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 1,261 records · Page 70
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A physics‐informed learning technique for fault location of DC microgrids using traveling waves

Abstract Fast and accurate fault location in DC power systems is of particular importance to ensure their reliable operation. One of the approaches for implementing a fast‐tripping protection scheme is to use Traveling waves (TW) initiated by a fault scenario. This paper proposes a physics‐informed machine learning approach that utilizes TWs for fault location in DC microgrids. TWs are extracted by the so‐called multiresolution analysis which identifies the TW's wavelet coefficients for multiple frequency ranges. This paper deploys Parseval's theorem to find the energy of wavelet coefficients as a quantitative metric for describing TWs. The hypothesis of this paper is that once the Parseval energy curves for a specific cable are extracted, they can be utilized to locate faults along with that cable regardless of the DC system in which the cable is deployed. The fault location algorithm uses Parseval energy curves to train a Gaussian Process (GP) estimator. With the Parseval energy values of measured current at the protection device location, the GP estimator is able to estimate fault locations with high accuracy. The effectiveness of the proposed algorithm is verified by simulating a DC microgrid system in PSCAD/EMTDC.

Paruthiyil, Sajay Krishnan↗
DOE OSTI2012

Savannah River Site, Liquid Waste Program, Savannah River Remediation American Recovery and Reinvestment Act Benefits and Lessons Learned - 12559

Utilizing funding provided by the American Recovery and Reinvestment Act (ARRA), the Liquid Waste Program at Savannah River site successfully executed forty-one design, procurement, construction, and operating activities in the period from September 2009 through December 2011. Project Management of the program included noteworthy practices involving safety, integrated project teams, communication, and cost, schedule and risk management. Significant upgrades to plant capacity, progress toward waste tank closure and procurement of needed infrastructure were accomplished. Over 1.5 million hours were worked without a single lost work day case. Lessons Learned were continually identified and applied to enhance the program. Investment of Recovery Act monies into the Liquid Waste Program has ensured continued success in the disposition of radioactive wastes and the closure of high level waste tanks at SRS. The funding of a portion of the Liquid Waste Program at SRS by ARRA was a major success. Significant upgrades to plant capacity, progress toward waste tank closure and procurement of needed infrastructure was accomplished. Integrated Project Teams ensured quality products and services were provided to the Operations customers. Over 1.5 million hours were worked without a single lost work day case. Lessons Learned were continually reviewed and reapplied to enhance the program. Investment of Recovery Act monies into the Liquid Waste Program has ensured continued success in the disposition of radioactive wastes and the closure of high level waste tanks at SRS. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Role of reinforcement learning for risk-based robust control of cyber-physical energy systems

Critical infrastructures such as cyber-physical energy systems (CPS-E) integrate information flow and physical operations that are vulnerable to natural and targeted failures. Safe, secure, and reliable operation and control of CPS-E is critical to ensure societal well-being and economic prosperity. Automated control is key for real-time operations and may be mathematically cast as a sequential decision-making problem under uncertainty. Emergence of data-driven techniques for decision making under uncertainty, such as reinforcement learning (RL), have led to promising advances for addressing sequential decision-making problems for risk-based robust CPS-E control. However, existing research challenges include understanding the applicability of RL methods across diverse CPS-E applications, addressing the effect of risk preferences across multiple RL methods, and development of open-source domain-aware simulation environments for RL experimentation within a CPS-E context. This article systematically analyzes the applicability of four types of RL methods (model-free, model-based, hybrid model-free and model-based, and hierarchical) for risk-based robust CPS-E control. Problem features and solution stability for the RL methods are also discussed. We demonstrate and compare the performance of multiple RL methods under different risk specifications (risk-averse, risk-neutral, and risk-seeking) through the development and application of an open-source simulation environment. Motivating numerical simulation examples include representative single-zone and multizone building control use cases. Finally, six key insights for future research and broader adoption of RL methods are identified, with specific emphasis on problem features, algorithmic explainability, and solution stability.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Does practice make perfect? Lessons learned from full-scale power system incident response exercise

While threats to the energy sector occur daily, few utilities get the opportunity to fully test out their detection and response mechanisms to advanced threats in the real world. With the high demand for reliability, few grid operators would allow execution of simulated cyber-attacks on their live systems. The DOE-funded Liberty Eclipse project offers a unique opportunity for small and large utilities and coops to practice their combined IT/OT responses to a live red team executing attacks against an isolated power system on an island in New York. Both cyber teams and power operations teams must work together to detect and respond to attacks, even restoring the power system against extreme impacts. Lessons learned from these exercises reveal key takeaways for understanding what a real attack against the electric sector will look like, gaps in execution of the best-laid plans when the pressure of a real event is bearing down, and how organizations can better prepare for advanced attacks by optimizing participation in exercises. This presentation will discuss successes and opportunities for improvement both in how utilities can prepare for and respond to events, as well as how full-scale IT/OT exercises can be coordinated.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Lessons Learned From Ventilation and Glovebox Flooding Via Overfilling of the Wet Vacuum System in a Plutonium Facility

In the summer of 2021, operations personnel requested maintenance personnel to fill a wet vacuum (Wetvac) seal water tank in a plutonium facility at Los Alamos National Laboratory (LANL). After the filling was finished, the fill valve of the Wetvac seal water tank was left open and a ‘dead-man’ valve on an isolation line failed to close properly. After a series of other failures, the water exited the glovebox and contaminated three rooms of the first floor of the facility and an underlying area in the basement. A retrospective analysis of this event determined that there was no risk of a criticality due to the inherent design features of the ventilation system. This paper will explain the driving factors behind how this event was able to happen, as well as some of the major lessons learned that can be universally applied to other nuclear facilities. One of the main causes of the event was the delegation of work to maintenance personnel that were not qualified for the work being asked of them. Additionally, there was a lack of coordination between criticality safety engineers and facility operations equipment owners regarding equipment and connections present on the seal water tanks for the Wetvac, specifically the presence of overflow drain lines. The respective criticality safety evaluation credited an overflow drain line being present on the seal water tanks that was later found to have not been present. Lastly, there are lessons to be learned regarding equipment configuration and designing systems with safety in mind.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Spatial Transferability of Machine Learning Based Volume Estimation Models

High-quality traffic volume data is essential for efficient transportation planning and operations. However, such high-quality data is expensive to collect, owing primarily to the high capital cost of installing and maintaining continuous counting stations (CCSs). Recent availability of probe-based vehicle data offers a cost-effective solution for increasing the observability of traffic volumes. However, having ample ground truth traffic data is a prerequisite for developing robust volume estimation models. Though this might not be a big issue in many states, states with scarce CCS data might be able to benefit from robust volume estimation models developed in (adjacent) data-rich states. While there is a reasonable amount of spatial transferability research in the transportation domain, there is a dearth of knowledge on the spatial transferability of probe-based volume estimation models. To address this gap, this paper explores spatial transferability of volume estimation models developed from data in three states (Colorado, North Carolina, and Pennsylvania). Results indicate that it is extremely important to maintain temporal consistency when attempting spatial transferability of volume estimation models. It was also found that models trained on regions with lower peak traffic volumes will limit the performance of models transferred to states with higher peak hourly traffic volumes. Corroborating findings from existing spatial transferability research on other topics, it was found that a meta-model (developed using data from multiple states) performs better than volume estimation models developed within any one of the states.

ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2019

Neural network modeling of in situ fluid-filled pore size distributions in subsurface shale reservoirs under data constraints

Subsurface nuclear magnetic resonance (NMR) logs acquired in the wellbore environment are sensitive to fluid-filled pore size distribution, fluid mobility, permeability, and porosity in the near-wellbore reservoir volume. NMR response of a formation layer is processed to extract the T2 distribution, which approximates the fluid-filled pore size distribution. NMR logs are acquired in limited number of wells due to financial and operational challenges, which adversely affects reservoir characterization. We developed here two neural-network-based machine learning techniques, long short-term memory (LSTM) network and variational autoencoder with a convolutional layer (VAEc) network, to process the ‘easy-to-acquire’ formation mineral and fluid saturation logs to generate synthetic NMR T2 distributions in the absence of ‘hard-to-acquire’ NMR T2 distribution log. Both the predictive models are trained and tested on limited wireline log measurements randomly selected from a 300-ft depth interval of the Bakken shale formation. Synthesis performances of LSTM and VAEc models in terms of R 2 are 0.78 and 0.75, respectively. Noise is inevitable in logging data due to the complex wellbore and formation conditions. Notably, both the predictive models robustly synthesize the fluid-filled pore size distributions in the presence of 50% noise in input logs and 30% noise in training T2 data. The performance of the proposed methodology improves with access to larger volume of training data from other formation types. The proposed method is critical to the synthesis of in situ fluid-filled pore size distributions in shale formations under data constraints due to financial and operational challenges.

58 GEOSCIENCES↗
DOE OSTI2013

How Stakeholder Engagement is Evolving at the Caldas Uranium Mining Site in Minas Gerais, Brazil - 13223

The Caldas site is located in the Federal State of Minas Gerais in Brazil about 25 km from the city of Pocos de Caldas. While the city itself has 150,000 inhabitants there is a total population of around 0.5 million people living in an area that could potentially be influenced by the site. Uranium ore was mined and milled here between the years of 1982 and 1995, with ore extraction taking place from an open pit. Of the material removed, aside from that extracted for uranium, some was used on-site for road construction and building embankments while the remainder was disposed of onto two major rock piles. There are a number of potential historical and current environmental impacts to groundwater as a consequence of discharges into streams which then flow off site. The site is now undergoing a phase of decommissioning which includes the formulation and substantiation of a site remediation strategy. As part of a wider International Atomic Energy Agency (IAEA) Technical Cooperation Project aimed at providing practical guidance for implementing a decommissioning and remediation plan at the site, WSP E and E were invited to lead a mission in order to provide advice on the importance and merits of stakeholder engagement and how to ultimately build an engagement program. In November 2011, WSP E and E met with personnel from the site operators, the Brazilian regulatory bodies and representatives from the local stakeholder community and explained the principles of stakeholder engagement and how the process had internationally evolved principally from a decide-announce-defend approach to a more formal two way mechanism of engagement. Historically there had been insufficient liaison between the site operator, the nuclear regulator and the environmental regulator. All parties had recognized that greater interaction was necessary. There had also been very little engagement with local stakeholders about the various activities on the site and the potential implications of these activities on human health and the environment. The main concerns of the local stakeholders were in relation to potential environmental impacts on groundwater and surface water as well as their lack of knowledge about the site's activities and how it might evolve over time. There was a feeling that the site brought no real benefit to the local community as local labor was rarely utilized when work was being undertaken. WSP E and E were asked many questions about stakeholder engagement processes and had to address a number of concerns relating to being able to construct and control an engagement program. Advice was provided on how to construct a phased program in a manner that would allow the site operator to demonstrate increased transparency and allow as wide a range of stakeholders as possible the opportunity to become engaged. We provided an important message in that engagement often had to be culture and project specific and that what might work in one country could not necessarily purely be transposed to another. Since the WSP E and E mission there has been evidence of a number of positive steps in many of the areas of stakeholder engagement related to the Caldas site. The nuclear and environmental regulators work in a more open and transparent manner and continue to undertake joint inspections of the Caldas site. They have agreed to develop a written agreement that will enable them to jointly assess and discuss the issues on the site. Both regulatory bodies had previously accompanied the site operator on a visit to the Wismut uranium mining area in Germany and as well as providing useful learning had also allowed the regulators to discuss some common issues, thus bringing them closer together. A local stakeholder group under the auspices of the Water Commission had previously been set up but now they are starting to have more regular meetings with the site operator and nuclear regulator. They are now additionally considering the formation of a site specific advisory board (based on similar lines to those at US legacy sites) in order to gain some further technical focus within the stakeholder community. The site operator has started to present and explain the proposed environmental remediation plans to various towns and cities potentially influenced by the Caldas site. The successes to date can be attributed primarily to the willingness of the site operator to engage more openly with local community representatives in addition to the enthusiasm of the Water Commission itself. Providing stakeholder engagement advice to all the relevant parties in a manner which recognized their concerns, aspirations and country specific culture was extremely important for this positive progress to have been established. The process established and the subsequent successes could provide useful learning to those countries that face similar cultural engagement challenges. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Scalable algorithms for physics-informed neural and graph networks

Physics-informed machine learning (PIML) has emerged as a promising new approach for simulating complex physical and biological systems that are governed by complex multiscale processes for which some data are also available. In some instances, the objective is to discover part of the hidden physics from the available data, and PIML has been shown to be particularly effective for such problems for which conventional methods may fail. Unlike commercial machine learning where training of deep neural networks requires big data, in PIML big data are not available. Instead, we can train such networks from additional information obtained by employing the physical laws and evaluating them at random points in the space–time domain. Such PIML integrates multimodality and multifidelity data with mathematical models, and implements them using neural networks or graph networks. Here, we review some of the prevailing trends in embedding physics into machine learning, using physics-informed neural networks (PINNs) based primarily on feed-forward neural networks and automatic differentiation. For more complex systems or systems of systems and unstructured data, graph neural networks (GNNs) present some distinct advantages, and here we review how physics-informed learning can be accomplished with GNNs based on graph exterior calculus to construct differential operators; we refer to these architectures as physics-informed graph networks (PIGNs). We present representative examples for both forward and inverse problems and discuss what advances are needed to scale up PINNs, PIGNs and more broadly GNNs for large-scale engineering problems.

42 ENGINEERING↗
DOE OSTI2021

DETECTING FIRE WITH MACHINE LEARNING-ENABLED VISUAL MONITORING FOR NUCLEAR POWER PLANT ENVIRONMENTS

Nuclear power plants are experiencing significant cost challenges to remain competitive with other energy-generation utilities. Unlike other industries, the cost of operation and maintenance activities is mostly attributed to workforce costs. To mitigate this, nuclear power plant stakeholders are increasingly interested in the development and deployment of machine learning methods to potentially automate or augment manually intensive tasks to reduce costs, especially for monitoring activities. One monitoring function that is visually demanding and that can occur frequently to meet the requirements of a fire protection program is visually monitoring an area for fire occurrence. Currently, fire watch activities consist of a worker physically stationed at a given location with the sole responsibility of observing a given area to ensure a fire is detected and mitigated promptly. This effort focused on the development and evaluation of a suitable deep convolutional neural network to classify individual video frames at a sub-second frequency for the occurrence of “fire” and “no fire” in varying industrial environments similar to nuclear power plants. It is believed that a trained neural network model could be integrated with existing facility video surveillance camera feeds to generate alerts when fire inferences occur in individual frames captured at sub-second temporal resolutions. Extensive effort was dedicated to identifying and curating suitable imagery training data representing varying environments and scene settings with and without flame features to maximize generalization in nuclear power plant environments. The data collection effort resulted in the aggregation of a large, labeled image library exceeding 12,000 images to support model training for diverse industrial environments. A deep neural network model incorporating parallel multi-scale capabilities was developed and trained to support accurate image-based detection of flame incidents of varying sizes and spectral feature properties within heterogeneous scenes. Analysis results show that the trained model can achieve high inference accuracy despite heterogeneous scene environments and components. Testing accuracy exceeded 95.0 percent with very low false positive and false negative inferences.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2018

Machine learning at the energy and intensity frontiers of particle physics

Our knowledge of the fundamental particles of nature and their interactions is summarized by the standard model of particle physics. Advancing our understanding in this field has required experiments that operate at ever higher energies and intensities, which produce extremely large and information-rich data samples. The use of machine-learning techniques is revolutionizing how we interpret these data samples, greatly increasing the discovery potential of present and future experiments. Here we summarize the challenges and opportunities that come with the use of machine learning at the frontiers of particle physics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Unraveling the impact of initial choices and in-loop interventions on learning dynamics in autonomous scanning probe microscopy

The current focus in Autonomous Experimentation (AE) is on developing robust workflows to conduct the AE effectively. This entails the need for well-defined approaches to guide the AE process, including strategies for hyperparameter tuning and high-level human interventions within the workflow loop. This paper presents a comprehensive analysis of the influence of initial experimental conditions and in-loop interventions on the learning dynamics of Deep Kernel Learning (DKL) within the realm of AE in scanning probe microscopy. We explore the concept of the “seed effect,” where the initial experiment setup has a substantial impact on the subsequent learning trajectory. Additionally, we introduce an approach of the seed point interventions in AE allowing the operator to influence the exploration process. Using a dataset from Piezoresponse Force Microscopy on PbTiO 3 thin films, we illustrate the impact of the “seed effect” and in-loop seed interventions on the effectiveness of DKL in predicting material properties. The study highlights the importance of initial choices and adaptive interventions in optimizing learning rates and enhancing the efficiency of automated material characterization. This work offers valuable insights into designing more robust and effective AE workflows in microscopy with potential applications across various characterization techniques.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

What We Learned From Analyzing 18 Million Rows of Commercial Buildings’ HVAC Fault Data

To achieve ambitious decarbonization goals it is critical that buildings operate to their full potential. Commercial HVAC systems, however, experience a wide range of operational faults, adversely affecting energy consumption, occupant comfort, and maintenance costs. Analytical tools such as fault detection & diagnostics (FDD) software identify and help diagnose these types of sensing, mechanical, or control-related faults. While significant energy savings has been documented for FDD, along with limited-scale studies on technical capabilities, there is a lack of empirical data on faults being reported by FDD tools. With FDD deployment accelerating significantly over the past decade there is an opportunity to gather and analyze data on commercial HVAC operational problems at an unprecedented scale. Such data could address many questions such as: [a] What faults are most commonly reported?; and [b] How does fault reporting vary by time of year and other possible drivers? A recent study into FDD fault reporting amassed the largest U.S. dataset of commercial HVAC air-side fault records, drawn from multi-year monitoring across over 60,000 pieces of HVAC equipment. The results of this study provide granular data on fault reporting for over 90 unique fault types. In this paper we provide an overview of the research process and highlight key findings and lessons learned. This study presents an extraordinary level of detail on FDD fault reporting characteristics across many climate zones and building types. Armed with these new insights, commercial building industry stakeholders can make better informed decisions when designing, configuring, and operating commercial HVAC systems.

Crowe, Eliot↗
DOE OSTI2026

A machine learning based approach to online electron reconstruction at CLAS12

Online reconstruction is key for monitoring purposes and real time analysis in High Energy and Nuclear Physics experiments. A necessary component of reconstruction algorithms is particle identification that combines information left by a particle passing through several detector components to identify the particle’s type. Of particular interest to electro-production Nuclear Physics experiments such as CLAS12 is electron identification which is used to trigger data recording. A machine learning approach was developed for CLAS12 to reconstruct and identify electrons by combining raw signals at the data acquisition level from several detector components. Here, this approach achieves an electron identification purity above 75% whilst retaining an efficiency close to 100%. The machine learning tools are capable of running at high rates exceeding the data acquisition rates and will allow electron reconstruction in real-time. This work enhances online analyses and monitoring and can contribute to improved triggering at CLAS12. This machine learning driven approach will also be crucial for experiments aiming to transition to streaming readout operations where online reconstruction will be a key component of the data taking paradigm.

Artificial intelligence↗
DOE OSTI2018

Scoping Study of Machine Learning Techniques for Visualization and Analysis of Multi-source Data in Nuclear Safeguards

In implementation of nuclear safeguards, many different techniques are being used to monitor operation of nuclear facilities and safeguard nuclear materials, ranging from radiation detectors, flow monitors, video surveillance, satellite imagers, digital seals to open source search and reports of onsite inspections/verifications. Each technique measures one or more unique properties related to nuclear materials or operation processes. Because these data sets have no or loose correlations, it could be beneficial to analyze the data sets together to improve the effectiveness and efficiency of safeguards processes. Advanced visualization techniques and machine-learning based multi-modality analysis could be effective tools in such integrated analysis. In this project, we will conduct a survey of existing visualization and analysis techniques for multi-source data and assess their potential values in nuclear safeguards.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Verification of Triso Fuel Burnup Using Machine Learning Algorithms

Pebble Bed Reactors are fueled with fuel pebbles that are circulated multiple times through the reactor vessel before discharge. During the normal operation of a PBR, ejected pebbles are returned to the reactor or discharged depending on the fuel burnup and physical condition of the pebbles. The burnup measurement is usually based on detected radiation signatures of fission products accumulated in the pebble fuel over burnup. Previous research has shown that height of photopeaks of fission products, such as 134 Cs, 137 Cs, 154 Eu, etc., can be used independently or in combination to infer or predict the level of burnup in the fuel. However, it remains challenging to measure such complex sources due to self-shielding effects, strong radiation background and intervening materials. Another operational challenge is the required high throughput of burnup measurement, which necessitates limited measurement time and thus impacts quality of measured gamma-ray spectra. Hence, advanced spectral analysis methods are needed to analyze the noisy gamma spectra and predict the burnup values. We propose to use machine learning (ML) method to interpret gamma-ray spectra and predict the burnup values of the pebbles. ML has achieved widespread success and adoption across a few domains that require pattern recognition and analysis in varied data types. In this work, we apply three proven ML approaches - multilayer perceptrons, convolutional neural networks, and transformers - to the task of predicting fuel burnup from measured gamma spectra, and compile a dataset of simulated spectra for training and validation of the ML models. In this paper, we will discuss the network architecture of these three ML approaches and compare the performance of the simplest of these (MLP) to a standard linear regression.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

VERIFICATION OF TRISO FUEL BURNUP USING MACHINE LEARNING ALGORITHMS

Pebble Bed Reactors are fueled with fuel pebbles that are circulated multiple times through the reactor vessel before discharge. During the normal operation of a PBR, ejected pebbles are returned to the reactor or discharged depending on the fuel burnup and physical condition of the pebbles. The burnup measurement is usually based on detected radiation signatures of fission products accumulated in the pebble fuel over burnup. Previous research has shown that height of photopeaks of fission products, such as 134Cs, 137Cs, 154Eu, etc., can be used independently or in combination to infer or predict the level of burnup in the fuel. However, it remains challenging to measure such complex sources due to self-shielding effects, strong radiation background and intervening materials. Another operational challenge is the required high throughput of burnup measurement, which necessitates limited measurement time and thus impacts quality of measured gamma-ray spectra. Hence, advanced spectral analysis methods are needed to analyze the noisy gamma spectra and predict the burnup values. We propose to use machine learning (ML) method to interpret gamma-ray spectra and predict the burnup values of the pebbles. ML has achieved widespread success and adoption across a few domains that require pattern recognition and analysis in varied data types. In this work, we apply three proven ML approaches - multilayer perceptrons, convolutional neural networks, and transformers - to the task of predicting fuel burnup from measured gamma spectra, and compile a dataset of simulated spectra for training and validation of the ML models. In this paper, we will discuss the network architecture of these three ML approaches and compare the performance of the simplest of these (MLP) to a standard linear regression.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗