Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “simulation modeling training analysis”

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 487 records · Page 27
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Accelerated Probabilistic Marching Cubes by Deep Learning for Time-Varying Scalar Ensembles

Visualizing the uncertainty of ensemble simulations is challenging due to the large size and multivariate and temporal features of en-semble data sets. One popular approach to studying the uncertainty of ensembles is analyzing the positional uncertainty of the level sets. Probabilistic marching cubes is a technique that performs Monte Carlo sampling of multivariate Gaussian noise distributions for positional uncertainty visualization of level sets. However, the technique suffers from high computational time, making interactive visualization and analysis impossible to achieve. This paper introduces a deep-learning-based approach to learning the level-set uncertainty for two-dimensional ensemble data with a multivariate Gaussian noise assumption. We train the model using the first few time steps from time-varying ensemble data in our workflow. We demonstrate that our trained model accurately infers uncertainty in level sets for new time steps and is up to 170X faster than that of the original probabilistic model with serial computation and 10X faster than that of the original parallel computation.

Han, Mengjiao↗
NASA NTRS2004

Simulation Based Acquisition for NASA's Office of Exploration Systems

In January 2004, President George W. Bush unveiled his vision for NASA to advance U.S. scientific, security, and economic interests through a robust space exploration program. This vision includes the goal to extend human presence across the solar system, starting with a human return to the Moon no later than 2020, in preparation for human exploration of Mars and other destinations. In response to this vision, NASA has created the Office of Exploration Systems (OExS) to develop the innovative technologies, knowledge, and infrastructures to explore and support decisions about human exploration destinations, including the development of a new Crew Exploration Vehicle (CEV). Within the OExS organization, NASA is implementing Simulation Based Acquisition (SBA), a robust Modeling & Simulation (M&S) environment integrated across all acquisition phases and programs/teams, to make the realization of the President s vision more certain. Executed properly, SBA will foster better informed, timelier, and more defensible decisions throughout the acquisition life cycle. By doing so, SBA will improve the quality of NASA systems and speed their development, at less cost and risk than would otherwise be the case. SBA is a comprehensive, Enterprise-wide endeavor that necessitates an evolved culture, a revised spiral acquisition process, and an infrastructure of advanced Information Technology (IT) capabilities. SBA encompasses all project phases (from requirements analysis and concept formulation through design, manufacture, training, and operations), professional disciplines, and activities that can benefit from employing SBA capabilities. SBA capabilities include: developing and assessing system concepts and designs; planning manufacturing, assembly, transport, and launch; training crews, maintainers, launch personnel, and controllers; planning and monitoring missions; responding to emergencies by evaluating effects and exploring solutions; and communicating across the OExS enterprise, within the Government, and with the general public. The SBA process features empowered collaborative teams (including industry partners) to integrate requirements, acquisition, training, operations, and sustainment. The SBA process also utilizes an increased reliance on and investment in M&S to reduce design risk. SBA originated as a joint Industry and Department of Defense (DoD) initiative to define and integrate an acquisition process that employs robust, collaborative use of M&S technology across acquisition phases and programs. The SBA process was successfully implemented in the Air Force s Joint Strike Fighter (JSF) Program.

Hale, Joe↗
DOE OSTI2025

Integration of a grey-box refrigerated case model in EnergyPlus via Python plugin

Commercial buildings, in particular grocery stores (due mainly to their large refrigeration load), provide opportunities for energy cost reductions. Grocery stores could offer substantial load flexibility to the power grid through participation in demand response programs because of their usage patterns and relatively high energy intensity. This load flexibility could come from modifying the control of heating, ventilation, and air conditioning (HVAC) systems, refrigeration systems, or both. Although estimation of the HVAC system’s load flexibility potential is relatively targeted in the literature, estimating load flexibility of refrigeration systems is nascent and has been a challenge, in part because of the lack of proper simulation tools that capture the dynamics in the refrigeration cases. The existing refrigerated case model within EnergyPlus, a whole building energy simulation program, assumes a constant case temperature throughout the simulation period and does not explicitly model the cycling of the compressor serving the refrigerated case. In addition, it does not encompass modeling of temperatures of the product inside the refrigerated case. This difference between modeled and actual operation can be a barrier to the development of demand control algorithm and accurate analysis of load flexibility potential. In this paper, we present a grey-box model for modeling refrigerated cases in grocery stores, which include medium temperature and low temperature. Four cases are modeled; two are low-temperature closed cases and two are medium-temperature cases with one closed and one open. Data from an experimental facility are used to train and test the models. Results demonstrate the efficacy of the grey-box models in predicting the temperatures. This model is integrated into EnergyPlus to capture the dynamic effects of case temperature on the environment and enhance the calculation of sensible and latent heat exchange with the environment (case credits). These enhancements can be leveraged more broadly to model advanced refrigeration controls such as defrost, develop and test unique algorithms that could affect refrigeration interactions with HVAC, and refine store design for any commercial building with refrigeration.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2026

Efficient data-driven regression for reduced-order modeling of spatial pattern formation

We present an efficient data-driven regression approach for constructing reduced-order models (ROMs) of reaction-diffusion systems exhibiting pattern formation. The ROMs are learned non-intrusively from available training data of physically accurate numerical simulations. The method can be applied to general nonlinear systems through the use of polynomial model form, while not requiring knowledge of the underlying physical model, governing equations, or numerical solvers. The process of learning ROMs is posed as a low-cost least-squares problem in a reduced-order subspace identified via Proper Orthogonal Decomposition (POD). Numerical experiments on classical pattern-forming systems–including the Schnakenberg and Mimura–Tsujikawa models–demonstrate that higher-order surrogate models significantly improve prediction accuracy while maintaining low computational cost. The proposed method provides a flexible, non-intrusive model reduction framework, well suited for the analysis of complex spatio-temporal pattern formation phenomena.

Data-driven modeling↗
DOE OSTI2024

UFNet: Joint U-Net and Fully Connected Neural Network to Bias Correct Precipitation Predictions from

Paper information. Shuang Yu, Indrasis Chakraborty, Gemma J. Anderson, Donald D. Lucas, Yannic Lops, and Daniel Galea. UFNet: Joint U-Net and fully connected neural network to bias correct precipitation predictions from climate models. Artificial Intelligence for the Earth Systems, 2024. Overview. This work develops the UFNet methodology to correct E3SM historical precipitation projection bias. The UFNet deep learning framework consists of a two-part architecture: a U-Net convolutional network to capture the spatiotemporal distribution of precipitation and a fully connected network to capture the distribution of higher-order statistics. The joint network, termed UFNet, can simultaneously improve the spatial structure of the modeled precipitation and capture the distribution of extreme precipitation values. Below we provide guidance for applying UFNet to correct the Energy Exascale Earth System Model (E3SM; Golaz et al. 2019) daily precipitation projection over the contiguous United States (CONUS). Getting started 1. Obtain the historical climate simulation and observation data. The E3SM historical simulation data are available through https://aims2.llnl.gov/search/cmip6/. The CPC unified gauge-based analysis of daily precipitation can be found through https://psl.noaa.gov/data/gridded/data.cpc.globalprecip.html. The ECMWF atmospheric reanalysis of the 20th century (ERA-20C) data are available through https://www.ecmwf.int/en/forecasts/datasets/reanalysis-datasets/era-20c. The spatial resolution of E3SM and observed datasets are both regridded to a common 1° resolution grid using conservative interpolation. The regridded E3SM, CPC and ERA-20C with 1° resolution can be found throught ./data/. 2. Train the fully connected network (DNN) Python train_dnn.py 3. Train the UFNet Python train_ufnet.py 4. Evaluation and compared with the baseline Python evaluation.py

Lucas, DonaldD↗
DOE OSTI2022

Noise-Resilient Quantum Machine Learning for Stability Assessment of Power Systems

Transient stability assessment (TSA) is a cornerstone for resilient operations of todays interconnected power grids. This paper is a confluence of quantum computing, data science and machine learning to potentially address the power system TSA issue. Here, we devise a quantum TSA (QTSA) method to enable scalable and efficient data-driven transient stability prediction for bulk power systems, which is the first attempt to tackle the TSA issue with quantum computing. Our contributions are three-fold: 1) A high expressibility, low-depth (HELD) quantum circuit is designed for accurate and noise-resilient TSA; 2) A quantum natural gradient descent algorithm is developed for efficient HELD circuit training; 3) A systematical analysis on QTSAs performance under various quantum factors is per-formed. QTSA underpins a foundation of quantum-enabled and data-driven power grid stability analytics. It renders the intractable TSA straightforward and effortless in the Hilbert space, and therefore provides stability information for power system operations. Extensive experiments on quantum simulators and real quantum computers verify the accuracy, noise-resilience, scalability and universality of QTSA.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
NASA NTRS2008

A Multi-Season Study of the Effects of MODIS Sea-Surface Temperatures on Operational WRF Forecasts at NWS Miami, FL

Studies at the Short-term Prediction Research and Transition (SPORT) Center have suggested that the use of Moderate Resolution Imaging Spectroradiometer (MODIS) sea-surface temperature (SST) composites in regional weather forecast models can have a significant positive impact on short-term numerical weather prediction in coastal regions. Recent work by LaCasse et al (2007, Monthly Weather Review) highlights lower atmospheric differences in regional numerical simulations over the Florida offshore waters using 2-km SST composites derived from the MODIS instrument aboard the polar-orbiting Aqua and Terra Earth Observing System satellites. To help quantify the value of this impact on NWS Weather Forecast Offices (WFOs), the SPORT Center and the NWS WFO at Miami, FL (MIA) are collaborating on a project to investigate the impact of using the high-resolution MODIS SST fields within the Weather Research and Forecasting (WRF) prediction system. The project's goal is to determine whether more accurate specification of the lower-boundary forcing within WRF will result in improved land/sea fluxes and hence, more accurate evolution of coastal mesoscale circulations and the associated sensible weather elements. The NWS MIA is currently running WRF in real-time to support daily forecast operations, using the National Centers for Environmental Prediction Nonhydrostatic Mesoscale Model dynamical core within the NWS Science and Training Resource Center's Environmental Modeling System (EMS) software. Twenty-seven hour forecasts are run dally initialized at 0300, 0900, 1500, and 2100 UTC on a domain with 4-km grid spacing covering the southern half of Florida and adjacent waters of the Gulf of Mexico and Atlantic Ocean. Each model run is initialized using the Local Analysis and Prediction System (LAPS) analyses available in AWIPS. The SSTs are initialized with the NCEP Real-Time Global (RTG) analyses at 1/12deg resolution (approx.9 km); however, the RTG product does not exhibit fine-scale details consistent with its grid resolution. SPORT is conducting parallel WRF EMS runs identical to the operational runs at NWS MIA except for the use of MODIS SST composites in place of the RTG product as the initial and boundary conditions over water, The MODIS SST composites for initializing the SPORT WRF runs are generated on a 2-km grid four times daily at 0400, 0700, 1600, and 1900 UTC, based on the times of the overhead passes of the Aqua and Terra satellites. The incorporation of the MODIS SST data into the SPORT WRF runs is staggered such that SSTs are updated with a new composite every six hours in each of the WRF runs. From mid-February to July 2007, over 500 parallel WRF simulations have been collected for analysis and verification. This paper will present verification results comparing the NWS MIA operational WRF runs to the SPORT experimental runs, and highlight any substantial differences noted in the predicted mesoscale phenomena for specific cases.

Case, Jonathan L.↗
DOE OSTI2024

Reinforcement learning for block decomposition of planar CAD models

Abstract The problem of hexahedral mesh generation of general CAD models has vexed researchers for over 3 decades and analysts often spend more than 50% of the design-analysis cycle time decomposing complex models into simpler blocks meshable by existing techniques. The decomposed blocks are required for generating good quality meshes (tilings of quadrilaterals or hexahedra) suitable for numerical simulations of physical systems governed by conservation laws. We present a novel AI-assisted method for decomposing (segmenting) planar CAD (computer-aided design) models into well shaped rectangular blocks. Even though the simple examples presented here can also be meshed using many conventional methods, we believe this work is proof-of-principle of a AI-based decomposition method that can eventually be generalized to complex 2D and 3D CAD models. Our method uses reinforcement learning to train an agent to perform a series of optimal cuts on the CAD model that result in a good quality block decomposition. We show that the agent quickly learns an effective strategy for picking the location and direction of the cuts and maximizing its rewards. This paper is the first successful demonstration of an agent autonomously learning how to perform this block decomposition task effectively, thereby holding the promise of a viable method to automate this challenging process for more complex cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Deep Learning and Likelihood Approaches for Viral Phylogeography Converge on the Same Answers Whether the Inference Model Is Right or Wrong

Abstract Analysis of phylogenetic trees has become an essential tool in epidemiology. Likelihood-based methods fit models to phylogenies to draw inferences about the phylodynamics and history of viral transmission. However, these methods are often computationally expensive, which limits the complexity and realism of phylodynamic models and makes them ill-suited for informing policy decisions in real-time during rapidly developing outbreaks. Likelihood-free methods using deep learning are pushing the boundaries of inference beyond these constraints. In this paper, we extend, compare, and contrast a recently developed deep learning method for likelihood-free inference from trees. We trained multiple deep neural networks using phylogenies from simulated outbreaks that spread among 5 locations and found they achieve close to the same levels of accuracy as Bayesian inference under the true simulation model. We compared robustness to model misspecification of a trained neural network to that of a Bayesian method. We found that both models had comparable performance, converging on similar biases. We also implemented a method of uncertainty quantification called conformalized quantile regression that we demonstrate has similar patterns of sensitivity to model misspecification as Bayesian highest posterior density (HPD) and greatly overlap with HPDs, but have lower precision (more conservative). Finally, we trained and tested a neural network against phylogeographic data from a recent study of the SARS-Cov-2 pandemic in Europe and obtained similar estimates of region-specific epidemiological parameters and the location of the common ancestor in Europe. Along with being as accurate and robust as likelihood-based methods, our trained neural networks are on average over 3 orders of magnitude faster after training. Our results support the notion that neural networks can be trained with simulated data to accurately mimic the good and bad statistical properties of the likelihood functions of generative phylogenetic models.

Evolutionary Biology↗
DOE OSTI2023

Neural network surrogate models for equations of state

Equation of state (EOS) data provide necessary information for accurate multiphysics modeling, which is necessary for fields such as inertial confinement fusion. Here, we suggest a neural network surrogate model of energy and entropy and use thermodynamic relationships to derive other necessary thermodynamic EOS quantities. We incorporate phase information into the model by training a phase classifier and using phase-specific regression models, which improves the modal prediction accuracy. Our model predicts energy values to 1% relative error and entropy to 3.5% relative error in a log-transformed space. Although sound speed predictions require further improvement, the derived pressure values are accurate within 10% relative error. Our results suggest that neural network models can effectively model EOS for inertial confinement fusion simulation applications.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2019

Integrating narratives into decision making for complex systems engineering design issues

Abstract Engineering decision making and design requires collaboration between groups from different disciplines, each with different tools, vocabulary, and concerns. Traditional engineering decision‐making tools are generally based on understanding the decision makers’ values, modeling uncertainty with probability, and selecting the alternative that maximizes utility. This rational approach to decision making may not be well understood or used by many stakeholders involved in the engineering design process. Constructing narratives, a basic means of human communication, may aid in engineering communication and comprehension and help with decision making. Narratives represent events by means of a story and usually include characters or agents who cause events and to whom events happen. This paper recommends three methods for how the use of narrative can be applied to the area of engineering decision making. These methods include connecting the decision maker to the analysis, creating narrative simulations for training decision makers, and fostering consensus in problems with multiple stakeholders. An illustrative example of designing a better cookstove for the developing world demonstrates the role that understanding narratives of various stakeholders can play for accomplishing complex systems engineering.

MacKenzie, Cameron A.↗
DOE OSTI2019

Vehicle energy consumption estimation using large scale simulations and machine learning methods

Vehicle energy consumption and powertrain operations for future vehicle powertrain technologies are predicted through full-vehicle simulations using Autonomie, a simulation tool developed at Argonne National Laboratory. Over 1 million vehicles, with different powertrain types (conventional and numerous electrified powertrains) and component technologies (advanced engines, batteries, electrical machines, light weighting) are simulated for outputs including vehicle fuel economy and cost. Despite the ability of Autonomic to predict fuel economy given various combination of vehicle inputs, the full-vehicle simulation is very time-consuming. It takes approximately 84 h to simulate for 33,060 vehicles even using distributed computing on a cluster of 128 worker nodes. Moreover, Autonomic is unable to populate a continuous output space through simulation since it only yields outputs with discrete values instead of an input-output relation. This paper proposes a novel large-scale learning and prediction process (LSLPP) via machine learning approaches to answer the need for a continuous space of vehicle fuel economy and a more efficient simulation process. By learning in a supervised fashion to discover structures in data, the machine learning approaches seek to train a model that can explain the data with which we can perform prediction over unseen data. As such, we are able to accomplish analytic continuation on the current discrete space of simulation results. In addition, we present a random sampling -based numerosity reduction algorithm incorporated in LSLPP that reduces simulation runs and improves efficiency of data procurement. We analytically derive a theoretical bound in order to guarantee the effectiveness of our algorithm. We also compare random sampling to stratified sampling and suggest sampling strategies. A user-friendly tool is developed to support the process. Our experimental results confirm that the proposed LSLPP is able to greatly accelerate prediction and analysis of vehicle fuel economy. The output of this study is used by the US government to evaluate the impact of its R&D funding on energy security and CO 2 emission as well as for the setting of Corporate Average Fuel Economy (CAFE) standards.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Improving neutrino oscillation measurements through event classification

Precise neutrino energy reconstruction is essential for next-generation long-baseline oscillation experiments, yet current methods remain limited by large uncertainties in neutrino-nucleus interaction modeling. Even so, it is well established that different interaction channels produce systematically varying amounts of missing energy and therefore yield different reconstruction performance–information that standard calorimetric approaches do not exploit. We introduce a strategy that incorporates this structure by classifying events according to their underlying interaction type prior to energy reconstruction. Using supervised machine-learning techniques trained on labeled generator events, we leverage intrinsic kinematic differences among quasielastic scattering, meson-exchange current, resonance production, and deep-inelastic scattering processes. A cross-generator testing framework demonstrates that this classification approach is robust to microphysics mismodeling and, when applied to a simulated DUNE 𝜈 𝜇 disappearance analysis, yields improved accuracy and sensitivity at the 10%–20% level. These results highlight a practical path toward reducing reconstruction-driven systematics in future oscillation measurements.

Ellis, Sebastian A. R. [King's College, London (Un↗
DOE OSTI2019

Methodology for Estimating Safe Charge Limits of Flammable Refrigerants in HVAC&R Applications - Part 2

This report provides a detailed description of the development of a reduced order model (ROM) that could be used for estimation of safe charge limits based on a computational fluid dynamics (CFD) parametric study. The ROM was developed to simulate leak events from a single side-wall duct penetration into a room and provide estimates of refrigerant concentration together with flammable volume fraction (FVF), accumulated fuel volume (AFV) and other outputs vs. time. The ROM is based on a range of seven parameters listed in Table ES1 and assumes that the AC unit air circulation blower is off. A total of 586 CFD “training” cases were run and used as the basis for development and training or calibration of the ROM. The regression analysis used to develop the ROM was performed in Tasmanian ( T oolkit for A daptive S tochastic M odeling A nd N on- I ntrusive A pproximatio N ). This is a tool developed at ORNL for high-dimensional integration, interpolation and parameter calibration. Comparison of the ROM vs. several CFD test cases (at points not used in the training set) showed maximum absolute and root mean square errors (RMSE) for FVF of 1.32% and 0.5%, respectively. Initial CFD runs were conducted to gauge the sensitivity of the results to each parameter. Based on the findings, the numbers of design of experiment (DoE) levels for each parameter was determined. Then, for each parameter, Tasmanian calculated the value of each level and defined a DoE of 586 unique CFD simulation cases.

42 ENGINEERING↗
NASA NTRS1988

Wave/current interaction model

The wave-current interaction for the application to remote sensing data via numerical simulations and data comparison is modelled. Using the field data of surface current shear, wind condition and ambient wave spectrum, the numerical simulations of directional wave spectrum evolution were used to interpret and to compare with the aircraft data from Radar Ocean Wave Spectrometer (ROWS) and Surface Contour Radar (SCR) across the front during Frontal Air Sea Interaction Experiment (FASINEX). The wave-ice interaction was inspired by the observation of large amplitude waves hundreds of kms inside the ice pack in the Weddell Sea, resulting in breakup of the ice pack. The developed analysis of processes includes the refraction of waves at the pack edge, the effects of pack compression on wave propagation, wave train stability and buckling stability in the ice pack. Sources of pack compression and interaction between wave momentum and pack compression are investigated. Viscous camping of propagating waves in the marginal ice zone are also studied. The analysis suggests an explanation for the change in wave dispersion observed from the ship and the sequence of processes that cause ice pack breakup, pressure ridge formation and the formation of open bands of water.

Liu, A. K.↗
DOE OSTI2022

Normalizing flows for likelihood-free inference with fusion simulations

Fluid-based scrape-off layer transport codes, such as UEDGE, are heavily utilized in tokamak analysis and design, but typically require user-specified anomalous transport coefficients to match experiments. Determining the uniqueness of these parameters and the uncertainties in them to match experiments can provide valuable insights to fusion scientists. Here, we leverage recent work in the area of likelihood-free inference (‘simulation-based inference’) to train a neural network, which enables accurate statistical inference of the anomalous transport coefficients given experimental plasma profile input. UEDGE is treated as a black-box simulator and runs multiple times with anomalous transport coefficients sampled from priors, and the neural network is trained on these simulations to emulate the posterior. The neural network is trained as a normalizing flow model for density estimation, allowing it to accurately represent complicated, high-dimensional distribution functions. With a fixed simulation budget, we compare a single-round procedure to a multi-round approach that guides the training simulations toward a specific target observation. Finally, we discuss the future possibilities for use of amortized models, which train on a wide range of simulations and enable fast statistical inference for results during experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1997

Neural Network Prediction of Failure of Damaged Composite Pressure Vessels from Strain Field Data Acquired by a Computer Vision Method

This effort used a new and novel method of acquiring strains called Sub-pixel Digital Video Image Correlation (SDVIC) on impact damaged Kevlar/epoxy filament wound pressure vessels during a proof test. To predict the burst pressure, the hoop strain field distribution around the impact location from three vessels was used to train a neural network. The network was then tested on additional pressure vessels. Several variations on the network were tried. The best results were obtained using a single hidden layer. SDVIC is a fill-field non-contact computer vision technique which provides in-plane deformation and strain data over a load differential. This method was used to determine hoop and axial displacements, hoop and axial linear strains, the in-plane shear strains and rotations in the regions surrounding impact sites in filament wound pressure vessels (FWPV) during proof loading by internal pressurization. The relationship between these deformation measurement values and the remaining life of the pressure vessels, however, requires a complex theoretical model or numerical simulation. Both of these techniques are time consuming and complicated. Previous results using neural network methods had been successful in predicting the burst pressure for graphite/epoxy pressure vessels based upon acoustic emission (AE) measurements in similar tests. The neural network associates the character of the AE amplitude distribution, which depends upon the extent of impact damage, with the burst pressure. Similarly, higher amounts of impact damage are theorized to cause a higher amount of strain concentration in the damage effected zone at a given pressure and result in lower burst pressures. This relationship suggests that a neural network might be able to find an empirical relationship between the SDVIC strain field data and the burst pressure, analogous to the AE method, with greater speed and simplicity than theoretical or finite element modeling. The process of testing SDVIC neural network analysis and some encouraging preliminary results are presented in this paper. Details are given concerning the processing of SDVIC output data such that it may be used as back propagation neural network (BPNN) input data. The software written to perform this processing and the BPNN algorithm are also discussed. It will be shown that, with limited training, test results indicate an average error in burst pressure prediction of approximately six percent,

Russell, Samuel S.↗
DOE OSTI2025

Ensemble cure kinetics network (ECK-Net): A method to derive cure kinetics of thermosetting resin

This paper introduces an Ensemble Cure Kinetics Network (ECK-Net), a neural network (NN)–based framework for modeling the cure kinetics of thermosetting resins within a phenomenological context. ECK-Net replaces traditional analytic models, which require extensive chemical insight and multiple isothermal/non-isothermal experiments, with a data-driven surrogate that maps nonlinear relationships between temperature, degree of cure, and reaction rate from differential scanning calorimetry data. The proposed approach predicts input-dependent kinetic coefficients of a generalized nth-order reaction equation rather than reaction rates directly, enabling a single unified model to represent various epoxy systems without relying on iso-conversional analysis or predefined functional forms. To ensure robustness, multiple independently trained networks under different random initializations are blended through an ensemble strategy, effectively mitigating the stochastic variability inherent to neural networks. The framework is validated using experimental datasets from multiple resin systems, including aerospace-grade materials (Toray 3900-2, Cycom 5320-1, and Hexcel 8552) and a windmill-grade resin (RIMR 035c). The model accurately reproduces the temporal evolution of the degree of cure under manufacturers’ recommended cure cycles across all tested resins systems, yielding Pearson’s correlation coefficients of 0.992, 0.994, 0.993, 0.997, respectively. To demonstrate process-level applicability, the trained network was implemented within the Abaqus environment to simulate out-of-autoclave (OOA) curing process of the CFRP panel composed of Toray T830H-6K/3900-2D prepreg. The simulation results showed excellent agreement with experimental temperature response (maximum peak temperature, simulation: 189.6 °C, experiment: 188.5 °C) and the final degree of cure (simulation: 0.948, experiment: 0.960 ± 0.013), confirming ECK-Net’s capability as a reliable alternative to conventional cure kinetics modeling methods.

Composite curing↗