Search NASA⌕ Search

SEARCH · Search NASA

Results for “SURROGATE MODEL”

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 1,459 records · Page 81

Surrogate oracles, generalized dependency and simpler models

Software reliability models require the sequence of interfailure times from the debugging process as input. It was previously illustrated that using data from replicated debugging could greatly improve reliability predictions. However, inexpensive replication of the debugging process requires the existence of a cheap, fast error detector. Laboratory experiments can be designed around a gold version which is used as an oracle or around an n-version error detector. Unfortunately, software developers can not be expected to have an oracle or to bear the expense of n-versions. A generic technique is being investigated for approximating replicated data by using the partially debugged software as a difference detector. It is believed that the failure rate of each fault has significant dependence on the presence or absence of other faults. Thus, in order to discuss a failure rate for a known fault, the presence or absence of each of the other known faults needs to be specified. Also, in simpler models which use shorter input sequences without sacrificing accuracy are of interest. In fact, a possible gain in performance is conjectured. To investigate these propositions, NASA computers running LIC (RTI) versions are used to generate data. This data will be used to label the debugging graph associated with each version. These labeled graphs will be used to test the utility of a surrogate oracle, to analyze the dependent nature of fault failure rates and to explore the feasibility of reliability models which use the data of only the most recent failures.

Wilson, Larry↗

Artificial Intelligence/Machine Learning Technologies for Advanced Reactors (Workshop Summary Report)

A workshop on artificial intelligence and machine learning (AI/ML) for advanced reactors (AR) was held October 5-6, 2021. The workshop was to be attended in-person at ANL but COVID restrictions forced the workshop to go virtual. The objectives of the workshop were to identify the most promising AI/ML opportunities for improving advanced reactor design, optimizing plant performance, and enhancing economic competitiveness and to develop an understanding of the scientific, engineering and licensing challenges facing their application. The workshop planning committee included GAIN, EPRI and NEI and members of three national laboratories (ANL, INL, and ORNL). The workshop was attended by more than 200 individuals representing academic and scientific institutions and the nuclear power industry. The definition put forth for an AI/ML system was one that perceives its environment and takes actions that maximize its chance of achieving its goals. In this report AI/ML refers to next generation algorithms that include deep learning, statistical analysis and data analytics and associated scientific computing and their potential application to the design, licensing, operation and maintenance of ARs. These methods typically incorporate models built from process data and may also include data generated by simulations that represent the behavior of a system. The workshop was organized in response to the growing interest in application of AI/ML for improving the economic competitiveness of nuclear energy. Increasingly more resources are being allocated to investigating the benefits of AI/ML methods. The DOE created the Artificial Intelligence & Technology Office to promote their development. And within the Office of Nuclear Energy, resources have been allocated to explore and understand the potential benefits of AI/ML. Additionally, the national laboratories are strategically positioned with DOE computing facilities such as Summit, Perlmutter, Aurora and Frontier that support large-scale simulations, hybrid HPC models with AI surrogates, and the exploration of new types of generative models emerging from multi-model data streams and sources. The workshop was organized with members of the AR community to understand the effort and to identify the level of interest and progress in this emerging technology. The workshop discussions focused on identifying opportunities for AI/ML across diverse areas of the nuclear industry and identifying current scientific and engineering challenges for advanced reactors that might be addressed through transformational uses of AI/ML. Discussion panels focused on four high-interest technical domains for advanced reactors: design, maintenance and operations, energy storage, and materials. The results of those discussions are summarized in this report. This includes opportunities that were identified for exploiting AI techniques and methods to improve the efficacy and efficiency of reactor analysis and to improve the operation and optimization of advanced reactors. Advanced reactor developers expressed an interest in learning more about AI/ML methods and their application. This included understanding whether ML methods can provide an advantage over existing nonlinear data regression methods for collapsing high-fidelity simulation results into faster running models. A consensus emerged that AR advances planned for the next decade will benefit from the use of AI/ML tools. The need exists to understand and model complex systems across length scales and modalities. AI/ML is a tool for discovery that can yield a set of engineering principles for use by nuclear engineers, licensing bodies, and operators to solve problems in plant design, safety analyses, autonomous operation, and predictive maintenance. While AI/ML represents a new set of tools, an awareness by the nuclear community of the full potential is still in the early stages so there is a need to increase awareness. It appears that the wide-spread adoption of AI/ML tools for ARs would be facilitated by future educational workshops that describe foundational methods and capabilities and describe successful applications.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Deep-learning-enabled Bayesian inference of fuel magnetization in magnetized liner inertial fusion

Fuel magnetization in magneto-inertial fusion (MIF) experiments improves charged burn product confinement, reducing requirements on fuel areal density and pressure to achieve self-heating. By elongating the path length of 1.01 MeV tritons produced in a pure deuterium fusion plasma, magnetization enhances the probability for deuterium–tritium reactions producing 11.8-17.1 MeV neutrons. Nuclear diagnostics thus enable a sensitive probe of magnetization. Characterization of magnetization, including uncertainty quantification, is crucial for understanding the physics governing target performance in MIF platforms, such as magnetized liner inertial fusion (MagLIF) experiments conducted at Sandia National Laboratories, Z-facility. We demonstrate a deep-learned surrogate of a physics-based model of nuclear measurements. A single model evaluation is reduced from O ( 10 – 100 ) (10–100) CPU hours on a high-performance computing cluster down to O ( 10 – 100 ) (10) ms on a laptop. This enables a Bayesian inference of magnetization, rigorously accounting for uncertainties from surrogate modeling and noisy nuclear measurements. The approach is validated by testing on synthetic data and comparing with a previous study. We analyze a series of MagLIF experiments systematically varying preheat, resulting in the first ever systematic experimental study of magnetic confinement properties of the fuel plasma as a function of fundamental inputs on any neutron-producing MIF platform. We demonstrate that magnetization decreases from B R ∼ 0.2 ~0.5 to B R ∼ 0.2 ~0.2 MG cm as laser preheat energy deposited increases from E preheat ∼ 460 ~460 J to E preheat ∼ 460 ~1.4 kJ. This trend is consistent with 2D LASNEX simulations showing Nernst advection of the magnetic field out of the hot fuel and diffusion into the target liner.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Recent Progress in the Development of Diesel Surrogate Fuels

There has been much recent progress in the area of surrogate fuels for diesel. In the last few years, experiments and modeling have been performed on higher molecular weight components of relevance to diesel fuel such as n-hexadecane (n-cetane) and 2,2,4,4,6,8,8-heptamethylnonane (iso-cetane). Chemical kinetic models have been developed for all the n-alkanes up to 16 carbon atoms. Also, there has been much experimental and modeling work on lower molecular weight surrogate components such as n-decane and do-decane which are most relevant to jet fuel surrogates, but are also relevant to diesel surrogates where simulation of the full boiling point range is desired. For the cycloalkanes, experimental work on decalin and tetralin recently has been published. For multi-component surrogate fuel mixtures, recent work on modeling of these mixtures and comparisons to real diesel fuel is reviewed. Detailed chemical kinetic models for surrogate fuels are very large in size. Significant progress also has been made in improving the mechanism reduction tools that are needed to make these large models practicable in multidimensional reacting flow simulations of diesel combustion. Nevertheless, major research gaps remain. In the case of iso-alkanes, there are experiments and modeling work on only one of relevance to diesel: iso-cetane. Also, the iso-alkanes in diesel are lightly branched and no detailed chemical kinetic models or experimental investigations are available for such compounds. More components are needed to fill out the iso-alkane boiling point range. For the aromatic class of compounds, there has been no new work for compounds in the boiling point range of diesel. Most of the new work has been on alkyl aromatics that are of the range C7 to C8, below the C10 to C20 range that is needed. For the chemical class of cycloalkanes, experiments and modeling on higher molecular weight components are warranted. Finally for multi-component surrogates needed to treat real diesel, the inclusion of higher molecular weight components is needed in models and experimental investigations.

02 PETROLEUM↗

Recent Progress in the Development of Diesel Surrogate Fuels

There has been much recent progress in the area of surrogate fuels for diesel. In the last few years, experiments and modeling have been performed on higher molecular weight components of relevance to diesel fuel such as n-hexadecane (n-cetane) and 2,2,4,4,6,8,8-heptamethylnonane (iso-cetane). Chemical kinetic models have been developed for all the n-alkanes up to 16 carbon atoms. Also, there has been much experimental and modeling work on lower molecular weight surrogate components such as n-decane and n-dodecane that are most relevant to jet fuel surrogates, but are also relevant to diesel surrogates where simulation of the full boiling point range is desired. For two-ring compounds, experimental work on decalin and tetralin recently has been published. For multi-component surrogate fuel mixtures, recent work on modeling of these mixtures and comparisons to real diesel fuel is reviewed. Detailed chemical kinetic models for surrogate fuels are very large in size. Significant progress also has been made in improving the mechanism reduction tools that are needed to make these large models practicable in multi-dimensional reacting flow simulations of diesel combustion. Nevertheless, major research gaps remain. In the case of iso-alkanes, there are experiments and modeling work on only one of relevance to diesel: iso-cetane. Also, the iso-alkanes in diesel are lightly branched and no detailed chemical kinetic models or experimental investigations are available for such compounds. More components are needed to fill out the iso-alkane boiling point range. For the aromatic class of compounds, there has been no new work for compounds in the boiling point range of diesel. Most of the new work has been on alkyl aromatics that are of the range C7 to C8, below the C10 to C20 range that is needed. For the chemical class of cycloalkanes, experiments and modeling on higher molecular weight components are warranted. Finally for multi-component surrogates needed to treat real diesel, the inclusion of higher molecular weight components is needed in models and experimental investigations.

10 SYNTHETIC FUELS↗

Optimization of Desalination Systems with Detailed Water Chemistry through Integration of Reaktoro in WaterTAP

Chemistry predictions are critical for an accurate estimation of performance and costs in desalination process models, which allows for the estimation of the value of new technologies and the viability of treating new water sources. Herein, we present how an implicit function formulation can be used to integrate the chemical modeling package, Reaktoro, into the techno-economic assessment and modeling platform, WaterTAP. This approach resolves the critical issues of integrating large-scale thermodynamic models and databases into equation-oriented process models while allowing more flexibility relative to previously presented surrogate-based methods. We describe how this integration into Pyomo and WaterTAP models is implemented and used through the open-source package Reaktoro-PSE . We first validate this integration approach by performing optimization on a previously presented desalination treatment train with softening and acid addition as the pretreatment steps. Then, to demonstrate the value of this approach, we extend the cost-optimization problem to include the simultaneous addition of lime and soda ash for softening, and HCl and H 2 SO 4 in the acidification steps. Finally, we were able to confirm the previously established results that were obtained by using surrogate models and demonstrate that the implicit function approach enables exploration of different feedwater compositions and a larger number of chemicals and their combinations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Data driven learning of robust nonlocal models

Nonlocal models use integral operators that embed length-scales in their definition. However, the integrands in these operators are difficult to define from the data that are typically available for a given physical system, such as laboratory mechanical property tests. In contrast, molecular dynamics (MD) does not require these integrands, but it suffers from computational limitations in the length and time scales it can address. To combine the strengths of both methods and to obtain a coarse-grained, homogenized continuum model that efficiently and accurately captures materials' behavior, we propose a learning framework to extract, from MD data, an optimal nonlocal model as a surrogate for MD displacements. Our framework guarantees that the resulting model is mathematically well-posed, physically consistent, and that it generalizes well to settings that are different from the ones used during training. The efficacy of this approach is demonstrated with several numerical tests for single layer graphene both in the case of perfect crystal and in the presence of thermal noise.

36 MATERIALS SCIENCE↗

Model of Mixing Layer With Multicomponent Evaporating Drops

A mathematical model of a three-dimensional mixing layer laden with evaporating fuel drops composed of many chemical species has been derived. The study is motivated by the fact that typical real petroleum fuels contain hundreds of chemical species. Previously, for the sake of computational efficiency, spray studies were performed using either models based on a single representative species or models based on surrogate fuels of at most 15 species. The present multicomponent model makes it possible to perform more realistic simulations by accounting for hundreds of chemical species in a computationally efficient manner. The model is used to perform Direct Numerical Simulations in continuing studies directed toward understanding the behavior of liquid petroleum fuel sprays. The model includes governing equations formulated in an Eulerian and a Lagrangian reference frame for the gas and the drops, respectively. This representation is consistent with the expected volumetrically small loading of the drops in gas (of the order of 10 3), although the mass loading can be substantial because of the high ratio (of the order of 103) between the densities of liquid and gas. The drops are treated as point sources of mass, momentum, and energy; this representation is consistent with the drop size being smaller than the Kolmogorov scale. Unsteady drag, added-mass effects, Basset history forces, and collisions between the drops are neglected, and the gas is assumed calorically perfect. The model incorporates the concept of continuous thermodynamics, according to which the chemical composition of a fuel is described probabilistically, by use of a distribution function. Distribution functions generally depend on many parameters. However, for mixtures of homologous species, the distribution can be approximated with acceptable accuracy as a sole function of the molecular weight. The mixing layer is initially laden with drops in its lower stream, and the drops are colder than the gas. Drop evaporation leads to a change in the gas-phase composition, which, like the composition of the drops, is described in a probabilistic manner

Bellan, Josette↗

Dataset for SIAM MPI23 Project "Model inversion for complex physical systems using low-dimensional surrogates"

Training and testing data for the SIAM MPI23 workshop "Model inversion for complex physical systems using low-dimensional surrogates". The data consists of ensembles of input and output pairs corresponding to queries of a 2D saturated groundwater flow model. The inputs consist of random vectors which map to discretized model parameter fields via a Kosambi-Karhunen-Loève expansion. Output corresponds to discretized pressure fields.

basis adaptation, conditional Karhunen-Loève expan↗

Modeling of autoignition and NO sensitization for the oxidation of IC engine surrogate fuels

This paper presents an approach for modeling with one single kinetic mechanism the chemistry of the autoignition and combustion processes inside an internal combustion engine, as well as the chemical kinetics governing the postoxidation of unburned hydrocarbons in engine exhaust gases. Therefore a new kinetic model was developed, valid over a wide range of temperatures including the negative temperature coefficient regime. The model simulates the autoignition and the oxidation of engine surrogate fuels composed of n-heptane, iso-octane, and toluene, which are sensitized by the presence of nitric oxides. The new model was obtained from previously published mechanisms for the oxidation of alkanes and toluene where the coupling reactions describing interactions between hydrocarbons and NO{sub x} were added. The mechanism was validated against a wide range of experimental data obtained in jet-stirred reactors, rapid compression machines, shock tubes, and homogeneous charge compression ignition engines. Flow rate and sensitivity analysis were performed in order to explain the low temperature chemical kinetics, especially the impact of NO{sub x} on hydrocarbon oxidation. (author)

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A data-driven peridynamic continuum model for upscaling molecular dynamics

Nonlocal models, including peridynamics, often use integral operators that embed lengthscales in their definition. However, the integrands in these operators are difficult to define from the data that are typically available for a given physical system, such as laboratory mechanical property tests. In contrast, molecular dynamics (MD) does not require these integrands, but it suffers from computational limitations in the length and time scales it can address. To combine the strengths of both methods and to obtain a coarse-grained, homogenized continuum model that efficiently and accurately captures materials’ behavior, we propose a learning framework to extract, from MD data, an optimal Linear Peridynamic Solid (LPS) model as a surrogate for MD displacements. To maximize the accuracy of the learnt model we allow the peridynamic influence function to be partially negative, while preserving the well-posedness of the resulting model. To achieve this, we provide sufficient well-posedness conditions for discretized LPS models with sign-changing influence functions and develop a constrained optimization algorithm that minimizes the equation residual while enforcing such solvability conditions. This framework guarantees that the resulting model is mathematically well-posed, physically consistent, and that it generalizes well to settings that are different from the ones used during training. We illustrate the efficacy of the proposed approach with several numerical tests for single layer graphene. Our two-dimensional tests show the robustness of the proposed algorithm on validation data sets that include thermal noise, different domain shapes and external loadings, and discretizations substantially different from the ones used for training.

homogenization↗

Invertible Neural Networks for Airfoil Design

We report the airfoil design problem, in which an engineer seeks a shape with desired performance characteristics, is fundamental to aerodynamics. Design workflows traditionally rely on iterative optimization methods using low-fidelity integral boundary-layer methods as higher-fidelity adjoint-based computational fluid dynamics methods are computationally expensive. Surrogate-based approaches can accelerate the design process but still rely on some iterative inverse design procedure. In this work, we leverage emerging invertible neural network (INN) tools to enable the rapid inverse design of airfoil shapes for wind turbines. INNs are specialized deep-learning models with well-defined inverse mappings. When trained appropriately, INN surrogate models are capable of forward prediction of aerodynamic and structural quantities for a given airfoil shape as well as inverse recovery of airfoil shapes with specified aerodynamic and structural characteristics. The INN approach offers a roughly 100 times speed-up compared to adjoint-based methods for inverse design. We demonstrate the INN tool for inverse design on three test cases of 100 airfoils each that satisfy the performance characteristics close to those of airfoils used in wind-turbine blades. All generated shapes satisfy the desired aerodynamic characteristics, demonstrating the success of the INN approach for inverse design of airfoils.

17 WIND ENERGY↗

An efficient Bayesian inversion of a geothermal prospect using a multivariate adaptive regression spline method

In this study, an efficient Bayesian framework equipped with a multivariate adaptive regression spline (MARS) technique is developed to alleviate computational burdens encountered in a conventional Bayesian inversion of a geothermal prospect. Fast MARS models are developed from training dataset generated by CPU-intensive hydrothermal models and used as surrogate of high-fidelity physical models in Markov Chain Monte Carlo (MCMC) sampling. This Bayesian inference with MARS-enabled MCMC method is used to reduce prior estimates of uncertainty in structural or characteristic hydrothermal flow parameters of the model to posterior distributions. A geothermal prospect near Superstition Mountain in Imperial County of California in USA is used to illustrate the proposed framework and demonstrate the computational efficiency of MARS-based Bayesian inversion. The developed MARS models are also used to efficiently drive calculation of Sobol’ total sensitivity indices. Furthermore, only top sensitive parameters are included in Bayesian inference to further improve the computational efficiency of inversion. Sensitivity analysis also confirms that water circulation through high permeable structures, rather than heat conduction through impermeable granite, is the primary heat transfer method. The presented framework is demonstrated an efficient tool to update knowledge of geothermal prospects by inversing field data. Although only thermal data is used in this study, other type of data, such as flow and transport observations, can be jointly used in this method for underground hydrocarbon reservoirs.

15 GEOTHERMAL ENERGY↗

Auto-ignition study of FACE gasoline and its surrogates at advanced IC engine conditions

Robust surrogate formulation for gasoline fuels is challenging, especially in mimicking auto-ignition behavior observed under advanced combustion strategies including boosted spark-ignition and advanced compression ignition. This work experimentally quantifies the auto-ignition behavior of bi- and multi-component surrogates formulated to represent a mid-octane (Anti-Knock Index 91.5), full boiling-range, research grade gasoline (Fuels for Advanced Combustion Engines, FACE-F). A twin-piston rapid compression machine is used to achieve temperature and pressure conditions representative of in-cylinder engine operation. Changes in low- and intermediate-temperature behavior, including first-stage and main ignition times, are quantified for the surrogates and compared to the gasoline. This study identifies significant discrepancies in the first-stage ignition behavior, the influence of pressure for the bi- to ternary blends, and highlights that better agreement is achieved with multi-component surrogates, particularly at lower temperature regimes. A recently-updated detailed kinetic model for gasoline surrogates is also used to simulate the measurements. Finally, sensitivity analysis is employed to interpret the kinetic pathways responsible for reactivity trends in each gasoline surrogate.

36 MATERIALS SCIENCE↗

Implicit neural representations for experimental steering of advanced experiments

Scattering measurements using electrons, neutrons, or photons are essential for obtaining microscopic insights into materials. However, limited facility availability and high-dimensional scattering data necessitate more efficient experimental steering techniques. Here, we report a machine learning method that guides scattering data collection and facilitates real-time estimation of model parameters, given a reliable forward model to simulate experimental signals. We employ implicit neural representations as efficient surrogates that link model parameters with simulated spectroscopies. This enables a Bayesian optimal experimental design framework to estimate the probability distributions of parameters from high-dimensional scattering data. We demonstrate the proposed method using inelastic neutron scattering with simulated and real experimental data, highlighting the method’s ability to provide real-time parameter estimation with quantified uncertainties and to deliver informed experimental guidance that reduces experimental time while maximizing scientific output. This approach paves the way for accelerated discoveries in condensed matter through scattering measurements.

36 MATERIALS SCIENCE↗

Learning to Simulate Aerosol Dynamics with Graph Neural Networks

Aerosol effects on climate, weather, and air quality depend on characteristics of individual particles, which are tremendously diverse and change in time. Particle-resolved models are the only models able to capture this diversity in particle physiochemical properties, and these models are computationally expensive. As a strategy for accelerating particle-resolved microphysics models, we introduce Graph-based Learning of Aerosol Dynamics (GLAD) and use this model to train a surrogate of the particle-resolved model PartMC-MOSAIC. GLAD implements a Graph Network-based Simulator (GNS), a machine learning framework that has been used to simulate particle-based fluid dynamics models. In GLAD, each particle is represented as a node in a graph, and the evolution of the particle population over time is simulated through learned message passing. Here, we demonstrate our GNS approach on a simple aerosol system that includes condensation of sulfuric acid onto particles composed of sulfate, black carbon, organic carbon, and water. A graph with particles as nodes is constructed, and a graph neural network (GNN) is then trained using the model output from PartMC-MOSAIC. The trained GNN can then be used for simulating and predicting aerosol dynamics over time. Results demonstrate the framework's ability to accurately learn chemical dynamics and generalize across different scenarios, achieving efficient training and prediction times. We evaluate the performance across four scenarios, highlighting the framework's robustness and adaptability in modeling aerosol microphysics and chemistry.

aerosol chemistry dynamics↗