Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning dynamics”

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 901 records · Page 50
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems

Abstract Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Structure and dynamics of $\mathrm{Fe_{90}}$$\mathrm{Si_3}$$\mathrm{O_7}$ liquids close to Earth's liquid core conditions

Using an artificial neural-network machine learning interatomic potential, we have performed molecular dynamics simulations to study the structure and dynamics of $\mathrm{Fe_{90}}$$\mathrm{Si_3}$$\mathrm{O_7}$ liquid close to the Earth's liquid core conditions. Here, the simulation results reveal that the short-range structural order (SRO) in the $\mathrm{Fe_{90}}$$\mathrm{Si_3}$$\mathrm{O_7}$ liquid is very strong. About 80% of the atoms are arranged in crystallinelike SRO motifs. In particular, ~ $70$% of Fe-centered clusters can be classified as either hexagonal-close-packed-like or icosahedrallike SRO motifs. The SRO clusters centered on Fe, Si, or O atoms are strongly intermixed and homogenously distributed throughout the liquid. The atomic structure of the liquid and the fractions of dominant SRO clusters are not sensitive to pressure/temperature used in the simulations except that the SRO of the O-centered clusters is enhanced close to inner core pressures. The O-diffusion coefficient is about two to three times larger than the Fe and Si ions and increases more rapidly in the deeper core regions.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2026

Neural entropy-stable conservative flux form neural networks for learning hyperbolic conservation laws

We propose a neural entropy-stable conservative flux form neural network (NESCFN) for learning hyperbolic conservation laws and their associated entropy functions directly from solution trajectories, without requiring any predefined numerical discretization. While recent neural network architectures have successfully integrated classical numerical principles into learned models, most rely on prior knowledge of the governing equations or assume a fixed discretization. Our approach removes this dependency by embedding entropy-stable design principles into the learning process itself, enabling the discovery of physically consistent dynamics in a fully data-driven setting. By jointly learning both the flux function and a corresponding entropy, NESCFN promotes conservation and entropy dissipation, which is critical for long-term stability and fidelity in the system of hyperbolic conservation laws. Furthermore, numerical results demonstrate that the method achieves stability and conservation over extended time horizons and accurately captures shock propagation speeds, even without oracle access to future-time solution profiles in the training data.

Conservative flux form↗
DOE OSTI2023

Black and gray box learning of amplitude equations: Application to phase field systems

Here, we present a data-driven approach to learning surrogate models for amplitude equations and illustrate its application to interfacial dynamics of phase field systems. In particular, we demonstrate learning effective partial differential equations describing the evolution of phase field interfaces from full phase field data. We illustrate this on a model phase field system, where analytical approximate equations for the dynamics of the phase field interface (a higher-order eikonal equation and its approximation, the Kardar-Parisi-Zhang equation) are known. For this system, we discuss data-driven approaches for the identification of equations that accurately describe the front interface dynamics. When the analytical approximate models mentioned above become inaccurate, as we move beyond the region of validity of the underlying assumptions, the data-driven equations outperform them. In these regimes, going beyond black box identification, we explore different approaches to learning data-driven corrections to the analytically approximate models, leading to effective gray box partial differential equations.

42 ENGINEERING↗
DOE OSTI2022

Utilizing CellBox to Describe Varied Dynamical Systems

CellBox is a hybrid modeling framework that integrates machine-learning approaches with explicit mathematical modeling to determine the behavior of dynamical systems, intended for determining the complex interactions of molecule and phenotype within a cellular environment using perturbation/response-based data. The original work utilized analysis of a melanoma cell line, SK-Mel-133, which we sought to expand to and evaluate effectiveness in describing other nonlinear systems both within and outside of biology. We evaluated with two models. One model is based upon the free-fall of an object under a velocity-dependent drag force; this produced inherent perturbation/response data. The other model is based upon a form of mass-action molecular kinetics; for this, we ran the simulation to steady state in each species for each perturbation and select the steady state as input for CellBox. We determined that CellBox, outside of its original use case, can still strongly predict even non-biological dynamical systems in the small-perturbation regime, with r = 0.99977 to 0.85123, p < 0.05 for freefall. However, CellBox cannot accurately predict behavior within large-perturbation regimes, p >> 0.05 for freefall. In addition, we performed a naïve comparison of CellBox network structure to known network structure in the mass-action model to assess accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Learning Constrained Parametric Differentiable Predictive Control Policies With Guarantees

We present differentiable predictive control (DPC), a method for offline learning of constrained neural control policies for nonlinear dynamical systems with performance guarantees. We show that the sensitivities of the parametric optimal control problem can be used to obtain direct policy gradients. Specifically, we employ automatic differentiation (AD) to efficiently compute the sensitivities of the model predictive control (MPC) objective function and constraints penalties. To guarantee safety upon deployment, we derive probabilistic guarantees on closed-loop stability and constraint satisfaction based on indicator functions and Hoeffding’s inequality. We empirically demonstrate that the proposed method can learn neural control policies for various parametric optimal control tasks. In particular, we show that the proposed DPC method can stabilize systems with unstable dynamics, track time-varying references, and satisfy nonlinear state and input constraints. Our DPC method has practical time savings compared to alternative approaches for fast and memory-efficient controller design. Specifically, DPC does not depend on a supervisory controller as opposed to approximate MPC based on imitation learning. We demonstrate that, without losing performance, DPC is scalable with greatly reduced demands on memory and computation compared to implicit and explicit MPC while being more sample efficient than model-free reinforcement learning (RL) algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

Going deeper and wider in neural architectures improves their accuracy, while the limited GPU DRAM places an undesired restriction on the network design domain. Deep Learning (DL) practitioners either need to change to less de- sired network architectures, or nontrivially dissect a network across multiGPUs. These distract DL practitioners from concentrating on their original machine learning tasks. We present SuperNeurons: a dynamic GPU memory scheduling runtime to enable the network training far beyond the GPU DRAM capacity. SuperNeurons features 3 memory optimizations, Liveness Analysis, Unified Tensor Pool, and Cost-Aware Recomputation; together they effectively reduce the network-wide peak memory usage down to the maximal memory usage among layers. We also address the performance issues in these memory-saving techniques. Given the limited GPU DRAM, SuperNeurons not only provisions the necessary memory for the training, but also dynamically allocates the memory for convolution workspaces to achieve the high performance. Evaluations against Caffe, Torch, MXNet and TensorFlow have demonstrated that SuperNeurons trains at least 3.2432 deeper network than current ones with the leading performance. Particularly, SuperNeurons can train ResNet2500 that has 104 basic network layers on a 12GB K40c.

Wang, Linnan↗
DOE OSTI2024

Linking Threat Agents to Targeted Organizations: A Pipeline for Enhanced Cybersecurity Risk Metrics

In this study, we present a methodology leveraging Large Language Models (LLMs) to transform Cybersecurity Threat Intelligence (CTI) narratives into actionable insights for individual organizations. Our approach automates the extraction of machine-readable adversary SKRAM (Skills, Knowledge, Resources, Authorities, and Motivation) attributes from open-source reports, extending LLM utility beyond typical interactions. This innovation enables precise, automated assessments of cybersecurity risks posed by various adversaries. Using a chain-of-thought and multi-shot prompting strategy, our methodology advances the automation of cybersecurity feature extraction for new machine-learning models that predict the risk of adversary targeting. This approach is refined using a substantial dataset of over 150 analyst-validated threat reports and synthetic organizational data from 900 companies. Here, by bootstrapping the training data with a rule-based heuristic over synthetic data, we have developed a high-accuracy machine-learning model that allows entities to dynamically prioritize threats and defensive actions.

Cyber Threat Intelligence↗
DOE OSTI2025

Integrating Analytical Solutions and U-Net Model for Predicting Groundwater Contaminant Plumes in Pump-and-Treat Systems

Pump-and-treat (P&T) is a common technique for groundwater remediation involving the extraction and treatment of contaminated water above ground. Optimizing the design and operation of the P&T well network is essential for maximizing the system’s effectiveness and efficiency. However, this optimization often necessitates many model evaluations, leading to computationally demanding tasks. This study introduces a novel approach that integrates analytical solutions for groundwater dynamics with the U-Net (Ronneberger et al., 2015) deep learning framework to predict groundwater contaminant plume migration under dynamic pumping conditions. By incorporating the Thiem equation (Thiem, 1906) into the input preprocessing, the U-Net model transforms sparse well data into a continuous spatial field that captures the hydraulic impacts of pumping activities. This integration enables the model to leverage both deep learning capabilities and classical physics-based groundwater theories, enhancing prediction accuracy and computational efficiency. These advancements can facilitate rapid, large-scale evaluations of P&T optimization simulations, allowing for timely and effective decision-making in well placement and system management. We demonstrate the model's robust performance across both simplified transient 2D models and a more complex 3D heterogeneous site model at the 200 West P&T facility at the Hanford Site. The U-Net-based model offers substantial computational advantages, reducing simulation times significantly compared to full physics-based models and providing a powerful tool for rapid site evaluation and P&T system optimization, such as evaluating alternative P&T well network designs. Our findings highlight the potential of advanced machine learning models to significantly enhance the efficiency and sustainability of groundwater remediation efforts, offering a novel application of U-Net architecture in environmental science.

Pump-and-treat↗
DOE OSTI2021

Utilizing a Dynamic Segmentation Convolutional Neural Network for Microstructure Analysis of Additively Manufactured Superalloy 718

Additive manufacturing (AM) is revolutionizing almost all industries through the production of intricate geometries previously prohibited by cost or machinability. Ni-based superalloys form a primary alloy class for high temperature applications in the petrochemical, aerospace, and nuclear industries because of their intrinsic resistance to creep and the ability to heat treat the superalloy for high strength. Despite these attractive properties, the extreme work hardening of Ni-based superalloys makes traditional manufacturing of complex shapes difficult and thus, these alloys are an attractive target for AM. Superalloy 718 was chosen as an example superalloy because of the wide variety of precipitates that can form within its composition space from the repetitive heating and cooling cycles of the AM process. The precipitates and other microstructure features, such as grain boundaries and dislocations, will dictate the mechanical properties and thus, there is an extensive challenge to characterize the size, number density, composition, and volume fraction of each microstructural feature from AM fabrication using analytical electron microscopy. This work focused on the application of a pixel-wise classification machine learning (ML) model called a dynamic segmentation convolutional neural network (DSCNN) to identify the microstructural features of an as-fabricated additively manufactured superalloy 718.

Taller, Stephen↗
DOE OSTI2021

Reservoir Computing as a Tool for Climate Predictability Studies

Reduced-order dynamical models play a central role in developing our understanding of predictability of climate irrespective of whether we are dealing with the actual climate system or surrogate climate models. In this context, the linear inverse modeling (LIM) approach, by capturing a few essential interactions between dynamical components of the full system, has proven valuable in providing insights into predictability of the full system. We demonstrate that reservoir computing (RC), a form of learning suitable for systems with chaotic dynamics, provides an alternative nonlinear approach that improves on the predictive skill of the LIM approach. We do this in the example setting of predicting sea surface temperature in the North Atlantic in the preindustrial control simulation of a popular earth system model, the Community Earth System Model so that we can compare the performance of the new RC-based approach with the traditional LIM approach both when learning data are plentiful and when such data are more limited. The improved predictive skill of the RC approach over a wide range of conditions—larger number of retained EOF coefficients, extending well into the limited data regime, etc.—suggests that this machine-learning technique may have a use in climate predictability studies. While the possibility of developing a climate emulator—the ability to continue the evolution of the system on the attractor long after failing to be able to track the reference trajectory—is demonstrated in the Lorenz-63 system, it is suggested that further development of the RC approach may permit such uses of the new approach in more realistic predictability studies.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2016

Space Launch System Vibration Analysis Support

The ultimate goal for my efforts during this internship was to help prepare for the Space Launch System (SLS) integrated modal test (IMT) with Rodney Rocha. In 2018, the Structural Engineering Loads and Dynamics Team will have 10 days to perform the IMT on the SLS Integrated Launch Vehicle. After that 10 day period, we will have about two months to analyze the test data and determine whether the integrated vehicle modes/frequencies are adequate for launching the vehicle. Because of the time constraints, NASA must have newly developed post-test analysis methods proven well and with technical confidence before testing. NASA civil servants along with help from rotational interns are working with novel techniques developed and applied external to Johnson Space Center (JSC) to uncover issues in applying this technique to much larger scales than ever before. We intend to use modal decoupling methods to separate the entangled vibrations coming from the SLS and its support structure during the IMT. This new approach is still under development. The primary goal of my internship was to learn the basics of structural dynamics and physical vibrations. I was able to accomplish this by working on two experimental test set ups, the Simple Beam and TAURUS-T, and by doing some light analytical and post-processing work. Within the Simple Beam project, my role involves changing the data acquisition system, reconfiguration of the test set up, transducer calibration, data collection, data file recovery, and post-processing analysis. Within the TAURUS-T project, my duties included cataloging and removing the 30+ triaxial accelerometers, coordinating the removal of the structure from the current rolling cart to a sturdy billet for further testing, preparing the accelerometers for remounting, accurately calibrating, mounting, and mapping of all accelerometer channels, and some testing. Hammer and shaker tests will be performed to easily visualize mode shapes at low frequencies. Short analytical projects using MATLAB were also assigned to aid in research efforts. These included integration of acceleration data for comparison to measured displacement data. Laplace and Fourier transforms were also investigated to determine viability as a method of modal decoupling. In addition to these projects, I was also able contribute work that would benefit future interns and the division as a whole. I gave a short presentation and answered questions to aid in the recruitment of subsequent interns and co-ops for the division. I also assisted in revisions and additions to Intern/Co-Op Handbook to provide incoming employees with background information on the organization they are about to work for. I further developed tutorial on Pulse software, which was used for data acquisition for both experiments and will be helpful to interns and engineers that may be unfamiliar to the software. I gained a diverse range of experience throughout my internship. I was introduced to advanced dynamics and analytical techniques. This was through new experience with both hands on experimentation and analytical post processing methods. I was exposed to the benefits of interdepartmental collaboration and developed stronger skills in time management by coordinating two different tests at once. This internship provided an excellent opportunity to see how engineering theories applied to real life scenarios, and an introduction to how NASA/JSC solves technical problems.

Johnson, Katie↗
DOE OSTI2022

Dynamical electron correlation and the chemical bond. I. Covalent bonds in AH and AF (A = B–F)

Dynamical electron correlation has a major impact on the computed values of molecular properties and the energetics of molecular processes. This study focused on the effect of dynamical electron correlation on the spectroscopic constants ($R$ e , $ω$ e , $D$ e ), and potential energy curves, Δ$E$($R$), of the covalently bound AH and AF molecules, A = B–F. The changes in the spectroscopic constants (Δ$R$ e , Δ$ω$ e , Δ$D$ e ) caused by dynamical correlation are erratic and, at times, even surprising. These changes can be understood based on the dependence of the dynamical electron correlation energies of the AH and AF molecules as a function of the bond distance, i.e., Δ$E$ DEC ($R$). At large $R$, the magnitude of Δ$E$ DEC ($R$) increases nearly exponentially with decreasing $R$, but this increase slows as $R$ continues to decrease and, in many cases, even reverses at very short $R$. The changes in Δ$E$ DEC ($R$) in the region around $R$ e were as unexpected as they were surprising, e.g., distinct minima and maxima were found in the curves of Δ$E$ DEC ($R$) for the most polar molecules. The variations in Δ$E$ DEC ($R$) for $R$ ≲ $R$ e are directly correlated with major changes in the electronic structure of the molecules as revealed by a detailed analysis of the spin-coupled generalized valence bond wave function. In conclusion, the results reported here indicate that we have much to learn about the nature of dynamical electron correlation and its effect on chemical bonds and molecular properties and processes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Deep learning of parameterized equations with applications to uncertainty quantification

We propose a learning algorithm for discovering unknown parameterized dynamical systems by using observational data of the state variables. Our method is built upon and extends the recent work of discovering unknown dynamical systems, in particular those using deep neural network (DNN). We propose a DNN structure, largely based upon the residual network (ResNet), to not only learn the unknown form of the governing equation but also take into account the random effect embedded in the system, which is generated by the random parameters. Once the DNN model is successfully constructed, it is able to produce system prediction over longer term and for arbitrary parameter values. For uncertainty quantification, it allows us to conduct uncertainty analysis by evaluating solution statistics over the parameter space.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Continual Learning for Production-Level Machine Learning in Particle Accelerators

Particle accelerators operate in complex environments where data distribution can change dynamically, leading to data drifts that significantly challenge Machine Learning (ML) models. These non-stationary conditions often cause ML models to deteriorate in performance, making it difficult to maintain reliable predictions in operation. The primary sources of data drifts are changes in accelerator settings and changes in equipment performance which cannot be measured directly. To bridge this gap between ML development and long-term deployment in operational settings, we identify key areas within particle accelerators where continual learning can help mitigate drift-induced performance degradation. We will provide a practical guide on selecting the appropriate method given resource constraints and desired stability plasticity trade offs. As a concrete example, we will present a real-world use case for anomaly detection to predict errant beams at the Spallation Neutron Source accelerator, where continual learning has been employed to demonstrate stable performance on drifting data streams. We will present practical challenges, lessons learned, and the results from the deployed ML model.

Rajput, Kishansingh [Thomas Jefferson National Acc↗