Search NASA⌕ Search

SEARCH · Search NASA

Results for “Code 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 19 records

Regression with Small Data Sets: A Case Study using Code Surrogates in Additive Manufacturing

There has been an increasing interest in recent years in the mining of massive data sets whose sizes are measured in terabytes. While it is easy to collect such large data sets in some application domains, there are others where collecting even a single data point can be very expensive, so the resulting data sets have only tens or hundreds of samples. For example, when complex computer simulations are used to understand a scientific phenomenon, we want to run the simulation for many different values of the input parameters and analyze the resulting output. The data set relating the simulation inputs and outputs is typically quite small, especially when each run of the simulation is expensive. However, regression techniques can still be used on such data sets to build an inexpensive \surrogate" that could provide an approximate output for a given set of inputs. A good surrogate can be very useful in sensitivity analysis, uncertainty analysis, and in designing experiments. In this paper, we compare different regression techniques to determine how well they predict melt-pool characteristics in the problem domain of additive manufacturing. Our analysis indicates that some of the commonly used regression methods do perform quite well even on small data sets.

97 MATHEMATICS AND COMPUTING↗

BAYESIAN CALIBRATION OF SAFETY CODES USING DATA FROM SEPARATE-AND INTEGRAL EFFECTS TESTS

Large-scale system codes for simulation of safety performance of nuclear plants may contain parameters whose values are not known very accurately. In order to be able to use the results of these simulation codes with confidence, it is important to learn how the uncertainty on the values of these parameters affects the output of the codes. New information from tests or operating experience is incorporated into safety codes by a process known as calibration, which reduces uncertainty in the output of the safety code, and thereby improves its support for decision-making. Modern analysis capabilities afford very significant improvements on classical ways of doing calibration, and the work reported here implements some of those improvements. The key innovation has come from development of safety code surrogate model (code emulator) construction and prediction algorithms. A surrogate is needed for calibration of plant-scale simulation codes because the multivariate nature of the problem (i.e., the need to adjust multiple uncertain parameters at once to fit multiple pieces of new information) calls for multiple evaluations of performance, which, for a computation-intensive model, makes calibration very computation-intensive. Use of a fast surrogate makes the calibration processes used here with Markov Chain Monte Carlo (MCMC) sampling feasible. Moreover, most traditional surrogates do not provide uncertainty information along with their predictions, but the Gaussian Process (GP) based code surrogates used here do. This improves the soundness of the code calibration process. Results are demonstrated on a simplified scenario with data from Separate and Integral Effect Tests.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Demonstration of emulator-based Bayesian calibration of safety analysis codes: Theory and formulation

System codes for simulation of safety performance of nuclear plants may contain parameters whose values are not known very accurately. New information from tests or operating experience is incorporated into safety codes by a process known as calibration, which reduces uncertainty in the output of the code and thereby improves its support for decision-making. The work reported here implements several improvements on classic calibration techniques afforded by modern analysis techniques. The key innovation has come from development of code surrogate model (or code emulator) construction and prediction algorithms. Use of a fast emulator makes the calibration processes used here with Markov Chain Monte Carlo (MCMC) sampling feasible. This study uses Gaussian Process (GP) based emulators, which have been used previously to emulate computer codes in the nuclear field. The present work describes the formulation of an emulator that incorporates GPs into a factor analysis-type or pattern recognition-type model. This “function factorization” Gaussian Process (FFGP) model allows overcoming limitations present in standard GP emulators, thereby improving both accuracy and speed of the emulator-based calibration process. Calibration of a friction-factor example using a Method of Manufactured Solution is performed to illustrate key properties of the FFGP based process.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

A Systematic Approach to Offshore Wind Turbine Jacket Pre-Design and Optimization: Geometry, Cost, and Surrogate Structural Code Check Models

The main obstacles in preliminary design studies or optimization of jacket substructures for offshore wind turbines are high numerical expenses for structural code checks and simplistic cost assumptions. In order to create a basis for fast design evaluations, this article provides the following: firstly, a jacket model is proposed that covers topology and tube sizing with a limited set of design variables. Secondly, a cost model is proposed that goes beyond the simple and common mass-dependent approach. And thirdly, the issue of numerical efficiency is addressed by surrogate models both for fatigue and ultimate limit state code checks. In addition, this work shows an example utilizing all models. The outcome can be utilized for preliminary design studies and jacket optimization schemes and is suitable for scientific and industrial applications.

17 WIND ENERGY↗

Model Structural Inference Using Local Dynamic Operators

This paper focuses on the problem of quantifying the effects of model-structure uncertainty in the context of time-evolving dynamical systems. This is motivated by multi-model uncertainty in computer physics simulations: developers often make different modeling choices in numerical approximations and process simplifications, leading to different numerical codes that ostensibly represent the same underlying dynamics. We consider model-structure inference as a two-step methodology: the first step is to perform system identification on numerical codes for which it is possible to observe the full state; the second step is structural uncertainty quantification, in which the goal is to search candidate models "close" to the numerical code surrogates for those that best match a quantity of interest (QOI) from some empirical data sets. Here, we (1) define a discrete, local representation of the structure of a partial differential equation, which we refer to as the "local dynamical operator" (LDO); (2) identify model structure nonintrusively from numerical code output; (3) nonintrusively construct a reduced-order model (ROM) of the numerical model through POD-DEIM-Galerkin projection; (4) perturb the ROM dynamics to approximate the behavior of alternate model structures; and (5) apply Bayesian inference and energy conservation laws to calibrate a LDO to a given QOI. We demonstrate these techniques using the two-dimensional rotating shallow water equations as an example system.

97 MATHEMATICS AND COMPUTING↗

Stellarator Design Exploration Using Symbolic-Regression Neutronics Surrogates

Systems codes require fast, simplified models to rapidly evaluate fusion power plant concepts, but neutronics analyses are often a computational bottleneck. Here, to address this, surrogate models for key neutronics responses have been developed using 3-D neutronics-ready models built with the open-source code ParaStell from a database of stellarator equilibria. Neutronics responses such as tritium breeding ratio (TBR), nuclear heating, and neutron-induced radiation damage displacements per atom (dpa) were simulated using OpenMC. Through sensitivity analysis and symbolic regression (SR), simple power-law formulas were derived connecting these neutronics responses to global stellarator parameters, including fusion power, plasma surface area, and plasma elongation. Validation shows these formulas can predict the simulation results with low error, enabling quick and accurate assessment of neutronics requirements in stellarator design exploration activities with systems codes.

Modeling↗

Reactor physics benchmark of Westinghouse PWR core design suite for high burnup/high enrichment fuel - Part 2: 2D and 3D core simulations

Westinghouse has performed a comprehensive set of code-to-code benchmark comparisons to corroborate application of its state-of-the-art NEXUS-based code suite to high burnup and high enrichment (HB/HE) fueled PWR core design and reload analysis. The benchmark consisted of a progression in complexity from modeling single 2D pin cells, through 2D lattices and finally to whole core 2D and then 3D scenarios. The accompanying paper (Part 1) presented the results for a variety of pin cell and lattices representative of high energy cores and established the ability of the MPACT code to accurately match the predictions of the Monte-Carlo code SERPENT2 such that the former may be used as a surrogate reference code in spatially complex whole core modeling applications where using Monte-Carlo methods is somewhat impractical. This paper focuses on comparisons at the whole core level using a representative high power density 3-loop Westinghouse NSSS core operating for 24 month cycles employing high enriched fuel with use of combined burnable absorbers to hold down excess reactivity. The evolution of the core reactivity and power distribution characteristics throughout the cycle are calculated using the Westinghouse NEXUS-based code suite and compared to the results using MPACT. The results of this whole core benchmark confirm the conclusions that the Westinghouse code suite accurately models HB/HE fuel designs, with very good prediction of core reactivity and power distribution throughout the cycle. The industry can be confident that the NEXUS code system can be deployed to support PWR reload safety and operational analyses for cores featuring HB/HE fuel and 24-month cycle operation. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

PHASM: A Toolkit for Creating AI Surrogate Models within Legacy Codebases

PHASM (“Parallel Hardware viA Surrogate Models”) is a software toolkit for creating AI-based surrogate models of scientific code. AI-based surrogate models are widely used for creating fast and inverse simulations. PHASM anticipates an additional future use case: adapting legacy code to modern hardware. While data centers are investing in heterogeneous hardware such as GPUs and FPGAs, many established scientific codebases remain unable to take advantage of the hardware’s higher parallelism without undergoing a costly rewrite. An alternative is to train a AI-based surrogate model to mimic computationally intensive functions in the code, and run the surrogate instead. PHASM formalizes a development lifecycle for such surrogate models, including discovering functions amenable to replacement with a surrogate model, predicting the resulting performance, identifying the function’s space of inputs and outputs, binding the model to the code, and managing model versions. A suite of software tools for facilitating these steps was written and validated against a set of model problems.

97 MATHEMATICS AND COMPUTING↗

Machine learning surrogates for ion energy–angle distributions in thermal and RF plasma sheaths

Ion energy–angle distributions (IEADs) at material surfaces are a critical input for plasma–material interaction (PMI) studies in fusion devices, yet they are computationally expensive to obtain using particle-in-cell (PIC) simulations. In this work, we develop a machine learning surrogate based on a deep deconvolutional neural network (DDeCNN) trained on large databases generated with the hPIC2 code. The surrogate is capable of reconstructing IEADs from sheath parameters for both thermal and radio-frequency (RF) plasmas, including cases with multiple ion species. Across thousands of test cases, the model achieves high accuracy, with over 97 % of predictions classified as good or average based on standard error metrics (MAE, MSE, L2). Even in the more challenging RF and multi-species regimes, the surrogate reliably captures the multi-peak structure of PIC results. Once trained, the surrogate produces IEADs in milliseconds on a common workstation, yielding speedups of six to seven orders of magnitude compared with running a full PIC simulation. This computational gain enables dense parameter scans and direct coupling of IEAD predictions with PMI and erosion models on whole-device scales in fusion-relevant conditions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Optimization of artificial viscosity in production codes based on Gaussian Regression surrogate models

To accurately model flows with shock waves using staggered-grid Lagrangian hydrodynamics, artificial viscosity has to be introduced to convert kinetic energy into internal energy, thereby increasing the entropy across shocks. Determining the appropriate strength of the artificial viscosity is an art and strongly depends on the particular problem and experience of the researcher. The objective of this study is to pose the problem of finding the appropriate strength of artificial viscosity as an optimization problem and solve this problem using machine learning (ML) tools, specifically using surrogate models based on Gaussian Process regression and Bayesian analysis. We describe the optimization method and discuss various practical details of its implementation. The shock-containing problems for which we apply this method all have been implemented in the LANL code FLAG. First, we apply ML to find optimal values to isolated shock problems of different strengths. Second, we apply ML to optimize viscosity for a 1D propagating detonation problem based on Zel’dovich-von Neumann-Doring (ZND) detonation theory using a reactive burn model. We compare results for default (currently used values in FLAG) and optimized values of artificial viscosity for these problems demonstrating the potential for significant improvement in the accuracy of computations.

42 ENGINEERING↗

Dynamic PRA-Based Estimation of PWR Coping Time Using a Surrogate Model for Accident Tolerant Fuel

In this study, we propose an interpolation-based response surface surrogate methodology to manage a large number of scenarios in dynamic probabilistic risk assessment. It adopts the shape Dynamic Time Warping algorithm to cluster the interpolation neighborhood from time series sample data. The interpolation method was adapted from Taylor Kriging to allow a reduced-order model of the Taylor series. In order to demonstrate its applicability to complex issues in risk assessment for nuclear engineering, an example risk response surface to estimate emergency core cooling system (ECCS) criteria for triplex silicon carbide (SiC) accident-tolerant fuel was constructed. The response surface was exploited to estimate the cumulative failure probability of the fuel cladding structure due to the uncertainties in operator actions and safety systems. The functional failures were assessed based on a combination of individual layer failures computed by coupling Risk Analysis Virtual Environment software with a pressurized water reactor 1000-MW(electric) RELAP5 model and the in-house fuel performance assessment module. Results showed that SiC cladding failure probability spiked less than 1 min after a large-break loss-of- coolant accident whenever the current ECCS criteria for Zircaloy-4 (Zr-4) cladding was used. However, it still provides an increased safety margin of three orders of magnitude compared to Zr-4. This positive margin could be utilized to relax active ECCS requirements by allowing deviations of up to 450 s in its actuation time. The proposed surrogate methodology generated a response surface of SiC cladding failure probability reasonably well, with a significant savings of computation time. This methodology is expected to be useful in the analysis of system response with complex uncertainty sources.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Data mining and statistical inference in selective laser melting

Selective laser melting (SLM) is an additive manufacturing process that builds a complex three-dimensional part, layer-by-layer, using a laser beam to fuse fine metal powder together. The design freedom afforded by SLM comes associated with complexity. As the physical phenomena occur over a broad range of length and time scales, the computational cost of modeling the process is high. At the same time, the large number of parameters that control the quality of a part make experiments expensive. In this paper, we describe ways in which we can use data mining and statistical inference techniques to intelligently combine simulations and experiments to build parts with desired properties. We start with a brief summary of prior work in finding process parameters for high-density parts. We then expand on this work to show how we can improve the approach by using feature selection techniques to identify important variables, data-driven surrogate models to reduce computational costs, improved sampling techniques to cover the design space adequately, and uncertainty analysis for statistical inference. Here, our results indicate that techniques from data mining and statistics can complement those from physical modeling to provide greater insight into complex processes such as selective laser melting.

36 MATERIALS SCIENCE↗

Sensitivity Analysis of Passive Heat Removal Capability of FHR Based on Efficient Surrogate Model and GenFlow

Code Scaling, Applicability and Uncertainty Evaluation Methodology (CSAU) is used for quantifying reactor safety margins and works as an alternative method for licensing nuclear power plant. In the framework of CSAU, sensitivity and uncertainty analysis (SA and UA) should be performed. However, for large-scale complicated thermal hydraulics analysis simulated by code (e.g. RELAP5, CFD and subchannel analysis, the sensitivity and uncertainty analysis is really time-consuming. Furthermore, sometimes it is not feasible to perform SA and UA. Specifically, the computation time for Monte Carlo sampling or advanced LHS sampling can be neglected, but the computation time for thermal hydraulics code makes up main part of time during SA and UA process. In order to accelerate the speed of SA and UA, thermal hydraulics code can be improved based on advanced mathematic algorithm or using parallel method. However, the development for new mathematic method needs long time and strict verification and validation process is needed for a new code, which usually takes a couple of years or even longer time to have an approved code that can be used in nuclear industry. An alternative way to improve the speed of SA and UA is using surrogate model. The surrogate model is derived from the input as well as output data of the original code, assuming the code as a black box. The most common method is using response surface method (RSM) as a surrogate for the code, the input parameters are then sampled from their assumed distribution and the corresponding value of the response surface function is calculated. However, a couple of input parameters need hundreds or even thousands of original code calculations. The large number of runs is an obvious disadvantage of this method. Besides, the second disadvantage is an appropriate response surface function must be selected (e.g. quadratic, cubic, quartic, with or without cross product terms, or using a non-polynomial form) to avoid the overfit and underfit problem. This process is time consuming and expensive. Polynomial chaos expansion method is a reasonably fast and attractive alternative, stochastic model. The chaos expansion provides an efficient high-order method of including non-linear effects in stochastic analysis. Usually, the information about the model parameters and their probability distribution is limited and the dependence between them is not known. However, if arbitrary polynomial chaos is used, instead of assuming probability distribution for input parameters which may introduces additional subjectivity into the analysis, the available information can directly and most purely be used in stochastic analysis based on arbitrary data distribution. Thus, it is not necessary to know the exact probability density functions to perform SA and UA based on arbitrary polynomial chaos (aPC). The aPC has been applied for uncertainty quantification in many fields (e.g. in solid mechanics, fluid flows, thermal sciences), and become widely used in nuclear industry recently. Mk1 PB-FHR is a small modular fluoride-salt-cooled, high-temperature reactors (FHRs) that is a concept design by University of California, Berkeley (UCB). It has inherently safe features like natural-circulation-driven systems (e.g. direct reactor auxiliary cooling system (DRACS)) to passively remove decay heat from the reactor core during design basis and beyond design. It is necessary to perform SA and UA, since the licensing process of this new kind of reactor is under way and there are many design parameters that have not been fixed. Current nuclear commercial codes, such as RELAP5, have mainly been developed for light water reactors, which require the use of comprehensive two-phase flow models. This capability is not required to simulate single-phase flow phenomena in FHRs, whose baseline coolant, flibe, remains liquid up to 1430 deg. C at atmospheric pressure. The FHR advanced natural circulation analysis (FANCY) code has been developed specifically for FHR technology modeling and validation work has been performed by using CIET data in UCB. The code has been renamed General Flow (GenFlow) because it has been further developed to have the capability to model complicated pipework system based on object-oriented concept for user friendly purpose. Besides, it can be used to simulate both the force circulation as well as natural circulation. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Towards Z-Next: The Integration of Theory, Experiments, and Computational Simulation in a Bayesian Data Assimilation Framework

Making reliable predictions in the presence of uncertainty is critical to high-consequence modeling and simulation activities, such as those encountered at Sandia National Laboratories. Surrogate or reduced-order models are often used to mitigate the expense of performing quality uncertainty analyses with high-fidelity, physics-based codes. However, phenomenological surrogate models do not always adhere to important physics and system properties. This project develops surrogate models that integrate physical theory with experimental data through a maximally-informative framework that accounts for the many uncertainties present in computational modeling problems. Correlations between relevant outputs are preserved through the use of multi-output or co-predictive surrogate models; known physical properties (specifically monotoncity) are also preserved; and unknown physics and phenomena are detected using a causal analysis. By endowing surrogate models with key properties of the physical system being studied, their predictive power is arguably enhanced, allowing for reliable simulations and analyses at a reduced computational cost.

97 MATHEMATICS AND COMPUTING↗

Sequential Importance Sampling for Rare Event Estimation with Computer Experiments

Importance sampling often drastically improves the variance of percentile and quantile estimators of rare events. We propose a sequential strategy for iterative refinement of importance distributions for sampling uncertain inputs to a computer model to estimate quantiles of model output or the probability that the model output exceeds a fixed or random threshold. A framework is introduced for updating a model surrogate to maximize its predictive capability for rare event estimation with sequential importance sampling. Examples of the proposed methodology involving materials strength and nuclear reactor applications will be presented. The conclusions are: (1) Importance sampling improves UQ of percentile and quantile estimates relative to brute force approach; (2) Benefits of importance sampling increase as percentiles become more extreme; (3) Iterative refinement improves importance distributions in relatively few iterations; (4) Surrogates are necessary for slow running codes; (5) Sequential design improves surrogate quality in region of parameter space indicated by importance distributions; and (6) Importance distributions and VRFs stabilize quickly, while quantile estimates may converge slowly.

97 MATHEMATICS AND COMPUTING↗

Light Water Reactor Sustainability Program Status of Adaptive Surrogates within the RAVEN framework

The RAVEN code has been under development at the Idaho National Laboratory since 2012. Its main goal is to create a multi-purpose platform for the deploying of all the capabilities needed for Probabilistic Risk Assessment, uncertainty quantification, data mining analysis and optimization studies. RAVEN has demonstrated a good level of maturity in terms of state-of-art and advanced analysis methodologies. Indeed, in the past year the RAVEN code has been released as open-source project and is available to download (raven.inl.gov) free of charge. The main subject of this report is to show the activities that have been recently accomplished with respect the adaptive surrogate modeling: Implementation of the metric system for the assessment of surrogate model validity; Implementation of cross-validation techniques for the global assessment of surrogate models; Implementation of an automatic infrastructure for switching between a high-fidelity model (e.g. physical code) and a surrogate or set of surrogates; Implementation of a scheme for automatic optimization of surrogate model parameters. The aim of this document is to report the status of the development of methods, within the RAVEN framework, to assess the validity of the predictive capabilities of surrogate models. Indeed, after the construction of a surrogate tight to a certain physical model, it is crucial to assess the goodness of its representation, in order to be confident with its prediction. A cross-validation technique has been employed. This report will highlight the implementation details and proof its correct implementation by an application example. The implementation of a way to assess the predictive capabilities of a surrogate allowed the construction of a RAVEN new entity named “HybridModel” that is aimed to switch between an high-fidelity code and its linked surrogate. In addition, leveraging the optimization algorithms that have been implemented in RAVEN last fiscal year, a new scheme has been developed for automatic tuning of the surrogates’ parameters (e.g. penalty factors in support vector machines).

97 MATHEMATICS AND COMPUTING↗

GANpiler

Focal Area(s): Rather than augment or replace physical models with machine learning, we instead preserve the existing models and augment the underlying code with faster surrogate models created by generative adversarial networks (GAN). To leverage the performance optimization, we also propose a runtime system and user interfaces that allow prediction and tracking of accumulated error as well as dynamic, per-process decision making as to which model (if any) to use for each iteration. Science Challenge: This proposal sits at the nexus of two hard problems. First, climate models based on machine learning will be, by their nature, difficult to trust once their predictions begin diverging from the consensus. Second, compilers and hardware have been making only incremental performance gains for decades. GPGPUs have provided a welcome performance boost for codes that can take advantage of them, but there is no similar technology on the horizon to provide the next performance leap.

54 ENVIRONMENTAL SCIENCES↗

Application of Gaussian Process Modeling to Analysis of Functional Unreliability

This paper applies Gaussian Process (GP) modeling to analysis of the functional unreliability of a “passive system.” GPs have been used widely in many ways [1]. The present application uses a GP for emulation of a system simulation code. Such an emulator can be applied in several distinct ways, discussed below. All applications illustrated in this paper have precedents in the literature; the present paper is an application of GP technology to a problem that was originally analyzed [2] using neural networks (NN), and later [3, 4] by a method called “Alternating Conditional Expectations” (ACE). This exercise enables a multifaceted comparison of both the processes and the results. Given knowledge of the range of possible values of key system variables, one could, in principle, quantify functional unreliability by sampling from their joint probability distribution, and performing a system simulation for each sample to determine whether the function succeeded for that particular setting of the variables. Using previously available system simulation codes, such an approach is generally impractical for a plant-scale problem. It has long been recognized, however, that a well-trained code emulator or surrogate could be used in a sampling process to quantify certain performance metrics, even for plant-scale problems. “Response surfaces” were used for this many years ago. But response surfaces are at their best for smoothly varying functions; in regions of parameter space where key system performance metrics may behave in complex ways, or even exhibit discontinuities, response surfaces are not the best available tool. This consideration was one of several that drove the work in [2]. In the present paper, (1) the original quantification of functional unreliability using NN [2], and later ACE [3], is reprised using GP; (2) additional information provided by the GP about uncertainty in the limit surface, generally unavailable in other representations, is discussed; (3) a simple forensic exercise is performed, analogous to the inverse problem of code calibration, but with an accident management spin: given an observation about containment pressure, what can we say about the system variables? References 1. For an introduction to GPs, see (for example) Gaussian Processes for Machine Learning, C. E. Rasmussen and C. K. I. Williams (MIT, 2006). 2. Reliability Quantification of Advanced Reactor Passive Safety Systems, J. J. Vandenkieboom, PhD Thesis (University of Michigan, 1996). 3. Z. Cui, J. C. Lee, J. J. Vandenkieboom, and R. W. Youngblood, “Unreliability Quantification of a Containment Cooling System through ACE and ANN Algorithms,” Trans. Am. Nucl. Soc. 85, 178 (2001). 4. Risk and Safety Analysis of Nuclear Systems, J. C. Lee and N. J. McCormick (Wiley, 2011). See especially §11.2.4.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗