Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computationally efficient surrogate 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.

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

At least 433 records · Page 24

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

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

deep learning↗

Web-Based Tools for Data-Informed Remedy Optimization: Software Theory and User Guide

This report documents the development and application of two web-based decision-support tools for pump-and-treat (P&T) groundwater remediation systems: PTOLEMY (Pump-and-Treat Optimized Location Evaluation to Maximize Yields) and OPTIMA (Optimization for Pump-and-Treat Implementation, Management, & Assessment). These tools enhance remedy design and management by leveraging advanced computational methods – specifically deep learning and multi-objective optimization – within a user-friendly platform. By integrating data-driven models with established hydrogeological knowledge, PTOLEMY and OPTIMA enable more efficient evaluation of well placement and operational strategies, helping site managers balance multiple remediation objectives under complex conditions. Both tools are implemented as modules within the SOCRATES (Suite Of Comprehensive Rapid Analysis Tools for Environmental Sites) web platform, which provides data access, visualization, and analytics to support remedy optimization across sites in the U.S. Department of Energy Office of Environmental Management complex. PTOLEMY is a rapid screening module designed to identify promising locations for new extraction wells. It employs a multi-channel three-dimensional convolutional neural network (MC3D-CNN) trained on high-fidelity simulation data to predict the relative performance (in terms of contaminant mass recovery) of potential well sites. Through an interactive web interface, PTOLEMY visualizes the probability of high performance across a site, highlighting areas where an extraction well is likely to yield above-threshold contaminant removal over a multi-year period. PTOLEMY’s map-based displays and exportable results support transparent communication of screening analyses. By focusing attention on the most favorable candidate locations, the tool augments traditional engineering judgment and physics-based modeling, providing a data informed basis for subsequent detailed evaluations. OPTIMA is a multi objective optimization module designed to find wellfield layouts and operating schedules that meet various cleanup goals. It quickly evaluates thousands of candidate setups – combinations of well locations, timing, and rates – and returns a small set of best trade-off options for comparison. At its core, OPTIMA uses a U-Net-based surrogate model – a deep-learning emulator of a groundwater flow and transport simulator – to dramatically accelerate scenario evaluations. Coupling this fast surrogate with the NSGA-II (Non-dominated Sorting Genetic Algorithm II) evolutionary algorithm, OPTIMA explores a wide decision space of well locations and schedules to identify Pareto-optimal solutions that trade off key objectives (e.g., minimizing cleanup time, maximizing contaminant mass removal, and minimizing plume extent). The tool outputs a family of optimal configurations and visualizes their trade-offs (Pareto frontiers of cleanup metrics and maps of optimized well placements). Site managers can use these results to understand the range of viable strategies and to select candidate designs for more detailed verification. OPTIMA is currently under active development and not yet fully released; this guide provides early documentation to support planning and gather user feedback.

54 ENVIRONMENTAL SCIENCES↗

Orthorhombic Structures as Inorganic Halide Perovskite Models for High-Throughput DFT Investigations

Although high-symmetry Pm-3m space group cubic models are computationally efficient for high-throughput density functional theory (DFT) calculations of inorganic ternary (ABX 3 ) halide perovskites (HPs), they frequently predict band gaps (E g ) that disagree with experiment. Conversely, while low-symmetry cubic polymorphous networks (PN) comprised of 160 to 320 atoms incur significantly greater computational cost, they predict E g ’s that are more closely aligned with experiment. Here, in this study, we compare the DFT total energies and E g ’s predicted by four high-symmetry structure models (Pnma orthorhombic, R3m trigonal, P4/mbm tetragonal, and Pm-3m cubic) to cubic PNs for 5 experimentally characterized ternary HPs and find that the orthorhombic model computes Eg’s with the smallest MAD of 0.23 eV relative to the PNs. Pair distribution functions and DFT-computed total energies show that octahedral tilting, which is present in the 20-atom orthorhombic and 160-atom cubic PN models but not in the 5-atom cubic models, stabilizes all 5 compositions in our benchmarking set. We also find that imposing PN constraints when generating and optimizing these orthorhombic structures by fixing the unit cell lattice vectors and displacing the atoms prior to ionic relaxation with DFT, which we call the orthorhombic surrogate model (OSM), lowers the MAD of E g predictions to 0.09 eV. Our OSM predicts the PN band gaps of an additional 95 theoretical inorganic ternary HPs with MAD of 0.08 eV, supporting its usage in high-throughput DFT investigations to closely estimate PN band gaps with much less computational expense.

14 SOLAR ENERGY↗

High-Dimensional Spectral Sampling

A wide variety of applications in science and engineering depend on effectively and efficiently exploring high- dimensional parameter spaces. Common examples are uncertainty quantification, inverse problems, or various optimization approaches. In such applications, the first step is to create an initial uniform, random sampling of the space to create a baseline of knowledge. The simulations evaluated at these samples are then used for subsequent processing. In its most generic form, the goal of sampling is to produce the maximal amount of information with the minimal number of samples. However, despite being the first step and thus influencing the performance of the entire workflow, the quality of the initial sample designs is rarely analyzed or optimized. This project develops a new spectral sampling theory for analyzing and creating experiment designs in high-dimensional spaces. Further, new algorithms for estimating sample properties and sample synthesis are designed. Finally, applications of the proposed spectral sampling tools in surrogate modeling, scientific machine learning and image analysis are presented.

97 MATHEMATICS AND COMPUTING↗

Active oversight and quality control in standard Bayesian optimization for autonomous experiments

The fusion of experimental automation and machine learning has catalyzed a new era in materials research, prominently featuring Gaussian Process (GP) Bayesian Optimization (BO) driven autonomous experiments. Here we introduce a Dual-GP approach that enhances traditional GPBO by adding a secondary surrogate model to dynamically constrain the experimental space based on real-time assessments of the raw experimental data. This Dual-GP approach enhances the optimization efficiency of traditional GPBO by isolating more promising space for BO sampling and more valuable experimental data for primary GP training. We also incorporate a flexible, human-in-the-loop intervention method in the Dual-GP workflow to adjust for unanticipated results. We demonstrate the effectiveness of the Dual-GP model with synthetic model data and implement this approach in autonomous pulsed laser deposition experimental data. This Dual-GP approach has broad applicability in diverse GPBO-driven experimental settings, providing a more adaptable and precise framework for refining autonomous experimentation for more efficient optimization.

36 MATERIALS SCIENCE↗

Automatic Selection of High-Fidelity Models and Surrogates for Uncertainty Analysis

Surrogate models (SMs) with distinct features developed in the last decade provide an efficient substitute to the high-fidelity physical simulations. However, it is generally challenging to quantify the accuracy of surrogate models in a region of interest and examine reliability in the overall domain without additional system evaluations. This paper introduces a new scheme, automated adaptive model selection, to adaptively construct and quantify a set of surrogate models and automatically switch between the surrogates and a high-fidelity code. Cross-validation approaches, such as KFold, Leave One Out (LOO) and Leave P Out (LPO), are employed to assess the global accuracy of the surrogates. The switching strategy is based on local validation metrics, crowding distance, that are able to provide an assessment on the goodness of the prediction made by the surrogates. This decision metric decides whether the surrogates are good enough for a certain realization or whether the high-fidelity code needs to be executed. This new scheme has been implemented in Risk Analysis in Virtual ENvironment (RAVEN) software, which can be employed to accelerate the Probabilistic Risk Assessment (PRA) and Uncertainty Quantification (UQ) processes.

97 MATHEMATICS AND COMPUTING↗

Application of Bound-to-Bound Data Collaboration approach for development and uncertainty quantification of a reduced char combustion model

The development of efficient industrial oxy-coal boilers can be significantly aided by Computational Fluid Dynamics (CFD) tools, as far as fidelity in modeling coal combustion is also complemented by feasible computational costs. Reduced and predictive models are the most suitable for this application scale. Reduced models feature predictivity when they are validated against a broad range of experiments and targeted by Uncertainty Quantification (UQ) procedures. This work proposes a numerical procedure that uses Bound-to-Bound Data Collaboration (B2B-DC) to derive a reduced char combustion model describing transport phenomena and reactions between char carbon and O 2 , CO 2 and H 2 O, in both conventional and oxy-conditions. The approach determines the consistency between a numerical model and an experimental dataset. The latter is made up of the experiments carried out in an optically accessible laminar entrained flow reactor, operated by Sandia National Laboratories. The procedure follows five steps towards predictive modeling capability, namely: quantification of the uncertainty in the experiments, via instrument verification and modeling; development of a physics model and continuous improvement of its fidelity, via model-form uncertainty; identification of the uncertain and most sensitive parameters and of their prior bounds; sampling of the initial uncertain parameter space and training of a surrogate model; validation of the physics model via inference from the data. The last step, also known as inverse problem, is performed by applying the Bound-to-Bound Data Collaboration approach. A char combustion model is found consistent with the experimental data and its validity stands for conventional and oxy-combustion conditions. It accounts for heterogeneous reactions at the particle surface, mass transport of species in the particle boundary layer, pore diffusion and surface area changes. The consistent reduced model overcomes the differences in mass transport and kinetics observed in the experimental campaign. In conclusion, a reduction of the initial degree of uncertainty in both model and experiments is achieved.

42 ENGINEERING↗

Thermal Energy Transport in Oxide Nuclear Fuel

To efficiently capture the energy of the nuclear bond, advanced nuclear reactor concepts seek solid fuels that must withstand unprecedented temperature and radiation extremes. In these advanced fuels, thermal energy transport under irradiation is directly related to reactor performance as well as reactor safety. The science of thermal transport in nuclear fuel is a grand challenge as a result of both computational and experimental complexities. Here we provide a comprehensive review of thermal transport research on two actinide oxides: one currently in use in commercial nuclear reactors, uranium dioxide (UO 2 ), and one advanced fuel candidate material, thorium dioxide (ThO 2 ). In both materials, heat is carried by lattice waves or phonons. Crystalline defects caused by fission events effectively scatter phonons and lead to a degradation in fuel performance over time. Bolstered by new computational and experimental tools, researchers are now developing the foundational work necessary to accurately model and ultimately control thermal transport in advanced nuclear fuels. We begin by reviewing research aimed at understanding thermal transport in perfect single crystals. The absence of defects enables studies that focus on the fundamental aspects of phonon transport. Next, we review research that targets defect generation and evolution. Here the focus is on ion irradiation studies used as surrogates for damage caused by fission products. We end this review with a discussion of modeling and experimental efforts directed at predicting and validating mesoscale thermal transport in the presence of irradiation defects. While efforts in these research areas have been robust, challenging work remains in developing holistic tools to capture and predict thermal energy transport across widely varying environmental conditions.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗

Interpretable AI forecasting for numerical relativity waveforms of quasicircular, spinning, nonprecessing binary black hole mergers

We present a deep-learning artificial intelligence model (AI) that is capable of learning and forecasting the late-inspiral, merger and ringdown of numerical relativity waveforms that describe quasicircular, spinning, nonprecessing binary black hole mergers. We used the NRHybSur3dq8 surrogate model to produce train, validation and test sets of ℓ = |m| = 2 waveforms that cover the parameter space of binary black hole mergers with mass ratios q ≤ 8 and individual spins |s$^{z}_ {(1,2)}$| ≤ 0.8. These waveforms cover the time range t ∊ [-5000 M, 130 M], where t = 0M marks the merger event, defined as the maximum value of the waveform amplitude. We harnessed the ThetaGPU supercomputer at the Argonne Leadership Computing Facility to train our AI model using a training set of 1.5 million waveforms. We used 16 NVIDIA DGX A100 nodes, each consisting of 8 NVIDIA A100 Tensor Core GPUs and 2 AMD Rome CPUs, to fully train our model within 3.5 h. Our findings show that artificial intelligence can accurately forecast the dynamical evolution of numerical relativity waveforms in the time range t ∊ [-100 M, 130 M]. Sampling a test set of 190,000 waveforms, we find that the average overlap between target and predicted waveforms is ≳99% over the entire parameter space under consideration. We also combined scientific visualization and accelerated computing to identify what components of our model take in knowledge from the early and late-time waveform evolution to accurately forecast the latter part of numerical relativity waveforms. This work aims to accelerate the creation of scalable, computationally efficient and interpretable artificial intelligence models for gravitational wave astrophysics

79 ASTRONOMY AND ASTROPHYSICS↗

ASSESSING FUEL PROPERTY EFFECTS ON CAVITATION AND EROSION PROPENSITY USING A COMPUTATIONAL FUEL SCREENING TOOL

To advance compression ignition combustion strategies, researchers have evaluated fuel property effects and their impact on achieving higher efficiencies and lower emissions levels relative to current capabilities. Within the Department of Energy's Co-Optima initiative, there has been a recent focus on understanding the influence of fuel properties on fuel injection performance. To help identify candidate fuels that can meet desired injector performance metrics, a computational fuel screening tool is under development that can link fuel properties with the tendency of a given fuel to cavitate and lead to cavitation-induced erosion. In the initial development of this tool, five liquid fuel properties were selected to represent candidate fuels, namely density, viscosity, vapor pressure, surface tension, and heat of vaporization. A design of experiments methodology was employed to generate a set of pseudo fuel cases, which can represent the main effects and interactions among the fuel properties and be related to cavitation erosion predictions. Large eddy simulations were performed using a mixture modeling approach to predict the cavitation and erosion propensity of these pseudo-fuels in terms of the mean fuel vapor mole fraction and stored impact energy from repeated cloud collapse events. The low order regression models generated from this study revealed the importance of liquid fuel density on cavitation formation, whereas liquid viscosity was found to have a strong negative correlation with erosion severity. The surrogate models were then used in the fuel screening tool to rank the cavitation and erosion tendency of four candidate single-component fuels: methyl decanoate, isooctane, ethanol and n-dodecane. While the fuel screening tool was not able to quantitatively predict the cavitation and erosion response metrics, the tool was able to accurately rank the relative cavitation and erosion propensity of the four fuels. Overall, ethanol and iso-octane were observed to produce the highest levels of cavitation and erosion, respectively.

cavitation-induced erosion↗

IDAES-PSE 2.0 Release

The Institute for the Design of Advanced Energy Systems (IDAES) Integrated Platform is a versatile computational environment offering extensive process systems engineering (PSE) capabilities for optimizing the design and operation of complex, interacting technologies and systems. IDAES enables users to efficiently search vast, complex design spaces to discover the lowest cost, most environmentally sustainable solutions while supporting the full process modeling lifecycle, from conceptual design to dynamic optimization and control. The extensible, open platform empowers users to create models of novel processes and rapidly develop custom analyses, workflows, and end-user applications. IDAES-PSE 2.0.0 Release Highlights Removal of deprecated features from IDAES v1 Update to Pyomo v6.5 – this required a number of updates to support the new NL solver writer and to address some changes in Pyomo Creation of new testing suite for backward compatibility, model robustness and verification More general implementation of the Helmholtz EoS. This brings some new features like standard property diagrams, choice of mass or mole basis, and new state variable options Standardizing names in Heat Exchanger models (breaking change from v2.0.0a2): Control Volumes named hot_side and cold_side Ports names hot_side_inlet, hot_side_outlet, cold_side_inlet and cold_side_outlet Config Blocks names hot_side_config and cold_side_config Config arguments for user provided names for each side: hot_side_name and cold_side_name. Updating Keras surrogate tool to use v1.1 of OMLT New prototype API for model initialization (idaes.core.initialization) The new API uses "Model Initializer" objects instead of class methods, allowing for the definition of multiple initialization routines for a single model A number of common, model agnostic initialization routines have also been defined, including initialization from data, block-decomposition and a general hierarchical approach equivalent to the existing method for common unit models New metadata for thermophysical properties – valid_range This can be used to record the range of values over which a property value can be trusted, such as the range of experimental data used to regress parameters A number of new utility functions have been added to check for properties with values outside the valid range and to set bounds based on this metadata Updated construction of balance expressions in Control Volumes to remove unneeded terms In the past, unneeded terms were added as a constant 0 term, however they will now be dropped entirely from the expression This was necessary due to more strict unit checking in the new Pyomo solver writer which no longer ignores 0 terms Updates to metadata for thermophysical properties to better define known properties and units of measurement This results in more strict enforcement of standard naming for thermophysical and reaction properties Users can still define custom properties, but these must be done explicitly using the define_custom_properties() method instead of being implicitly created by add_property() Updated convergence tester utility tool to support definition of benchmark files (JSON format) and comparison of performance to benchmarks Set default iteration limit for IPOPT in IDAES config to 200 iterations Update scaling of example models to work with new Pyomo NL solver writer Improve testing of extensions and examples infrastructure to avoid need for downloading files Updated distillation column to centralize common functionality and remove a number of Pyomo warnings

IDAES↗

BeyondFingerprinting: AI-guided discovery of robust materials & processes

BeyondFingerprinting was a 2021-2024 Sandia Grand Challenge LDRD exploring the potential to develop new resilient materials and manufacturing processes by taking an artificial-intelligence (AI)-guided approach that integrates human-subject-matter expertise with algorithms enriched with physics-based constraints to unearth process-structure-property correlations. Such algorithms, trained on high-throughput experiments and simulations, are shown to serve as surrogate models that efficiently detect key “fingerprints” in materials data, prognose material performance, and guide effective process improvements. To accelerate broader adoption across mission areas, this AI-guided approach was demonstrated with three complex process-centric exemplars: electroplating, physical vapor deposition, and laser powder bed fusion. Together, these exemplars impact nearly every hardware component relevant to DOE and NNSA national security missions.

36 MATERIALS SCIENCE↗

Integrating ytopt and libEnsemble to autotune OpenMC

Ytopt is a Python machine-learning-based autotuning software package developed within the ECP PROTEAS-TUNE project. The ytopt software adopts an asynchronous search framework that consists of sampling a small number of input parameter configurations and progressively fitting a surrogate model over the input-output space until exhausting the user-defined maximum number of evaluations or the wall-clock time. libEnsemble is a Python toolkit for coordinating workflows of asynchronous and dynamic ensembles of calculations across massively parallel resources developed within the ECP PETSc/TAO project. libEnsemble helps users take advantage of massively parallel resources to solve design, decision, and inference problems and expands the class of problems that can benefit from increased parallelism. In this paper we present our methodology and framework to integrate ytopt and libEnsemble to take advantage of massively parallel resources to accelerate the autotuning process. Specifically, we focus on using the proposed framework to autotune the ECP ExaSMR application OpenMC, an open source Monte Carlo particle transport code. OpenMC has seven tunable parameters some of which have large ranges such as the number of particles in-flight, which is in the range of 100,000 to 8 million, with its default setting of 1 million. Setting the proper combination of these parameter values to achieve the best performance is extremely time-consuming. Therefore, we apply the proposed framework to autotune the MPI/OpenMP offload version of OpenMC based on a user-defined metric such as the figure of merit (FoM) (particles/s) or energy efficiency energy-delay product (EDP) on Crusher at Oak Ridge Leadership Computing Facility. In conclusion, the experimental results show that we achieve the improvement up to 29.49% in FoM and up to 30.44% in EDP.

Autotuning↗

Accelerating Hamiltonian Monte Carlo for Bayesian inference in neural networks and neural operators

Hamiltonian Monte Carlo (HMC) is a powerful and accurate method to sample from the posterior distribution in Bayesian inference. However, HMC techniques are computationally demanding for Bayesian neural networks due to the high dimensionality of the network’s parameter space and the non-convexity of their posterior distributions. Therefore, various approximation techniques, such as variational inference (VI) or stochastic gradient MCMC, are often employed to infer the posterior distribution of the network parameters. Such approximations introduce inaccuracies in the inferred distributions, resulting in unreliable uncertainty estimates. In this work, we propose a hybrid approach that combines inexpensive VI and accurate HMC methods to efficiently and accurately quantify uncertainties in neural networks and neural operators. The proposed approach leverages an initial VI training on the full network. We examine the influence of individual parameters on the prediction uncertainty, which shows that a large proportion of the parameters do not contribute substantially to uncertainty in the network predictions. This information is then used to significantly reduce the dimension of the parameter space, and HMC is performed only for the subset of network parameters that strongly influence prediction uncertainties. This yields a framework for accelerating the full batch HMC for posterior inference in neural networks. We demonstrate the efficiency and accuracy of the proposed framework on deep neural networks and operator networks, showing that inference can be performed for large networks with tens to hundreds of thousands of parameters. Finally, we show that this method can effectively learn surrogates for complex physical systems by modeling the operator that maps from upstream conditions to wall-pressure data on a cone in hypersonic flow.

Bayesian inference↗

Numerical Analysis of Fuel Effects on Advanced Compression Ignition Using a Cooperative Fuel Research Engine Computational Fluid Dynamics Model

Growing environmental concerns and demand for a better fuel economy are driving forces that motivate the research for more advanced engines. Multi-mode combustion strategies have gained attention for their potential to provide high thermal efficiency and low emissions for light-duty applications. These strategies target optimizing the engine performance by correlating different combustion modes to load operating conditions. The extension from boosted spark ignition (SI) mode at high loads to advanced compression ignition (ACI) mode at low loads can be achieved by increasing the compression ratio and utilizing intake air heating. Further, in order to enable an accurate control of intake charge condition for ACI mode and rapid mode-switches, it is essential to gain fundamental insights into the autoignition process. Within the scope of ACI, homogeneous charge compression ignition (HCCI) mode is of significant interest. It is known for its potential benefits, operation at low fuel consumption, low NOx, and particulate matter (PM) emissions. In the present work, a virtual Cooperative Fuel Research (CFR) engine model is used to analyze fuel effects on ACI combustion. In particular, the effect of fuel octane sensitivity (S) (at constant Research Octane Number (RON)) on autoignition propensity is assessed under beyond-RON (BRON) and beyond-MON (BMON) ACI conditions. The three-dimensional CFR engine computational fluid dynamics (CFD) model employs a finite-rate chemistry approach with a multi-zone binning strategy to capture autoignition. Two binary blends with Research Octane Number (RON) of 90 are chosen for this study: primary reference fuel (PRF) with S = 0 and toluene–heptane (TH) blend with S = 10.8, representing paraffinic and aromatic gasoline surrogates. Reduced mechanisms for these blends are generated from a detailed gasoline surrogate kinetic mechanism. Simulation results with the reduced mechanisms are validated against experimental data from an in-house CFR engine, with respect to in-cylinder pressure, heat release rate, and combustion phasing. Thereafter, the sensitivity of combustion behavior to ACI operating condition (BRON versus BMON), air-fuel ratio (λ = 2 and 3), and engine speed (600 and 900 rpm) is analyzed for both fuels. It is shown that the sensitivity of a fuel’s autoignition characteristics to λ and engine speed significantly differs at BRON and BMON conditions. Moreover, this sensitivity is found to vary among fuels, despite the same RON. It is also observed that the presence of low-temperature heat release (LTHR) under BRON condition leads to more sequential autoignition and longer combustion duration than BMON condition. Finally, the study indicates that the octane index (OI) fails to capture the trend in the variation of autoignition propensity with S under the BMON condition.

33 ADVANCED PROPULSION SYSTEMS↗

Latent Space Simulation for Carbon Capture Design Optimization

The CO2 capture efficiency in solvent-based carbon capture systems (CCSs) critically depends on the gas-solvent interfacial area (IA), making maximization of IA a foundational challenge in CCS design. While the IA associated with a particular CCS design can be estimated via a computational fluid dynamics (CFD) simulation, using CFD to derive the IAs associated with numerous CCS designs is prohibitively costly. However, previous works such as Deep Fluids (Kim et al., 2019) show that large simulation speed-ups and low error are achievable by replacing CFD simulators with neural-network (NN) surrogates that mimic the CFD simulation process. This raises the possibility for a fast, accurate replacement for a CFD simulator, and thus computationally feasible IA-based CCS-design optimization. As such, here, we explore whether an existing NN-surrogate approach (and variants we develop) can successfully be applied to our complex carbon-capture CFD simulations, with the ultimate goal of obtaining a fast and accurate simulator for our CCS-design application. Our experiments build on the Deep Fluids approach and find that resulting surrogates can produce large speed ups (4000x) while maintaining IA relative errors as low as 4% on unseen CCS configurations (interpolating between configurations seen during training). Thus, despite less faithfulness to the underlying physics of the problem, NN surrogates may be a promising tool for our CCS design optimization problem. Notably, though, the Deep Fluids approach has limitations for our application (such as model non-transferability to CCS-packing changes), which we discuss. We conclude with potential directions for future work that may, like innovations we introduced here (e.g., transformer-based dynamics prediction), improve performance on our complicated dataset of CCS CFD simulations.

AI Surrogate Simulation, Carbon Capture, design op↗

Multi-Source Machine Learning and Thermoplastics Enhanced Aerostructure Manufacturing (mTEAM)

RTX Technology Research Center (RTRC), together with Collins Aerospace (Collins) and Oak Ridge National Laboratory (ORNL) has developed an Artificial Intelligence (AI) / Machine Learning (ML) guided solution to advance the manufacturing and assembly of high performance and lightweight thermoplastic composite (TPC) aerospace products. The solution aims to lower risk, cost and lead time for induction heating based welding and consolidation processes for TPC structure. The cost and lead time of part and material specific process development for induction welding (IW) and induction consolidation will be reduced by replacing traditional empirical methods with optimization methods that merge AI/ML and physics-based process simulations and process experiments with sensing and controls. TPC-IW process development is empirical in nature, and uncertainties in material & process behavior exist near & far from the induction coil. Physics-based simulations can be leveraged directly for process optimization but can be too computationally expensive to run in high fidelity and real time to do robust process optimization. The key impact of successful TPC induction consolidation and welding is cost & lead time reduction for part & material specific consolidation and welding recipes. This is an enabler for more rapid deployment of TPC structures via joining assembly, which can reduce energy & cost intensive usage of autoclaves & ovens. The solution aimed to advance the U.S. Department of Energy’s interests in using thermoplastics and automation in composite manufacturing for improvement of products for existing markets via increased production speeds, reduced costs, and lowered use of energy. Welded TPC structures can offer significant weight & energy savings for high-value commercial aerospace & industrial applications compared to metal & thermoset composite structures assembled by mechanical fastening and/or adhesive bonding. The project was organized into two Budget Periods. Budget Period 1 (BP1) was 15 months and its goal was to perform ML process optimization framework development & deployment on lab-coupon aerostructure components. A Go/No-Go Review was performed at the end of BP1 to verify fulfilment of key tasks & milestones to justify a Go Decision to move into the next Budget Period. Budget Period 2 (BP2) was 12 months and its goal was the deployment of the ML framework for ML process optimization of pilot industrial scale aerostructure components. The overall project aim was to develop & demonstrate ML-enhanced modeling framework that learns process-property mapping from multiple data sources at different fidelities. During BP1, the team accomplished key tasks & milestones to demonstrate the concept of multi-source ML for TPC aerostructure consolidation and assembly. First, the team completed documentation of induction based TPC heating requirements including baseline metrics to compare measured results against. Next the team completed demonstration of data generation from physics-based simulations for ML surrogate model generation and demonstrated the integration of physics-based simulation data into multi-source AI/ML algorithms. In parallel, the team established the lab-coupon scale induction welding system and completed a process to label and reduce generated data from physics-based simulation and experiments for ML surrogate models to enable multi-source ML model training & testing. To complete BP1, the team integrated physics-based simulation data and experimental data into multi-source ML algorithms. This was based on the team completing ML deployment of the induction welding on a lab system at RTRC and AI/ML deployment on existing induction welding line at Collins. ORNL visited both Collins and RTRC sites to witness the TPC induction welding process. Then, ORNL designed and constructed a new version of their vision-based sensing system better adapted to acquire process signals of the TPC induction welding process for process anomaly and defect detection. In BP2, the team accomplished key tasks & milestones to scale up multi-source ML for TPC aerostructure consolidation and assembly from the lab-coupon scale to the pilot-industrial scale. In BP2, the team demonstrated real time anomaly & defect detection via experiments performed by ORNL & RTRC. The team completed ML-optimization heating trials for TPC induction consolidation at Collins, and the team confirmed pilot industrial scale experimental data from Collins was compatible with the developed ML pipeline from RTRC. The team completed sub-element scale ML process optimization demonstration at RTRC, where the team leveraged RTRC’s robotic TPC welding setup to de-risk the ML process optimization by performing ML analysis of recorded temperatures to account for complex part features. Then, the team applied its ML-derived control strategies and ML process optimization framework at Collins to the pilot-industrial scale on a demo skin-stiffener part representative of a nacelle aerostructure fan cowl section. The key innovation is the AI/ML framework enabling effective process development of high performance, lightweight, energy efficient TPCs for composite aircraft structures.

36 MATERIALS SCIENCE↗