Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Neural Network”

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 1,423 records · Page 79

Incomplete fuzzy data processing systems using artificial neural network

In this paper, the implementation of a fuzzy data processing system using an artificial neural network (ANN) is discussed. The binary representation of fuzzy data is assumed, where the universe of discourse is decartelized into n equal intervals. The value of a membership function is represented by a binary number. It is proposed that incomplete fuzzy data processing be performed in two stages. The first stage performs the 'retrieval' of incomplete fuzzy data, and the second stage performs the desired operation on the retrieval data. The method of incomplete fuzzy data retrieval is proposed based on the linear approximation of missing values of the membership function. The ANN implementation of the proposed system is presented. The system was computationally verified and showed a relatively small total error.

Patyra, Marek J.↗

Artificial neural network for the determination of Hubble Space Telescope aberration from stellar images

An artificial-neural-network method, first developed for the measurement and control of atmospheric phase distortion, using stellar images, was used to estimate the optical aberration of the Hubble Space Telescope. A total of 26 estimates of distortion was obtained from 23 stellar images acquired at several secondary-mirror axial positions. The results were expressed as coefficients of eight orthogonal Zernike polynomials: focus through third-order spherical. For all modes other than spherical the measured aberration was small. The average spherical aberration of the estimates was -0.299 micron rms, which is in good agreement with predictions obtained when iterative phase-retrieval algorithms were used.

Barrett, Todd K.↗

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↗

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↗

Neural network technologies

A whole new arena of computer technologies is now beginning to form. Still in its infancy, neural network technology is a biologically inspired methodology which draws on nature's own cognitive processes. The Software Technology Branch has provided a software tool, Neural Execution and Training System (NETS), to industry, government, and academia to facilitate and expedite the use of this technology. NETS is written in the C programming language and can be executed on a variety of machines. Once a network has been debugged, NETS can produce a C source code which implements the network. This code can then be incorporated into other software systems. Described here are various software projects currently under development with NETS and the anticipated future enhancements to NETS and the technology.

Villarreal, James A.↗

Stimulus Sensitivity of a Spiking Neural Network Model

Some recent papers relate the criticality of complex systems to their maximal capacity of information processing. In the present paper, we consider high dimensional point processes, known as age-dependent Hawkes processes, which have been used to model spiking neural networks. Using mean-field approximation, the response of the network to a stimulus is computed and we provide a notion of stimulus sensitivity. It appears that the maximal sensitivity is achieved in the sub-critical regime, yet almost critical for a range of biologically relevant parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events, and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system. The artificial intelligence approach is useful because it provides (1) the use of human experts' knowledge of sensor behavior and faulty engine conditions in interpreting data; (2) the use of engine design knowledge and physical sensor locations in establishing relationships among the events of multiple sensors; (3) the use of stored analysis of past data of faulty engine conditions; and (4) the use of knowledge-based reasoning in distinguishing sensor failure from actual faults. The neural network approach appears promising because neural nets (1) can be trained on extremely noisy data and produce classifications which are more robust under noisy conditions than other classification techniques; (2) avoid the necessity of noise removal by digital filtering and therefore avoid the need to make assumptions about frequency bands or other signal characteristics of anomalous behavior; (3) can, in effect, generate their own feature detectors based on the characteristics of the sensor data used in training; and (4) are inherently parallel and therefore are potentially implementable in special-purpose parallel hardware.

Ali, Moonis↗

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↗

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↗

Neural network representation of electronic structure from ab initio molecular dynamics

Despite their rich information content, electronic structure data amassed at high volumes in ab initio molecular dynamics simulations are generally under-utilized. Here we introduce a transferable high-fidelity neural network representation of such data in the form of tight-binding Hamiltonians for crystalline materials. This predictive representation of ab initio electronic structure, combined with machine-learning boosted molecular dynamics, enables efficient and accurate electronic evolution and sampling. When it is applied to a one-dimension charge-density wave material, carbyne, we are able to compute the spectral function and optical conductivity in the canonical ensemble. The spectral functions evaluated during soliton-antisoliton pair annihilation process reveal significant renormalization of low-energy edge modes due to retarded electron-lattice coupling beyond the Born–Oppenheimer limit. The availability of an efficient and reusable surrogate model for the electronic structure dynamical system will enable calculating many interesting physical properties, paving the way to previously inaccessible or challenging avenues in materials modeling.

74 ATOMIC AND MOLECULAR PHYSICS↗

Multiscale graph neural network autoencoders for interpretable scientific machine learning

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN) autoencoding architecture with demonstrations on complex fluid flow applications. To address the first goal of interpretability, the GNN autoencoder achieves reduction in the number nodes in the encoding stage through an adaptive graph reduction procedure. Further, this reduction procedure essentially amounts to flowfieldconditioned node sampling and sensor identification, and produces interpretable latent graph representations tailored to the flowfield reconstruction task in the form of so-called masked fields. These masked fields allow the user to (a) visualize where in physical space a given latent graph is active, and (b) interpret the time-evolution of the latent graph connectivity in accordance with the time-evolution of unsteady flow features (e.g. recirculation zones, shear layers) in the domain. To address the goal of unstructured mesh compatibility, the autoencoding architecture utilizes a series of multi-scale message passing (MMP) layers, each of which models information exchange among node neighborhoods at various lengthscales. The MMP layer, which augments standard single-scale message passing with learnable coarsening operations, allows the decoder to more efficiently reconstruct the flowfield from the identified regions in the masked fields. Analysis of latent graphs produced by the autoencoder for various model settings are conducted using unstructured snapshot data sourced from large-eddy simulations in a backward-facing step (BFS) flow configuration with an OpenFOAM-based flow solver at high Reynolds numbers.

97 MATHEMATICS AND COMPUTING↗

Review of internal cyber attacks in nuclear facilities and an artificial neural network model for implementing internal cyberforensics

Deployment of digital technologies within a modern shift in cyber defense systems is essential for protecting the energy production units. One of the important components of defense is cyberforensics: once an attack has been detected to locate its origin. In this paper, a review of well-known cyberattacks in nuclear facilities is provided, with the lessons learned leading to the development of a machine learning approach implementing identification of internal at- tacks in the facility's data networks. Our approach may be seen as one of the layers in a defense-in-depth strategy that identifies if the attack comes from inside, which may result in identifying faster the attacker's origin. The presented model exploits network packet examination to cast accurate predictions on detailing the origin of malicious network connections. The approach fuses multiple mathematical functions within an artificial neural network to provide a response in the form of 0/1, i. e., whether the attack is identified as internal or not. The utilization of a variety of test cases is developed to explore the relevance and validity of the predictive approach. The proposed implementation is examined with network data packet variance, and the results obtained exhibit a highly accurate detection rate.

Nuclear Science & Technology↗

A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data Using Unstructured Spatial Discretizations

In this work, we propose a nonlinear manifold learning technique based on deep convolutional autoencoders that is appropriate for model order reduction of physical systems in complex geometries. Convolutional neural networks have proven to be highly advantageous for compressing data arising from systems demonstrating a slow-decaying Kolmogorov n-width. However, these networks are restricted to data on structured meshes. Unstructured meshes are often required for performing analyses of real systems with complex geometry. Our custom graph convolution operators based on the available differential operators for a given spatial discretization effectively extend the application space of deep convolutional autoencoders to systems with arbitrarily complex geometry that are typically discretized using unstructured meshes. We propose sets of convolution operators based on the spatial derivative operators for the underlying spatial discretization, making the method particularly well suited to data arising from the solution of partial differential equations. We demonstrate the method using examples from heat transfer and fluid mechanics and show better than an order of magnitude improvement in accuracy over linear methods.

97 MATHEMATICS AND COMPUTING↗

Volumetric Segmentation via Neural Networks Improves Neutron Crystallography Data Analysis

Crystallography is the powerhouse technique for molecular structure determination, with applications in fields ranging from energy storage to drug design. Accurate structure determination, however, relies partly on determining the precise locations and integrated intensities of Bragg peaks in the resulting data. Here, we describe a method for Bragg peak integration that is accomplished using neural networks. The network is based on a U-Net and identifies peaks in three-dimensional reciprocal space through segmentation, allowing prediction of the full 3D peak shape from noisy data that is commonly difficult to process. The procedure for generating appropriate training sets is detailed. Trained networks achieve Dice coefficients of 0.82 and mean IoUs of 0.69. Carrying out integration over entire datasets, it is demonstrated that integrating neural network-predicted peaks results in improved intensity statistics. Furthermore, using a second dataset, the possibility of transfer learning between datasets is shown. Given the ubiquity and growing complexity of crystallography, we anticipate integration by machine learning to play an increasingly important role across the physical sciences. These early results demonstrate the applicability of deep learning techniques for integrating crystallography data and suggest a possible role in the next generation of crystallography experiments.

Sullivan, Brendan T.↗

Optimizing High-Throughput Inference on Graph Neural Networks at Shared Computing Facilities with the NVIDIA Triton Inference Server

Abstract With machine learning applications now spanning a variety of computational tasks, multi-user shared computing facilities are devoting a rapidly increasing proportion of their resources to such algorithms. Graph neural networks (GNNs), for example, have provided astounding improvements in extracting complex signatures from data and are now widely used in a variety of applications, such as particle jet classification in high energy physics (HEP). However, GNNs also come with an enormous computational penalty that requires the use of GPUs to maintain reasonable throughput. At shared computing facilities, such as those used by physicists at Fermi National Accelerator Laboratory (Fermilab), methodical resource allocation and high throughput at the many-user scale are key to ensuring that resources are being used as efficiently as possible. These facilities, however, primarily provide CPU-only nodes, which proves detrimental to time-to-insight and computational throughput for workflows that include machine learning inference. In this work, we describe how a shared computing facility can use the NVIDIA Triton Inference Server to optimize its resource allocation and computing structure, recovering high throughput while scaling out to multiple users by massively parallelizing their machine learning inference. To demonstrate the effectiveness of this system in a realistic multi-user environment, we use the Fermilab Elastic Analysis Facility augmented with the Triton Inference Server to provide scalable and high-throughput access to a HEP-specific GNN and report on the outcome.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

The use of artificial neural networks and multiple linear regression to predict rate of medical waste generation

Prediction of the amount of hospital waste production will be helpful in the storage, transportation and disposal of hospital waste management. Based on this fact, two predictor models including artificial neural networks (ANNs) and multiple linear regression (MLR) were applied to predict the rate of medical waste generation totally and in different types of sharp, infectious and general. In this study, a 5-fold cross-validation procedure on a database containing total of 50 hospitals of Fars province (Iran) were used to verify the performance of the models. Three performance measures including MAR, RMSE and R{sup 2} were used to evaluate performance of models. The MLR as a conventional model obtained poor prediction performance measure values. However, MLR distinguished hospital capacity and bed occupancy as more significant parameters. On the other hand, ANNs as a more powerful model, which has not been introduced in predicting rate of medical waste generation, showed high performance measure values, especially 0.99 value of R{sup 2} confirming the good fit of the data. Such satisfactory results could be attributed to the non-linear nature of ANNs in problem solving which provides the opportunity for relating independent variables to dependent ones non-linearly. In conclusion, the obtained results showed that our ANN-based model approach is very promising and may play a useful role in developing a better cost-effective strategy for waste management in future.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Flare Statistics for Young Stars from a Convolutional Neural Network Analysis of TESS Data

All-sky photometric time-series missions have allowed for the monitoring of thousands of young (t age < 800 Myr) stars in order to understand the evolution of stellar activity. In this work, we developed a convolutional neural network (CNN), stella, specifically trained to find flares in Transiting Exoplanet Survey Satellite (TESS) short-cadence data. We applied the network to 3200 young stars in order to evaluate flare rates as a function of age and spectral type. The CNN takes a few seconds to identify flares on a single light curve. We also measured rotation periods for 1500 of our targets and find that flares of all amplitudes are present across all spot phases, suggesting high spot coverage across the entire surface. Additionally, flare rates and amplitudes decrease for stars t age > 50 Myr across all temperatures T eff ≥ 4000 K, while stars from 2300 ≤ T eff < 4000 K show no evolution across 800 Myr. Stars of T eff ≤ 4000 K also show higher flare rates and amplitudes across all ages. We investigate the effects of high flare rates on photoevaporative atmospheric mass loss for young planets. In the presence of flares, planets lose 4%–7% more atmosphere over the first 1 Gyr. stella is an open-source Python toolkit hosted on GitHub and PyPI.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Reconstructing High Resolution ESM Data Through a Novel Fast Super Resolution Convolutional Neural Network (FSRCNN)

In this work, we present the first application of a fast super resolution convolutional neural network (FSRCNN) based approach for downscaling earth system model (ESM) simulations. Unlike other SR approaches, FSRCNN uses the same input feature dimensions as the low resolution input. This allows it to have smaller convolution layers, avoiding over-smoothing, and reducing computational costs. We adapt the FSRCNN to improve reconstruction on ESM data, we term the FSRCNN-ESM. We use high-resolution (~0.25°) monthly averaged model output of five surface variables over North America from the US Department of Energy's Energy Exascale Earth System Model's control simulation. These high-resolution and corresponding coarsened low-resolution (~1°) pairs of images are used to train the FSRCNN-ESM and evaluate its use as a downscaling approach. We find that FSRCNN-ESM outperforms FSRCNN and other super-resolution methods in reconstructing high resolution images producing finer spatial scale features with better accuracy for surface temperature, surface radiative fluxes, and precipitation.

58 GEOSCIENCES↗