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 1,207 records · Page 67

Extending RISMC Capabilities for Real-Time Diagnostics and Prognostics

Quick and effective accident management is essential in any industry in order to limit and contain possible threats to both people and environment/assets. This is in particular relevant in the nuclear industry where accidents may have major impacts from an economic, health and societal point of view. As an example, the Fukushima Dai-ichi nuclear power plant accident highlighted the importance of the ability of plant operators and plant staff to react quickly and effectively in accident conditions. This particular event showed the importance of being able to: • Determine/estimate the actual status of the plant (i.e., diagnosis) when the monitoring system is corrupted or partially unavailable, and, • Forecast its future evolution (i.e., prognosis). In this paper we want to describe a research direction geared toward the development of a new set of advanced diagnosis and prognosis tools. We employ innovative data mining and machine learning techniques that are able to infer plant status and mimic the plant’s full temporal behavior in order to assist the reactor operators during an accident scenario.

97 MATHEMATICS AND COMPUTING↗

Generating an implicit voronoi mesh to decompose a domain of arbitrarily many dimensions

Described herein are technologies pertaining to generating a Voronoi mesh for an enclosed domain of arbitrarily many dimensions. An implicit Voronoi mesh is received that comprises locations of seeds in the domain. Neighbors of a seed are identified by extending a segment from the seed to the boundary of the domain and performing successive hyperplane trimming of the segment to identify a point on the facet of the Voronoi cell of the seed. A vertex of the cell can be identified by successively extending and trimming one or more additional spokes to identify points on a facet of the cell that are constrained to lie in a (d−n) space, where d is a number of dimensions of the domain and n is a number of iterations. A numerical simulation is performed based on the Voronoi mesh to generate simulation results in applications including surrogate modeling, global optimization, calibration, dimension reduction.

97 MATHEMATICS AND COMPUTING↗

EFFICIENT SURROGATE FOR LOW ENERGY DAMAGE EFFECTS IN POLYATOMIC MATERIALS

We present an efficient surrogate for binary-collision Monte-Carlo (BCMC) calculations in polyatomic materials for low ion energies based on Parkin and Coulter’s net displacement function. Most of BCMC’s execution time is spent on the low energy tail of cascades when recoils’ residual travel distance is small compared to the desired resolution of the damage calculation. We propose to curtail an ions’ random walk if its energy reduces below a threshold Et and locally deposit an estimate of the expected number of defects it creates; the estimate of the number of defects is obtained from Parkin and Coulter’s net displacement functions. We find that results obtained with the BCMC code MyTRIM with and without truncation of the random walks compare well for large energy thresholds Et > 5 keV. For Et = 5 keV larger discrepancies are observed because of large differences between the net displacement function and MyTRIM for very low energy recoils. Future work will investigate and resolve this discrepancy. The energy threshold should be chosen so that ions’ average distance to next nuclear scattering is small compared to the desired resolution. A reduction of execution time of damage cascades by over 90 % is observed for an energy threshold of Et = 5 keV and a 1 MeV Xe-135 primary impinging on UO2. The desired application of this surrogate model are coupled FEM-BCMC calculations with varying compositions where net displacement functions are tabulated by composition. For reducing the number of required net displacement functions, derivatives of the net displacement function with respect to number fraction are computed.

97 MATHEMATICS AND COMPUTING↗

EFFICIENT SURROGATE FOR LOW ENERGY DAMAGE EFFECTS IN POLYATOMIC MATERIALS

We present an efficient surrogate for binary-collision Monte-Carlo (BCMC) calculations in polyatomic materials for low ion energies based on Parkin and Coulter’s net displace- ment function. Most of BCMC’s execution time is spent on the low energy tail of cascades when recoils’ residual travel distance is small compared to the desired resolution of the damage calculation. We propose to curtail an ions’ random walk if its energy reduces below a threshold Et and locally deposit an estimate of the expected number of defects it creates; the estimate of the number of defects is obtained from Parkin and Coulter’s net displacement functions. We find that results obtained with the BCMC code MyTRIM with and without truncation of the random walks compare well for large energy thresholds Et > 5 keV. For Et = 5 keV larger discrepancies are observed because of large differ- ences between the net displacement function and MyTRIM for very low energy recoils. Future work will investigate and resolve this discrepancy. The energy threshold should be chosen so that ions’ average distance to next nuclear scattering is small compared to the desired resolution. A reduction of execution time of damage cascades by over 90 % is observed for an energy threshold of Et = 5 keV and a 1 MeV Xe-135 primary impinging on UO2. The desired application of this surrogate model are coupled FEM-BCMC cal- culations with varying compositions where net displacement functions are tabulated by composition. For reducing the number of required net displacement functions, derivatives of the net displacement function with respect to number fraction are computed.

97 MATHEMATICS AND COMPUTING↗

A Boundary Topology Optimization Approach for Lightweighting Electric Machines Inspired by Additive Manufacturing

Minimizing the mass in electric machines while maintaining superior performance has become a new requirement for the advancement of drivetrains used in wind energy and electric mobility. Topology optimization for light-weighting electric machines using traditional approaches typically explore a restricted design space allowed by standard parametrizable geometry and manufacturing, while advanced methods like cell-based density approaches suffer from a lack of robust manufacturability constraints during the optimization process. To overcome these drawbacks, we explore a grid-independent, boundary TO where the outer shape of the magnet is parameterized using Bezier curves. We conduct a design of experiments (DOE) to study the effect of different magnet shapes on machine performance by varying the control points on the Bezier curves. A machine-learning based surrogate model is constructed using the data from the DOE to quantify the relationship between the control points, air-gap torque and mass. The control points are then optimized to maximize the torque density. The approach is used for minimizing electrical steel mass in the IEA-15MW radial flux direct-drive wind turbine generator. The free-from boundary TO resulted in smooth and concise shapes that can be easily additively manufactured with upto 20-ton reduction in electrical steel mass.

additive manufacturing↗

A New Shape Optimization Approach for Lightweighting Electric Machines Inspired by Additive Manufacturing: Preprint

Minimizing the mass in electric machines while maintaining superior performance is a new requirement for the advancement of drivetrains used in wind energy and electric mobility. Topology optimization (TO) for lightweighting electric machines using traditional approaches typically explores a restricted design space allowed by standard parametrizable geometry and manufacturing, while advanced methods, such as cell-based density approaches, suffer from a lack of robust manufacturability constraints during the optimization process. To overcome these drawbacks, we explore a grid-independent, boundary TO where the outer shape of the magnet is parameterized using Bezier curves. We conduct a design of experiments (DOE) to study the effect of different magnet shapes on machine performance by varying the control points on the Bezier curves. A machine-learning-based surrogate model is constructed using the data from the DOE to quantify the relationship between the control points, air-gap torque, and mass. The control points are then optimized to maximize the torque density. The approach is used for minimizing electrical steel mass in the International Energy Agency (IEA) 15-MW radial flux direct-drive wind turbine generator. The free-form boundary TO resulted in smooth and concise shapes that can be easily additively manufactured with up to a 20-ton reduction in electrical steel mass.

additive manufacturing↗

Deep Symbolic Optimization for Electric Component Sizing in Fixed Topology Power Converters

Power converters (PC) are a major component in any current electronic hardware device. The development and design is usually guided by expert knowledge and heavily relies on human intuition and experience. The process is a very time consuming and costly activity and it is generally hard to improve upon current designs. As a first step towards autonomous PC design, we are here proposing a new framework for the sizing of components for fixed topology PCs based on given design requirements. To this end, we developed surrogate models for rapid evaluation of new topologies and adapt the deep symbolic optimization (DSO) framework to generate new topologies guided by a reinforcement learning training signal. In an empirical evaluation, we show that our DSO based approach is able to find the optimal configuration for all investigated topologies, while reducing the learning time by at least a factor of 100 compared to popular RL algorithms.

Xue, Lincoln↗

Scaling Wind Power Innovation Assessment for Rapid Energy Transition with Artificial Intelligence

Planning for energy system decarbonization requires new insights into the potential of renewable technologies, deployed at unprecedented scale, to meet urgent sustainability goals. However, limited scalability of current wind energy research tools restricts characterization of innovation impacts to isolated reference sites, challenging investment and decision making under rapid growth. We demonstrate the transformative potential of artificial intelligence (AI) to inform future technology advancement and energy systems design by leveraging a state-of-the-art surrogate model to conduct a series of fleet-wide wind plant layout optimizations for greater than 6,800 projected U.S. onshore buildout locations. We show how innovative wake steering technology can address an array of barriers to large-scale deployment and integration of wind power. Specifically, wake steering reduces required plant area by an average of 18% and could preserve upwards of 13,000 km2 for future greenfield deployment, potentially easing siting challenges associated with wind energy infrastructure. Further, by enabling reduced turbine spacing and increased energy production, flexible operations of wake steering improve levelized cost of energy, particularly for large plants and in land-constrained settings. Finally, optimizations that consider dynamic energy prices can deliver increased power production and revenue capture during high-value (often low-wind) periods, further bolstering plant economics. Our computationally efficient approach offers a pathway to accelerate nationwide geographic evaluation of innovative technologies.

graph neural networks↗

DEMONSTRATION OF A DATA-DRIVEN PHYSICS-BASED APPROACH FOR COMPUTATIONALLY EFFICIENT CFD PREDICTION OF TWO-PHASE BUBBLY FLOW

To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale physics-guided data-driven approach, Feature Similarity Measurement (FSM) technique was developed for error estimation in two-phase flow simulation using coarse-mesh CFD, to achieve a comparable accuracy as fine-mesh simulations with fast-running feature. By defining physics-guided parameters and variable gradients as physical features, FSM has the capability to capture the underlying local patterns in the coarse-mesh CFD simulation. Massive low-fidelity data and respective high-fidelity data are used to explore the underlying information relevant to the main simulation errors and the effects of phenomenological scaling. By learning from previous simulation data, a surrogate model using deep feedforward neural network (DFNN) can be developed and trained to estimate the simulation error of coarse-mesh CFD. In a demonstration case of two-phase bubbly flow, the DFNN model well captured and corrected the unphysical “peaks” in the velocity and void fraction profiles near the wall in the coarse-mesh configuration, even for extrapolative predictions. The research documented supports the feasibility of the physics-guided deep learning methods for coarse mesh CFD simulations which has a potential for the efficient industrial design.

42 ENGINEERING↗

Insights on fuel performance in advanced compression ignition engines: combining engine thermodynamic trajectory and fuel ignition delay iso-contour

With the development of various low temperature engine combustion strategies, the behavior of gasoline-type fuels under compression ignition conditions has attracted extensive research interest. In this study, gasoline surrogates based on toluene primary reference fuel blends (TPRF) with different research and motor octane numbers (i.e., RON and MON) and fuel octane sensitivity (OS) have been strategically designed using a recently established surrogate model, and their combustion chemistry is further described using a well-validated kinetic mechanism. Based on a typical advanced compression ignition engine configuration, the crank angle corresponding to 50% total heat release (CA50) was utilized as an indicator of the overall fuel reactivity, and representative engine operating conditions have been selected based on the regime exhibited from the CA50 iso-contours. By combining the thermodynamic trajectory and ignition delay isocontours, useful insights on the fuel reactivity and sensitivity have been obtained to evaluate the fuel performance under various engine operating regimes with distinct chemistry, accounting for the effects of equivalence ratio and ratio of exhaust gas recirculation (EGR). This study provides useful insight on the different effects of engine operating conditions on a fuel’s performance following different engine trajectories, based on the different controlling fuel chemistry.

Tao, Mingyuan↗

Exact-to-precision generalized perturbation for neutron transport calculation

This manuscript extends the exact-to-precision generalized perturbation theory (E{sub P}GPT), introduced previously, to neutron transport calculation whereby previous developments focused on neutron diffusion calculation only. The E{sub P}GPT collectively denotes new developments in generalized perturbation theory (GPT) that place premium on computational efficiency and defendable accuracy in order to render GPT a standard analysis tool in routine design and safety reactor calculations. EPGPT constructs a surrogate model with quantifiable accuracy which can replace the original neutron transport model for subsequent engineering analysis, e.g. functionalization of the homogenized few-group cross sections in terms of various core conditions, sensitivity analysis and uncertainty quantification. This is achieved by reducing the effective dimensionality of the state variable (i.e. neutron angular flux) by projection onto an active subspace. Confining the state variations to the active subspace allows one to construct a small number of what is referred to as the 'active' responses which are solely dependent on the physics model rather than on the responses of interest, the number of input parameters, or the number of points in the state phase space. (authors)

97 MATHEMATICS AND COMPUTING↗

Adaptive polynomial chaos techniques for uncertainty quantification of a gas cooled fast reactor transient

Uncertainty quantification plays an increasingly important role in the nuclear community, especially with the rise of Best Estimate Plus Uncertainty methodologies. Sensitivity analysis, surrogate models, Monte Carlo sampling and several other techniques can be used to propagate input uncertainties. In recent years however polynomial chaos expansion has become a popular alternative providing high accuracy at affordable computational cost. This paper presents such polynomial chaos (PC) methods using adaptive sparse grids and adaptive basis set construction, together with an application to a Gas Cooled Fast Reactor transient. Comparison is made between a new sparse grid algorithm and the traditionally used technique proposed by Gerstner. An adaptive basis construction method is also introduced and is proved to be advantageous both from an accuracy and a computational point of view. As a demonstration the uncertainty quantification of a 50% loss of flow transient in the GFR2400 Gas Cooled Fast Reactor design was performed using the CATHARE code system. The results are compared to direct Monte Carlo sampling and show the superior convergence and high accuracy of the polynomial chaos expansion. Since PC techniques are easy to implement, they can offer an attractive alternative to traditional techniques for the uncertainty quantification of large scale problems. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Application of adaptive hierarchical sparse grid collocation to the uncertainty quantification of nuclear reactor simulators

Recent efforts in the application of uncertainty quantification to nuclear systems have utilized methods based on generalized perturbation theory and stochastic sampling. While these methods have proven to be effective they both have major drawbacks that may impede further progress. A relatively new approach based on spectral elements for uncertainty quantification is applied in this paper to several problems in reactor simulation. Spectral methods based on collocation attempt to couple the approximation free nature of stochastic sampling methods with the determinism of generalized perturbation theory. The specific spectral method used in this paper employs both the Smolyak algorithm and adaptivity by using Newton-Cotes collocation points along with linear hat basis functions. Using this approach, a surrogate model for the outputs of a computer code is constructed hierarchically by adaptively refining the collocation grid until the interpolant is converged to a user-defined threshold. The method inherently fits into the framework of parallel computing and allows for the extraction of meaningful statistics and data that are not within reach of stochastic sampling and generalized perturbation theory. This paper aims to demonstrate the advantages of spectral methods-especially when compared to current methods used in reactor physics for uncertainty quantification-and to illustrate their full potential. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Robust Multi-fidelity Bayesian Optimization with Deep Kernel and Partition

Multi-fidelity Bayesian optimization (MFBO) is a powerful approach that utilizes lowfidelity, cost-effective sources to expedite the exploration and exploitation of a high-fidelity objective function. Existing MFBO methods with theoretical foundations either lack justification for performance improvements over single-fidelity optimization or rely on strong assumptions about the relationships between fidelity sources to construct surrogate models and direct queries to low-fidelity sources. To mitigate the dependency on cross-fidelity assumptions while maintaining the advantages of low-fidelity queries, we introduce a random sampling and partition-based MFBO framework with deep kernel learning. This framework is robust to cross-fidelity model misspecification and explicitly illustrates the benefits of low-fidelity queries. Our results demonstrate that the proposed algorithm effectively manages complex cross-fidelity relationships and efficiently optimizes the target fidelity function.

Zhang, Fengxue [University of Chicago, Illinois, U↗

Predictive Modeling and Uncertainty Quantification in Condition Monitoring of Active Components: A Reactor Coolant Pump Use Case

This work develops data-driven models for onset of thermal barrier leakage in reactor coolant pumps. It incorporates uncertainty quantification to enhance the reliability and robustness of pre- dictions. Using synthetic data generated by the Generic Pressurized Water Reactor simulator, realistic degradation scenarios were simulated across lifecycle stages—beginning, middle, and end of life. Key variables, including differential pressure, flow rate, vibration, and temperatures, were analyzed using machine learning framework. The fully connected neural network models demonstrated exceptional performance, achieving R2 scores exceeding 0.99 and root mean square errors as low as around 8.23 × 10-2 gallon per minute (gpm) for the three stages of the lifecy- cle. UQ analysis further validated the model’s robustness, with narrow uncertainty bounds during steady-state operations and appropriately wider bounds during transitional phases, reflecting the physical behavior of the system. This work addresses important gaps in real-time condition moni- toring and regulatory compliance by integrating advanced condition monitoring technologies with UQ into IST programs. The ability to detect thermal barrier leakage early and quantify prediction reliability supports optimizing maintenance strategies while ensuring nuclear power plants’ safe and reliable operation.

99 - GENERAL AND MISCELLANEOUS↗

Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models

This study aims to implement a hybrid ensemble surrogate machine learning technique in predicting the compressive strength (CS) of concrete, an important parameter used for durability design and service life prediction of concrete structures in civil engineering projects. For this purpose, an experimental database consisting of 1030 records has been compiled from the machine learning repository of the University of California, Irvine. The database was used to train and validate four conventional machine learning (CML) models, namely Artificial Neural Network (ANN), Linear and Non-Linear Multivariate Adaptive Regression Splines (MARS-L and MARS-C), Gaussian Process Regression (GPR), and Minimax Probability Machine Regression (MPMR). Subsequently, the predicted outputs of CML models were combined and trained using ANN to construct the Hybrid Ensemble Model (HENSM). It is observed that the proposed HENSM produces higher predictive accuracy compared to the CML models used in the present study. The predictive performance of all models for CS prediction was compared using the testing dataset and it is found that the HENSM model attained the highest predictive accuracy in both phases. Based on the experimental results, the newly constructed HENSM model is very potential to be a new alternative in handling the overfitting issues of CML models and hence, can be used to predict the concrete CS, including the design of less polluting and more sustainable concrete constructions.

36 MATERIALS SCIENCE↗

Real-Time Drag Optimization of Aspect Ratio 13.5 Common Research Model with Distributed Flap System

This paper presents a real-time drag optimization study of the aspect ratio 13.5 Common Research Model (CRM) with a distributed mini-plain flap system. A surrogate aerodynamic model of the aspect ratio 13.5 CRM is developed based on an aerodynamic database computed by a transonic panel method to capture the aerodynamic coefficients as functions of the angle of attack, flap deflections, and Mach number. A recursive least-squares parameter estimation algorithm is designed to estimate the aerodynamic parameters of the surrogate model. The estimated surrogate model is then used in an on-line drag optimization strategy based on an adjoint method. The results of the real-time drag optimization indicate a drag reduction of 2.46% for Mach 0.80, 3.37% for Mach 0.85, and 1.95% for Mach 0.88. The results show the convergence of all parameter estimates.

Drag Optimization↗

Active learning using hybrid surrogate tool life modeling for machining process optimization

Here, this paper describes an active learning approach for part-to-part iterative machining process optimization using a hybrid surrogate tool life model. A probabilistic interpolating tool life model is developed by combining the empirical Taylor-type tool life equation and the model fit error. The probabilistic tool life model is then used to calculate the machining cost per part distribution. The optimal machining parameters are selected using an expected improvement in machining cost per part criterion. The method is validated numerically using experimental results; the results show a median convergence error of 2.2% after three tests over 400 simulations. The method is validated experimentally on two industrial applications for Ti-6Al-4V roughing resulting in a cost per part reduction greater than 23% after two tests. The described method is a robust solution for rapid convergence to optimal machining parameters in an industrial production environment.

Active learning↗