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 1,243 records · Page 69
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Identifying and Explaining Anomalous Activity in Surveillance Video with Compression Algorithms

The primary purpose of this document is to outline the progress made on the LDRD titled “Identifying and Explaining Anomalous Activity in Surveillance Video with Compression Algorithms” in FY22 and FY23. In this LDRD, we explored the usage of compression-based analytics to identify anomalous activity in video. We developed a novel algorithm, Spatio-Temporal N-Gram PPM (STNG PPM) that accounts for spatially and temporally aware anomalies in video. We extracted features using motions vectors from video as well as operating on the raw features. STNG PPM is comparable to many deep learning approaches but does not require specialized hardware (GPUs) to run efficiently. We also examine the evaluation metrics and propose novel measures addressing faults in the current evaluation measures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Enhancing Fluid Flow Pressure and Saturation Prediction Accuracy and Reducing Uncertainty with Committee Machine – Illinois Basin Decatur Project (IBDP) as a Case Study

Presentation at the 17th International Conference on Greenhouse Gas Control Technologies GHGT-17 held in Calgary, Canada, October 20-24, 2024. Carbon capture and storage (CCS) is a way to play a critical role in the global transition to a low-emission economy. Current progress is hampered by a number of factors, among which the lack of risk-informed design tools and decision support frameworks is seen as a major roadblock. Significant interest exists in using artificial intelligence to accelerate CCS site feasibility studies, as well as to facilitate the permit application process. Existing works commonly train a single deep learning model. This work investigates the feasibility of using a conventional ensemble learning (committee machine) technique to further improve prediction accuracy. Ensemble-based algorithms generally improve over individual base learners in terms of robustness and accuracy. Deep ensembles, however, are time-consuming to create and train. A pragmatic question is whether small-sized ensembles may lead to prediction improvement. Here we evaluated the efficacy of an ensemble learning technique using the latent spectral model (LSM), an efficient deep neural operator algorithm, as base learners. Preliminary results, obtained using the Illinois Basin-Decatur Project (IBDP) carbon sequestration data/model, show that small-sized ensembles can improve prediction over the base learners, achieving prediction accuracy of ~1.6 psi root mean square error (RMSE) on pressure (relative the average reservoir pressure of 3150 psi), and less than 1.3% for saturation.

Sun, Alexander↗
DOE OSTI2022

Classification of Photovoltaic Failures with Hidden Markov Modeling, an Unsupervised Statistical Approach

Failure detection methods are of significant interest for photovoltaic (PV) site operators to help reduce gaps between expected and observed energy generation. Current approaches for field-based fault detection, however, rely on multiple data inputs and can suffer from interpretability issues. In contrast, this work offers an unsupervised statistical approach that leverages hidden Markov models (HMM) to identify failures occurring at PV sites. Using performance index data from 104 sites across the United States, individual PV-HMM models are trained and evaluated for failure detection and transition probabilities. This analysis indicates that the trained PV-HMM models have the highest probability of remaining in their current state (87.1% to 93.5%), whereas the transition probability from normal to failure (6.5%) is lower than the transition from failure to normal (12.9%) states. A comparison of these patterns using both threshold levels and operations and maintenance (O&M) tickets indicate high precision rates of PV-HMMs (median = 82.4%) across all of the sites. Although additional work is needed to assess sensitivities, the PV-HMM methodology demonstrates significant potential for real-time failure detection as well as extensions into predictive maintenance capabilities for PV.

classification↗
DOE OSTI2023

Di-CNN: Domain-Knowledge-Informed Convolutional Neural Network for Manufacturing Quality Prediction

In manufacturing, convolutional neural networks (CNNs) are widely used on image sensor data for data-driven process monitoring and quality prediction. However, as purely data-driven models, CNNs do not integrate physical measures or practical considerations into the model structure or training procedure. Consequently, CNNs’ prediction accuracy can be limited, and model outputs may be hard to interpret practically. This study aims to leverage manufacturing domain knowledge to improve the accuracy and interpretability of CNNs in quality prediction. A novel CNN model, named Di-CNN, was developed that learns from both design-stage information (such as working condition and operational mode) and real-time sensor data, and adaptively weighs these data sources during model training. It exploits domain knowledge to guide model training, thus improving prediction accuracy and model interpretability. A case study on resistance spot welding, a popular lightweight metal-joining process for automotive manufacturing, compared the performance of (1) a Di-CNN with adaptive weights (the proposed model), (2) a Di-CNN without adaptive weights, and (3) a conventional CNN. The quality prediction results were measured with the mean squared error (MSE) over sixfold cross-validation. Model (1) achieved a mean MSE of 6.8866 and a median MSE of 6.1916, Model (2) achieved 13.6171 and 13.1343, and Model (3) achieved 27.2935 and 25.6117, demonstrating the superior performance of the proposed model.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Final Targeting Strategy for the Sloan Digital Sky Survey IV Apache Point Observatory Galactic Evolution Experiment 2 North Survey

The Apache Point Observatory Galactic Evolution Experiment 2 (APOGEE-2) is a dual-hemisphere, near-infrared (NIR), spectroscopic survey with the goal of producing a chemodynamical mapping of the Milky Way. The targeting for APOGEE-2 is complex and has evolved with time. In this paper, we present the updates and additions to the initial targeting strategy for APOGEE-2N presented in Zasowski et al. (2017). These modifications come in two implementation modes: (i) “Ancillary Science Programs” competitively awarded to Sloan Digital Sky Survey IV PIs through proposal calls in 2015 and 2017 for the pursuit of new scientific avenues outside the main survey, and (ii) an effective 1.5 yr expansion of the survey, known as the Bright Time Extension (BTX), made possible through accrued efficiency gains over the first years of the APOGEE-2N project. For the 23 distinct ancillary programs, we provide descriptions of the scientific aims, target selection, and how to identify these targets within the APOGEE-2 sample. The BTX permitted changes to the main survey strategy, the inclusion of new programs in response to scientific discoveries or to exploit major new data sets not available at the outset of the survey design, and expansions of existing programs to enhance their scientific success and reach. After describing the motivations, implementation, and assessment of these programs, we also leave a summary of lessons learned from nearly a decade of APOGEE-1 and APOGEE-2 survey operations. Finally, a companion paper, F. Santana et al. (submitted; AAS29036), provides a complementary presentation of targeting modifications relevant to APOGEE-2 operations in the Southern Hemisphere.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2014

Evaluation Of Sludge Heel Dissolution Efficiency With Oxalic Acid Cleaning At Savannah River Site

The chemical cleaning process baseline strategy at the Savannah River Site was revised to improve efficiency during future execution of the process based on lessons learned during previous bulk oxalic acid cleaning activities and to account for operational constraints imposed by safety basis requirements. These improvements were also intended to transcend the difficulties that arise from waste removal in higher rheological yield stress sludge tanks. Tank 12 implemented this improved strategy and the bulk oxalic acid cleaning efforts concluded in July 2013. The Tank 12 radiological removal results were similar to previous bulk oxalic acid cleaning campaigns despite the fact that Tank 12 contained higher rheological yield stress sludge that would make removal more difficult than the sludge treated in previous cleaning campaigns. No appreciable oxalate precipitation occurred during the cleaning process in Tank 12 compared to previous campaigns, which aided in the net volume reduction of 75-80%. Overall, the controls established for Tank 12 provide a template for an improved cleaning process.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2018

Potential Experimental Topics for EGS Collab Experiment 3

To facilitate the success of FORGE, the DOE GTO has initiated a new research effort, the EGS Collab project, which will utilize readily accessible underground facilities that can refine our understanding of rock mass response to stimulation and provide a test bed at intermediate (~10 m) scale for the validation of thermal-hydrological-mechanical-chemical modeling approaches as well as novel monitoring tools. The first two EGS Experiments 1 and 2 are planned be performed under different stress/fracture conditions, and will evaluate different stimulation processes: Experiment 1 will focus on hydrofracturing of a competent rock mass, while Experiment 2 will concentrate on hydroshearing of a rock mass that contains natural fractures. Experiment 3 is scheduled to begin in 2019 will build off the lessons learned in Experiments 1 and 2 and will investigate alternate stimulation and operation methods to improve heat extraction in an EGS reservoir. This paper evaluates potential experiments that could potentially be conducted in Experiment 3. The two technical parameters defining energy extracted from EGS reservoirs with the highest economic uncertainty and risk are the production well flow rates and the reservoir thermal drawdown rate. A review of historical and currently on-going EGS studies has identified that over 1/2 of the projects have identified heat extraction challenges during their operation associated with these two parameters as well as some additional secondary issues. At present, no EGS reservoir has continuously produced flow rates on the order of 80 kg/s. Short circuiting (i.e. early thermal breakthrough) has been identified in numerous cases. In addition, working fluid loss (i.e. the difference between the injected fluid mass and the extracted fluid mass as compared to the injected mass) has been as high as 90%. Finally, the engineering aspects of operating a true EGS multi-fracture reservoir such as repairing/modifying fractures and controlling working fluid fluxes within multiple fractures for the effective EGS fracture management has not been sufficiently studied. To examine issues such as these, EGS Collab Experiment 3 may be conducted in the testbeds prepared for Experiments 1 and 2 by improving the previously performed stimulations, or conducted at a new site performing new stimulations with alternate method. Potential experiments may include using different stimulation and working fluids, evaluating different stimulation methods, using proppants to enhance permeability, and other high-risk high-reward methods that can be evaluated at the 10-m scale environment.

15 GEOTHERMAL ENERGY↗
DOE OSTI2018

Potential Experimental Topics for EGS Collab Experiment 3

To facilitate the success of FORGE, the DOE GTO has initiated a new research effort, the EGS Collab project, which will utilize readily accessible underground facilities that can refine our understanding of rock mass response to stimulation and provide a test bed at intermediate (~10 m) scale for the validation of thermal-hydrological-mechanical-chemical modeling approaches as well as novel monitoring tools. The first two EGS Experiments 1 and 2 are planned be performed under different stress/fracture conditions, and will evaluate different stimulation processes: Experiment 1 will focus on hydrofracturing of a competent rock mass, while Experiment 2 will concentrate on hydroshearing of a rock mass that contains natural fractures. Experiment 3 is scheduled to begin in 2019 will build off the lessons learned in Experiments 1 and 2 and will investigate alternate stimulation and operation methods to improve heat extraction in an EGS reservoir. This paper evaluates potential experiments that could potentially be conducted in Experiment 3. The two technical parameters defining energy extracted from EGS reservoirs with the highest economic uncertainty and risk are the production well flow rates and the reservoir thermal drawdown rate. A review of historical and currently on-going EGS studies has identified that over ½ of the projects have identified heat extraction challenges during their operation associated with these two parameters as well as some additional secondary issues. At present, no EGS reservoir has continuously produced flow rates on the order of 80 kg/s. Short circuiting (i.e. early thermal breakthrough) has been identified in numerous cases. In addition, working fluid loss (i.e. the difference between the injected fluid mass and the extracted fluid mass as compared to the injected mass) has been as high as 90%. Finally, the engineering aspects of operating a true EGS multi-fracture reservoir such as repairing/modifying fractures and controlling working fluid fluxes within multiple fractures for the effective EGS fracture management has not been sufficiently studied. To examine issues such as these, EGS Collab Experiment 3 may be conducted in the testbeds prepared for Experiments 1 and 2 by improving the previously performed stimulations, or conducted at a new site performing new stimulations with alternate method. Potential experiments may include using different stimulation and working fluids, evaluating different stimulation methods, using proppants to enhance permeability, and other high-risk high-reward methods that can be evaluated at the 10-m scale environment.

15 GEOTHERMAL ENERGY↗
DOE OSTI2021

Cyber Threat Assessment Methodology for Autonomous and Remote Operations for Advanced Reactors (Conference Presentation)

The next generation of Advanced Reactors include planned capabilities for both Autonomous (operating without human interaction for a set period-of-time) and Remote (operating with human interaction from a separate physical location) Operations. Existing Nuclear Reactor architectures include a set of safety and security constraints tightly coupled with personnel policies and procedures. As Advanced Reactors are fielded with these new Autonomous and Remote operational capabilities, the architectures and associated infrastructure services and components will perceivably expand the overall attack surface and risk calculations with regards to safe and secure operations. This paper is part of an FY21 work program focused on ensuring Advanced Reactor designs are informed with threat-based guidance on design and operation of Secure Architectures with a specific focus on the deployment of Autonomous Systems in support of Advanced Reactor Operations. The next phase of this research program is to complement produce a methodology for assessment of the cyber threat against these architectures as well as a catalogue of Use Cases to support the Advanced Reactor community in their implementation of Autonomous and Remote Operations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2013

Cesium Removal at Fukushima Nuclear Plant - 13215

The Great East Japan Earthquake that took place on March 11, 2011 created a number of technical challenges at the Fukushima Daiichi Nuclear Plant. One of the primary challenges involved the treatment of highly contaminated radioactive wastewater. Avantech Inc. developed a unique patent pending treatment system that addressed the numerous technical issues in an efficient and safe manner. Our paper will address the development of the process from concept through detailed design, identify the lessons learned, and provide the updated results of the project. Specific design and operational parameters/benefits discussed in the paper include: - Selection of equipment to address radionuclide issues; - Unique method of solving the additional technical issues associated with Hydrogen Generation and Residual Heat; - Operational results, including chemistry, offsite discharges and waste generation. Results show that the customized process has enabled the utility to recycle the wastewater for cooling and reuse. This technology had a direct benefit to nuclear facilities worldwide. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2017

Mobile Manipulation and Survey System for H-Canyon and Other Applications across the DOE Complex - 17309

The Nuclear and Applied Robotics Group (NRG) at the University of Texas at Austin is leading a team of university, industry, and national lab partners to develop and deploy a mobile manipulation and survey system for the H-Canyon Air Exhaust (CAEX) tunnels. Since the 1950's, these tunnels have connected Savannah River's nuclear chemical separations facilities to a terminus of sand filters. The tunnel must be periodically inspected. The conditions are harsh: 30+ mph air flow, acid vapors, alpha contamination, high beta and gamma dose, uneven floor surfaces, small entry port, obstacle debris, 'muddy' paths, standing water, and overhead obstacles. Since 2003, 5 crawlers have been deployed to inspect the tunnel with sufficient but limited success. Thus, H-Canyon provides an opportunity to develop and deploy a more robust system adhering to the notion of Multi-user / Multi-use (Mu2) in which a system is developed to complete a particular mission, but designed to maximize its extended use (multiple missions, locations, operators, etc.). Previous deployments provide a set of experiences upon which to learn and build. The environment is challenging and representative of other envisioned scenarios across the national nuclear complex. This paper reviews the history of system deployment into H-Canyon, the lessons learned from these experiences and then derives the requirements that will drive a 3 year effort to develop and deploy a system for H-Canyon inspection and other missions. The paper then concludes with a summary of technologies that enable a path to a functional prototype based on the current conceptual solution. This examination of available technologies and remaining technological gaps can assist the client in assessing the risk associated with proposed development and the range of application possible with a delivered functional prototype. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2024

Enhancing Fluid Flow Pressure and Saturation Prediction Accuracy and Reducing Uncertainty with Committee Machine – Illinois Basin Decatur Project (IBDP) as a Case Study

This is the conference paper accompanying an oral presentation at the 17th International Conference on Greenhouse Gas Control Technologies GHGT-17 held in Calgary, Canada, October 20-24, 2024. Carbon capture and storage (CCS) is a way to play a critical role in the global transition to a low-emission economy. Current progress is hampered by a number of factors, among which the lack of risk-informed design tools and decision support frameworks is seen as a major roadblock. Significant interest exists in using artificial intelligence to accelerate CCS site feasibility studies, as well as to facilitate the permit application process. Existing works commonly train a single deep learning model. This work investigates the feasibility of using a conventional ensemble learning (committee machine) technique to further improve prediction accuracy. Ensemble-based algorithms generally improve over individual base learners in terms of robustness and accuracy. Deep ensembles, however, are time-consuming to create and train. A pragmatic question is whether small-sized ensembles may lead to prediction improvement. Here we evaluated the efficacy of an ensemble learning technique using the latent spectral model (LSM), an efficient deep neural operator algorithm, as base learners. Preliminary results, obtained using the Illinois Basin-Decatur Project (IBDP) carbon sequestration data/model, show that small-sized ensembles can improve prediction over the base learners, achieving prediction accuracy of ~1.6 psi root mean square error (RMSE) on pressure (relative the average reservoir pressure of 3150 psi), and less than 1.3% for saturation.

Sun, Alexander↗
DOE OSTI2021

Detecting False Data Injection Attacks in Smart Grids: A Semi-Supervised Deep Learning Approach

The dependence on advanced information and communication technology increases the vulnerability in smart grids under cyber-attacks. Recent research on unobservable false data injection attacks (FDIAs) reveals the high risk of secure system operation, since these attacks can bypass current bad data detection mechanisms. To mitigate this risk, this paper proposes a data-driven learning-based algorithm for detecting unobservable FDIAs in distribution systems. We use autoencoders for efficient dimension reduction and feature extraction of measurement datasets. Further, we integrate the autoencoders into an advanced generative adversarial network (GAN) framework, which successfully detects anomalies under FDIAs by capturing the unconformity between abnormal and secure measurements. Also, considering that the datasets collected from practical power systems are partially labeled due to expensive labeling costs and missing labels, the proposed method only requires a few labeled measurement data in addition to unlabeled data for training. Numerical simulations in three-phase unbalanced IEEE 13-bus and 123-bus distribution systems validate the detection accuracy and efficiency of this method.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

The Use of Machine Learning Models for Predicting the Dielectric Strength of Gases

Technological advancements in high voltage systems have pushed sulfur hexafluoride (SF6) to its operational limits. Furthermore, this gas has other drawbacks including a high liquefaction temperature and a high global warming potential. Therefore, there has been an urgent need to find alternative gases with high dielectric strength (DS). In this work, density functional theory (DFT) is used to calculate molecular descriptors that are fed into an artificial neural network (ANN) and a random forest (RF). These machine learning (ML) models are then used to predict the DS for hundreds of molecules. A finite element model (FEM) is also used to calculate the electric field profile of multiple simple electrode geometries as the applied voltage to the system is increased. Results indicate that the random forest model has better generalization to unseen data than the neural network. The highest DS value predicted by the RF was 2.16 relative to the experimental DS of SF6. The results also demonstrate how choosing a gas with a higher DS and a geometry with minimal edges and corners can significantly increase the operating voltage of an electrical system. Due to its superior generalization, the RF represents the most promising path toward an accurate DS predictor once sufficient experimental data are available.

Mileski, Matthew [AFIT]↗
DOE OSTI2023

Uncertainty Aware Deep Learning for Fault Prediction Using Multivariate Time Series Signals

The superconducting radio-frequency cavities are a crucial component of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. When a cavity faults, beam delivery to experimental end users is disrupted. Prediction of cavity faults prior to onset is essential to reduce operation and maintenance costs. In this work, a parallel long short-term memory (LSTM)-convolution neural network (CNN)-based deep learning (DL) model is proposed to predict impending faults using pre-fault signals. Further, we introduce an uncertainty quantification approach using Monte Carlo dropout with the LSTM-CNN model to ascertain confidence in the prediction. The model was tested using multivariate time series signals from stable cavity operations and before faults. Initial results show that on the test dataset, the model can identify impending faults before their onset with an average 10-fold cross validation accuracy of 97.39% and a standard deviation of 0.12% using a 100-ms time window. It is also observed that the model performs better as the prediction time moves closer to the fault onset. For additional context, we compare the performance of the model with three machine-learning-based (ML) fault prediction models. Our proposed parallel LSTM-CNN-based DL method shows better performance than the ML-based methods.

Rahman, Md Monibor↗
DOE OSTI2022

Matrix Multiply Performance of GPUs on Exascale-class HPE/Cray Systems

The computation of dense matrix-matrix products (GEMMs) is central to many modeling and simulation workloads as well as AI/ML deep learning campaigns. In fact, millions of dollars are spent annually on computing GEMMs, and large model training demands are increasing exponentially. Specialized processors such as GPUs are designed to perform well for these operations. However, the performance of GEMMs on GPUs can exhibit complex behaviors depending on many factors, making it challenging to optimize the performance of GEMMs on these processors. In this study we undertake an examination of GEMM performance on several leading GPU models taken from product lines of GPUs to be deployed in forthcoming exascale computing systems. We show results to illustrate the many factors that can affect performance of GEMMs on GPUs. We then present data collected from a large number of test runs for an example GEMM operation to show the dependence behaviors of GEMM rate on matrix dimensions. Finally, we show results from machine learning-based performance models using novel feature engineering methods to fit the measured performance, providing a potential basis for GEMM performance tuning and autotuning methods for GPUs. Recommendations are also given for how to achieve high GEMM performance on modern GPUs.

Melesse Vergara, Veronica↗
DOE OSTI2024

Integrating an Ensemble Reward System into an Off-Policy Reinforcement Learning Algorithm for the Economic Dispatch of Small Modular Reactor-Based Energy Systems

Nuclear Integrated Energy Systems (NIES) have emerged as a comprehensive solution for navigating the changing energy landscape. They combine nuclear power plants with renewable energy sources, storage systems, and smart grid technologies to optimize energy production, distribution, and consumption across sectors, improving efficiency, reliability, and sustainability while addressing challenges associated with variability. The integration of Small Modular Reactors (SMRs) in NIES offers significant benefits over traditional nuclear facilities, although transferring involves overcoming legal and operational barriers, particularly in economic dispatch. This study proposes a novel off-policy Reinforcement Learning (RL) approach with an ensemble reward system to optimize economic dispatch for nuclear-powered generation companies equipped with an SMR, demonstrating superior accuracy and efficiency when compared to conventional methods and emphasizing RL’s potential to improve NIES profitability and sustainability. Finally, the research attempts to demonstrate the viability of implementing the proposed integrated RL approach in spot energy markets to maximize profits for nuclear-driven generation companies, establishing NIES’ profitability over competitors that rely on fossil fuel-based generation units to meet baseload requirements.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2026

Optimal CO 2 storage management considering safety constraints in multi-stakeholder multi-site GCS projects: A Markov game perspective

Geological carbon storage (GCS) projects could involve a diverse array of stakeholders or players from public, private, and regulatory sectors, each with different objectives and responsibilities. Given the complexity, scale, and long-term nature of GCS operations, determining whether individual stakeholders can independently optimize their interests — or whether collaborative coalition agreements are needed — remains a central question for effective GCS project planning and management. To access large, high-quality storage resources, future GCS deployment may increasingly occur in geologically connected sites, where shared geological features such as pressure space and reservoir pore capacity can lead to competitive behavior among stakeholders. In this work, we propose a paradigm based on Markov games to quantitatively investigate how different coalition structures affect the goals of stakeholders. We frame this multi-stakeholder multi-site problem as a multi-agent reinforcement learning problem with safety constraints. Our approach enables agents to learn optimal strategies while complying with safety regulations. We present an example where multiple operators are injecting CO 2 into their respective project areas in a geologically connected basin. To address the high computational cost of repeated simulations of high fidelity models, a previously developed surrogate model based on the Embed-to-Control (E2C) framework is employed. Our results demonstrate the effectiveness of the proposed framework in addressing optimal management of CO 2 storage when multiple stakeholders with different objectives and goals are involved.

58 GEOSCIENCES↗