Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Operator inference”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

A simplified approach for creep damage and remaining life calculation for materials surveillance in advanced reactors

High temperature reactor materials will experience a combination of mechanical degradation caused by creep and fatigue and environmental degradation caused by neutron irradiation and, in some cases, exposure to corrosive coolants. A materials surveillance program is one option for ensuring the safe, reliable operation of key reactor components under these conditions. Such a program would monitor the degradation in key material properties over time, using this data to predict how changes in the material properties affect components performance. This could then be used to make plant operational decisions and support eventual plant license extensions. Past work de-scribes such a material surveillance program based on passively actuated mechanical test articles that impose creep-fatigue type loading on test materials driven only by changes in temperature, for example those experienced by components under standard operating cycles. This report focuses on two aspects of the proposed material surveillance program: how to design the test articles to mimic the mechanical response of the corresponding component and how to use ex-situ test data to deter-mine the amount of damaged experienced by the test article (and hence the corresponding compo-nent) in service. Specifically, this report derives and validated simplified methods for both tasks, replacing earlier, more complicated approaches based on simulating the test article response and finding the best specimen design or current damage via complex numerical optimization. The sim-plified methods for each task developed here can be implemented in spreadsheet software and are simple enough for practical use in future operating plants. This report derives the methods (one for sizing and two options for damage inference), verifies the simplified approaches versus more so-phisticated methods, and compares the results of applying the simplified methods to previous re-sults using the complex numerical optimization approach. The report also provides a worked sam-pled problem applying the simplified techniques to a realistic high temperature reactor component.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Karhunen–Loève deep learning method for surrogate modeling and approximate Bayesian parameter estimation

We evaluate the performance of the Karhunen-Loève Deep Neural Network (KL-DNN) framework for surrogate modeling and approximate Bayesian parameter estimation in partial differential equation models. In the surrogate model, the Karhunen-Loève (KL) expansions are used for the dimensionality reduction of the number of unknown parameters and variables, and a deep neural network is employed to relate the reduced space of parameters to that of the state variables. The KL-DNN surrogate model is used to formulate a maximum-a-posteriori-like least-squares problem, which is randomized to draw samples of the posterior distribution of the parameters. We test the proposed framework for a hypothetical unconfined aquifer via comparison with the forward MODFLOW and inverse PEST++ iterative ensemble smoother (IES) solutions as well as the state-of-the-art Fourier neural operator (FNO) and deep operator networks (DeepONets) operator learning surrogate models. Our results show that the KL-DNN surrogate model outperforms FNO and DeepONet for forward predictions. For solving inverse problems, the randomized algorithm provides the same or more accurate Bayesian predictions of the parameters than IES as evidenced by the higher log-predictive probability of both the estimated parameter field and the forecast hydraulic head. The posterior mean obtained from the randomized algorithm is closer to the reference parameter field than that obtained with FNO as the maximum a posteriori estimate.

Approximate Bayesian inference↗
DOE OSTI2022

Improvement of two-phase closure models in CTF using Bayesian inference

Under the Consortium for Advanced Simulation of Light Water Reactors (CASL) program, extensive capabilities have been developed in CTF to analyze light-water reactors (LWRs) for normal operating conditions, departure from nucleate boiling (DNB), and system transients. However, further improvements are required in the modeling and simulation of boiling water reactors (BWRs), which is a focus of the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program. In this work, CTF validation results were used to optimize selected modeling coefficients by calibrating to experimental data using a Bayesian inference approach. Here, calibration studies were conducted to improve (vapor) void fraction prediction without worsening the two-phase pressure drop prediction, as well as to improve the two-phase pressure drop prediction. Calibration was performed for interfacial drag and wall shear models. Surrogates were developed to alleviate the computational expense required for sampling the parameter space using Markov chain Monte Carlo (MCMC). An assessment performed with calibrated models demonstrated an improvement of CTF in its prediction of key parameters such as void fraction and two-phase pressure drop.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Developing an Evolutionary Baseline Model for Humans: Jointly Inferring Purifying Selection with Population History

Building evolutionarily appropriate baseline models for natural populations is not only important for answering fundamental questions in population genetics—including quantifying the relative contributions of adaptive versus nonadaptive processes—but also essential for identifying candidate loci experiencing relatively rare and episodic forms of selection (e.g., positive or balancing selection). Here, a baseline model was developed for a human population of West African ancestry, the Yoruba, comprising processes constantly operating on the genome (i.e., purifying and background selection, population size changes, recombination rate heterogeneity, and gene conversion). Specifically, to perform joint inference of selective effects with demography, an approximate Bayesian approach was employed that utilizes the decay of background selection effects around functional elements, taking into account genomic architecture. This approach inferred a recent 6-fold population growth together with a distribution of fitness effects that is skewed towards effectively neutral mutations. Importantly, these results further suggest that, although strong and/or frequent recurrent positive selection is inconsistent with observed data, weak to moderate positive selection is consistent but unidentifiable if rare.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Nuclear activation analysis of zirconium-90 isomeric and ground-state reactions at the OMEGA Laser Facility

Nuclear activation is a well-established technique for inferring neutron yields in laser direct-drive deuterium–tritium (DT) and deuterium–deuterium (D 2 ) implosions at the OMEGA Laser Facility. Zirconium has long been considered an excellent candidate for measuring DT neutron fusion yields by observing decays of the 90 Zr(n,2n) 89 Zr ground-state reaction. As it has a higher energy threshold than present activation detectors utilizing copper, zirconium provides a means to infer primary neutron yields that are less susceptible to being skewed due to neutron scattering within the experimental environment. However, with a 78.41-h half-life, it is not operationally practical to utilize this reaction for OMEGA experiments, which have a 1-h shot cycle. Zirconium’s 90 Zr(n,2n) 89 mZr reaction presents itself as a viable candidate to infer neutron yields within a shot cycle, given its half-life of 4.16 min. Here, we present an overview of the approach and methodology, utilizing first principles techniques, to infer the primary neutron yields from OMEGA DT fusion experiments by using both the isomeric and the ground-state reaction. Yields inferred from both reactions are compared, which are in good agreement between the two.

Activation analysis↗
DOE OSTI2022

Human reliability analysis studies from simulator experiments using Bayesian inference

Probabilistic Safety Assessment (PSA) of complex facilities is performed to arrive at the risk posed by them. PSA also accounts for the contribution of the human errors towards the overall risk through Human Reliability Analysis (HRA) in terms of Human Error Probability (HEP). Human operators are part of the system and do not work in isolation. Their performance is influenced by the context in which the actions are performed. As a result, quantification of HEP requires operator performance data under the given context. Some good sources of operator performance data are plant‘s operation data, simulator data and expert judgement. The plant operation data pertaining to HRA is generally sparse. In this situation, a full scope plant simulator provides a good alternative for operator performance data generation. Many of the currently practiced HRA methods have been developed by combining the empirical evidence with expert judgement and contain a lot of uncertainty in their estimates. Bayesian inference is suitable for updating the prior HRA estimates with the simulator evidence to obtain the posterior HEP. Here, posterior HEP has been calculated for postulated accident scenarios in advanced reactor (first of its kind) at design stage, using plant simulator.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Cognitive IoT and Edge Computing for Intrusion Detection with Federated TinyML

Internet of Things (IoT) and Edge Computing (EC) are rapidly becoming an integral part of the modern society. By 2030, there is estimated to be over 40 billion active and connected IoT devices [1]. This rapid progress also comes with a significant implication on cybersecurity. Back-end infrastructure and systems have a much broader attack than they did previously due to vulnerable IoT/EC devices being connected to wireless networks. This expanding attack surface is a growing concern because IoT/EC are increasingly being used in critical systems such as power grids, health care, and smart homes. To effectively address a problem of this scale, cognitive cyber methods—which can autonomously detect and react to cyber attacks as they develop—are needed. To address this, we bring Artificial Intelligence (AI) and Machine Learning (ML) to IoT/EC devices, using tinyML to monitor voluminous IoT data against cyber threats, and using Federated Learning (FL) to share local detection knowledge across the system while preserving privacy. We propose a novel three-layer architecture: (1) an IoT layer for tinyML-based inference, (2) an edge layer for ML model training, and (3) a cloud layer for FL operations. Using the publicly available 11-class N-BaIoT dataset [2], we demonstrate that this architecture mitigates resource constraints at the IoT layer while improving detection accuracy over standard two-layer designs. An outlier-resistant scaler, feature reduction, and quantization enable the tinyML model to maintain detection accuracy with a reduced model size. Additionally, federated learning that only utilizes the intersection (across heterogenous devices) of the reduced feature set achieves superior detection accuracy compared to locally trained models.

Li, Mingyan [ORNL] (ORCID:0009000569532640)↗
DOE OSTI2023

A GPU-Accelerated Population Generation, Sorting, and Mutation Kernel for an Optimization-Based Causal Inference Model

We develop a GPU-accelerated machine learning generative adversarial network model that can be used with observational data for the purpose of constructing causal inferences. The theoretical basis of our machine learning model is novel and is conceptualized to be operable and scalable for high performance computing platforms. Our GPU-accelerated code enables large-scale parallelization of the computation within a common and accessible computing environment. This will expand the reach of our model and empower research in new substantive domains while maintaining the underlying theoretical properties.

Cho, Wendy K. Tam↗
DOE OSTI2024

Approach for Inferring Full-Scope Human Reliability Data Based on Simplified Simulator Data

This paper proposes a method for inferring full-scope human reliability data based on the Simplified Human Error Experimental Program (SHEEP) data. It mainly focuses on the human errors observed when using simulators with different complexity levels. In the proposed method, the manner in which human error probabilities (HEPs) change as a result of increasing simulator complexity and how simulator complexity levels are quantified represent key information for inferring full-scope data. In the present study, SHEEP error data pertaining to actual professional operators using Rancor Microworld (Rancor) (i.e., a more simplified simulator) and Compact Nuclear Simulator (CNS) (i.e., a less simplified simulator) were compared with the HuREX error data. An approach to quantifying simulator complexity levels was then proposed based on information theory and acquired eye-tracker data.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

Grandparent Inference from Genetic Data: The Potential for Parentage-Based Tagging Programs to Identify Offspring of Hatchery Strays

Abstract Fisheries managers routinely use hatcheries to increase angling opportunity. Many hatcheries operate as segregated programs where hatchery-origin fish are not intended to spawn with natural-origin conspecifics in order to prevent potential negative effects on the natural-origin population. Currently available techniques to monitor the frequency with which hatchery-origin strays successfully spawn in the wild rely on either genetic differentiation between the hatchery- and natural-origin fish or extensive sampling of fish on the spawning grounds. We present a method to infer grandparent–grandchild trios by using only genotypes from two putative grandparents and one putative grandchild. We developed estimators of false-positive and false-negative error rates and showed that genetic panels containing 500–700 single-nucleotide polymorphisms or 200–300 microhaplotypes are expected to allow application of this technique for monitoring segregated hatchery programs. We discuss the ease with which this technique can be implemented by pre-existing parentage-based tagging programs and provide an R package that applies the method.

Delomas, Thomas A. (ORCID:000000015154759X)↗
DOE OSTI2021

Application of Sequential Design of Experiments (SDoE) to Large Pilot-Scale Solvent-Based CO2 Capture Process at Technology Centre Mongstad (TCM)

The United States Department of Energy’s Carbon Capture Simulation for Industry Impact (CCSI2) program has developed a framework for sequential design of experiments (SDoE) that aims to maximize knowledge gained from budget- and schedule-limited pilot scale testing. SDoE was applied to the planning and execution of campaigns for testing CO2 capture systems at pilot-scale in order to optimally allocate resources available for the testing. In this methodology, a stochastic process model is developed by quantifying the parametric uncertainty in submodels of interest; for a solvent-based CO2 capture system, these may include physical properties and equipment performance submodels (e.g., mass transfer, interfacial area). This uncertainty is propagated through the full process model, over variable operating conditions, for estimating the resulting uncertainty in key model outputs (e.g., percentage of CO2 capture, solvent regeneration energy requirement). In developing a data collection plan, the predicted output uncertainty is incorporated into an algorithm that seeks simultaneously to select process operating conditions for which the predicted uncertainty is relatively high and to ensure that the entire space of operation is well represented. This test plan is then used to guide operation of the pilot plant at varying steady-state conditions, with resulting process data incorporated into the existing model using Bayesian inference to refine parameter distributions. The updated stochastic model, with reduced parametric uncertainty from data collected, is then used to guide additional data collection, thus the sequential nature of the experimental design. The SDoE process was implemented at the pilot test unit (12 MWe in scale) at Norway’s Technology Centre Mongstad (TCM) in a summer 2018 test campaign with aqueous monoethanolamine (MEA). During the test campaign, the varied operating conditions included the flowrates of circulated solvent, flue gas, and reboiler steam and the CO2 concentration in the flue gas. The process data were used to update probability distributions of mass transfer and interfacial area parameters of a stochastic process model developed by the CCSI2 team. Two iterations of the SDoE process were executed, resulting in the uncertainty in model predicted CO2 capture percentage decreasing by an average of 58.0 ± 4.7% over the full input space of interest. This work demonstrates the potential of the SDoE process for model refinement through reduction in process model parametric uncertainty, and ultimately risk in scale-up, in CO2 capture technology performance.

carbon capture↗
DOE OSTI2024

Development of Whole System Digital Twins for Advanced Reactors: Leveraging Graph Neural Networks and SAM Simulations

Here, in this work, we introduce a novel method to develop whole system digital twins (DTs) for advanced nuclear reactors. This method treats a complex reactor system as a heterogeneous graph: with the system components as different types of graph nodes and their physical interconnections as edges. Based on the heterogeneous graph, a graph neural network combining graph convolution and temporal node attention is developed as the DT, facilitating a comprehensive understanding of the system's dynamic behavior. By utilizing the System Analysis Module (SAM) code for simulating various operational transients, we develop a graph-based database that trains the DT. This DT is characterized by two primary functions: It can infer the entire system's status using sparse node information, and it can predict the progress of transients based on current and historical system information. Our approach is validated through case studies on the Experimental Breeder Reactor II (EBR-II) system and a generic Fluoride-salt-cooled High-temperature Reactor (gFHR), demonstrating the DT's accuracy in forecasting operational transients. The DT's rapid computation capabilities enhance its potential for supporting advanced reactor operations, offering benefits in intelligent simulation, autonomous control, and anomaly detection, paving the way for improved safety analysis and intelligent component health management for advanced reactor systems and reducing their operations and maintenance cost.

EBR-II↗
DOE OSTI2025

A GPU‐Accelerated Generative Adversarial Model for Causal Inference

We develop a GPU-accelerated machine learning generative adversarial model designed to facilitate causal inferences from observational data. Our model's theoretical framework is conceptualized in a manner that is amenable to being operable and scalable for high-performance computing platforms. We leverage GPU acceleration to develop a parallel evolutionary algorithm to achieve large-scale parallel computation of the model within a now widely accessible computing platform. This capability both enhances computational speedup and efficiency and also extends the use of the model to a broader range of substantive research domains while maintaining the underlying theoretical properties of the model.

GPU↗
DOE OSTI2021

Binary Complex Neural Network Acceleration on FPGA

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today’s real-valued deep neural networks (DNNs) have shown efficiency in latent information analysis but fall short when applied to the complex domain. Deep complex networks (DCN) , in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision making requirements of many deployable systems dealing with short observations or short signal bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs with binarized neural networks (BNN), shows great potential in classifying complex data in real-time. In this paper, we propose a structural pruning based accelerator of BCNN, which is able to provide more than 5000 frames/s inference throughput on edge devices. The high performance comes from both the algorithm and hardware sides. On the algorithm side, we conduct structural pruning to the original BCNN models and obtain 20 × pruning rates with negligible accuracy loss; on the hardware side, we propose a novel 2D convolution operation accelerator for the binary complex neural network. Experimental results show that the proposed design works with over 90% utilization and is able to achieve the inference throughput of 5882 frames/s and 4938 frames/s for complex NIN-Net and ResNet-18 using CIFAR-10 dataset and Alveo U280 Board.

Peng, Hongwu↗
DOE OSTI2023

Tomographic optical emission spectroscopy of an atmospheric pressure plasma jet and surface ionization waves on planar and structured surfaces

Here in this paper, an approach for 3D plasma structure diagnostics using tomographic optical emission spectroscopy (Tomo-OES) of a nanosecond pulsed atmospheric pressure plasma jet (APPJ) is presented. In contrast to the well-known Abel inversion, Tomo-OES does not require cylindrical symmetry to recover 3D distributions of plasma light emission. Instead, many 2D angular projections are measured with intensified cameras and the multiplicative algebraic reconstruction technique is used to recover the 3D distribution of light emission. This approach solves the line-of-sight integration problem inherent to optical diagnostics, allowing recovery of localized OES information within the plasma that can be used to better infer plasma parameters within complex plasma structures. Here, Tomo-OES was applied to investigate an APPJ operated with helium in ambient air and impinging on planar and structured dielectric surfaces. Surface charging caused the guided streamer from the APPJ to transition to a surface ionization wave (SIW) that propagated along the surface. The SIW experienced variable geometrical and electrical material properties as it propagated, leading to 3D configurations that were non-symmetric and spatially complex. Light emission from He, N$_2^+$, and N2 were imaged at ten angular projections and the respective time-resolved 3D emission distributions in the plasma were then reconstructed. The spatial resolution of each tomographic reconstruction was 7.4 µm and the temporal resolution was 5 ns, sufficient to observe the guided streamer and the effects of the structured surface on the SIW. Emission from He showed the core of the jet and emission from N$_2^+$ and N2 indicated effects of entrainment of ambient air. Penning ionization of N2 created a ring or outer layer of N$_2^+$ that spatially converged to form the 'plasma bullet' or spatially diverged across a surface as part of a SIW. The SIW entered trenches of size 150 µm, leading to decreases in plasma light emission in regions above the trenches. The plasma light emission was higher in some regions with trenches, possibly due to effects of field enhancement.

plasma interactions with complex surfaces↗
DOE OSTI2022

Design-Technology Co-Optimization for NVM-based Neuromorphic Processing Elements

An emerging use-case of machine learning (ML) is to train a model on a high-performance system and deploy the trained model on energy-constrained embedded systems. Neuromorphic hardware platforms, which operate on principles of the biological brain, can significantly lower the energy overhead of a machine learning inference task, making these platforms an attractive solution for embedded ML systems. In this paper, we present a design-technology tradeoff analysis to implement such inference tasks on the processing elements (PEs) of a Non-Volatile Memory (NVM)-based neuromorphic hardware. Through detailed circuit-level simulations at scaled process technology nodes, we show the negative impact of technology scaling on the information-processing latency, which impacts the quality-of-service (QoS) of an embedded ML system. At a finer granularity, the latency inside a PE depends on 1) the delay introduced by parasitic components on its current paths, and 2) the varying delay to sense different resistance states of its NVM cells. Based on these two observations, we make the following three contributions. First, on the technology front, we propose an optimization scheme where the NVM resistance state that takes the longest time to sense is set on current paths having the least delay, and vice versa, reducing the average PE latency, which improves the QoS. Second, on the architecture front, we introduce isolation transistors within each PE to partition it into regions that can be individually power-gated, reducing both latency and energy. Finally, on the system-software front, we propose a mechanism to leverage the proposed technological and architectural enhancements when implementing a machine-learning inference task on neuromorphic PEs of the hardware. Evaluations with a recent neuromorphic hardware architecture show that our proposed design-technology co-optimization approach improves both performance and energy efficiency of machine-learning inference tasks without incurring high cost-per-bit.

42 ENGINEERING↗
DOE OSTI2026

WellPINN: Accurate Well Representation for Transient Fluid Pressure Diffusion in Subsurface Reservoirs With Physics‐Informed Neural Networks

Accurate representation of pumping wells is essential for reliable reservoir characterization and simulation of operational scenarios in subsurface flow models. Physics-informed neural networks (PINNs) are emerging as a promising alternative to numerical models for reservoir modeling, offering seamless integration of monitoring data and governing physical equations. However, existing PINN-based studies face major challenges in capturing fluid pressure near wells when using a source/sink term, particularly during the early stages after pumping begins. We address this problem by introducing WellPINN, a workflow in which an initially trained PINN infers fluid pressure across the entire reservoir domain using a large equivalent well radius. This initial PINN solution is then locally refined around the well by a set of subdomain PINNs that are trained for smaller equivalent well radii. Continuity across these subdomain interfaces as well as at the initial condition is ensured by hard-constraining each PINN on its subdomain boundary. Our results demonstrate WellPINN as the first workflow of its kind to focus on accurate inference of fluid pressure from pumping rates throughout the entire injection period, significantly advancing the potential of PINNs for inverse modeling and operational scenario simulations. All data and code for this paper are openly available at https://doi.org/10.20350/DIGITALCSIC/17260.

58 GEOSCIENCES↗
DOE OSTI2023

Empirical radius formulas for canonical neutron stars from bidirectionally selecting features of equations of state in extended Bayesian analyses of observational data

Significant advancement in Bayesian inference of nuclear equation of state (EOS) from gravitational wave and x-ray observations of neutron stars (NSs) has been made by the nuclear astrophysics community especially since GW170817. By extending the traditional Bayesian analysis which normally ends at presenting the marginalized posterior probability distribution functions (PDFs) of individual EOS parameters and their correlations (or sometimes only the Pearson correlation coefficients which are only reliably useful when the variables are linearly correlated while they are actually often not), we search for a data-driven and robust empirical formula for the radius 𝑅 1.4 of canonical NSs in terms of the characteristic EOS parameters (features). We also identify the single most important but currently poorly known EOS parameter for determining the 𝑅 1.4 . Using three regression-model-building methodologies: bidirectional stepwise feature selection, least absolute shrinkage selection operator (LASSO) regression, and neural network regression on a large set of posterior EOSs and the corresponding 𝑅 1.4 values inferred from earlier comprehensive Bayesian analyses of NS observational data, we systematically and rigorously develop the most probable 𝑅 1.4 formulas with varying statistical accuracy and technical complexity. Here, the most important EOS parameters for determining 𝑅 1.4 are found consistently in each of the feature selection processes to be (in order of decreasing importance): curvature 𝐾 sym , slope 𝐿, skewness 𝐽 sym of nuclear symmetry energy, skewness 𝐽 0 , incompressibility 𝐾 0 of symmetric nuclear matter, and the magnitude 𝐸 sym ⁡(𝜌 0 ) of symmetry energy at the saturation density 𝜌 0 of nuclear matter.

Bayesian methods↗