONSTRATION PROJECTS

Washington Clean Energy Fund energy storage demonstration projects created opportunities for learning many aspects of Energy Storage Systems (ESS) including its control for economic operation. PNNL, as the lead for use case analytics program for the demonstration projects, had the opportunity to experience practical aspects of ESS control in terms of control strategy development, control systems deployment, and performance of ESS during actual operation. This paper presents some of those learning opportunities availed to date and a few key lessons with an intention to benefit the wider energy storage community.

Washington CEF, ESS control strategy, control syst↗
DOE OSTI2026

FORGE: Summer Internship Experience

The presentation summarizes my summer internship experience with the Fluids Group at Fermilab. During the internship, I learned about the maintenance and operation of water pumps and other equipment that support important facility systems. I worked alongside fluids technicians and gained hands-on experience with maintaining machinery, installing pipes, refilling water, cleaning RF cavities, and observing new water-pump construction for PIP-II. My projects included repairing an air dryer, learning how heat exchangers cool low-conductivity water, and cleaning the copper cooling rings used in RF cavities. Overall, this experience helped me better understand the work processes of technicians and the importance of practical technical knowledge for engineers.

Uribe, Anthony [Unlisted, US, IL]↗
DOE OSTI2021

Non-intrusive data-driven model reduction for differential–algebraic equations derived from lifting transformations

In this paper we present a non-intrusive data-driven approach for model reduction of nonlinear systems. The approach considers the particular case of nonlinear partial differential equations (PDEs) that form systems of partial differential–algebraic equations (PDAEs) when lifted to polynomial form. Such systems arise, for example, when the governing equations include Arrhenius reaction terms (e.g., in reacting flow models) and thermodynamic terms (e.g., the Helmholtz free energy terms in a phase-field solidification model). Using the known structured form of the lifted algebraic equations, the approach computes the reduced operators for the algebraic equations explicitly, using straightforward linear algebra operations on the basis matrices. The reduced operators for the differential equations are inferred from lifted snapshot data using operator inference, which solves a linear least squares regression problem. The approach is illustrated for the nonlinear model of solidification of a pure material. The lifting transformations reformulate the solidification PDEs as a system of PDAEs that have cubic structure. The operators of the lifted system for this solidification example have affine dependence on key process parameters, permitting us to learn a parametric reduced model with operator inference. Numerical experiments show the effectiveness of the resulting reduced models in capturing key aspects of the solidification dynamics.

42 ENGINEERING↗
DOE OSTI2018

Final Technical Report

In September 2010, RTI and the DOE/NETL signed a cooperative agreement (DE-FE000489) to design, build, and operate a pre-commercial syngas cleaning system that would capture up to 90% of the CO 2 in the syngas slipstream, and demonstrate the ability to reduce syngas contaminants to meet DOE’s specifications for chemical production application. This pre-commercial syngas cleaning system is operated at Tampa Electric Company’s (TEC) 250-MWe integrated gasification combined cycle (IGCC) plant at Polk Power Station (PPS), located near Tampa, Florida. The syngas cleaning system consists of the following units: Warm Gas Desulfurization Process (WDP) - this unit processes a syngas flow equivalent of 50 MWe of power (50 MWe equivalent corresponds to about 2.0 MM scfh of syngas on dry basis) to produce a desulfurized syngas with a total sulfur (H 2 S+COS) concentration ~ 10 ppmv. Water Gas Shift (WGS) Reactor - this unit converts sufficient CO into CO 2 to enable 90% capture of the CO 2 in the syngas slipstream. This reactor uses conventional commercial shift catalyst technologies. Low Temperature Gas Cooling (LTGC) - this unit cools the syngas for the low temperature activated MDEA process and separates any condensed water. Activated MDEA Process (aMDEA) - this unit employs a non-selective separation for the CO 2 and H 2 S present in the raw syngas stream. Because of the selective sulfur removal by the upstream WDP unit, the CO 2 capture target of 90% CO 2 can be achieved with the added benefit that total sulfur concentration in the CO 2 product is < 100 ppmv. An additional advantage of the activated MDEA process is that the non-selective sulfur removal from the treated syngas reduces sulfur in the treated gas to very low sub-ppmv concentrations, which are required for chemical production applications. Testing to date of this pre-commercial syngas cleaning system has shown that the technology has great potential to provide clean syngas from coal and petcoke-based gasification at increased efficiency and at significantly lower capital and operating costs than conventional syngas cleanup technologies. However, before the technology can be deemed ready for scale-up to a full commercial-scale demonstration, additional R&D testing is needed at the site to address the following critical technical risks: WDP sorbent stability and performance; Impact of WDP on downstream cleanup and conversion steps; Metallurgy and refractory; Syngas cleanup performance and controllability; Carbon capture performance and additional syngas cleanup The proposed plan to acquire this additional R&D data involves: Operation of the units to achieve an additional 3,000 hours of operation of the system within the performance period, with a target of achieving 1,000 hours of those hours via continuous operation of the entire integrated pre-commercial demonstration system; Rapid turnaround of repairs and/or modifications required as necessary to return any specific unit to operating status with documentation and lessons learned to support technology maturation, and; Proactive performance of maintenance activities during any unplanned outages and if possible while operating.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Neighborhood Keeper Program Review

Dragos provided INL access to their Neighborhood Keeper platform, which contains simulated data, sample reports given to utilities, and access to anonymized program data that is sent from utilities to the cloud. Dragos has specifically asked INL to review the available data and respond to the following questions: 1) What detections or combinations of detections are most useful? 2) What additional analysis would benefit the electricity subsector? 3) How could Neighborhood Keeper reporting be modified to benefit the electricity subsector? 4) What lessons learned from the Cybersecurity for the Operational Technology Environment (CyOTE) program could be provided? 5) Based on INL’s experience with utilities, are there lessons learned about data sharing that could be provided? 6) Are there recommendations that could benefit the electricity subsector?

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference

This work introduces a method for learning low-dimensional models from data of high-dimensional black-box dynamical systems. The novelty is that the learned models are exactly the reduced models that are traditionally constructed with classical projection-based model reduction techniques. Thus, the proposed approach learns models that are guaranteed to have the well-studied properties of reduced models known from model reduction, without requiring full knowledge of the governing equations and without requiring the operators of the high-dimensional systems. The key ingredient is a new data sampling scheme to obtain re-projected trajectories of high-dimensional systems that correspond to Markovian dynamics in low-dimensional subspaces. The exact recovery of reduced models from these re-projected trajectories is guaranteed pre-asymptotically under certain conditions for finite amounts of data and for a large class of systems with polynomial nonlinear terms. Numerical results demonstrate that the low-dimensional models learned with the proposed approach match reduced models from traditional model reduction up to numerical errors in practice. In conclusion, the numerical results further indicate that low-dimensional models fitted to re-projected trajectories are predictive even in situations where models fitted to trajectories without re-projection are inaccurate and unstable.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2014

Drilling and abandonment preparation of CO₂ storage wells – Experience from the Ketzin pilot site

At Ketzin, located west of Berlin, the GFZ German Centre for Geosciences is operating Europe's largest CO₂ research storage site. This pilot site has been developed since 2004 and is comprised of one combined injection/observation well and four monitoring wells. From June 2008 to August 2013, a total of 67 kilotons of CO₂ were safely injected into the sandstone units of the Upper Triassic Stuttgart Formation in a depth between 630 to 650 m. The paper discusses the well designs and lessons learned in drilling engineering and operations. The abandonment phase started in Ketzin with the first plug cementation of the observation well Ktzi 202 shortly after shut-in of CO₂ injection. The experience with the first CO₂ well killing operation will be reviewed.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Integration of scanning probe microscope with high-performance computing: Fixed-policy and reward-driven workflows implementation

The rapid development of computation power and machine learning algorithms has paved the way for automating scientific discovery with a scanning probe microscope (SPM). The key elements toward operationalization of the automated SPM are the interface to enable SPM control from Python codes, availability of high computing power, and development of workflows for scientific discovery. Here, we build a Python interface library that enables controlling an SPM from either a local computer or a remote high-performance computer, which satisfies the high computation power need of machine learning algorithms in autonomous workflows. We further introduce a general platform to abstract the operations of SPM in scientific discovery into fixed-policy or reward-driven workflows. Furthermore, our work provides a full infrastructure to build automated SPM workflows for both routine operations and autonomous scientific discovery with machine learning.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Continuous integration data-driven platform of industrial-scale subsurface storage for real-time analytics

This project helped address the growing need for efficient and scalable models to support geological carbon and energy storage, which are crucial for achieving net-zero emissions. Traditionally accurate high-fidelity numerical models have been used to simulate relevant storage processes under a handful of processes, however such models are computationally demanding, making uncertainty quantification impractical. Consequently, we first developed a machine learning framework, based on Graph Neural Operators (GNOs), to improving the accuracy of model predictions for a fixed computational budget. We then developed an Ensemble of Improved Neural Operators (ENO), which uses bagging and Monte Carlo dropout techniques, to further improve prediction accuracy. Lastly, we developed the way to explain progressive transfer learning methods to reduce the amount of training data and computational cost of training (i.e., reduce trainable parameters) when using our models for multiple storage sites. Our numerical investigation, which used real-world case studies, demonstrated that our framework can significantly improve the safety and efficiency of geological storage operations, with potential applications in other domains such as geothermal reservoirs and climate modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Accelerated CO2 Storage Optimization Using Multi-Resolution Fourier Neural Operator at the Illinois Basin Decatur Project (IBDP)

This paper presents a deep learning-based approach for optimizing CO2 injection in carbon capture and storage (CCS) operations. We developed a multi-resolution machine learning model to significantly reduce data generation costs. Utilizing this proxy model, we implemented a multi-objective genetic algorithm to optimize well control during the CO2 injection process. The proposed approach was applied to the Illinois Basin Decatur Project (IBDP), successfully optimizing the CO2 injection schedule based on three key objectives: maximizing the amount of CO2 stored, maximizing sweep efficiency, and minimizing pressure increase. The use of the proxy model accelerated the optimization workflow by two orders of magnitude, while the cost of data generation for the proxy model was reduced by 90% by utilizing a coarse-scale model.

accelerated CO2 storage optimization↗
DOE OSTI2019

Vehicle energy consumption estimation using large scale simulations and machine learning methods

Vehicle energy consumption and powertrain operations for future vehicle powertrain technologies are predicted through full-vehicle simulations using Autonomie, a simulation tool developed at Argonne National Laboratory. Over 1 million vehicles, with different powertrain types (conventional and numerous electrified powertrains) and component technologies (advanced engines, batteries, electrical machines, light weighting) are simulated for outputs including vehicle fuel economy and cost. Despite the ability of Autonomic to predict fuel economy given various combination of vehicle inputs, the full-vehicle simulation is very time-consuming. It takes approximately 84 h to simulate for 33,060 vehicles even using distributed computing on a cluster of 128 worker nodes. Moreover, Autonomic is unable to populate a continuous output space through simulation since it only yields outputs with discrete values instead of an input-output relation. This paper proposes a novel large-scale learning and prediction process (LSLPP) via machine learning approaches to answer the need for a continuous space of vehicle fuel economy and a more efficient simulation process. By learning in a supervised fashion to discover structures in data, the machine learning approaches seek to train a model that can explain the data with which we can perform prediction over unseen data. As such, we are able to accomplish analytic continuation on the current discrete space of simulation results. In addition, we present a random sampling -based numerosity reduction algorithm incorporated in LSLPP that reduces simulation runs and improves efficiency of data procurement. We analytically derive a theoretical bound in order to guarantee the effectiveness of our algorithm. We also compare random sampling to stratified sampling and suggest sampling strategies. A user-friendly tool is developed to support the process. Our experimental results confirm that the proposed LSLPP is able to greatly accelerate prediction and analysis of vehicle fuel economy. The output of this study is used by the US government to evaluate the impact of its R&D funding on energy security and CO 2 emission as well as for the setting of Corporate Average Fuel Economy (CAFE) standards.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2017

Analysing lessons from experience as part of a project to prepare/train teams to manage potentially stressful crisis situations - 164

Following the presentation of the methodology for making use of Operating Experience (OE) data, implemented as part of a study on preparing teams to manage potentially stressful crisis situations, this paper discusses and enhances the 'Implementing a Learning Organisation (ILO)' model, the aim of which is to organise operating experience for learning purposes. By way of introduction, we first present this model, which is divided into four fields of investigation for organising an OE mechanism to support learning, to pose the question we aim to answer in this paper: how does the field relating to the use of OE in the ILO model help us to turn the experience acquired to good account? With this in mind, we then present the different stages of the methodology for making use of OE. The first stage involves defining the area under examination in line with current best practices. This definition is then used in the second stage, as a basis for developing a framework to guide the analysis of OE. Finally, the third stage of the methodology involves selecting the OE data to be analysed. The findings obtained in the chosen case are then presented and several points are discussed based on this experience. These relate to the following: the acquisition of knowledge on current working situations enabled by OE; the stored data analysis method; and the conditions facilitating the use of OE. (authors)

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2022

Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems

Fault detection and diagnosis (FDD) technologies are critical to ensure satisfactory building performance, such as reducing energy wastes and negative impacts on occupant comfort and productivity. Existing FDD technologies mainly focus on component-level FDD solutions, which could lead to mis-diagnosis of cross-level faults in heating, ventilating, and air-conditioning (HVAC) systems. Cross-level faults are those faults that occur in one component or subsystem, but cause operational abnormalities in other components or subsystems, and result in a building level performance degradation. How to effectively diagnose the root cause of a cross-level fault is the focus of this study. Here, this paper presents a novel discrete Bayesian Network (DisBN)-based method for diagnosing cross-level faults in an HVAC system commonly used in commercial buildings. A two-level DisBN structure model is developed in this study. The parameters used in the DisBN model are obtained either from expert knowledge or through machine-learning strategies from normal system operation data. Meanwhile, the probability parameters are discretized to incorporate the uncertainties associated with typical expert knowledge. Thus, the developed DisBN method addresses the challenges many other BN based FDD methods face, i.e., the lack of fault data for BN parameter training. The developed DisBN represents causal relationships between a fault and its cross-level system impacts (i.e., fault symptoms or fault indicators) by considering how fault impacts propagate across different levels in an HVAC system. A weather and schedule information-based Pattern Matching (WPM) method is employed to automatically create WPM baseline data sets for each incoming real time snapshot data from the building systems. Consequently, BN inference and real-time diagnostics are achieved by comparing incoming snapshot data and the WPM baseline data set. The proposed method is evaluated using experimental fault data collected in a campus building. Fault diagnosis results demonstrate that the WPM-DisBN method is effective at locating the root causes of cross-level faults in an HVAC system.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Artificial Intelligence-Driven Management of Sustainable Energy Resources: Visibility, Operation, and Control

The rapid global transition toward sustainable energy resources (SERs) is reshaping how modern power systems are observed, optimized, and controlled. While SERs have significantly advanced decarbonization, their weather dependence, variability, and inverter-dominated characteristics challenge traditional, centralized, and deterministic grid operation. At the same time, the proliferation of high-resolution data from inverters, smart meters, and sensors offers unprecedented visibility into system dynamics. Yet, it also exceeds the analytical capability of conventional model-based approaches. Artificial intelligence (AI) provides a new foundation for addressing these challenges by bridging physical laws with data-driven learning, enabling accurate state awareness, adaptive operation, and coordinated control across distributed assets. This article examines how AI transforms the management of SER-rich power systems along three critical dimensions: 1) enhancing visibility by inferring behind-the-meter (BTM) activities, assessing SER flexibility, and reconstructing system states from sparse or noisy measurements; 2) improving operation through AI-enhanced SER service provision, volt/var control (VVC), and dynamic operating envelopes (DOE) for efficiency and security; and 3) advancing control by embedding learning-based intelligence into inverter coordination, voltage and frequency regulation, and long-term dispatch. Together, these developments reveal how AI can convert the variability of SERs from an operational challenge into a source of flexibility, resilience, and intelligence, paving the way toward sustainable, adaptive, and self-optimizing power systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Development and assessment of a reactor system prognosis model with physics-guided machine learning

Autonomous control systems provide recommendations to help operators in decision-making during plant operations ranging from normal operation to accident management. An important step of autonomous control is prognosis. In nuclear engineering domain, prognosis is the process of predicting future conditions of a system or equipment based on present signs and symptoms of a fault. The prognosis model allows predicting future reactor states for possible candidate control strategies so that the outcomes can be evaluated to determine the best control strategy. The prognosis model requires representing direct relationships between the symptoms and the predictions. In nuclear engineering, computational simulations are approximate representations of the operation of the real system. However, prognosis with computational simulations requires high computation power and time due to possible large number of scenarios. Necessary computation resources can be reduced with machine learning (ML) approach for fast predictions by building a surrogate function using the simulation data. A critical issue is, ML models are ignorant of physical knowledge, and these models approximate statistical relationships between the system variables. This ignorance can produce results that are inconsistent with physical laws, even if an optimal result is achieved from a mathematical point of view. Physics-guided machine learning (PGML) is an approach to tackle this issue. Here, this work formulates and illustrates a framework to guide development and assessment of the ML-based prognosis model for autonomous control systems. The development of the prognosis model considers the training of a ML model which consists of optimizing many aspects of the ML approach. The assessment of the prognosis model considers training data limitations and uncertainties of the ML approach. Prognosis models with standalone ML and PGML are developed and assessed on the loss-of-flow scenario of Experimental Breeder Reactor II. The results indicate that PGML based prognosis model has the best performance compared to other prognosis models.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2019

Machine-Learning Analysis of Moisture Carryover in Boiling Water Reactors

Moisture carryover (MCO) is modeled in the General Electric Type-4 boiling water reactor (BWR) using machine-learning methods and data from operating plants. Understanding MCO and the conditions that give rise to an elevated value is important since excessive MCO can damage critical turbine components, can result in elevated dose levels to on-site personnel, and can interfere with late-cycle power management. The analysis of MCO takes into account simplifying reactor symmetries and important geometric dependencies. The plant data are taken from several reactors and were collected over multiple years and multiple fuel cycles. A brief description of the origin of MCO in U.S. BWR plants is given. A machine-learning model is constructed from the data using applicable algorithms and data-reduction techniques. Matching model complexity with available data is one of the more challenging machine-learning tasks. Too many features and too little data will lead to overfitting. The data for each fuel cycle included over 6876 original features, 9 for each fuel bundle. Two approaches are used to reduce the data set into a manageable number of features. The first was an engineering analysis that resulted in the selection of steam quality Q and steam liquid phase velocity V L as the main features driving MCO. Using a Q and a V L for each fuel bundle gives 1528 Q and a V L feature describing the reactor behavior. An analysis of different functional forms of these two variables led to the actual inputs to the neural network model. The second approach involved the use of statistical techniques such as Pearson’s correlation and k-means analysis. The identified groupings of bundles behaved similarly. Treating each grouping as a single feature further reduced the input variable set to a manageable number. Here, a model selection criterion is proposed, and results are presented along with a discussion of related issues.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗