Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “surrogates”

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 1,279 records · Page 71
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Determination of aquatic hazard concentrations for the oil spill response product class of surface washing agents using species sensitivity distributions

Surface washing agents (SWAs) are a diverse class of oil spill response products intended to facilitate removal of stranded oil from shorelines. This class of agents has high application rates relative to other categories of spill response products, but global toxicity data is generally limited to two standard test species: inland silverside and mysid shrimp. Here, in this study, we provide a framework to maximize the utility of limited toxicity data across a product class. To characterize species sensitivity to SWAs, the toxicity of three agents spanning a range of chemical and physical properties were tested in eight species. The relative sensitivity of mysids shrimp and inland silversides as surrogate test organisms was determined. Toxicity normalized species sensitivity distributions (SSDn) were used to estimate fifth centile hazard concentration (HC5) values for SWAs with limited toxicity data. Chemical toxicity distributions (CTD) of SWA HC5 values were used to compute a fifth centile chemical hazard distribution (HD5) to provide a more comprehensive assessment of hazard across a spill response product class with limited toxicity data than traditional single species or single agent approaches can give.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2025

Machine learning-enabled multiscale modeling of mechanical deformation of aluminum and Al-SiC nanocomposites

A machine learning-enabled multiscale framework is developed for modeling the mechanical response of both pure metal and nanoparticle-reinforced metal matrix nanocomposites (MMNCs). Using aluminum–silicon carbide (Al-SiC) as an example MMNC, atomistic simulations reveal three distinct deformation mechanisms (i.e., defect-free, dislocation-based, and interface separation) governed by the interfaces between the Al matrix and SiC nanoparticles. As compared with single crystal Al, the lattice undergoes a more abrupt failure once the dislocation network becomes extensive and void nucleation initiates, whereas in Al-SiC, nanoparticle interfaces enable a more gradual progression of damage. These mechanisms are captured through a combined classification-regression neural network surrogate model that bridges atomic-scale insights with continuum-scale finite element analysis. Machine learning-enabled multiscale modeling of pure Al accurately predicted strain localization and confirmed by in-situ scanning electron microscopic tensile testing on perforated Al specimens. This study underscores the promise of integrating physics-informed machine learning with hierarchical modeling to capture the interface dominated phenomena and guide the design of advanced MMNCs.

Al-SiC↗
DOE OSTI2023

Multi-objective Bayesian alloy design using multi-task Gaussian processes

In design applications, correlations among material properties (such as the tendency for stronger materials to be less ductile) are often neglected. This approach is echoed in multi-objective optimization techniques which treat each performance characteristic as an independent objective, aiming to optimize scalar functions and find optimal Pareto fronts. However, this overlooks the statistical relationships between performance characteristics inherent in a material system. To address this, we propose the use of Bayesian optimization, a highly efficient black-box optimization algorithm known for constructing Gaussian processes (GPs) – uncorrelated surrogates - to model objective functions. Rather than evaluating multiple GPs for each objective function separately, we argue for a shift towards jointly modeling these objective functions, considering their statistical correlations. This integrated approach utilizes naturally occurring relationships among material properties, providing additional information to enhance the performance of the design framework. This requires the replacement of multiple independent GPs with a single multi-task GP, employing a correlation matrix to construct a multi-task kernel function, wherein each task corresponds to a single objective function. Here, we anticipate this refined methodology will better leverage material correlations, improving design optimization results.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Process window estimation in manufacturing through Entropy-Sigma active learning

In manufacturing, there exist boundary identification problems for defining parameter spaces that meet desired thresholds on outcomes. This paper presents an Entropy-Sigma acquisition function for active learning of the process window/map in manufacturing using a Gaussian Process surrogate. Here, the method is applied to identify the stability boundary for the stability process map in machining using time-domain simulations with a periodic sampling stability metric. Results show that the proposed Entropy-Sigma method significantly outperforms Latin hypercube sampling or grid-based methods. The described method can be applied to identify the process window/map for any manufacturing application using a quantitative process outcome metric.

42 ENGINEERING↗
DOE OSTI2020

Polymer informatics: Current status and critical next steps

Artificial intelligence (AI) based approaches are beginning to impact several domains of human life, science and technology. Polymer informatics is one such domain where AI and machine learning (ML) tools are being used in the efficient development, design and discovery of polymers. Surrogate models are trained on available polymer data for instant property prediction, allowing screening of promising polymer candidates with specific target property requirements. Questions regarding synthesizability, and potential (retro)synthesis steps to create a target polymer, are being explored using statistical means. Data-driven strategies to tackle unique challenges resulting from the extraordinary chemical and physical diversity of polymers at small and large scales are being explored. Other major hurdles for polymer informatics are the lack of widespread availability of curated and organized data, and approaches to create machine-readable representations that capture not just the structure of complex polymeric situations but also synthesis and processing conditions. Methods to solve inverse problems, wherein polymer recommendations are made using advanced AI algorithms that meet application targets, are being investigated. As various parts of the burgeoning polymer informatics ecosystem mature and become integrated, efficiency improvements, accelerated discoveries and increased productivity can result. Here in this paper, we review emergent components of this polymer informatics ecosystem and discuss imminent challenges and opportunities.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Stochasticity and robustness in spiking neural networks

Despite drawing inspiration from biological systems which are inherently noisy and variable, artificial neural networks have been shown to require precise weights to carry out the task which they are trained to accomplish. This creates a challenge when adapting these artificial networks to specialized execution platforms which may encode weights in a manner which restricts their accuracy and/or precision.Reflecting back on the non-idealities which are observed in biological systems, we investigated the effect these properties have on the robustness of spiking neural networks under perturbations to weights. First, we examined techniques extant in conventional neural networks which resemble noisy processes, and postulated they may produce similar beneficial effects in spiking neural networks. Second, we evolved a set of spiking neural networks utilizing biological non-idealities to solve a pole-balancing task, and estimated their robustness. We showed it is higher in networks using noisy neurons, and demonstrated that one of these networks can perform well under the variance expected when a hafnium-oxide based resistive memory is used to encode synaptic weights. Lastly, we trained a series of networks using a surrogate gradient method on the MNIST classification task. We confirmed that these networks demonstrate similar trends in robustness to the evolved networks. We discuss these results and argue that they display empirical evidence supporting the role of noise as a regularizer which can increase network robustness.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Mitigating spectral bias in neural operators via high-frequency scaling for physical systems

Neural operators have emerged as powerful surrogates for modeling complex physical problems. However, they suffer from spectral bias making them oblivious to high-frequency modes, which are present in multiscale physical systems. Therefore, they tend to produce over-smoothed solutions, which is particularly problematic in modeling turbulence and for systems with intricate patterns and sharp gradients such as multi-phase flow systems. In this work, we introduce a new approach named high-frequency scaling (HFS) to mitigate spectral bias in convolutional-based neural operators. By integrating HFS with proper variants of UNet, we demonstrate a higher prediction accuracy by mitigating spectral bias in single and two-phase flow problems. Unlike Fourierbased techniques, HFS is directly applied to the latent space, thus eliminating the computational cost associated with the Fourier transform. Additionally, we investigate alternative spectral bias mitigation through a diffusion model conditioned on neural operators. While the diffusion model integrated with the standard neural operator may still suffer from significant errors, these errors are substantially reduced when the diffusion model is integrated with a HFS-enhanced neural operator.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Uncertainty propagation in feed-forward neural network models

We develop new uncertainty propagation methods for feed-forward neural network architectures with leaky ReLU activation functions subject to random perturbations in the input vectors. In particular, we derive analytical expressions for the probability density function (PDF) of the neural network output and its statistical moments as a function of the input uncertainty and the parameters of the network, i.e., weights and biases. A key finding is that an appropriate linearization of the leaky ReLU activation function yields accurate statistical results even for large perturbations in the input vectors. This can be attributed to the way information propagates through the network. We also propose new analytically tractable Gaussian copula surrogate models to approximate the full joint PDF of the neural network output. To validate our theoretical results, we conduct Monte Carlo simulations and a thorough error analysis on a multi-layer neural network representing a nonlinear integro-differential operator between two polynomial function spaces. Our findings demonstrate excellent agreement between the theoretical predictions and Monte Carlo simulations.

MLP networks↗
DOE OSTI2021

Development of a versatile, high-temperature, high-throughput ion irradiation system

We report ion irradiation has long been used as a surrogate for neutron irradiation experiments which are comparatively slower, more expensive, and often can leave materials activated and difficult to handle post-irradiation. However, with the growing use of combinatorial synthesis methods and high-throughput, automated characterization techniques, ion irradiation facilities will need to upgrade their capabilities to be able to accommodate these new material platforms. To address this challenge, a high-throughput ion irradiation system has been developed at the University of Wisconsin-Madison Ion Beam Laboratory (IBL). The system is capable of accommodating large sample arrays of arbitrary geometries and heat samples individually using an infrared laser to enable high-temperature, high-throughput ion irradiation while mitigating the risk of annealing the irradiation damage in nearby samples. To control stage motion, laser power, and beam current measurement, among other tasks, the program Chronos was developed which enables automated high-throughput irradiation experiments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Model calibration of the liquid mercury spallation target using evolutionary neural networks and sparse polynomial expansions

The mercury constitutive model predicting the strain and stress in the target vessel plays a central role in improving the lifetime prediction and future target designs of the mercury targets at the Spallation Neutron Source. We leverage the experiment strain data collected over multiple years to improve the mercury constitutive model through a combination of large scale simulations of the target behavior and the use of machine learning tools for parameter estimation. We present two interdisciplinary approaches for surrogate-based model calibration of expensive simulations using evolutionary neural networks and sparse polynomial expansions. The newly calibrated simulations achieve 7% average improvement on the prediction accuracy and 8% reduction in mean absolute error compared to previously reported reference parameters, with some individual sensors experiencing up to 30% improvement. The calibrated simulations can aid in fatigue analysis to estimate the mercury target lifetime, which reduces abrupt failure and saves tremendous amount of costs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Topology optimization of an airfoil fin microchannel heat exchanger using artificial intelligence

High-performance microchannel heat exchangers are needed to supply heat for power conversion for nuclear microreactors. An airfoil fin microchannel design, constructed of Alloy 617 with helium as the working fluid, is analyzed and optimized using a design of experiments with artificial intelligence techniques. The use of airfoil fins offers the potential to reduce pressure drop across the heat exchanger, as compared to other types of channel configurations. A framework for topology optimization of airfoil fin printed circuit heat exchangers (PCHEs) has been developed that can be readily extended to different fin sizes and shapes, as well as different inlet and operating conditions, materials of construction, and working fluids. An optimization procedure is developed that employs computational fluid dynamics for a set of design points identified using Latin hypercube sampling. Computational fluid dynamics is used to analyze a simplified two-channel configuration where five design parameters are varied – inlet angle, fin scale, extent of staggering, transverse and longitudinal pitches. Two methods (a 5D polynomial and a regression neural network) are compared for generating surrogate models and the resulting response surface approximation is input to a genetic algorithm that is used to identify a set of optimal parameters. The optimal geometries are found across six channel Reynolds numbers ranging from 1000 to 5000, since inlet conditions affect flow through the heat exchanger. Additionally, a set of optimal designs that maximizes heat transfer and minimizes pressure drop is identified, and a thermal stress analysis is performed on the optimal design. Correlations for the Nusselt number and Darcy friction factor are developed that can be useful for thermal hydraulic analyses using system codes. Thermal stresses are analyzed and a brief discussion of the status of code cases of PCHEs for nuclear applications is given. Testing and thermomechanical modeling is needed to facilitate future code compliance of PCHEs for high pressure and high temperature applications.

42 ENGINEERING↗
DOE OSTI2022

Study of alkaline carbonate cooling to mitigate Ex-Vessel molten corium accidents

To mitigate adverse effects from molten corium following a reactor pressure vessel failure (RPVF), some new reactor designs employ a core catcher and a sacrificial material (SM), such as ceramic or concrete, to stabilize the molten corium and avoid containment breach. Existing reactors cannot easily be modified to include these SMs but could be modified to allow injectable cooling materials. Current reactor designs are limited to using water to stabilize the corium, but this can create other issues such as reaction of water with the concrete forming hydrogen gas. Here the novel SM proposed is a granular carbonate mineral that can be used in existing light water reactor plants. The granular carbonate will decompose when exposed to heat, inducing an endothermic reaction to quickly solidify the corium in place and producing a mineral oxide and carbon dioxide. Corium spreading is a complex process strongly influenced by coupled chemical reactions, including decay heat from the corium, phase change, and reactions between the concrete containment and available water. A recently completed Sandia National Laboratories laboratory directed research and development (LDRD) project focused on two research areas: experiments to demonstrate the feasibility of the novel SM concept, and modeling activities to determine the potential applications of the concept to actual nuclear plants. Small-scale experiments using lead oxide (PbO) as a surrogate for molten corium demonstrate that the reaction of the SM with molten PbO results in a fast solidification of the melt due to the endothermic carbonate decomposition reaction and the formation of open pore structures in the solidified PbO from CO 2 released during the decomposition. A simplified carbonate decomposition model was developed to predict thermal decomposition of carbonate mineral in contact with corium. This model was incorporated into MELCOR, a severe accident nuclear reactor code. A full-plant MELCOR simulation suggests that by the introduction of SM to the reactor cavity prior to RPVF ex-vessel accident progression, e.g., core-concrete interaction and core spreading on the containment floor, could be delayed by at least 15 h; this may be enough for additional accident management to be implemented to alleviate the situation.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Simulation of natural circulation cartridge loop experiments and application to molten salt reactors

This work uses the TRAC/RELAP Advanced Computational Engine (TRACE) thermal hydraulics (TH) code to model natural circulation cartridge loop experiments previously conducted at Oak Ridge National Laboratory (ORNL) using water and compares the simulated and experimental results. TRACE is also used to characterize natural circulation in the cartridge loop vehicle using FLiNaK as the working fluid. The experimental vehicle is a buoyancy-aided, annular cartridge loop, referred to as a thermosyphon, and is designed to aid in qualifying liquid–fueled and/or liquid–cooled irradiation experiments for the Versatile Test Reactor (VTR), which is currently being designed in the United States. Out-of-pile water experiments have been conducted using the cartridge and the Thermosyphon Test Loop facility at ORNL, and future experiments are anticipated that would use other molten salt surrogates as the working fluid, followed by eventual insertion of a similar cartridge into VTR. Additionally, this work aims to determine how well TRACE can replicate the natural convection conditions that were observed experimentally; this serves as an initial step for validating the modeling tool for design and safety calculations to support future irradiation experiments in VTR. Initial predictions of potential experiments were made using FLiNaK as the natural circulation fluid to demonstrate the relevance of the cartridge design to molten salt reactors (MSRs). Results from this study indicate that TRACE can accurately capture natural convection phenomena in the thermosyphon and that several design changes to the current cartridge vehicle are necessary to achieve hydraulic conditions similar to those expected in MSRs.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Development and assessment of a reactor system prognosis model with physics-guided machine learning

Autonomous control systems provide recommendations to help operators in decision-making during plant operations ranging from normal operation to accident management. An important step of autonomous control is prognosis. In nuclear engineering domain, prognosis is the process of predicting future conditions of a system or equipment based on present signs and symptoms of a fault. The prognosis model allows predicting future reactor states for possible candidate control strategies so that the outcomes can be evaluated to determine the best control strategy. The prognosis model requires representing direct relationships between the symptoms and the predictions. In nuclear engineering, computational simulations are approximate representations of the operation of the real system. However, prognosis with computational simulations requires high computation power and time due to possible large number of scenarios. Necessary computation resources can be reduced with machine learning (ML) approach for fast predictions by building a surrogate function using the simulation data. A critical issue is, ML models are ignorant of physical knowledge, and these models approximate statistical relationships between the system variables. This ignorance can produce results that are inconsistent with physical laws, even if an optimal result is achieved from a mathematical point of view. Physics-guided machine learning (PGML) is an approach to tackle this issue. Here, this work formulates and illustrates a framework to guide development and assessment of the ML-based prognosis model for autonomous control systems. The development of the prognosis model considers the training of a ML model which consists of optimizing many aspects of the ML approach. The assessment of the prognosis model considers training data limitations and uncertainties of the ML approach. Prognosis models with standalone ML and PGML are developed and assessed on the loss-of-flow scenario of Experimental Breeder Reactor II. The results indicate that PGML based prognosis model has the best performance compared to other prognosis models.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2023

A non-fueled nuclear-heated rod for in-pile transient boiling studies

Separate-effects boiling experiments have recently been conducted in the Transient Reactor Test Facility at Idaho National Laboratory to investigate transient heating and irradiation effects on cladding-to-coolant heat transfer. Specifically, transient critical heat flux (CHF) remains an important area of research, and better understanding of this phenomenon has potential for improving predictive models related to operational and safety limits. Consequently, this knowledge is expected to improve efficiency of light-water reactor operations. A novel borated nuclear-heated rodlet (BNHR) was designed to enable observation of transient cladding-to-coolant heat transfer phenomena. The final BNHR design takes a surrogate approach, wherein nuclear heating is induced by 10 B(n, α) reactions rather than derived from fissions in a fueled specimen. The structure of the BNHR consists of a hollowed out borated (B nat ~ 2.05 wt %) stainless steel tube with an hourglass-shaped outer surface, capped at both ends with non-borated stainless steel. This geometry allows for inner-rodlet instrumentation and generation of the highest nuclear heating rates near the center of the rodlet to ensure onset of boiling near instrumentation for real-time observation. A novel approach to measuring the nuclear energy deposition rate in the BNHR separate and apart from the influence of the coolant, termed the n-a thermometer, is also detailed in this paper. This device has demonstrated excellent repeatability, and measurements indicate predictive modeling results for energy deposition in the BNHR rod agree within a 10% margin of the experiment measurements. In conclusion, these results give confidence that the BNHR design has successfully met experiment objectives.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

Porous Flow Modeling of Axial Gas Redistribution in Fragmented LWR Fuel Rods using MOOSE

Understanding how gas axially redistributes within fragmented fuel pellets is crucial for predicting the behavior of Light Water Reactor (LWR) fuel rods, particularly during transient and accidental scenarios. The time scale of this phenomenon plays a fundamental role in determining the progression and hazard of a Loss Of Coolant Accident (LOCA), especially when high burn-up fuel in a severe state of fragmentation is involved. Here, this study presents a Computational Fluid Dynamics (CFD) model developed within the Multiphysics Object-Oriented Simulation Environment (MOOSE) to predict the time-scale of plenum depressurization in Light-Water Reactor (LWR) fuel rods driven by axial gas transport through fragmented pellets. The model examines the effects of incorporating non-linearities in the friction term by comparing the results with experimental data. The experiment employed surrogate fuel rods containing pellets subjected to mechanical and/or thermal loadings to simulate various severity of cracking, and aimed at studying the influence of fuel conditions on axial gas redistribution. The results of this analysis indicate that under certain flow regime conditions - determined by the value of an equivalent Reynolds number - accounting for the non-linear friction term in Navier-Stokes equations guarantees better predictions for the time-scale of plenum depressurization. Also, the model enabled the simulation of the pressure decay by assigning distinct permeability values to each pellet instead of a single uniform value. Multiple simulations were run across all possible pellet position combinations, having each pellet assigned with values of permeability extracted from the experimental data. This allows to quantify the impact of the considering various non-uniform distributions of permeability on the dynamics of axial gas redistribution. The present work findings enhance the understanding of axial gas transport, and provide valuable insights for the integration of a model for predicting the axial gas redistribution during a LOCA scenario into the BISON fuel performance code.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2026

Development of a coupled experimental–computational approach for engineering optimization of spout-fluidized bed particle coating systems

The design of spout-fluidized bed (SFB) coating systems for nuclear particle fuels typically relies on trial-and-error processes, comprising iterative and time-consuming coating deposition experiments and post-deposition characterization. At an engineering scale, this approach to guided SFB system design is inefficient, highlighting the need for streamlined experimental methodologies which can correlate fluidization conditions to downstream coating outcomes. In this study, we combine time-resolved particle image velocimetry (PIV) with CFD–DEM simulations to benchmark hydrodynamic behavior in a 3D spout-fluidized bed. By exploiting easily accessible optical measurements of particle motion at the bed wall and within the spouting region, we obtain quantitative velocity fields that can be directly compared with model predictions of the occluded bed region, without resorting to complex imaging and characterization techniques such as X-ray or magnetic resonance tomography. Experimental benchmarking reveals strong agreement between CFD–DEM and PIV in the spout and annulus regions, while discrepancies near the wall highlight areas for future model development. Here, the proposed integrated experimental–numerical framework will enable a direct connection between measured variables and numerically predicted fluidization performance of dense, surrogate nuclear particle fuel feedstock such that experimental SFB component design can be rapidly evaluated, informing design decisions for nozzle geometry and operating conditions. Future work will extend this framework by correlating quantified fluidization metrics across nozzle geometries and operating conditions with the resulting coating morphology, microstructure, and uniformity. Establishing these correlations will enable predictive links between hydrodynamic performance and coating quality, providing a rational, scalable basis for optimizing SFB design prior to coating deposition.

CFD/DEM↗