SEARCH · Engineering Papers

Results for “surrogate systems modeling”

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 127 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Mixed-Integer Linear Programming Formulation with Embedded Machine Learning Surrogates for the Design of Chemical Process Families

In previous work, we introduced process family design. The main idea is to design a platform of common elements, and, allowing us to capture additional cost savings, simultaneously design a family of processes, and reducing both engineering and deployment timelines. We formulate this as an optimization problem, specifically a nonlinear generalized disjunctive program (GDP). We have proposed two approaches for reformulating and solving this problem: one based on full-discretization of the design space and one that uses Machine Learning (ML) surrogates to replace the nonlinear process models. Using ML surrogates to predict required system costs and performance indicators allows us to reformulate the nonlinearities in the GDP generate an efficient MILP formulation. In this work, we apply the ML surrogate approach to two case studies. One case study involves designing a family of carbon capture systems to cover a set of different flue gas flow rates and inlet CO 2 concentrations, where we consider the absorber and stripper as common unit module types. The second case study focuses on a water-desalination process, where we design a family of these processes for a variety of salt concentrations and flow rates. In both of these case studies, we demonstrate a scalable optimization approach that enables the design of multiple processes simultaneously, reducing the time-to-market and overall costs by maximizing the cost savings due to both economies of scale and economies of numbers.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

Density functional theory calculation of helium segregation and decohesion effect in W110/Ni111 interphase boundary

Density functional theory (DFT) is employed to study the preferential distribution and decohesion effect of He in a W-NiFe composite consisting of W particles embedded in an Ni-based solid solution matrix. A slab containing {110}<100>W//{111}<110>Ni interface is employed as a surrogate model for the W-NiFe system. Firstly, the fracture energy of the W/Ni interphase boundary (IB) (4.37 J/m 2 ) is higher than the cleavage energy of Ni{111} (3.82 J/m^2) and lower than the cleavage energy of W{110} (6.60 J/m 2 ). The comparison shows that the cohesion of the IB is stronger than the Ni{111} planes that are away from the IB. However, the cohesion between the Ni{111} planes adjacent to the IB is found to be the weakest in this system, with a cleavage energy of 3.11 J/m 2 . Subsequently, formation energy of He is calculated in the Ni slab, W slab, and various interstitial sites in the IB. The DFT calculations show that He is significantly more stable in Ni than in W, by about 1.75 eV. Interestingly, He does not prefer to segregate at the IB as compared to bulk Ni. Nevertheless, it prefers to segregate to the region between the Ni{111} planes adjacent to the IB, and decreases the cohesion of the already weakest region. Based on an estimated amount of He gas production in 5 years under first wall neutron irradiation (neutron flux of 1.04x10 15 n/cm 2 /s), the He will decrease the cleavage energy of the weakest region by 21.2%, 15.4%, and 12.2% at 800, 1000, and 1200 C, respectively.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2021

Surrogate multi-fidelity data and model fusion for scientific discovery and uncertainty quantification in Earth System Models

This whitepaper addresses the Earth and Environmental Systems Sciences Division (EESSD)’s predictability challenges in modeling the integrated water cycle and data-model integration. Specifically, it focuses on reducing and characterizing the uncertainty in the representation of process models for unresolved physics, either due to model resolution or limited by the physical under standing or computational efficiency, and the use of observational data for in-situ process parameter optimization within ESM. The described methods may also be used to determine the nature of responses (e.g. strength and direction), and hence to identify critical processes that drive the overall ESM responses to perturbation in the forcing

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

A Strategy for NACS investment in Machine Learning

The Nuclear and Chemical Sciences (NACS) Division furnishes the expertise in the scientific areas of chemical, nuclear and isotopic sciences that are foundational in the Laboratory’s national security missions. This expertise is maintained and advanced through identification, development and application of state-of-the-art theoretical, computational and experimental methods and tools. Recent developments in artificial intelligence and machine learning (AI/ML) techniques enabled by advances in computing capabilities and widespread availability of powerful software implementations have made use of these techniques ubiquitous across both science and industry. While the scope of AI/ML applications is incredibly large and evolves very rapidly, the topics most relevant to NACS missions fall into the general category of detecting, categorizing or identifying features in large, complex datasets using either supervised or unsupervised learning. This covers both basic scientific data analysis and the development of efficient surrogate models of real-life technological systems, experimental detectors, or theoretical models. To remain at the forefront of its core scientific disciplines, NACS must both cultivate ML expertise as well as continuously explore applying this expertise to new problems or utilizing new methods. This document identifies the key areas where this support is critical and provides a strategy for investing in them.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

DOE OSTI2022

Extended Modeling of DOE Sealed Canisters with Updated Chemistry Models

Road-ready and final disposition packaging configurations for the advanced test reactor (ATR) fuel currently specifies storage within helium backfilled DOE sealed standard canisters. The aluminum cladding of the ATR fuel contains an oxyhydroxide layer of boehmite/bayerite that generates hydrogen when subjected to irradiation. Understanding the effect of this hydrogen buildup over time to important for long term storage considerations. Previous modeling efforts have built a coupled CFD-chemical model to simulate the temperature gas phase concentrations within the DOE sealed standard canisters. These models have coupled the temperature conditions to both the gas phase radiolysis chemistry and the surface chemistry associated with the oxyhydroxide layer. The previous iteration of the model utilized constant G-values for the hydrogen generation a 50-year period. This new iteration of the model utilizes new experimental data to update the hydrogen generation rate, as well as increase the simulated time to a 200-year period. Given the half-life assumed for the primary Cs-137 isotope responsible for gamma radiation in the ATR spent fuel, the 200-year period decreases the decay heat and dose rate of the spent fuel by a factor of 100, which combined with the updated chemistry substantially decreases new hydrogen generation. Continued experimental work has identified trends for aluminum surrogate samples with oxyhydroxide layers for tests done at higher dose rates. At low initial doses a fast generation rate of hydrogen occurs which starts to roll over to a lower generation as the total dose applied increase. A small-scale chemical model was built to replicate as mini-canister surrogate system at SRNL as well as for the smaller capsule tests performed at INL. A variety of chemical models to capture this effect were tested, and a back reaction of H radical absorbing onto the surface, or inhibition of the reaction by significant H 2 cover gas were both able to fit both the mini-canister and the small capsule test data. Both kinetic fits were used to generate data from the new 200-year simulation. As additional experiments continue, the kinetic fits may be adjusted to adapt to new data. However, updated data shows that hydrogen atmosphere has little effect on actual generation data, so the model was reverted to use a star-stepped G-value for low-dose and high-dose regions. For the undried fuel case, the three models differ significantly with an end concentration of 1% for back reaction, 4.2% for inhibition, and 13.1% for constant G-value for the nominal scenario. For the dried fuel case, the nominal cases showed end concentrations of 0.23% for back reaction, 1.9% for inhibition, and 4.2% for const G-value for the nominal scenario. For the constant G-value case that is less conservative than the other two, the pressure for undried fuel increases to 1.94 atm over 200 years for the nominal case and 2.11 atm for the high decay heat case. The total hydrogen concentration after 200 years is 4.92% for the low decay heat case and 27.4% for the high decay heat case for undried fuel and is 1.4% and 9.6% for low and high decay heat fuel for the dried fuel case. If small amount of residual air is present, the potential for nitric acid formation of 595, 1568, and 2816 ppm for the lower, nominal, and upper fuel decay heat can occur. At long-term timeframes no significant shift in major species present occurs, so no appreciable amount of oxygen is present in the system. The continued rate of hydrogen generation in the canister occurs at an increase of 0.04% by mole over the final 10 years. Increasing the model range out to 1000 years continues to drop the hydrogen generation rate through decreasing dose rate.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

NASA NTRS2005

Multidisciplinary Multiobjective Optimal Design for Turbomachinery Using Evolutionary Algorithm

This report summarizes Dr. Lian s efforts toward developing a robust and efficient tool for multidisciplinary and multi-objective optimal design for turbomachinery using evolutionary algorithms. This work consisted of two stages. The first stage (from July 2003 to June 2004) Dr. Lian focused on building essential capabilities required for the project. More specifically, Dr. Lian worked on two subjects: an enhanced genetic algorithm (GA) and an integrated optimization system with a GA and a surrogate model. The second stage (from July 2004 to February 2005) Dr. Lian formulated aerodynamic optimization and structural optimization into a multi-objective optimization problem and performed multidisciplinary and multi-objective optimizations on a transonic compressor blade based on the proposed model. Dr. Lian s numerical results showed that the proposed approach can effectively reduce the blade weight and increase the stage pressure ratio in an efficient manner. In addition, the new design was structurally safer than the original design. Five conference papers and three journal papers were published on this topic by Dr. Lian.

Source record↗

DOE OSTI2023

Modeling DOE Standard Canister Configurations with Updated Surface Chemistry

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2025

Polynomial Chaos Surrogate Construction for Random Fields with Parametric Uncertainty

Engineering and applied science rely on computational experiments to rigorously study physical systems. The mathematical models used to probe these systems are highly complex, and sampling-intensive studies often require prohibitively many simulations for acceptable accuracy. Surrogate models provide a means of circumventing the high computational expense of sampling such complex models. In particular, polynomial chaos expansions (PCEs) have been successfully used for uncertainty quantification studies of deterministic models where the dominant source of uncertainty is parametric. We discuss an extension to conventional PCE surrogate modeling to enable surrogate construction for stochastic computational models that have intrinsic noise in addition to parametric uncertainty. We develop a PCE surrogate on a joint space of intrinsic and parametric uncertainty, enabled by Rosenblatt transformations, which are evaluated via kernel density estimation of the associated conditional cumulative distributions. Furthermore, we extend the construction to random field data via the Karhunen–Loève expansion. We then take advantage of closed-form solutions for computing PCE Sobol indices to perform a global sensitivity analysis of the model which quantifies the intrinsic noise contribution to the overall model output variance. Additionally, the resulting joint PCE is generative in the sense that it allows generating random realizations at any input parameter setting that are statistically approximately equivalent to realizations from the underlying stochastic model. The method is demonstrated on a chemical catalysis example model and a synthetic example controlled by a parameter that enables a switch from unimodal to bimodal response distributions.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Coarse-graining Hamiltonian systems using WSINDy

Abstract Weak form equation learning and surrogate modeling has proven to be computationally efficient and robust to measurement noise in a wide range of applications including ODE, PDE, and SDE discovery, as well as in coarse-graining applications, such as homogenization and mean-field descriptions of interacting particle systems. In this work we extend this coarse-graining capability to the setting of Hamiltonian dynamics which possess approximate symmetries associated with timescale separation. A smooth $$\varepsilon$$ ε -dependent Hamiltonian vector field $$X_\varepsilon$$ X ε possesses an approximate symmetry if the limiting vector field $$X_0=\lim _{\varepsilon \rightarrow 0}X_\varepsilon$$ X 0 = lim ε → 0 X ε possesses an exact symmetry. Such approximate symmetries often lead to the existence of a Hamiltonian system of reduced dimension that may be used to efficiently capture the dynamics of the symmetry-invariant dependent variables. Deriving such reduced systems, or approximating them numerically, is an ongoing challenge. We demonstrate that WSINDy can successfully identify this reduced Hamiltonian system in the presence of large perturbations imparted in the $$\varepsilon >0$$ ε > 0 regime, while remaining robust to extrinsic noise. This is significant in part due to the nontrivial means by which such systems are derived analytically. WSINDy naturally preserves the Hamiltonian structure by restricting to a trial basis of Hamiltonian vector fields. The methodology is computationally efficient, often requiring only a single trajectory to learn the global reduced Hamiltonian, and avoiding forward solves in the learning process. In this way, we argue that weak-form equation learning is particularly well-suited for Hamiltonian coarse-graining. Using nearly-periodic Hamiltonian systems as a prototypical class of systems with approximate symmetries, we show that WSINDy robustly identifies the correct leading-order system, with dimension reduced by at least two, upon observation of the relevant degrees of freedom. While our main contribution is computational, we also provide a contribution to the literature on averaging theory by proving that first-order averaging at the level of vector fields preserves Hamiltonian structure in nearly-periodic Hamiltonian systems. This provides theoretical justification for our approach as WSINDy’s computations occur at the level of Hamiltonian vector fields. We illustrate the efficacy of our proposed method using physically relevant examples, including coupled oscillator dynamics, the Hénon–Heiles system for stellar motion within a galaxy, and the dynamics of charged particles.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Resilience Enhancements through Deep Learning Yields

This report documents the Resilience Enhancements through Deep Learning Yields (REDLY) project, a three-year effort to improve electrical grid resilience by developing scalable methods for system operators to protect the grid against threats leading to interrupted service or physical damage. The computational complexity and uncertain nature of current real-world contingency analysis presents significant barriers to automated, real-time monitoring. While there has been a significant push to explore the use of accurate, high-performance machine learning (ML) model surrogates to address this gap, their reliability is unclear when deployed in high-consequence applications such as power grid systems. Contemporary optimization techniques used to validate surrogate performance can exploit ML model prediction errors, which necessitates the verification of worst-case performance for the models.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRSDate not supplied

Coaxial Rotor CFD Validation and ML Surrogate Model Generation

A fixed-pitch speed-controlled coaxial rotor system was tested in the NASA Langley Transonic Dynamics Tunnel in September 2022. The rotors have a diameter of 1.35 meters and an inter-rotor spacing of 25% of the diameter. Though this test was focused on the NASA New Frontiers Dragonfly mission, the resulting dataset is relevant to a wide array of applications of multirotor vehicles, especially those using fixed-pitch variable-speed rotors. Most notably beyond Dragonfly, perhaps, is the application of coaxial rotor pair configurations for eVTOL and Urban Air Mobility (UAM) aircraft. This work provides a thorough CFD validation study quantifying coaxial rotor performance estimation with accuracy on order 5-10% using an efficient hybrid BEMT-URANS flow solver over a wide range of operating conditions. This accuracy was achieved using novel approaches for the construction of both the C81 airfoil performance lookup tables and the BEMT rotor model. These novel approaches are combined with advanced scripting to further accelerate the commercial off-the-shelf CFD solver on GPU accelerated machines. Finally, the development of machine learning surrogate models is presented to produce highly efficient and accurate rotor performance predictions for fixed-pitch variable-speed multirotor aircraft over the complete flight regime including scout, cruise, climb, descent, as well as limiting cases of vortex-ring and windmill-brake states.

Coaxial↗

DOE OSTI2024

Data-driven models of nonautonomous systems

Nonautonomous dynamical systems are characterized by time-dependent inputs, which complicates the discovery of predictive models describing the spatiotemporal evolution of the state variables of quantities of interest from their temporal snapshots. When dynamic mode decomposition (DMD) is used to infer a linear model, this difficulty manifests itself in the need to approximate the time-dependent Koopman operators. Our approach is to approximate the original nonautonomous system with a modified system derived via a local parameterization of the time-dependent inputs. The modified system comprises a sequence of local parametric systems, which are subsequently approximated by a parametric surrogate model using the DRIPS (dimension reduction and interpolation in parameter space) framework. The offline step of DRIPS relies on DMD to build a linear surrogate model, endowed with reduced-order bases for the observables mapped from training data. The online step interpolates on suitable manifolds to construct a sequence of iterative parametric surrogate models; the target/test parameter points on these manifolds are specified by a local parameterization of the test time-dependent inputs. Here, we use numerical experimentation to demonstrate the robustness of our method and compare its performance with that of deep neural networks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Equipping Neural Network Surrogates with Uncertainty for Propagation in Physical Systems

Coarse-grained or filtered models typically rely on closure models to account for unresolved scales. For instance, large eddy simulation for modeling turbulent fluid flows explicitly resolves the largest scales, but requires modeling closure terms to account for the sub-filter scales. With the vast amount of data available from high-fidelity simulations, there are unique opportunities to leverage data-driven modeling techniques to formulate expressive and flexible closure models. Despite their flexibility, data-driven models struggle in domain shift settings, i.e. when deployed in configurations not captured in the training dataset. In particular, the efficacy of neural network surrogates is difficult to assess a priori due to the deterministic, point-estimate nature of predictions. In high-consequence applications, such models require reliable uncertainty estimates in the data-informed and out-of-distribution regimes. To quantify uncertainties in both regimes, we employ Bayesian neural networks which are able to capture both epistemic and aleatoric uncertainties. We will discuss challenges associated with the training and evaluation of these networks. Furthermore, we will discuss uncertainty embedding strategies to enable efficient sampling and propagation of uncertainty through high-fidelity simulations.

Bayesian neural networks↗

NASA NTRS2016

The Virtual Tablet: Virtual Reality as a Control System

In the field of human-computer interaction, Augmented Reality (AR) and Virtual Reality (VR) have been rapidly growing areas of interest and concerted development effort thanks to both private and public research. At NASA, a number of groups have explored the possibilities afforded by AR and VR technology, among which is the IT Advanced Concepts Lab (ITACL). Within ITACL, the AVR (Augmented/Virtual Reality) Lab focuses on VR technology specifically for its use in command and control. Previous work in the AVR lab includes the Natural User Interface (NUI) project and the Virtual Control Panel (VCP) project, which created virtual three-dimensional interfaces that users could interact with while wearing a VR headset thanks to body- and hand-tracking technology. The Virtual Tablet (VT) project attempts to improve on these previous efforts by incorporating a physical surrogate which is mirrored in the virtual environment, mitigating issues with difficulty of visually determining the interface location and lack of tactile feedback discovered in the development of previous efforts. The physical surrogate takes the form of a handheld sheet of acrylic glass with several infrared-range reflective markers and a sensor package attached. Using the sensor package to track orientation and a motion-capture system to track the marker positions, a model of the surrogate is placed in the virtual environment at a position which corresponds with the real-world location relative to the user's VR Head Mounted Display (HMD). A set of control mechanisms is then projected onto the surface of the surrogate such that to the user, immersed in VR, the control interface appears to be attached to the object they are holding. The VT project was taken from an early stage where the sensor package, motion-capture system, and physical surrogate had been constructed or tested individually but not yet combined or incorporated into the virtual environment. My contribution was to combine the pieces of hardware, write software to incorporate each piece of position or orientation data into a coherent description of the object's location in space, place the virtual analogue accordingly, and project the control interface onto it, resulting in a functioning object which has both a physical and a virtual presence. Additionally, the virtual environment was enhanced with two live video feeds from cameras mounted on the robotic device being used as an example target of the virtual interface. The working VT allows users to naturally interact with a control interface with little to no training and without the issues found in previous efforts.

virtual control interface↗

DOE OSTI2022

Recent progress on the mesoscale modeling of architected thin-films via phase-field formulations of physical vapor deposition

Thin-film coatings can be found everywhere in modern technological applications due to desirable electrical, mechanical, chemical, and optical properties. These properties directly depend upon the thin-film’s microstructural features, which are themselves influenced by the materials and vapor-deposition processing conditions used for fabrication. As such, understanding processing-microstructure relationships is essential to designing thin-films with optimized properties, and discovering new processing conditions that allow for novel thin-films with multifunctional microstructures. Here, a short review is presented on recent developments that utilize the phase-field method to simultaneously model the vapor-deposition process and corresponding microstructure formation at the mesoscale. Also phase-field-based vapor-deposition models that simulate thin-film growth of immiscible alloy and polycrystalline systems are highlighted in addition to machine-learning-based surrogate models that can facilitate accelerated high-fidelity simulations along with materials design and exploration studies.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Generative diffusion model surrogates for mechanistic agent-based biological models

Mechanistic, multicellular, agent-based models are commonly used to investigate tissue, organ, and organism-scale biology at single-cell resolution. The Cellular-Potts Model (CPM) is a powerful and popular framework for developing and interrogating these models. CPMs become computationally expensive at large space- and time- scales making application and investigation of developed models difficult. Surrogate models may allow for the accelerated evaluation of CPMs of complex biological systems. However, the stochastic nature of these models means each set of parameters may give rise to different model configurations, complicating surrogate model development. In this work, we leverage denoising diffusion probabilistic models (DDPMs) to train a generative AI surrogate of a CPM used to investigate in vitro vasculogenesis. We describe the use of an image classifier to learn the characteristics that define unique areas of a 2-dimensional parameter space. We then apply this classifier to aid in surrogate model selection and verification. Our CPM model surrogate generates model configurations 20,000 timesteps ahead of a reference configuration and demonstrates approximately a 22x reduction in computational time as compared to native code execution. Our work represents a step towards the implementation of DDPMs to develop digital twins of stochastic biological systems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

On Transfer Learning Of Neural Networks Using Bi-Fidelity Data For Uncertainty Propagation

Due to their high degree of expressiveness, neural networks have recently been used as surrogate models for mapping inputs of an engineering system to outputs of interest. Once trained, neural networks are computationally inexpensive to evaluate and remove the need for repeated evaluations of computationally expensive models in uncertainty quantification applications. However, given the highly parameterized construction of neural networks, especially deep neural networks, accurate training often requires large amounts of simulation data that may not be available in the case of computationally expensive systems. In this paper, to alleviate this issue for uncertainty propagation, we explore the application of transfer learning techniques using training data generated from both high- and low-fidelity models. We explore two strategies for coupling these two datasets during the training procedure, namely, the standard transfer learning and the bi-fidelity-weighted learning. In the former approach, a neural network model mapping the inputs to the outputs of interest is trained based on the low-fidelity data. The high-fidelity data are then used to adapt the parameters of the upper layer(s) of the low-fidelity network, or train a simpler neural network to map the output of the low-fidelity network to that of the high-fidelity model. In the latter approach, the entire low-fidelity network parameters are updated using data generated via a Gaussian process model trained with a small high-fidelity dataset. The parameter updates are performed via a variant of stochastic gradient descent with learning rates given by the Gaussian process model. Using three numerical examples, we illustrate the utility of these bi-fidelity transfer learning methods where we focus on accuracy improvement achieved by transfer learning over standard training approaches.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Predicting Catalyst Surface Stability Under Reaction Conditions Using Deep Reinforcement Learning and Machine Learning Potentials

Catalysts are critical for most large-scale energy intensive chemical transformation processes, such as energy storage, liquid fuel production, and the formation of chemical building blocks. The catalyst composition, structure, and morphology impact the performance under reaction conditions and influences properties like activity and selectivity. Many industrial catalysts offer imperfect activity/selectivity, or contain expensive metals. Further, catalysts can deactivate over time as the morphology changes or harsh reactive environments alter the surface structure. Methods to automatically model and predict the kinetics of how catalyst surfaces will restructure would enable engineers to design around these challenges, improve performance, increase longevity. This project investigated a specific type of machine learning model, deep reinforcement learning, machine learning models to act as surrogates for the physical system, and compared the results of these approaches with a specialized high-throughput experimental synthesis and measurement platform.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗