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 1,711 records · Page 95

Extending RISMC Capabilities for Real-Time Diagnostics and Prognostics

Quick and effective accident management is essential in any industry in order to limit and contain possible threats to both people and environment/assets. This is in particular relevant in the nuclear industry where accidents may have major impacts from an economic, health and societal point of view. As an example, the Fukushima Dai-ichi nuclear power plant accident highlighted the importance of the ability of plant operators and plant staff to react quickly and effectively in accident conditions. This particular event showed the importance of being able to: • Determine/estimate the actual status of the plant (i.e., diagnosis) when the monitoring system is corrupted or partially unavailable, and, • Forecast its future evolution (i.e., prognosis). In this paper we want to describe a research direction geared toward the development of a new set of advanced diagnosis and prognosis tools. We employ innovative data mining and machine learning techniques that are able to infer plant status and mimic the plant’s full temporal behavior in order to assist the reactor operators during an accident scenario.

97 MATHEMATICS AND COMPUTING↗

Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilities. Crucial to the success of this experimental paradigm are several emerging technologies, such as artificial intelligence and machine learning (AI/ML) and silicon microelectronics, and the advent of quantum algorithms and processing. Their intersection includes areas of research such as low-power and low-latency devices for edge computing, heterogeneous accelerator systems, reconfigurable hardware, novel codesign and synthesis strategies, readout for cryogenic or high-radiation environments, and analog computing. This white paper presents a community-driven vision to identify and prioritize research and development opportunities in hardware-based ML systems and corresponding physics applications, contributing towards a successful transition to the new data frontier of fundamental science.

Gonski, Julia [SLAC]↗

Artificial Intelligence Applications in Renewable Energy

Addressing new methodologies in deep learning (DL), machine learning (ML) and artificial intelligence (AI), the webinar speakers will provide an overview of the literature spanning these three overlapping fields as applied to energy systems research. The audience will learn how developments in these areas have added new capabilities for pattern recognition and predictive modeling that are complementary to more traditional modeling approaches used in energy systems research. The speakers will illustrate several use cases of these new approaches in the energy space, such as physics-guided neural networks to improve ML regressions for solar data and how AI agents can be used to explore power plant operations.

40 EE - Geothermal Technologies Office (EE-4G)↗

A novel data-driven learning method for radar target detection in nonstationary environments

Most existing radar algorithms are developed under the assumption that the environment (clutter) is stationary. However, in practice, the characteristics of the clutter can vary enormously depending on the radar-operational scenarios. If unaccounted for, these nonstationary variabilities may drastically hinder the radar performance. Therefore, to overcome such shortcomings, we develop a data-driven method for target detection in nonstationary environments. In this method, the radar dynamically detects changes in the environment and adapts to these changes by learning the new statistical characteristics of the environment and by intelligibly updating its statistical detection algorithm. Specifically, we employ drift detection algorithms to detect changes in the environment; incremental learning, particularly learning under concept drift algorithms, to learn the new statistical characteristics of the environment from the new radar data that become available in batches over a period of time. The newly learned environment characteristics are then integrated in the detection algorithm. Furthermore, we use Monte Carlo simulations to demonstrate that the developed method provides a significant improvement in the detection performance compared with detection techniques that are not aware of the environmental changes.

47 OTHER INSTRUMENTATION↗

Commercialization of Pumped Storage Hydropower Technologies

Argonne National Laboratory and the National Laboratory of the Rockies were tasked by the U.S. Department of Energy’s Water Power Technology Office (WPTO) to conduct the Commercialization of Pumped Storage Hydropower Technologies study to investigate commercialization challenges faced by developers of pumped storage hydropower (PSH) projects and technologies by going beyond literature review to gather direct industry insights, lessons learned and best practices from interviews and webinars with industry specialists to create this report for PSH stakeholders and the general public. Researchers explored key challenges faced by PSH developers and innovators seeking to commercialize new technologies to improve PSH design, siting, construction, and operations. Along with highlighting challenges, the study sought to identify the best practices in developing and deploying new PSH projects and innovations. This report is designed to present insights, lessons learned, and best practices relevant to those with an interest in highlighting, informing, or advancing these PSH commercialization efforts. Along with highlighting challenges and best practices, the study sought to identify avenues by which DOE and national laboratories can help support and streamline PSH commercialization and project development processes.

13 HYDRO ENERGY↗

The Direct Path To WIPP - 12471

Sandia National Laboratories/New Mexico (SNL/NM), designated as a small quantity site (SQS) by the National TRU Program (NTP), generated contact-handled (CH) and remote-handled (RH) transuranic (TRU) waste primarily from the decontamination and clean-out of glove boxes at the Hot Cell Facility (HCF) at Technical Area (TA) V. All of the waste required repackaging, with the CH TRU waste being repackaged from late 2007 through 2011. Three shipments of CH were completed in October 2011, which de-inventoried SNL/NM's legacy TRU waste. In FY11, RH TRU waste was repackaged at the Auxiliary Hot Cell Facility (AHCF) located in TAV with the support of the Central Characterization Project (CCP). The waste was originally packaged in SNL/NM fabricated casks, cement or lead-lined 55-gallon drums, or 30-gallon drums. The AHCF is a small hot cell, with access only through a roof port which presented challenges for inserting and removing waste from the hot cell. The CCP provided visual examination operators (VEOs) to observe and document each waste item repackaged, removal of prohibited items, and radiological sampling. Dose-to-Curie measurements were calculated by CCP after a radiological report was prepared using scaling factors determined by the analysis of swipe samples. Finally, headspace gas samples were taken and sent to the Advanced Mixed Waste Treatment Project (AMWTP) for analysis. Despite the challenges, the RH waste is on track to be shipped to WIPP in early FY12. The processes used and procedures developed to conduct the repackaging operations, the issues identified and mitigated were challenging but the cooperation between SNL/NM and the Central Characterization Program (CCP) enabled SNL/NM to complete the repackaging and support the characterization and shipment. An inventory list, identification of the campaigns, discussion of the challenges and mitigations, and the final loading of the RH 72-B casks at TA-V for direct shipment to the Waste Isolation Pilot Plant (WIPP) will be discussed. Lessons learned from the RH campaigns are: - Some containers that were originally identified as HC-3 have been re-evaluated and became < HC-3 due to the conservative estimates made by the original generators - Operators at the AHCF were not accustomed to the detail required by the VE operators. However, they worked well together and the repackaging was completed ahead of schedule. - The AK was not always accurate as was demonstrated by the solid waste found in the drum during the first visit by EPA. That waste has since been determined to be low-level. - Two drums originally thought to be RH turned out to be CH and arrangement for RTR had to be made quickly. - Six of the original RH repacked drums became low level. - Lessons learned from the CH campaigns were helpful in avoiding many issues. The RH repackaging effort has been a success due to the expertise of the AHCF operators, supervisor, and manager, the conscientious attention to detail of the CCP VE operators, the experience of the CCP DTC and headspace gas sampling staff, and the guidance and support from CCP and CBFO. Sometimes schedules had to be adjusted, processes updated, and issues discussed, but the communication between CCP and SNL/NM was good. SNL/NM hopes to have the legacy RH TRU waste shipped off-site by early 2012. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Deep Learning for Automated Identification of Eels in Sonar Data

Freshwater eels, such as the American eel (Anguilla rostrata) present numerous challenges related to safe downstream fish passage at hydroelectric facilities. One of those challenges is effective monitoring of their abundance, movements, and behavior to facilitate design and operation of eel protection and passage facilities. A previous EPRI study documented the ability of human analysts to reliably identify American eels in data obtained with a 1100/1800 kHz, multibeam sonar. This report describes a project to develop deep learning (a subset of artificial intelligence) tools to automate the time-consuming, subjective process of eel identification in multibeam sonar data. The project exploited new data collected in the laboratory and the existing data from the prior EPRI field study to develop and test deep learning and other data analytic tools, including wavelet filtering, differencing for static object removal, and convolutional neural network analysis. The analysis of the laboratory data demonstrated feasibility of the approach, revealed object characteristics observed with the sonar that distinguish eels from similarly sized and shaped acoustic targets, and provided additional data for algorithm selection and training. Deep learning algorithms trained and tested on the laboratory data alone achieved accuracy rates of greater than 98% when classifying acoustic images of eels and similar-sized neutrally buoyant sticks. The algorithm trained and tested on the pre-existing field data alone, and yielded classification accuracy of 9.3% false positives and 13.3% false negatives when distinguishing between eels and sticks/PVC pipes based on video clips (i.e., multiple, consecutive images). This performance is comparable to the classification accuracy achieved by human analysts in the prior study. The deep learning algorithm trained on a combination of video clips obtained in the laboratory and the field and tested on video clips from the field, was able to distinguish eels from sticks and PVC pipes (a river debris analog) of similar size with 100% accuracy. Outreach to the hardware, software, and end-user communities early in the project helped to identify needs and specify the application space. Outreach to those communities at the end of the project communicated project results and opportunities for further development. The project achieved proof of concept for automated identification of eel in multibeam sonar data. Future work should focus on acquisition of additional data for more robust algorithm training and testing; modification of the software tools to accommodate multiple acoustic targets in the acoustic field at a given time; identification of additional object classes; incorporation of motion in the object identification and classification algorithms; operationalizing the software tools, including integration with other existing sonar data analysis tools; and partnering with hardware and software providers for distribution of the software tools with their commercial products.

13 HYDRO ENERGY↗

Safe Reinforcement Learning for Emergency Load Shedding of Power Systems

The paradigm shift in the electric power grid necessitates a revisit of existing control methods to ensure the grid’s security and resilience. In particular, the increased uncertainties and rapidly changing operational conditions in power systems have revealed outstanding issues in terms of either speed, adaptiveness, or scalability of the existing control methods for power systems. On the other hand, the availability of massive real-time data can provide a clearer picture of what is happening in the grid. Recently, deep reinforcement learning (RL) has been regarded and adopted as a promising approach leveraging massive data for fast and adaptive grid control. However, like most existing machine learning (ML)- based control techniques, RL control usually cannot guarantee the safety of the power systems. In this paper, we introduce a novel method for safe RL-based load shedding of power systems that can enhance the safe voltage recovery of the electric power grid after experiencing faults. Numerical simulation on the IEEE 39-bus testcase is performed to demonstrate the effectiveness of the proposed safe RL emergency control, as well as its adaptive capability to faults not seen in the training.

reinforcement learning, emergency control, power g↗

Nested active learning for efficient model contextualization and parameterization: pathway to generating simulated populations using multi-scale computational models

There is increasing interest in the use of mechanism-based multi-scale computational models (such as agent-based models (ABMs)) to generate simulated clinical populations in order to discover and evaluate potential diagnostic and therapeutic modalities. The description of the environment in which a biomedical simulation operates (model context) and parameterization of internal model rules (model content) requires the optimization of a large number of free parameters. In this work, we utilize a nested active learning (AL) workflow to efficiently parameterize and contextualize an ABM of systemic inflammation used to examine sepsis. Contextual parameter space was examined using four parameters external to the model’s rule set. The model’s internal parameterization, which represents gene expression and associated cellular behaviors, was explored through the augmentation or inhibition of signaling pathways for 12 signaling mediators associated with inflammation and wound healing. We have implemented a nested AL approach in which the clinically relevant (CR) model environment space for a given internal model parameterization is mapped using a small Artificial Neural Network (ANN). The outer AL level workflow is a larger ANN that uses AL to efficiently regress the volume and centroid location of the CR space given by a single internal parameterization. We have reduced the number of simulations required to efficiently map the CR parameter space of this model by approximately 99%. In addition, we have shown that more complex models with a larger number of variables may expect further improvements in efficiency.

97 MATHEMATICS AND COMPUTING↗

Creating a Simulation Platform for Research and Development of Advanced Control Methods

Advanced nuclear reactors are essential to meet the changing energy requirements throughout both the United States and the rest of world. In addition to other features, they are designed to enable deployment in remote locations and operate in a fully (or near-fully) autonomous manner, which will require a new control paradigm. To realize autonomously operating reactors, the U.S. Department of Energy’s Nuclear Energy Enabling Technologies Advanced Sensors and Instrumentation (NEET ASI) program conducts research and development into the enabling technologies and methods needed, including digital twins, machine learning, and risk modeling, in addition to various types of control methods. These technologies and methods are the key foundations needed to achieve fully autonomous systems. To develop and evaluate the technologies and methods necessary for achieving autonomous operations, it is critical to identify a software tool capable of integrating all the required elements. In surveying the available solutions, no software platforms were identified that could accomplish what was needed without introducing drawbacks. This challenge was the motivation for the current effort: to develop a software platform that can seamlessly integrate autonomouscontrol-enabling technologies and methods, allowing for accelerated research and development and transfer of ideas. The resulting platform, known as the Control and Optimization Modular Modeling Application for Nuclear Deployment (COMMAND), is Python-based, and leverages open-source tools to provide flexibility and facilitate building upon prior research. It is designed to enable advanced reactor developers to deploy and test advanced control technologies and methods coupled with their own models, solutions, and hardware. Given the substantial undertaking of developing such a platform, the current effort focused on laying down scalable, flexible software foundations and infrastructure, then demonstrating the platform via a use case. These foundations included developing generic modules, which contain the base variable and system blocks (the information and functional building blocks, respectively, that can be used to design a simulation) and the data handling and storage blocks needed to exchange information between the various blocks; as well as enablingtechnology-specific modules. This platform was evaluated via a use case, which was to simulate and control a process for the Microreactor Automated Control System (MACS) test bed. While MACS is not currently directly coupled to any specific microreactor physics, it was initially developed in concert with the Microreactor Applications Research Validation and Evaluation (MARVEL) microreactor, and so the MARVEL physics are used here. As part of this use case, several enabling-technology-specific blocks within COMMAND were integrated, including a proportional integral derivative (PID) control block, a Reactor Excursion and Leak Analysis Program (RELAP5-3D) block, and an anomaly detection block. The COMMAND software platform was successfully demonstrated to achieve the scalability and flexibility objectives of this effort and will be leveraged by the program’s research efforts to advance state of the art control methodologies towards autonomous operations of advanced reactors. As new use cases are created and implemented, it is anticipated that COMMAND will continue to grow and evolve to meet new requirements.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Assessing wind power operating costs in the United States: Results from a survey of wind industry experts

This paper draws on a survey of wind industry professionals to clarify trends in the operational expenditures (OpEx) of U.S. land-based wind power plants. We find that average all-in lifetime OpEx has declined from approximately $80/kW-yr (~$35/MWh) for projects built in the late 1990s to a level approaching $40/kW-yr (~$11/MWh) for projects built in 2018. Turbine operations and maintenance costs represent the single largest component of overall OpEx and the primary source of cost reductions. We observe wide ranges of OpEx over time; respondents cite a range in average expected costs for recently commissioned projects from $33/kW-yr to $59/kW-yr. We also use historical OpEx learning rates, showing a 9% OpEx reduction for each doubling of global wind capacity, to project a further $5-$8/kW-yr reduction from 2018 to 2040. These findings suggest that continued OpEx reductions may contribute 10% or more of the expected reductions in land-based wind's levelized cost of energy. Moreover, these estimates understate the importance of OpEx owing to the multiplicative effects through which operational advancements influence not only operations and maintenance costs but also component reliability, performance, and plant-level availability - thereby also affecting levelized costs by enhancing annual energy production and plant lifetimes. Given the limited quantity and comparability of previously available OpEx data, the trends reported here may inform OpEx assumptions used by electric planners, analysts, and modelers. The results may also provide useful benchmarks to the wind industry, helping developers and asset owners compare their expectations with historical experience and other industry projections.

17 WIND ENERGY↗

SPIDARman: System-Level Physics-Informed Detection of Anomalies in Reactor Collected Data Considering Human Errors

In nuclear power plants (NPPs), anomalies arising from sensors or human errors (HEs) can undermine the performance and reliability of plant operations. Anomaly detection models can be employed to detect sensor errors and HEs. Additionally, physics-informed machine learning models can utilize the known physics of the system, as described by mathematical equations, to ensure that sensor values are consistent with physical laws. Hence, we propose SPIDARman: System-level Physics-Informed Detection of Anomalies in Reactor Collected Data Considering Human Errors, a holistic physics-informed anomaly detection approach based on generative adversarial networks (GANs) to detect anomalies in both automatically collected sensor data and manually collected surveillance data. Here we test our approach on data collected from a flow loop testbed, showcasing its potential to detect anomalies. Results demonstrate that the proposed model performs better than the baseline GAN-based models in detecting sensor and surveillance anomalies, suggesting the potential of physics-informed anomaly detection GAN models in NPPs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Enhanced plasma performance in C-2W advanced beam-driven field-reversed configuration experiments

TAE Technologies’ fifth-generation fusion device, C-2W (also called ‘Norman’), is the world’s largest compact-toroid device and has made significant progress in field-reversed configuration (FRC) plasma performance. C-2W produces record breaking, macroscopically stable, high-temperature advanced beam-driven FRC plasmas, dominated by injected fast particles and sustained in steady state, which is primarily limited by neutral-beam (NB) pulse duration. The NB power supply system has recently been upgraded to extend the pulse length from 30 ms to 40 ms, which allows for a longer plasma lifetime and thus better characterization and further enhancement of FRC performance. An active plasma control system is routinely used in C-2W to produce consistent FRC performance as well as for reliable machine operations using magnet coils, edge-biasing electrodes, gas injection and tunable-energy NBs. Google’s machine learning framework for experimental optimization has also been routinely used to enhance plasma performance. D

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

A Generalized Bio-inspired Method for Discovering Sequence-based Signatures

Many phenomena that we wish to discover are comprised of sequences of events or event primitives. Often signatures are constructed to identify such phenomena using either distributions or frequencies of attributes, or specific subsequences that are known to correlate to the phenomena. Distribution-based identification does not capture the essence of the sequence of behaviors and therefore may suffer from lack of specificity. At the other extreme, using specific subsequences to identify target phenomena is often too specific and suffers from lower sensitivity when natural variations arise in the phenomena, measuring process, or data analysis. We introduce here a method for discovering signatures for phenomena that are well characterized by sequences of event primitives. In this paper, we describe the steps taken and lessons learned in generalizing a sequence analysis method, BLAST, for use on non-biological datasets including expressing and operating on alphabets of varying length, constructing a reward/penalty model for arbitrary datasets, and discovering low complexity segments in sequence data by extending BLAST’s native low-complexity estimating algorithms. We also present several case studies that demonstrate the utility of this method to discovering signatures in a wide array of applications including network traffic, software analysis, server characterization, and others. Finally, we demonstrate how signatures discovered using this method can be expressed using a variety of model formalisms, each having its own relative benefit.

Signature Science↗

Agent-Based System for Transactive Control of Smart Residential Neighborhoods

Buildings consume 74% of the total electricity produced in the United States. A significant portion of the building electric load includes heating ventilation and air-conditioning (HVAC) systems and water heating (WH) systems. Enabling flexibility in the operations can improve overall electric grid efficiency. This paper describes a multi-agent system for supporting integration, learning, optimization, and control of HVAC and WH in supporting a future smart grid. The architecture supports a transactive-based negotiation strategy between homeowners and a microgrid controller to adjust consumption behavior and reduce electricity costs. The framework is deployed in a neighborhood and preliminary testing is underway. The agent architecture design is discussed along with the preliminary optimization results from the demonstration site.

Starke, Michael↗

Non-Intrusive Appliance Identification with Appliance-Specific Networks

The problem of noninstrusive load monitoring (NILM) is usually formulated as a single-channel blind source separation task, whose successful solution enable fast and convenient load identification and energy disaggregation. When applied at test time, NILM algorithms aim to identify the operating characteristics of individual appliances from an aggregate power measurement of the entire house. Recent advances in deep learning gave rise to many methods that mostly focus on learning a direct mapping from aggregate measurement to individual appliance power. However, these methods are not only computationally expensive, but they often suffer from overfitting and do not generalize very well. In this article, we propose a novel NILM method that leverages advances in statistical learning that have not been properly applied in this domain before. The proposed method consists of three stages: first, a Bayesian nonparametric learning-based approach for appliance state extraction; second, synthetic minority oversampling technique for data augmentation and mitigating the heavy imbalance in switching events; and third, appliance-specific lightweight long short-term memory networks for status classification for each appliance. Here, we adopt a “differential” input (the difference before and after the switching event) to reduce the complexity of network training and make the proposed method robust to multiappliance switching events. Experiments are conducted to demonstrate the effectiveness of the proposed method, achieving superior performance when compared to recent methods. An ablation study is conducted to demonstrate the effectiveness of each module of our method. Finally, we investigate the quality of generated synthetic samples.

42 ENGINEERING↗

Training data selection for event classification in a highly variable environment

A problem of interest for nuclear nonproliferation is monitoring activities at nuclear facilities, where proliferation events may only take place a few times and often under variable conditions. Machine learning has revolutionized data analytics by enabling the use of measurable signatures to generate predictive models of facility operations. However, traditional methods for training these models require large, reliable data sets with labeled observations, a challenge for nonproliferation. Highly variable conditions further complicate this as events from training data may have occurred in conditions quite different from the event of interest. Our hypothesis is that when events occur in a highly variable environment, careful training data selection for each test event could outperform the standard approach of using all available training data. We developed a method to optimize training data selection for the given test event and applied it to predicting the power level of the High Flux Isotope Reactor (HFIR) at Oak Ridge National Laboratory. In this study, the reactor startup exhibits variability between occurrences due to natural variability in environmental conditions and operational procedures. Using a combination of analysis techniques, a similitude assessment was performed on data collected from HFIR to isolate clusters that were optimal for training a predictive model. Concepts such as dynamic time warping and Jaccard similarity were used in conjunction with clustering analysis. In order to validate this approach, the model was trained on every combination of unique training events and the predictive performance was compared to the performance using a subset of the training data selected by isolated clusters found through the similitude assessment.

Iyer, A↗