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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

A Generation-Storage Coordination Dispatch Strategy for Power System Based on Causal Reinforcement Learning

In the backdrop of global energy transformation, power systems integrating high proportions of renewable energy sources are facing unprecedented challenges in operational stability and dispatch efficiency. To address these challenges, this study introduces a generation-storage coordination real-time dispatch strategy based on Causal Power System Dynamic Reinforcement Learning (CPSDRL). Diverging from traditional reinforcement learning approaches, CPSDRL innovatively incorporates causal inference within the state prediction model - the crux of model-based reinforcement learning - thereby establishing the Power Causal Dynamic Model (PCDM). Assisted by the prior knowledge of power systems, the model significantly enhances prediction accuracy and reliability through a two-stage training process. Utilizing PCDM, this study further applies a direct policy search algorithm to optimize the real-time dispatch strategy. Experimental results indicate that the proposed method improves the stability of generation-storage coordination real-time dispatch and exhibits competitive advantages in sample efficiency and computational speed, compared to traditional model-based and model-free reinforcement learning algorithms. This method is expected to enhance the practicality and adaptability of causal reinforcement learning techniques in power system scheduling and control.

causal reinforcement learning↗
DOE OSTI2023

Entropy-driven Optimal Sub-sampling of Fluid Dynamics for Developing Machine-learned Surrogates

Optimal sub-sampling of large datasets from fluid dynamics simulations is essential for training reduced-order machine learned models. A method using Shannon entropy was developed to weight flow features according to their level of information content, such that the most informative features can be extracted and used for training a surrogate model. The method is demonstrated in the canonical flow over a cylinder problem simulated with OpenFOAM. Both time-independent predictions and temporal forecasting were investigated as well as two types of prediction targets: local per-grid-point predictions and global per-time-step predictions. When tested on training a surrogate model, results indicate that our entropy-based sampling method typically outperforms random sampling and yields more reproducible results in less iterations. Finally, the method was used to train a surrogate model for modeling turbulence in magnetohydrodynamic flows, which revealed various challenges and opportunities for future research.

Brewer, Wes↗
NASA NTRS2005

Real-Time Principal-Component Analysis

A recently written computer program implements dominant-element-based gradient descent and dynamic initial learning rate (DOGEDYN), which was described in Method of Real-Time Principal-Component Analysis (NPO-40034) NASA Tech Briefs, Vol. 29, No. 1 (January 2005), page 59. To recapitulate: DOGEDYN is a method of sequential principal-component analysis (PCA) suitable for such applications as data compression and extraction of features from sets of data. In DOGEDYN, input data are represented as a sequence of vectors acquired at sampling times. The learning algorithm in DOGEDYN involves sequential extraction of principal vectors by means of a gradient descent in which only the dominant element is used at each iteration. Each iteration includes updating of elements of a weight matrix by amounts proportional to a dynamic initial learning rate chosen to increase the rate of convergence by compensating for the energy lost through the previous extraction of principal components. In comparison with a prior method of gradient-descent-based sequential PCA, DOGEDYN involves less computation and offers a greater rate of learning convergence. The sequential DOGEDYN computations require less memory than would parallel computations for the same purpose. The DOGEDYN software can be executed on a personal computer.

Duong, Vu↗
DOE OSTI2018

Data Driven Smart Proxy for CFD Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics, Part Three: Model Building at the Layer Level

To ensure the usefulness of simulation technologies in practice, their credibility needs to be established with Uncertainty Quantification (UQ) methods. In this project smart proxy is introduced to significantly reduce the computational cost of conducting large number of multiphase CFD simulations. Smart proxy for CFD models are developed using pattern recognition capabilities of Artificial Intelligence (AI), Machine Learning (LM) and Data Mining (DM) technologies. Several CFD simulation runs with different inlet air velocities for a rectangular fluidized bed are used to create a smart CFD proxy that is capable of replicating the CFD results for a wide variety of inlet velocities. The smart CFD proxy is validated with blind CFD runs (CFD runs that have not played any role during the development [training, calibration and validation] of the smart CFD proxy). In our earlier work, CFD data was used to train ANN at the cell level. That is an ANN was trained for each computational cell used in the CFD simulations. In the present work, the ANN is constructed and trained based on cross sectional area average of each variable, such as pressure, velocities and volume fraction (Layer Level). This leads to improvements in the training time at the expense of less spatial resolution. The resulting trained ANN provides spatially average value of parameters of interest, along the length of the fluidized bed. Upon completion of this project, UQ studies that rely on hundreds or thousands of smart CFD proxy runs can be accomplished in minutes. Following figure demonstrates a validation example (blind CFD run) showing the results from the MFiX and the smart CFD proxy for pressure drop across a fluidized bed at time-step of 1400 (the layer number corresponds to the vertical location in the bed).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Active Learning of Microgrid Frequency Dynamics Using Neural Ordinary Differential Equations

Accurate frequency modelling of inverter‐based resource (IBR)‐dominated power systems is crucial for ensuring stable, reliable and resilient operations, particularly given their inherent low‐inertia characteristics and fast dynamics that traditional swing equation‐based models inadequately capture. This paper explores neural ordinary differential equations (Neural ODEs) as a computationally efficient, data‐driven framework for modelling power system frequency dynamics, specifically within microgrids integrating high penetrations of distributed energy resources (DERs). The developed neural ODEs framework incorporates a neural network architecture designed to capture input dynamics. By actively perturbing the system with a known signal, the Python‐based neural ODEs framework was trained using measured system states and inputs, without the need for detailed system information. The framework, tested on a model of the Cordova, AK, microgrid, achieved a goodness of fit ranging from 60% to 99% across different state variables and maintained a mean square error in the 10 -6 p.u. range under square and step excitation signals. The proposed approach demonstrated robustness to measurement noise and initial condition variations while maintaining low computational complexity suitable for real‐time power system control applications. Furthermore, transfer learning enabled the neural ODEs model to adapt to the following changes in system topology or generator dispatch, highlighting its effectiveness for dynamic microgrids with frequently evolving configurations and diverse DERs.

Aryal, Tara [South Dakota State Univ., Brookings, ↗
NASA NTRS1992

A self-learning rule base for command following in dynamical systems

In this paper, a self-learning Rule Base for command following in dynamical systems is presented. The learning is accomplished though reinforcement learning using an associative memory called SAM. The main advantage of SAM is that it is a function approximator with explicit storage of training samples. A learning algorithm patterned after the dynamic programming is proposed. Two artificially created, unstable dynamical systems are used for testing, and the Rule Base was used to generate a feedback control to improve the command following ability of the otherwise uncontrolled systems. The numerical results are very encouraging. The controlled systems exhibit a more stable behavior and a better capability to follow reference commands. The rules resulting from the reinforcement learning are explicitly stored and they can be modified or augmented by human experts. Due to overlapping storage scheme of SAM, the stored rules are similar to fuzzy rules.

Tsai, Wei K.↗
DOE OSTI2024

Uncovering obscured phonon dynamics from powder inelastic neutron scattering using machine learning

The study of phonon dynamics is pivotal for understanding material properties, yet it faces challenges due to the irreversible information loss inherent in powder inelastic neutron scattering spectra and the limitations of traditional analysis methods. In this study, we present a machine learning framework designed to reveal obscured phonon dynamics from powder spectra. Using a variational autoencoder, we obtain a disentangled latent representation of spectra and successfully extract force constants for reconstructing phonon dispersions. Notably, our model demonstrates effective applicability to experimental data even when trained exclusively on physics-based simulations. The fine-tuning with experimental spectra further mitigates issues arising from domain shift. Analysis of latent space underscores the model’s versatility and generalizability, affirming its suitability for complex system applications. Furthermore, our framework’s two-stage design is promising for developing a universal pre-trained feature extractor. This approach has the potential to revolutionize neutron measurements of phonon dynamics, offering researchers a potent tool to decipher intricate spectra and gain valuable insights into the intrinsic physics of materials.

domain adaptation↗
DOE OSTI2025

Nuclear quantum effects of metal surface-mediated C–H activation

The nuclear quantum effects of surface-mediated C–H activation of surface CH 3 are considered for the pristine Pt(111) and Au(111) surfaces at 300 K. The kinetic barriers without nuclear quantum effects are calculated using both static density functional theory calculations and ab initio molecular dynamics. Static calculations are performed using the harmonic approximation while the free energy pathway is calculated using enhanced sampling molecular dynamics. Machine learning potentials are trained using generated datasets and validated against the ab initio molecular dynamics generated free energy pathways. The machine learning potentials are used to perform centroid molecular dynamics to consider the nuclear quantum effects of C–H activation. Nuclear quantum effects are found to have a very significant effect on the free energy pathway, with reduced importance at higher temperatures and in the CD 3 case.

Bunting, Rhys J. [Lawrence Livermore National Labo↗
DOE OSTI2020

SympNets: Intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems

Here, we propose new symplectic networks (SympNets) for identifying Hamiltonian systems from data based on a composition of linear, activation and gradient modules. In particular, we define two classes of SympNets: the LA-SympNets composed of linear and activation modules, and the G-SympNets composed of gradient modules. Correspondingly, we prove two new universal approximation theorems that demonstrate that SympNets can approximate arbitrary symplectic maps based on appropriate activation functions. We then perform several experiments including the pendulum, double pendulum and three-body problems to investigate the expressivity and the generalization ability of SympNets. The simulation results show that even very small size SympNets can generalize well, and are able to handle both separable and non-separable Hamiltonian systems with data points resulting from short or long time steps. In all the test cases, SympNets outperform the baseline models, and are much faster in training and prediction. We also develop an extended version of SympNets to learn the dynamics from irregularly sampled data. This extended version of SympNets can be thought of as a universal model representing the solution to an arbitrary Hamiltonian system.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Material Model Parameters Optimization in Liquid Mercury Target Dynamics Simulation With Machine Learning Surrogates

A pulsed spallation target is subjected to very short (∼0.7μs) but intense loads (23.3 kJ) from repeated proton pulses, which knock away neutrons from the mercury atoms’ nuclei for a wide range application in physics, engineering, medicine, petroleum exploration, biology, chemistry, etc. The effect of this pulsed loading on the stainless-steel target module which contains the flowing mercury target material is difficult to predict not only due to its short but intense explosive-like physical reaction, but also the nonlinear material behavior of the liquid mercury in the structure. Injecting small helium bubbles in the mercury has been an efficient method of mitigating the pressure wave at high power level stage. However, prediction of the resultant loading on the target is more difficult when helium gas is intentionally injected into the mercury. A 2-phase material model that incorporates the Rayleigh-Plesset (R-P) model is expected to address this complex multi-physics dynamics problem by including the bubble dynamics in the liquid mercury. A parameter sensitivity study was firstly employed to understand their impact on the simulation strains. The investigated parameters included E, μ, γ, σ, n, VFgas, and gas cumulative volume curve control parameters a and b. Verification and validation results from sparse polynomial expansions (SPE) method and directional Gaussian smoothing (DGS) optimization show that the surrogate model had training error of ∼7% and validation error of ∼15%, indicating that machine learning methods and surrogate models can help optimize the uncertain parameters in the complex 2-phase material model. This approach is expected to fill the knowledge gap between unknown liquid-gas mixture material model and measured vessel strain responses.

Lin, Lianshan↗
DOE OSTI2026

Surrogate model for third-integer resonance extraction at the Fermilab Delivery Ring

We present an ongoing work in which a surrogate model is being developed to reproduce the response dynamics of the third-integer resonant extraction process in the Delivery Ring (DR) at Fermilab. This is in pursuit of smoothly extracting circulating beam to the Mu2e Experiment’s production target, whereby the goal is to extract a uniform slice of the circulating 1e12 protons in the DR over 25,000 turns (43 ms). The DR contains 3 harmonic sextupoles that excite a third-integer resonance and three fast, tune-ramping quadrupole magnets that drive the horizontal tune towards the 29/3 resonance. In our initial work, the surrogate model trains on a semi-analytical simulation provided in the same format as live data. Using Reinforcement Learning (and other potential ML methods), the trained surrogate acts as the “environment” in which a simple ML control agent could learn to dynamically adjust the quadrupole ramp at 430 break points within the 43 microsecond spill window. The controller will be hosted on a dedicated Arria 10 FPGA. In this work, we report the accuracy and fidelity of the surrogate model in comparison to the response dynamics of the physics simulator.

Narayanan, Aakaash [Fermilab]↗
DOE OSTI2020

Machine Learning Analysis of Direct Dynamics Trajectory Outcomes for Thermal Deazetization of 2,3-Diazabicyclo[2.2.1]hept-2-ene

Experimentally, the thermal gas-phase deazetization of 2,3-diazabicyclo[2.2.1]hept-2-ene (1) results in the loss of N2 and the formation of bicyclo products 3 (exo) and 4 (endo) in a nonstatistical ratio, with preference for the exo product. Here, we report unrestricted M06-2X quasiclassical trajectories initialized from the concerted N2 ejection transition state that were able to replicate the experimental preference to form 3. We found that the 3:4 ratio results from the relative amounts of very fast (ballistic) exotype trajectories versus trajectories that lead to the 1,3-diradical intermediate 2. These quasiclassical trajectories provided a set of transition-state vibrational, velocity, momenta, and geometric features for the machine learning analysis. Additionally, a selection of popular supervised classification algorithms (e.g., random forest) provided poor prediction of trajectory outcomes based on only transition-state vibrational quanta and energy features. However, these machine learning models provided more accurate predictions using atomic velocities and atomic positions, attaining ~70% accuracy using initial conditions and between 85 and 95% accuracy at later reaction time steps. This increased accuracy allowed the feature importance analysis to reveal that, at the later-time analysis, the methylene bridge out-of-plane bending is correlated with trajectory outcomes for the formation of either the exo product or toward the diradical intermediate. Possible reasons for the struggle of machine learning algorithms to classify trajectories based on transition-state features is the heavily overlapping feature values, the finite but very large possible vibrational mode combinations, and the possibility of chaos as trajectories propagate. We examined this chaos by comparing a set of nearly identical trajectories that differed by only a very small scaling of the kinetic energies resulting from the transition-state reaction coordinate.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems

In this work, we present Lift & Learn, a physics-informed method for learning low-dimensional models for large-scale dynamical systems. The method exploits knowledge of a system’s governing equations to identify a coordinate transformation in which the system dynamics have quadratic structure. This transformation is called a lifting map because it often adds auxiliary variables to the system state. The lifting map is applied to data obtained by evaluating a model for the original nonlinear system. This lifted data is projected onto its leading principal components, and low-dimensional linear and quadratic matrix operators are fit to the lifted reduced data using a least-squares operator inference procedure. Analysis of our method shows that the Lift & Learn models are able to capture the system physics in the lifted coordinates at least as accurately as traditional intrusive model reduction approaches. This preservation of system physics makes the Lift & Learn models robust to changes in inputs. Numerical experiments on the FitzHugh–Nagumo neuron activation model and the compressible Euler equations demonstrate the generalizability of our model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Implementation and (Inverse Modified) Error Analysis for Implicitly Templated ODE-Nets

We focus on learning unknown dynamics from data using ODE-nets templated on implicit numerical initial value problem solvers. First, we perform inverse modified error analysis of the ODE-nets using unrolled implicit schemes for ease of interpretation. It is shown that training an ODE-net using an unrolled implicit scheme returns a close approximation of an inverse modified differential equation (IMDE). In addition, we establish a theoretical basis for hyperparameter selection when training such ODE-nets, whereas current strategies usually treat numerical integration of ODE-nets as a black box. We thus formulate an adaptive algorithm which monitors the level of error and adapts the number of (unrolled) implicit solution iterations during the training process, so that the error of the unrolled approximation is less than the current learning loss. This helps accelerate training while maintaining accuracy. Several numerical experiments are performed to demonstrate the advantages of the proposed algorithm compared to nonadaptive unrollings and validate the theoretical analysis. Here, we also note that this approach naturally allows for incorporating partially known physical terms in the equations, giving rise to what is termed “gray box” identification.

ODE-nets↗
DOE OSTI2017

Data Driven Smart Proxy for CFD: Application of Big Data Analytics & Machine Learning in Computational Fluid Dynamics (Part 1)

Simulation technologies can reduce the time and cost of the development and deployment of advanced technologies and allow rapid scale-up of these technologies for fossil fuel based energy systems. However, to ensure their usefulness in practice, the credibility of the simulations needs to be established with Uncertainty Quantification (UQ) methods. National Energy Technology Laboratory (NETL) has been applying non-intrusive UQ methodologies to categorize and quantify uncertainties in CFD simulations of gas-solid multiphase flows. To reduce the computational cost associated with gas-solid flow simulations required for UQ analysis, techniques commonly used in the area of Artificial Intelligence (AI) and Data Mining (DM) are used to construct smart proxy models, which can reduce the computational cost of conducting large number of multiphase CFD simulations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Generative AI models for learning flow maps of stochastic dynamical systems in bounded domains

Simulating stochastic differential equations (SDEs) in bounded domains, presents significant computational challenges due to particle exit phenomena, which requires accurate modeling of interior stochastic dynamics and boundary interactions. Despite the success of machine learning-based methods in learning SDEs, existing learning methods are not applicable to SDEs in bounded domains because they cannot accurately capture the particle exit dynamics. We present a unified hybrid data-driven approach that combines a conditional diffusion model with an exit prediction neural network to capture both interior stochastic dynamics and boundary exit phenomena. Our ML model consists of two major components: a neural network that learns exit probabilities using binary cross-entropy loss with rigorous convergence guarantees, and a training-free diffusion model that generates state transitions for non-exiting particles using closed-form score functions. The two components are integrated through a probabilistic sampling algorithm that determines particle exit at each time step and generates appropriate state transitions. Here, the performance of the proposed approach is demonstrated via three test cases: a one-dimensional simplified problem for theoretical verification, a two-dimensional advection-diffusion problem in a bounded domain, and a three-dimensional problem of interest to magnetically confined fusion plasmas.

Bounded domains↗
DOE OSTI2026

Origin of Metal-Insulator Transition in Rare-Earth Nickelates

Rare-earth nickelates RNiO3 (R=rare-earth element) undergo coupled structural, metal-insulator, and magnetic changes as temperature is lowered. Because the metal-insulator transition often occurs together with a symmetry-lowering distortion, it is commonly viewed as lattice driven. Here we use QSGW calculations to separate the roles of spin and structure. In the high-symmetry Pbnm phase, imposing spin disproportionation already starts to open an electronic gap, although the undistorted lattice cannot stabilize a full insulating state in both spin channels. In the low-symmetry P21/n phase, removing the spin disproportionation destroys the insulating solution even though the bond disproportionation remains. These tests show that spin disproportionation is the primary electronic driver of gap formation, while structural disproportionation acts as the enabler that allows the inequivalent Ni states to become spatially separated and fully insulating. As an explicit finite-temperature example, machine-learned molecular dynamics for NdNiO3 at 220 K shows that a nominally high-symmetry Pbnm structure dynamically samples local Ni-O bond disproportionation, while retaining Pbnm symmetry on average. This illustrates a general structural channel by which thermal fluctuations in the high-symmetry phase can help stabilize locally spin-disproportionated states.

36 MATERIALS SCIENCE↗