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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,297 records · Page 72

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Derivation of Integrated Load Distributions from Resampled Computational Data

Principal component analysis (PCA) has been the center of many surrogate models used to characterize fluid flows in recent years. However, little work has been done to character- ize the uncertainty in the PCA transform itself and its effect on derived surrogate models. To explore the uncertainty, a typical interpolated surrogate model is constructed for a represen- tative aerodynamic body from computational data. The computational data is then resampled to explore the robustness of the PCA transformation. The variations of the model predictions during this resampling are analyzed to get a measure of confidence in the PCA transformation, which is then applied to the interpolated surrogate model to get uncertainty on integrated force predictions. An initial test case has been explored with promising results.

Principal Component Analysis↗

NASA NTRSDate not supplied

Derivation of Integrated Load Distributions from Resampled Computational Data

Computational Fluid Dynamics↗

DOE OSTI2013

TEST SYSTEM FOR EVALUATING SPENT NUCLEAR FUEL BENDING STIFFNESS AND VIBRATION INTEGRITY

Transportation packages for spent nuclear fuel (SNF) must meet safety requirements specified by federal regulations. For normal conditions of transport, vibration loads incident to transport must be considered. This is particularly relevant for high-burnup fuel (>45 GWd/MTU). As the burnup of the fuel increases, a number of changes occur that may affect the performance of the fuel and cladding in storage and during transportation. The mechanical properties of high-burnup de-fueled cladding have been previously studied by subjecting defueled cladding tubes to longitudinal (axial) tensile tests, ring-stretch tests, ring-compression tests, and biaxial tube burst tests. The objective of this study is to investigate the mechanical properties and behavior of both the cladding and the fuel in it under vibration/cyclic loads similar to the sustained vibration loads experienced during normal transport. The vibration loads to SNF rods during transportation can be characterized by dynamic, cyclic, bending loads. The transient vibration signals in a specified transport environment can be analyzed, and frequency, amplitude and phase components can be identified. The methodology being implemented is a novel approach to study the vibration integrity of actual SNF rod segments through testing and evaluating the fatigue performance of SNF rods at defined frequencies. Oak Ridge National Laboratory (ORNL) has developed a bending fatigue system to evaluate the response of the SNF rods to vibration loads. A three-point deflection measurement technique using linear variable differential transformers is used to characterize the bending rod curvature, and electromagnetic force linear motors are used as the driving system for mechanical loading. ORNL plans to use the test system in a hot cell for SNF vibration testing on high burnup, irradiated fuel to evaluate the pellet-clad interaction and bonding on the effective lifetime of fuel-clad structure bending fatigue performance. Technical challenges include pure bending implementation, remote installation and detachment of the SNF test specimen, test specimen deformation measurement, and identification of a driving system suitable for use in a hot cell. Surrogate test specimens have been used to calibrate the test setup and conduct systematic cyclic tests. The calibration and systematic cyclic tests have been used to identify test protocol issues prior to implementation in the hot cell. In addition, cyclic hardening in unidirectional bending and softening in reverse bending were observed in the surrogate test specimens. The interface bonding between the surrogate clad and pellets was found to impact the bending response of the surrogate rods; confirming this behavior in the actual spent fuel segments will be an important aspect of the hot cell test implementation,

reversal bending fatigue tester↗

DOE OSTI2013

Reversible Bending Fatigue Test System for Investigating Vibration Integrity of Spent Nuclear Fuel during Transportation

Transportation packages for spent nuclear fuel (SNF) must meet safety requirements under normal and accident conditions as specified by federal regulations. During transportation, SNF experiences unique conditions and challenges to cladding integrity due to the vibrational and impact loading during road or rail shipment. Oak Ridge National Laboratory (ORNL) has been developing testing capabilities that can be used to improve the understanding of the impacts on SNF integrity due to vibration loading, especially for high burn-up SNF in normal transportation operation conditions. This information can be used to meet the nuclear industry and U.S. Nuclear Regulatory Commission needs in the area of safety and security of spent nuclear fuel storage and transport operations. The ORNL developed test system can perform reversible-bending fatigue testing to evaluate both the static and dynamic mechanical response of SNF rods under simulated loads. The testing apparatus is also designed to meet the challenges of hot-cell operation, including remote installation and detachment of the SNF test specimen, in-situ test specimen deformation measurement, and implementation of a driving system suitable for use in a hot cell. The system contains a U-frame set-up equipped with uniquely designed grip rigs, to protect SNF rod and to ensure valid test results, and use of 3 specially designed LVDTs to obtain the in-situ curvature measurement. A variety of surrogate test rods have been used to develop and calibrate the test system as well as in performing a series of systematic cyclic fatigue tests. The surrogate rods include stainless steel (SS) cladding, SS cladding with cast epoxy, and SS cladding with alumina pellets inserts simulating fuel pellets. Testing to date has shown that the interface bonding between the SS cladding and the alumina pellets has a significant impact on the bending response of the test rods as well as their fatigue strength. The failure behaviors observed from tested surrogate rods provides a fundamental understanding of the underlying failure mechanisms of the SNF surrogate rod under vibration which has not been achieved previously. The newly developed device is scheduled to be installed in the hot-cell in summer 2013 to test high burnup SNF.

high burn-up spent fuel↗

DOE OSTI2022

Computational Workflow for Accelerated Molecular Design Using Quantum Chemical Simulations and Deep Learning Models

Efficient methods for searching the chemical space of molecular compounds are needed to automate and accelerate the design of new functional molecules such as pharmaceuticals. Given the high cost in both resources and time for experimental efforts, computational approaches play a key role in guiding the selection of promising molecules for further investigation. Here, we construct a workflow to accelerate design by combining approximate quantum chemical methods [i.e. density-functional tight-binding (DFTB)], a graph convolutional neural network (GCNN) surrogate model for chemical property prediction, and a masked language model (MLM) for molecule generation. Property data from the DFTB calculations are used to train the surrogate model; the surrogate model is used to score candidates generated by the MLM. The surrogate reduces computation time by orders of magnitude compared to the DFTB calculations, enabling an increased search of chemical space. Furthermore, the MLM generates a diverse set of chemical modifications based on pre-training from a large compound library. We utilize the workflow to search for near-infrared photoactive molecules by minimizing the predicted HOMO-LUMO gap as the target property. Our results show that the workflow can generate optimized molecules outside of the original training set, which suggests that iterations of the workflow could be useful for searching vast chemical spaces in a wide range of design problems.

Blanchard, Andrew↗

DOE OSTI2023

Adaptive Data-Driven Model Predictive Control for Heat Pipe Microreactors

To establish a technical basis for self-regulating microreactors, a model predictive control (MPC) system is investigated to proactively respond to anomalies and disturbances in anticipation of potential deviations from operating setpoints. Due to the difficulty of developing a physics-based surrogate model that can accurately match plant data in various operating conditions, machine learning algorithms are used in MPC, which allow for learning from both simulation and operation data, thus efficiently describing the targeted transient with arbitrary accuracy. However, one of the biggest concerns in applying ML algorithms like artificial neural networks (ANNs) is that the predictive capabilities of ANN are limited by training data. If there are gaps between the training and target domain, the accuracy of an ANN can degrade significantly when it is used to predict unseen data. To improve the predictive capability of ANN and enable a confident use of data-driven MPCs outside the training data, this study proposes an adaptive data-driven MPC framework. The system will monitor the discrepancy between plant responses and surrogate predictions, fine-tune the ANN-based surrogate when a large discrepancy is detected, and continue MPC operation with updated surrogates. The framework is demonstrated on a point kinetic model for microreactors. The hyperparameters of the update strategy, including layers to update, error thresholds, learning rate discount, and number of data points used for fine-tuning, are optimized so the simulated microreactor is able to follow changes in setpoint with the smallest of deviations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2023

Adaptable Data Driven Model Predictive Control for Heat Pipe Microreactors

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2019

Oxide Growth and Validation for Aluminum Research Reactor Fuel - 19422

Aluminum fuel cladding will undergo general corrosion with resulting formation of adherent oxide films during in-reactor and post-discharge exposures under various water conditions and temperatures. These oxides include chemically-bound water that can pose challenges for extended dry storage. This paper describes laboratory experiments performed to produce hydroxide (oxide) films on aluminum 1100, 6061 and 5052 series alloy substrates immersed in water at controlled temperatures. The results are compared to the oxide film present on a spent fuel assembly irradiated in research reactor. This work is part of a broad investigation to address knowledge gaps and technical data needs for dry storage of aluminum-clad spent nuclear fuel (SNF). To adequately assess the risks posed by chemically-bound water on SNF in dry storage and strategies for removing chemically bound water, it is necessary to understand the expected composition and loading of oxide films on SNF of different service histories and to investigate the response of such oxides to irradiation and potential drying methods. These efforts require both the growth of films under controlled conditions and the production of non-radioactive surrogates for testing. The current work comprises experimental investigation of oxide growth via (1) laboratory experiments to produce hydroxide films on aluminum alloy substrates immersed in water at controlled temperatures and (2) characterization and comparison of laboratory-grown oxides to oxides on service-exposed aluminum alloys. The important factors affecting oxide growth and characteristics typical of oxide films formed by aqueous corrosion under conditions similar to in-reactor are reviewed. Aluminum oxide films were grown under a variety of controlled temperature conditions and durations to serve as surrogates for oxides found on aluminum-clad spent nuclear fuel due to aqueous corrosion. The chemically-bound water found in oxides formed by aqueous corrosion poses challenges for extended dry storage, requiring investigation of how the oxide loading and characteristics vary with exposure history and to provide the initial condition for investigation of drying methods. Characteristics including chemical composition, oxide morphology, and film thickness were measured to assess whether the surrogate films were representative of in-service-produced oxides on SNF. Tests were conducted in liquid water at atmospheric pressure in the temperature range 50-100 deg. C, with and without heat flux through the corroding surface, to replicate in-service conditions, and at 185 deg. C inside pressure vessels to replicate pre-filming procedures. Three different alloys commonly used in aluminum clad research reactor fuel were considered: Al-1100, Al-6061, and Al-5052. Specimens were characterized by weighing before and after exposure to measure oxide mass loading, X-ray diffraction to identify oxide composition, and scanning electron microscopy to examine the oxide morphology and film thickness. The oxide type and the morphological characteristics of the film on a fuel element from the Uruguay RU1 research reactor were determined and compared to the laboratory surrogates. The results show some differences compared to the 50 deg. C laboratory specimen that are rationalized with the service storage history of the element. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2024

Rapid Inverse Parameter Inference Using Physics-Informed Neural Network

As Li-ion batteries become more essential in today's economy, tools need to be developed to accurately and rapidly diagnose a battery's internal state-of-health. Using a Li-ion battery's (high-rate) voltage response, it is proposed to determine a battery's internal state through Bayesian calibration. However, Bayesian calibration is notoriously slow and requires thousands of model runs. To accelerate parameter inference using Bayesian calibration, a surrogate model is developed to replace the underlying physics-based Li-ion model. Developing a surrogate model for rapid Bayesian calibration analysis is discussed for both the single particle model (SPM) and the pseudo two-dimensional (P2D) model. Surrogate models are constructed using physics-informed neural networks (PINNs) that encode the influence of internal properties on observed voltage responses. In practice, a neural network can be trained by: 1) using simulation results of the physics-based model (i.e., a data-loss approach); 2) using the residuals of the governing equations themselves (i.e., a physics-loss approach); or 3) using a combination of simulation results and governing equation residuals. In the present work, PINNs are developed using a variety of training losses and neural network architectures. In this analysis, it is shown that a PINN surrogate model can be reliably trained with only physics-informed loss. However, using a coupled data-informed and physics-loss approach produced the most accurate PINNs.

Bayesian calibration↗

DOE OSTI2025

MOOSE ProbML: Parallelizable Probabilistic Machine Learning and Uncertainty Quantification Capabilities

The Multiphysics Object Oriented Simulation Environment (MOOSE) is a widely used open- source finite element software for performing multiphysics multiscale simulations in a massively parallel fashion. Recently, the computational team at Idaho National Laboratory (INL) has implemented Probabilistic Machine Learning (ProbML) capabilities in MOOSE—in a parallelized fashion—and enable active learning with large-scale computational models for tasks such as surrogate model development, scale bridging, forward/inverse uncertainty quantification (UQ), Bayesian optimization, etc. This presentation summarizes these developments in MOOSE along with demonstrations on several real applications relevant to nuclear energy. At the fundamental level, samplers like Monte Carlo/Latin Hypercube, variance reduction, parallelized Markov Chain Monte Carlo (MCMC) support uncertainty propagation in both forward and inverse settings. These samplers can be integrated with the Gaussian processes (GP) suite in MOOSE, which offer several variants like scalar GPs, multi-output GPs, and deep GPs, to enable active learning. These GPs can be tuned using gradient-based optimization methods like Adam and its variants or gradient-free methods like the elliptical slice sampler (a variant of MCMC adept under Gaussian settings) for more complex covariance kernels or likelihoods whose gradient computations can be cumbersome. A variety of batch acquisition functions permit parallelized evaluation of the computational model and support different learning objectives with high efficiency like Bayesian inference, global surrogate development, optimization, etc. Furthermore, libtorch integration supports training, evaluation, and re-training of neural networks and other complex machine learning models in active learning settings. The impacts of these developments are shown on several real applications: (1) nuclear fuel inverse UQ and model inadequacy assessment using the Kennedy O’Hagan framework; (2) uncertainty aware surrogate modeling for additive manufacturing to predict field quantities; (3) nuclear reactor rare events analysis; and (4) complex fluid flow prediction using a global surrogate with quantified prediction uncertainty. Finally, the outlook of MOOSE ProbML is discussed for both outer-loop and inner-loop computations in the broad view to accelerate fuels and materials qualification, address gaps in knowledge and data, and assess new reactor/fuel systems.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2023

Cerium oxide impact on fresh and hardened properties of cementitious materials

Cements used in global nuclear waste treatment, storage, and disposal require thorough testing of fresh and cured properties to demonstrate regulatory compliance. Using actual radioactive wastes is often cost-prohibitive during early scoping tests necessitating the use of non-radiological surrogates. Cerium (Ce) is often used as a surrogate for actinides uranium (U) and plutonium (Pu) in spent nuclear fuel, yet few studies have explored how Ce impacts the properties used to qualify a cement for use. Here, this work compares the fresh and cured properties of three classes of cements – ordinary portland cements, ultra-high performance cement composites, and magnesium phosphate cements – each with and without ceria (CeO 2 ). Due to CeO 2 sorption of water (54 vol%) that effectively decreases the water available to hydrate and form binding cement phases, variations in key cement properties were detected that suggest surrogate CeO 2 –cementitious matrices may not be representative of matrix behaviors when using U and Pu sources.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Factorization Machine‐Based Active Learning for Functional Materials Design with Optimal Initial Data

The optimization of functional materials is important to enhance their properties, but their complex geometries pose great challenges to optimization. Data-driven algorithms efficiently navigate such complex design spaces by learning relationships between material structures and performance metrics to discover high-performance functional materials. Surrogate-based active learning, continually improving its surrogate model by iteratively including high-quality data points, has emerged as a cost-effective data-driven approach. Furthermore, it can be coupled with quantum computing to enhance optimization processes, especially when paired with a special form of surrogate model (i.e., quadratic unconstrained binary optimization), formulated by factorization machine (FM). However, current practices often overlook the variability in design space sizes when determining the initial data size for optimization. In this work, we investigate the optimal initial data sizes required for efficient convergence across various design space sizes. By employing averaged piecewise linear regression, we identify initiation points where convergence begins, highlighting the crucial role of employing adequate initial data in achieving efficient optimization. These results contribute to the efficient optimization of functional materials by ensuring faster convergence and reducing computational costs in FM-based active learning.

active learning↗

DOE OSTI2022

Dispersion-enhanced sequential batch sampling for adaptive contour estimation

In computer simulation and optimal design, sequential batch sampling offers an appealing way to iteratively stipulate optimal sampling points based upon existing selections and efficiently construct surrogate modeling. Nonetheless, the issue of near duplicates poses tremendous quandary for sequential learning. It refers to the situation that selected critical points cluster together in each sampling batch, which are individually but not collectively informative towards the optimal design. Near duplicates severely diminish the computational efficiency as they barely contribute extra information towards update of the surrogate. To address this issue, we impose a dispersion criterion on concurrent selection of sampling points, which essentially forces a sparse distribution of critical points in each batch, and demonstrate the effectiveness of this approach in adaptive contour estimation. Specifically, we adopt Gaussian process surrogate to emulate the simulator, acquire variance reduction of the critical region from new sampling points as a dispersion criterion, and combine it with the modified expected improvement (EI) function for critical batch selection. The critical region here is the proximity of the contour of interest. This proposed approach is vindicated in numerical examples of a two-dimensional four-branch function, a four-dimensional function with a disjoint contour of interest and a time-delay dynamic system.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles

Optimal engine operation during a transient driving cycle is the key to achieving greater fuel economy, engine efficiency, and reduced emissions. In order to achieve continuously optimal engine operation, engine calibration methods use a combination of static correlations obtained from dynamometer tests for steady-state operating points and road and/or track performance data. As the parameter space of control variables, design variable constraints, and objective functions increases, the cost and duration for optimal calibration become prohibitively large. In order to reduce the number of dynamometer tests required for calibrating modern engines, a large-scale simulation-driven machine learning approach is presented in this work. A parallel, fast, robust, physics-based reduced-order engine simulator is used to obtain performance and emission characteristics of engines over a wide range of control parameters under various transient driving conditions (drive cycles). We scale the simulation up to 3,906 nodes of the Theta supercomputer at the Argonne Leadership Computing Facility to generate data required to train a machine learning model. The trained model is then used to predict various engine parameters of interest, and the results are compared with those predicted by the engine simulator. Our results show that a deepneural-network-based surrogate model achieves high accuracy: Pearson product-moment correlation values larger than 0.99 and mean absolute percentage error within 1.07% for various engine parameters such as exhaust temperature, exhaust pressure, nitric oxide, and engine torque. Once trained, the deep-neural-network-based surrogate model is fast for inference: it requires about 16 mu s for predicting the engine performance and emissions for a single design configuration compared with about 0.5 s per configuration with the engine simulator. Moreover, we demonstrate that transfer learning and retraining can be leveraged to incrementally retrain the surrogate model to cope with new configurations that fall outside the training data space.

deep learning↗

DOE OSTI2026

Enhanced accuracy through ensembling of randomly initialized auto-regressive models for dynamical systems

Computational mechanics simulations using traditional finite element methods (FEM) require prohibitively expensive computational resources for real-time engineering applications, design optimization, and digital twin implementations. While machine learning (ML) surrogate models offer significant computational speedups, autoregressive ML models for time-dependent mechanical systems suffer from error accumulation that compromises long-term prediction reliability - a critical concern for engineering applications where accuracy over extended time horizons is essential for safety and performance assessments. Here, we propose a deep ensemble framework specifically designed to address this challenge in computational mechanics applications, where multiple ML surrogate models with random weight initializations are trained in parallel and their predictions aggregated during inference. This approach leverages statistical diversity to maximize information gain from a fixed set of training data and to mitigate error propagation, while maintaining the computational efficiency that makes ML surrogates attractive for engineering practice. We validate the framework on three representative problems spanning critical areas of computational mechanics: stress field evolution in heterogeneous microstructures under complex loading (relevant to advanced materials design and composite analysis), planetary-scale shallow water dynamics (applicable to environmental and geotechnical engineering), and Gray-Scott reaction-diffusion systems (relevant to mass transport and chemical process engineering). Across all test cases, the ensemble approach demonstrates consistent error reduction of 15-33% compared to individual models. The codes for this work are available on GitHub (https://github.com/Graham-Brady-Research-Group/AutoregressiveEnsemble_SpatioTemporal_Evolution).

autoregressive prediction↗

DOE OSTI2016

POF-Darts: Geometric adaptive sampling for probability of failure

We introduce a novel technique, POF-Darts, to estimate the Probability Of Failure based on random disk-packing in the uncertain parameter space. POF-Darts uses hyperplane sampling to explore the unexplored part of the uncertain space. We use the function evaluation at a sample point to determine whether it belongs to failure or non-failure regions, and surround it with a protection sphere region to avoid clustering. We decompose the domain into Voronoi cells around the function evaluations as seeds and choose the radius of the protection sphere depending on the local Lipschitz continuity. As sampling proceeds, regions uncovered with spheres will shrink, improving the estimation accuracy. After exhausting the function evaluation budget, we build a surrogate model using the function evaluations associated with the sample points and estimate the probability of failure by exhaustive sampling of that surrogate. In comparison to other similar methods, our algorithm has the advantages of decoupling the sampling step from the surrogate construction one, the ability to reach target POF values with fewer samples, and the capability of estimating the number and locations of disconnected failure regions, not just the POF value. Furthermore, we present various examples to demonstrate the efficiency of our novel approach.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Sequence modeling of higher-order wave modes of quasi-circular, spinning, non-precessing binary black hole mergers

Higher-order gravitational wave modes from quasi-circular, spinning, non-precessing binary-black-hole (BBH) mergers encode rich information about the nonlinear dynamics of strong-field gravity. We present a transformer-based sequence-completion surrogate that, given an early-inspiral segment, forecasts the subsequent late inspiral, merger, and ringdown. The intended applications are (i) patching or completing expensive or interrupted numerical-relativity (NR) simulations and (ii) providing late-time cross-checks and rapid hybridization studies. The training set is built from the NRHybSur3dq8 surrogate, which provides spherical-harmonic modes up to $\ell$ ≤ 4 (excluding (4, 0) and (4,±1), and including (5, 5)) for mass ratios q ≤ 8, dimensionless spin components s$^{z}_{1,2}$ ϵ[–0.8, 0.8], and inclination angles θ ϵ [0, π]. Waveforms are supplied on the interval t ϵ [–5000M, –100 M) and the model autoregressively generates the plus and cross polarizations (h + , h x ) on t ϵ [–100 M, 130M]. Training on the Delta supercomputer with 16 NVIDIA A100 GPUs required ~15 h on more than 14 million hybrid waveforms. Evaluation on a held-out test set of 840,000 samples yields mean and median overlaps of 0.996 and 0.997, respectively, with respect to the surrogate ground truth.

black-hole merger↗

DOE OSTI2024

Efficient mapping between void shapes and stress fields using Deep Convolutional Neural Networks with sparse data

Establishing fast and accurate structure-to-property relationships is an important component in the design and discovery of advanced materials. Physics-based simulation models like the finite element method (FEM) are often used to predict deformation, stress, and strain fields as a function of material microstructure in material and structural systems. Such models may be computationally expensive and time intensive if the underlying physics of the system is complex. This limits their application to solve inverse design problems and identify structures that maximize performance. In such scenarios, surrogate models are employed to make the forward mapping computationally efficient to evaluate. However, the high dimensionality of the input microstructure and the output field of interest often renders such surrogate models inefficient, especially when dealing with sparse data. Deep convolutional neural network (CNN) based surrogate models have shown great promise in handling such high-dimensional problems. In this paper, a single ellipsoidal void structure under a uniaxial tensile load represented by a linear elastic, high-dimensional and expensive-to-query, FEM model. We consider two deep CNN architectures, a modified convolutional autoencoder framework with a fully connected bottleneck and a UNet CNN, and compare their accuracy in predicting the von Mises stress field for any given input void shape in the FEM model. Additionally, a sensitivity analysis study is performed using the two approaches, where the variation in the prediction accuracy on unseen test data is studied through numerical experiments by varying the number of training samples from 20 to 100.

surrogate modeling; convolutional neural networks;↗