Search NASA⌕ Search

SEARCH · Search NASA

Results for “operator training”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness

In this article, full waveform inversion (FWI) infers the subsurface structure information from seismic waveform data by solving a non-convex optimization problem. Data-driven FWI has been increasingly studied with various neural network architectures to improve accuracy and computational efficiency. Nevertheless, the applicability of pre-trained neural networks is severely restricted by potential discrepancies between the source function used in the field survey and the one utilized during training. Here, we develop a Fourier-enhanced deep operator network (Fourier-DeepONet) for FWI with the generalization of seismic sources, including the frequencies and locations of sources. Specifically, we employ the Fourier neural operator as the decoder of DeepONet, and we utilize source parameters as one input of Fourier-DeepONet, facilitating the resolution of FWI with variable sources. To test Fourier-DeepONet, we develop three new and realistic FWI benchmark datasets (FWI-F, FWI-L, and FWI-FL) with varying source frequencies, locations, or both. Our experiments demonstrate that compared with existing data-driven FWI methods, Fourier-DeepONet obtains more accurate predictions of subsurface structures in a wide range of source parameters. Moreover, the proposed Fourier-DeepONet exhibits superior robustness when handling data with Gaussian noise or missing traces and sources with Gaussian noise, paving the way for more reliable and accurate subsurface imaging across diverse real conditions.

42 ENGINEERING↗
DOE OSTI2022

Synthetic data generation for machine learning model training for energy theft scenarios using cosimulation

Abstract Technical and non‐technical losses in distribution circuits result in significant economic costs to power utilities. One type of non‐technical loss is energy theft by various means including illegal tapping of feeders, bypassing the meter, and billing fraud. These losses are usually hard to detect, and can remain undetected for long periods of time. Machine learning models have been proven effective in detecting these conditions, but rely on the availability of large, good‐quality training data sets. The problem is exacerbated by the imbalanced nature of data related to these conditions—energy theft, though costly, is very rare. The available data sets generally have very few samples of theft with most of the data pertaining to normal operation. Such data sets are generally not suitable to train machine learning models. In this paper, an overview of energy theft detection techniques, the challenges with their data needs, and the limitations of current techniques to bridge such data limitations is presented. A co‐simulation framework is proposed to generate reliable training data for machine learning algorithms for theft detection. An example scenario is presented and a machine learning model is built to detect certain kinds of energy theft.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Avatar Tools

Supervised machine learning is the process of using past experience to predict the future. "Ensembles" are a machine-learning meta-method that can be applied to most machine learning algorithms. Ensembles generally greatly improve accuracy, reduce or remove most of the design issues presented by machine learning, and are admirably suited to parallel and distributed computation. The Avatar Tools codes are an implementation of ensembles specifically for decision trees. Some features that distinguish Avatar Tools from other "ensembles for decision trees" codes are: (1) Does the bookkeeping necessary for out of bag (OOB) validation. (2) Can use OOB validation to automatically determine optimal ensemble size. (3) Provides an MPI-based parallel implementation, for distributed operation. (4) Provides convenient tools for cross-validation, to assess the accuracy provided by a training set. SAND2020-3858 M Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Siefert, Christopher↗
DOE OSTI2023

Effect of CLIQ on training of HL-LHC quadrupole magnets

The high-luminosity LHC upgrade requires stronger than LHC low-beta magnets to reach the luminosity goals of the project. The project is well advanced and HL-LHC quadrupole magnets are currently being commissioned in US Labs (MQXFA magnets) and CERN (MQXFB magnets). Those are the first Nb3Sn magnets to be used in any large particle accelerator. At development stages, many Nb3Sn accelerator sub-scale models showed relatively slow training and MQXFA magnets were projected to have low tens of quenches before reaching operational field. Recently it was shown that dedicated capacitor-based devices can affect Nb3Sn magnet training, and it was suggested that CLIQ, a capacitor-based device intended for quench protection, can do too. The present paper investigates effects on training induced by CLIQ, using the base fact that only half the coils in a quadrupole experience upward current modulation because of the capacitor discharge. The study encompasses all MQXFA production magnets trained at BNL to date. No other high-statistics data from identical magnets (series) with CLIQ protection exists so far. Implications and opportunities stemming from data analysis are discussed and conclusions drawn.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Beyond Price Taker: Optimizing Integrated Energy Systems Considering Market/Grid Interactions

Integrated Energy Systems (IES) combine two or more processes to increase the efficiency, flexibility of operation, and the overall reliability. However, analyzing IESs in volatile electricity markets is challenging, since the volatility in electricity prices makes the conventional levelized cost-type analysis less realistic. This work presents two approaches to address the challenge: price-taker and a surrogates-based approach for incorporating market interactions. The price-taker approach formulates a multiperiod optimization problem that takes the time-varying electricity prices into account, and solves the optimization problem to determine the optimal operational schedule that maximizes the chosen economic metric. This approach is successfully applied to investigate the performance of flexible power and hydrogen co-production systems. The market surrogates approach trains a machine learning model to predict the market behavior as a function of the characteristics of the IES. The trained surrogate model is used to optimize the design and operation of the given IES in an electricity market. This approach is demonstrated on a case study involving a nuclear power plant retrofitted with a low-temperature electrolysis unit to co-produce power and hydrogen.

beyond price taker↗
DOE OSTI2023

Anomaly Detection in Liquid Sodium Cold Trap Operation with Multisensory Data Fusion Using Long Short-Term Memory Autoencoder

Sodium-cooled fast reactors (SFR), which use high temperature fluid near ambient pressure as coolant, are one of the most promising types of GEN IV reactors. One of the unique challenges of SFR operation is purification of high temperature liquid sodium with a cold trap to prevent corrosion and obstructing small orifices. We have developed a deep learning long short-term memory (LSTM) autoencoder for continuous monitoring of a cold trap and detection of operational anomaly. Transient data were obtained from the Mechanisms Engineering Test Loop (METL) liquid sodium facility at Argonne National Laboratory. The cold trap purification at METL is monitored with 31 variables, which are sensors measuring fluid temperatures, pressures and flow rates, and controller signals. Loss-of-coolant type anomaly in the cold trap operation was generated by temporarily choking one of the blowers, which resulted in temperature and flow rate spikes. The input layer of the autoencoder consisted of all the variables involved in monitoring the cold trap. The LSTM autoencoder was trained on the data corresponding to cold trap startup and normal operation regime, with the loss function calculated as the mean absolute error (MAE). The loss during training was determined to follow log-normal density distribution. During monitoring, we investigated a performance of the LSTM autoencoder for different loss threshold values, set at a progressively increasing number of standard deviations from the mean. The anomaly signal in the data was gradually attenuated, while preserving the noise of the original time series, so that the signal-to-noise ratio (SNR) averaged across all sensors decreased below unity. Results demonstrate detection of anomalies with sensor-averaged SNR < 1.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Evaluation of Oak Ridge National Laboratory Health Physics Research Reactor Operation Data for Critical Benchmark Creation

The Oak Ridge National Laboratory (ORNL) Health Physics Research Reactor (HPRR) was a research reactor designed and built at ORNL in 1961. The critical assembly used a highly enriched uranium and molybdenum alloy as the fuel and could be operated in steady-state or burst modes. The HPRR has recently been the object of an investigation to create a criticality benchmark. Such benchmarks are very important, as they are used primarily to show the accuracy of newly developed modeling codes and to help experimental validation and reactor licensing. The evaluated experiments considered in this paper were carried out between 1974 and 1986 from various HPRR activities such as steady-state subcritical, steady-state critical, and burst prompt super-critical operations of the reactor for dosimetry, irradiation, or training purposes. By using the HPRR experimental logbook information and the as-built drawings of the critical assembly, a highly detailed model of the HPRR was created with SCALE 6.2.4/KENO-VI, and a first version of a critical benchmark of the HPRR was developed following the International Criticality Safety Benchmark Evaluation Project (ICSBEP) guidelines for thorough description and uncertainty/sensitivity quantification. Unfortunately, in most of the evaluated experiments, the obtained difference between calculated and experimental k eff is around 1,000 pcm, corresponding to a relative error of approximately 1%, beyond the quality standards of the ICSBEP recommending a relative error below 0.1%. Moreover, the derived experimental uncertainty is high, around 4% relative, mainly due to the U-Mo fuel density uncertainty, but also from numerous other factors. For these reasons, the creation of a valuable critical benchmark from HPRR operation data is thus far compromised. In this paper, the different steps of the experiments’ evaluation are summarized, and the reasons for the experimental/calculation discrepancies and potential ways to solve them are explored. This paper also aims to remind us always to exercise considerable care when performing experimental work, and to record all the data possible for potential future uses.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2025

Real-time inference and extrapolation with Time-Conditioned UNet: Applications in hypersonic flows, incompressible flows, and global temperature forecasting

Neural Operators are fast and accurate surrogates for nonlinear mappings between functional spaces within training domains. Extrapolation beyond the training domain remains a grand challenge across all application areas. We present Time-Conditioned UNet (TC-UNet) as an operator learning method to solve time-dependent PDEs continuously in time without any temporal discretization, including in extrapolation scenarios. TC-UNet incorporates the temporal evolution of the PDE into its architecture by combining a parameter conditioning approach with the attention mechanism from the Transformer architecture. After training, TC-UNet makes real-time inferences on an arbitrary temporal grid. We demonstrate its extrapolation capability on a climate problem by estimating the global temperature for several years and also for inviscid hypersonic flow around a double cone. We propose different training strategies involving temporal bundling and sub-sampling. We demonstrate performance improvements for several benchmarks, performing extrapolation for long time intervals and zero-shot super-resolution time.

Deep learning↗
DOE OSTI2024

Electromagnetic Radioisotope Separator for Methods Development, Testing, and Training

The major goal of the project is the construction and operation of an electromagnetic isotope separator. Included in that goal is the construction and installation of a high throughput surface ion source, with specific applicability to the Lanthanides. The surface ion source features a single-piece titanium crucible insert that mates with a tantalum hot surface ionizer. The titanium crucible, which does not readily activate, can be loaded with samarium and then irradiated simultaneously, greatly reducing operator dose.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2023

Global-Local Policy Search and its Application in Grid-Interactive Building Control

As the buildings sector represents over 70% of the total U.S. electricity consumption, it offers a great amount of untapped demand-side resources to tackle many critical grid-side problems and improve the overall energy system's efficiency. To help make buildings grid-interactive, this paper proposes a global-local policy search method to train a reinforcement learning (RL) based controller which optimizes building operation during both normal hours and demand response (DR) events. Experiments on a simulated five-zone commercial building demonstrate that by adding a local fine-tuning stage to the evolution strategy policy training process, the control costs can be further reduced by 7.55% in unseen testing scenarios. Baseline comparison also indicates that the learned RL controller outperforms a pragmatic linear model predictive controller (MPC), while not requiring intensive online computation.

demand response↗
DOE OSTI2024

Importance of Hands-on Training within the Nuclear Industry

Almost all work performed within the nuclear industry requires some form of training, regardless of an individual’s education. While many of the hazards that exist in nuclear operations are present in other industries (e.g., industrial safety), nuclear operations have the unique hazards of radiation and inadvertent criticality. Therefore, these topics require additional training for individuals performing hands-on work or accessing those work areas. Many methods are available to train people including lectures (either with an instructor or automated video), reading procedures/policies, hands-on demonstrations, and on-the-job training.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Efficient machine-learning model for fast assessment of elastic properties of high-entropy alloys

We combined descriptor-based analytical models for stiffness-matrix and elastic-moduli with mean-field methods to accelerate assessment of technologically useful properties of high-entropy alloys, such as strength and ductility. Model training for elastic properties uses Sure-Independence Screening (SIS) and Sparsifying Operator (SO) method yielding an optimal analytical model, constructed with meaningful atomic features to predict target properties. Computationally inexpensive analytical descriptors were trained using a database of elastic properties determined from density functional theory for binary and ternary subsets of Nb-Mo-Ta-W-V refractory alloys. The optimal Elastic-SISSO models, extracted from an exponentially large feature space, give an extremely accurate prediction of target properties, similar to or better than other models, with some verified from existing experiments. Here we also show that electronegativity variance and elastic-moduli can directly predict trends in ductility and yield strength of refractory HEAs, and reveals promising alloy concentration regions.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Building Monitoring and Energy Efficiency Training for Small and Mid-Sized Commercial Buildings in Non-Urbanized Areas of Alaska

The goal of this project was to create an effective training that increases understanding, competency and capacity in monitoring critical building data. Mentorship, verification and follow-up ensured participants now have necessary skills to install and maintain building monitoring systems. This training sought to empower building managers and maintenance staff to properly and efficiently operate their buildings for energy savings and increased lifespan of equipment. Through the project, participants’ knowledge of the building was increased through hands-on training using a familiar building environment and eliminating common barriers to effective training through peer-to peer delivery. In successful cases the host organization will save money and resources due to more efficient operation of building equipment already in place.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Measuring the electron temperature and identifying plasma detachment using machine learning and spectroscopy

A machine learning approach has been implemented to measure the electron temperature directly from the emission spectra of a tokamak plasma. This approach utilized a neural network (NN) trained on a dataset of 1865 time slices from operation of the DIII-D tokamak using extreme ultraviolet/vacuum ultraviolet emission spectroscopy matched with high-accuracy divertor Thomson scattering measurements of the electron temperature, T e . This NN is shown to be particularly good at predicting T e at low temperatures (T e < 10 eV) where the NN demonstrated a mean average error of less than 1 eV. Trained to detect plasma detachment in the tokamak divertor, a NN classifier was able to correctly identify detached states (T e < 5 eV) with a 99% accuracy (an F 1 score of 0.96) at an acquisition rate 10× faster than the Thomson scattering measurement. The performance of the model is understood by examining a set of 4800 theoretical spectra generated using collisional radiative modeling that was also used to predict the performance of a low-cost spectrometer viewing nitrogen emission in the visible wavelengths. Furthermore, these results provide a proof-of-principle that low-cost spectrometers leveraged with machine learning can be used to boost the performance of more expensive diagnostics on fusion devices and be used independently as a fast and accurate T e measurement and detachment classifier.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

D2NO: Efficient handling of heterogeneous input function spaces with distributed deep neural operators

Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems. However, challenges arise when dealing with input functions that exhibit heterogeneous properties, requiring multiple sensors to handle functions with minimal regularity. To address this issue, discretization-invariant neural operators have been used, allowing the sampling of diverse input functions with different sensor locations. However, existing frameworks still require an equal number of sensors for all functions. We propose a novel distributed approach to further relax the discretization requirements and solve the heterogeneous dataset challenges. Our method involves partitioning the input function space and processing individual input functions using independent and separate neural networks. A centralized neural network is used to handle shared information across all output functions. This distributed methodology reduces the number of gradient descent back-propagation steps, improving efficiency while maintaining accuracy. Here, we demonstrate that the corresponding neural network is a universal approximator of continuous nonlinear operators and present three numerical examples to validate its performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Commissioning, Performance, and Effect of the Quench Current-Boosting Device on a Dedicated Superconducting Magnet

Superconducting magnet training is one of the accelerator related issues attracting attention due to significant operational costs and time budget associated to it. It is especially worrisome that magnets based on the “next-generation” Nb 3 Sn technology are affected by long training. While various efforts are underway to better understand and resolve the problem a parallel path could also be investigated, a path bypassing the issue. Following the concept of fast induced over-current during magnet powering, FNAL has developed an upgradable capacitor-based device to discharge through a superconducting magnet at quench detection or operator chosen time. The 0.4 F/1 kV device has been tested on a 1-m-long dipole-coil in a “mirror” magnet configuration and conclusive results on magnet training elimination have been observed. Here in this paper we discuss the main characteristics of the device, compare simulated response and actual performance, elaborate on test drivers and outcomes. Next steps and perspectives for future use are debated.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

In recent years, advanced control strategies based on Deep Reinforcement Learning (DRL) proved to be effective in optimizing the management of integrated energy systems in buildings, reducing energy costs and improving indoor comfort conditions when compared to traditional reactive controllers. However, the scalability and implementation of DRL controllers are still limited since they require a considerable amount of time before converging to a near-optimal solution. This issue is currently addressed in literature through the offline pre-training of the DRL agent. However this solution results in two main critical issues: (1) the need to develop a building surrogate model to perform the training task, and (2) the need to perform a fine-tuning process over several training episodes to obtain a near-optimal control policy. In this context, this paper introduces an Online Transfer Learning (OTL) strategy that exploits two knowledge-sharing techniques, weight-initialization and imitation learning, to transfer a DRL control policy from a source office building to various target buildings in a simulation environment coupling EnergyPlus and Python. A DRL controller based on discrete Soft Actor–Critic (SAC) is trained on the source building to manage the operation of a cooling system consisting of a chiller and a thermal storage. Several target buildings are defined to benchmark the performance of the OTL strategy with that of a Rule-Based Controller (RBC) and two DRL-based control strategies, deployed in offline and online fashion. The strategy adopted for OTL emulates the real world implementation with a simulation process by implementing the transferred DRL agent for a single episode in the target buildings. Target buildings have the same geometrical features and are served by the same energy system as the source building, but differ in terms of weather conditions, electricity price schedules, occupancy patterns, and building envelope efficiency levels. The results show that the OTL strategy can reduce the cumulated sum of temperature violations on average by 50% and 80% respectively when compared to RBC and online DRL while enhancing the energy system operation with electricity cost savings ranging between 20% and 40%. Furthermore, the OTL agent performs slightly worse than the offline DRL controller but it does not require any modeling effort and can be implemented directly on target buildings emulating a real-world implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

PemNet: A Transfer Learning-Based Modeling Approach of High-Temperature Polymer Electrolyte Membrane Electrochemical Systems

Widespread adoption of high-temperature electrochemical systems such as polymer electrolyte membrane fuel cells (HT-PEMFCs) requires models and computational tools for accurate optimization and guiding new materials for enhancing fuel cell performance and durability. Furthermore, while robust and better suited for extrapolation, knowledge-based modeling has limitations as it is time-consuming and requires information about the system that is not always available (e.g., material properties and interfacial behavior between different materials). Data-driven modeling, on the other hand, is easier to implement but often necessitates large datasets that could be difficult to obtain. In this contribution, knowledge-based modeling and data-driven modeling are combined by implementing a few-shot learning (FSL) approach. A knowledge-based model originally developed for a HT-PEMFCs was used to generate simulated data (887,735 points) and used to pretrain a neural network source model tuned via a genetic algorithm-based AutoML. Then, experimental datasets from HT-PEMFCs with different materials and operating conditions (~50 points each) were used to train six target models via FSL. Models for the unseen data reached high accuracies in all cases (rRMSE < 10%).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗