Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “NEURAL NETWORKS”

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 703 records · Page 39
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

User Manual - HydraGNN v5.0: Distributed Implementation of Multi-Tasking Graph Neural Networks

This document serves as the user manual for HydraGNN v5.0, a scalable graph neural network (GNN) architecture for simultaneous prediction of multiple target properties using multi-task learning (MTL). This version of HydraGNN has been developed primarily to support the development, training, and deployment of predictive graph-based deep learning (DL) models for atomistic materials modeling. HydraGNN is templated over 13 message-passing policies, including invariant models (GIN, PNA, PNAPlus, GAT, MFC, CGCNN, SAGE, SchNet, DimeNet) and equivariant models (EGNN, PNAEq, PAINN, MACE), and supports distributed training via distributed data parallelism (DDP), DeepSpeed, and Fully Sharded Data Parallelism (FSDP) on leadership-class supercomputers. Although HydraGNN can be applied to problems beyond atomistic materials modeling, its current use is confined to homogeneous graphs. Additional capabilities include machine-learned interatomic potentials with energy-conserving forces, General, Powerful, and Scalable Graph Transformer (GraphGPS) global attention, periodic boundary conditions, hyperparameter optimization, mixed-precision training, and uncertainty quantification.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

A Convolution Neural Network for Voltage Event Classification at a Photovoltaic Inverter

This paper presents a convolutional neural network (CNN) developed to identify voltage events in photovoltaic (PV) inverters. The CNN is trained on synthetic data generated using the IEEE 13-bus distribution feeder model and evaluated on field measured data collected from Energy Northwest’s Horn Rapids Solar, Storage, and Training (HRSST) facility. The study focuses on two common voltage events: faults and voltage sags. The CNN is configured to analyze voltage and current waveforms from three-phase PV systems, demonstrating excellent accuracy during training. Field data from the HRSST facility is employed to assess its real-world performance, where the CNN achieves perfect identification of faults and voltage sags in a sample of nine events. This work highlights the potential of the proposed method to enhance PV protection schemes, providing a robust foundation for improved voltage event detection and grid reliability.

Cornachione, Matthew A.↗
DOE OSTI2020

Locally adaptive activation functions with slope recovery for deep and physics-informed neural networks

Here we propose two approaches of locally adaptive activation functions namely, layer-wise and neuron-wise locally adaptive activation functions, which improve the performance of deep and physics-informed neural networks. The local adaptation of activation function is achieved by introducing a scalable parameter in each layer (layer-wise) and for every neuron (neuron-wise) separately, and then optimizing it using a variant of stochastic gradient descent algorithm. In order to further increase the training speed, an activation slope-based slope recovery term is added in the loss function, which further accelerates convergence, thereby reducing the training cost. On the theoretical side, we prove that in the proposed method, the gradient descent algorithms are not attracted to sub-optimal critical points or local minima under practical conditions on the initialization and learning rate, and that the gradient dynamics of the proposed method is not achievable by base methods with any (adaptive) learning rates. We further show that the adaptive activation methods accelerate the convergence by implicitly multiplying conditioning matrices to the gradient of the base method without any explicit computation of the conditioning matrix and the matrix–vector product. The different adaptive activation functions are shown to induce different implicit conditioning matrices. Furthermore, the proposed methods with the slope recovery are shown to accelerate the training process.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Physics-informed graph neural networks for predicting cetane number with systematic data quality analysis

Designing alternative fuels for advanced compression ignition engines necessitates a predictive model for cetane number (CN). In this study, the physics-informed graph neural networks are introduced for a reliable CN prediction by considering molecular features pertinent to the physical properties of molecules that affect CN. The reliability of measured data is another key factor to consider for improving the predictive model. Various experimental instruments for measuring CN exist, including standard and non-standard methods. In this regard, a systematic data quality analysis was carried out for the total 630 CNs collected from literature and new measurements in this study using Advanced Fuel Ignition Delay Analyzer (AFIDA). The results from this data curation process were reflected in the model by imposing lower sample weights on the data coming from less reliable measurement techniques. This approach effectively maximized the prediction accuracy while incorporating data from all available sources. Using the sample weights decreased the mean absolute error (MAE) up to 0.8 CN units. The accuracy was also improved by introducing the CN-related physical properties (the number of hydrogen bond donors and acceptors); the test set MAE is 5.74 and 7.01 for the model with and without such properties, respectively. Investigating molecular structural effects on CN was also carried out to gain chemical insights into factors used to design new fuel candidates. The dimensionality reduction analysis of feature vectors showed a clear clustering in terms of functional groups and CN and the structural effect derived from the model was consistent with the physicochemical insights. Finally, this physics-informed model and data curation would be helpful for accurate CN prediction and inform rational fuel design.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Identifying Transient Candidates in the Dark Energy Survey Using Convolutional Neural Networks

The ability to discover new transient candidates via image differencing without direct human intervention is an important task in observational astronomy. For these kind of image classification problems, machine learning techniques such as Convolutional Neural Networks (CNNs) have shown remarkable success. In this work, we present the results of an automated transient candidate identification on images with CNNs for an extant data set from the Dark Energy Survey Supernova program, whose main focus was on using Type Ia supernovae for cosmology. By performing an architecture search of CNNs, we identify networks that efficiently select non-artifacts (e.g., supernovae, variable stars, AGN, etc.) from artifacts (image defects, mis-subtractions, etc.), achieving the efficiency of previous work performed with random Forests, without the need to expend any effort in feature identification. The CNNs also help us identify a subset of mislabeled images. Performing a relabeling of the images in this subset, the resulting classification with CNNs is significantly better than previous results, lowering the false positive rate by 27% at a fixed missed detection rate of 0.05.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Traffic Signal Control With Adaptive Online-Learning Scheme Using Multiple-Model Neural Networks

This article proposes a new traffic signal control algorithm to deal with unknown-traffic-system uncertainties and reduce delays in vehicle travel time. Unknown-traffic-system dynamics are approximated using a recurrent neural network (NN). To accurately identify the traffic system model, an online-learning scheme is developed to switch among a set of candidate NNs (i.e., multiple-model NNs) based on their estimation errors. Then, a bank of optimal signal-timing controllers is designed based on the online identification of the traffic system. Simulation studies have been carried out for the obtained control strategies using multiple-model NNs, and the desired results have been obtained. Moreover, compared with the widely used actuated traffic signal control schemes, it is shown that the proposed method can reduce vehicle travel delays and improve traffic system robustness.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

DSP Implementation of a Novel Recurrent Neural Network Controller into a TI Solar Microinverter

Single-phase grid-tied inverters are widely used to integrate small-scale renewable energy sources and distributed generations to the utility grid. A novel Recurrent Neural Network (RNN) current controller is introduced to solve the resonant problem associated with LCL based inverters. The well-trained RNN controller was validated through a Texas Instruments (TI) LCL filter based solar microinverter kit that contains a C2000 TI microcontroller. The inverter closed current loop test without the grid connection was conducted in a laboratory setup to verify the RNN contoller functionality. The laboratory waveform results verified that the RNN current controller produced the strong tracking of the measured inverter AC current to its reference value even at a low sampling frequency of 5KHz. The proposed RNN current controller also proved to perform better than the built-in three-pole-three-zero (3P3Z) current controller provided by TI and produce lower values of Total Harmonic Distortion (THD).

digital signal processor↗
DOE OSTI2020

Application of First-Principles-Based Artificial Neural Network Potentials to Multiscale-Shock Dynamics Simulations on Solid Materials

The use of artificial neural network (ANN) potentials trained with first-principles calculations has emerged as a promising approach for molecular dynamics (MD) simulations encompassing large space and time scales while retaining first-principles accuracy. To date, however, the application of ANN-MD has been limited to near-equilibrium processes. Here we combine first-principles-trained ANN-MD with multiscale shock theory (MSST) to successfully describe far-from-equilibrium shock phenomena. Overall, our ANN-MSST-MD approach describes shock-wave propagation in solids with first-principles accuracy but a 5000 times shorter computing time. Accordingly, ANN-MD-MSST was able to resolve fine, long-time elastic deformation at low shock speed, which was impossible with first-principles MD because of the high computational cost. This work thus lays a foundation of ANN-MD simulation to study a wide range of far-from-equilibrium processes.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Artificial Neural Networks as Mappings between Proton Potentials, Wave Functions, Densities, and Energy Levels

We report artificial neural networks (ANNs) have become important in quantum chemistry. Herein, applications to nuclear quantum effects, such as zero-point energy, vibrationally excited states, and hydrogen tunneling, are explored. ANNs are used to solve the time-independent Schrödinger equation for single- and double-well potentials representing hydrogen-bonded molecular systems capable of proton transfer. ANN mappings are trained to predict the lowest five proton vibrational energies, wave functions, and densities from the proton potentials and to predict the excited state proton vibrational energies and densities from the proton ground state density. For the inverse problem, ANN mappings are trained to predict the proton potential from the proton vibrational energy levels or the proton ground state density. This latter mapping is theoretically justified by the first Hohenberg-Kohn theorem establishing a one-to-one correspondence between the external potential and the ground state density. ANNs for two- and three-dimensional systems are also presented to illustrate the straightforward extension to higher dimensions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Global Nuclear Explosion Discrimination Using a Convolutional Neural Network

Using P-wave seismograms, we trained a seismic source classifier using a Convolutional Neural Network. We trained for three classes: earthquake P-wave, underground nuclear explosion (UNE) P-wave, and noise. With the current absence of nuclear testing by countries that have signed the Comprehensive Test Ban Treaty, high quality seismic data from UNEs is limited. Even with limited training data, our model can accurately characterize most events recorded at regional and teleseismic distances, finding over 95% signals in the validation set. We applied the model on holdout datasets of the North Korean test explosions to evaluate the performance on unique region and station-source pairs, with promising results. Additionally, we tested on the Source Physics Experiment events to investigate the potential for chemical explosions to act as a surrogate for nuclear explosions. We anticipate that machine-learning models like our classifier system can have broad application for other seismic signals including volcanic and non-volcanic tremor, anomalous earthquakes, ice-quakes or landslide-quakes.

58 GEOSCIENCES↗
DOE OSTI2024

AGS-GNN: Attribute-guided Sampling for Graph Neural Networks

We propose AGS-GNN, a novel attribute-guided sampling algorithm for Graph Neural Networks (GNNs) that exploits node features and connectivity structure of a graph while simultaneously adapting for both homophily and heterophily in graphs. (In homophilic graphs vertices of the same class are more likely to be connected, and vertices of different classes tend to be linked in heterophilic graphs.) While GNNs have been successfully applied to homophilic graphs, their application to heterophilic graphs remains challenging. The best-performing GNNs for heterophilic graphs do not fit the sampling paradigm, suffer high computational costs, and are not inductive. We employ samplers based on feature-similarity and feature-diversity to select subsets of neighbors for a node, and adaptively capture information from homophilic and heterophilic neighborhoods using dual channels. Currently, AGS-GNN is the only algorithm that we know of that explicitly controls homophily in the sampled subgraph through similar and diverse neighborhood samples. For diverse neighborhood sampling, we employ submodularity, which was not used in this context prior to our work. The sampling distribution is pre-computed and highly parallel, achieving the desired scalability. Using an extensive dataset consisting of 35 small (<=100K nodes) and large (>100K nodes) homophilic and heterophilic graphs, we demonstrate the superiority of AGS-GNN compare to the current approaches in the literature. AGS-GNN achieves comparable test accuracy to the best-performing heterophilic GNNs, even outperforming methods using the entire graph for node classification. AGS-GNN also converges faster compared to methods that sample neighborhoods randomly, and can be incorporated into existing GNN models that employ node or graph sampling.

artificial intelligence↗
DOE OSTI2024

Efficient training of physics-informed neural networks

Open-source software package designed for the efficient training of Physics-Informed Neural Networks (PINNs) and their variants, integrating advanced methodologies such as adaptive weighting and adaptive sampling

Chen, Wenqian [Pacific Northwest National Laborato↗
DOE OSTI2025

Predicting the von Neumann entanglement entropy using a graph neural network

Calculating the von Neumann entanglement entropy from experimental data is challenging due to its dependence on the complete wavefunction, forcing reliance on approximations such as classical mutual information (MI). We propose a machine learning approach using a graph neural network to predict the von Neumann entropy directly from experimentally accessible bitstrings. We test this approach on a Rydberg ladder system and achieve a mean absolute error of $3.6\,\times 10^{-3}$ when evaluating within the training range on a dataset with entropy values ranging from 0 to 1.9. The model achieves a mean absolute percentage error of 1.44% and outperforms MI-based bounds. When tested beyond the training range, the model maintains reasonable accuracy. Furthermore, we demonstrate that fine-tuning the model with small datasets significantly improves performance on data outside the original training range.

graph neural networks↗
DOE OSTI2022

Solving Newton’s equations of motion with large timesteps using recurrent neural networks based operators

Classical molecular dynamics simulations are based on solving Newton’s equations of motion. Using a small timestep, numerical integrators such as Verlet generate trajectories of particles as solutions to Newton’s equations. We introduce operators derived using recurrent neural networks that accurately solve Newton’s equations utilizing sequences of past trajectory data, and produce energy-conserving dynamics of particles using timesteps up to 4000 times larger compared to the Verlet timestep. We demonstrate significant speedup in many example problems including 3D systems of up to 16 particles.

Newton’s equations↗
DOE OSTI2020

Smart-PGSim: Using Neural Network to Accelerate AC-OPF Power Grid Simulation

In this work we address the problem of accelerating complex power-grid simulation through machine learning ( ML). Specifically, we develop a framework, Smart-PGSim,which generates multitask-learning (MTL) neural network (NN)models to predict the initial values of variables critical to the problem convergence. MTL models allow information sharing when predicting multiple dependent variables while including customized layers to predict individual variables. We show that,to achieve the required accuracy, it is paramount to embed domain-specific constraints derived from the specific power-grid components in the MTL model. Smart-PGSim then employs the predicted initial values as a high-quality initial condition for the power-grid numerical solver (warm start), resulting in both higher performance compared to state-of-the-art solutions while maintaining the required accuracy. Smart-PGSim brings 2.60×speedup on average (up to 3.28×) computed over 10,000 problems, without losing solution optimality.

machine learning, neural networks↗
DOE OSTI2021

Rotational and reflectional equivariant convolutional neural network for data-limited applications: Multiphase flow demonstration

This article deals with approximating steady-state particle-resolved fluid flow around a fixed particle of interest under the influence of randomly distributed stationary particles in a dispersed multiphase setup using convolutional neural network (CNN). The considered problem involves rotational symmetry about the mean velocity (streamwise) direction. Thus, this work enforces this symmetry using SE(3)-equivariant, special Euclidean group of dimension 3, CNN architecture, which is translation and three-dimensional rotation equivariant. This study mainly explores the generalization capabilities and benefits of a SE(3)-equivariant network. Accurate synthetic flow fields for Reynolds number and particle volume fraction combinations spanning over a range of [86.22, 172.96] and [0.11, 0.45], respectively, are produced with careful application of symmetry-aware data-driven approach.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗