Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep”

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 1,153 records · Page 64
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systems

This paper develops a model-free volt-VAR optimization (VVO) algorithm via multi-agent deep reinforcement learning (DRL) in unbalanced distribution systems. This method is novel since we cast the VVO problem in distribution networks to an intelligent deep Q-network (DQN) framework, which avoids solving a specific optimization model directly when facing time-varying operating conditions in the systems. We consider statuses/ratios of switchable capacitors, voltage regulators, and smart inverters installed at distributed generators as the action variables of the agents. A delicately designed reward function guides these agents to interact with the distribution system, in the direction of reinforcing voltage regulation and power loss reduction simultaneously. The forward-backward sweep method for radial three-phase distribution systems provides accurate power flow results within a few iterations to the DRL environment. The proposed method realizes the dual goals for VVO. We test this algorithm on the unbalanced IEEE 13-bus and 123-bus systems. Numerical simulations validate the excellent performance of this method in voltage regulation and power loss reduction.

41 EE - Solar Energy Technologies Office (EE-4S)↗
DOE OSTI2020

InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations

We propose InSituNet, a deep learning based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ. In situ visualization, generating visualizations at simulation time, is becoming prevalent in handling large-scale simulations because of the I/O and storage constraints. However, in situ visualization approaches limit the flexibility of post-hoc exploration because the raw simulation data are no longer available. Although multiple image-based approaches have been proposed to mitigate this limitation, those approaches lack the ability to explore the simulation parameters. Our approach allows flexible exploration of parameter space for large-scale ensemble simulations by taking advantage of the recent advances in deep learning. Specifically, we design InSituNet as a convolutional regression model to learn the mapping from the simulation and visualization parameters to the visualization results. With the trained model, users can generate new images for different simulation parameters under various visualization settings, which enables in-depth analysis of the underlying ensemble simulations. We demonstrate the effectiveness of InSituNet in combustion, cosmology, and ocean simulations through quantitative and qualitative evaluations.

deep learning↗
DOE OSTI2024

Efficient mapping between void shapes and stress fields using Deep Convolutional Neural Networks with sparse data

Establishing fast and accurate structure-to-property relationships is an important component in the design and discovery of advanced materials. Physics-based simulation models like the finite element method (FEM) are often used to predict deformation, stress, and strain fields as a function of material microstructure in material and structural systems. Such models may be computationally expensive and time intensive if the underlying physics of the system is complex. This limits their application to solve inverse design problems and identify structures that maximize performance. In such scenarios, surrogate models are employed to make the forward mapping computationally efficient to evaluate. However, the high dimensionality of the input microstructure and the output field of interest often renders such surrogate models inefficient, especially when dealing with sparse data. Deep convolutional neural network (CNN) based surrogate models have shown great promise in handling such high-dimensional problems. In this paper, a single ellipsoidal void structure under a uniaxial tensile load represented by a linear elastic, high-dimensional and expensive-to-query, FEM model. We consider two deep CNN architectures, a modified convolutional autoencoder framework with a fully connected bottleneck and a UNet CNN, and compare their accuracy in predicting the von Mises stress field for any given input void shape in the FEM model. Additionally, a sensitivity analysis study is performed using the two approaches, where the variation in the prediction accuracy on unseen test data is studied through numerical experiments by varying the number of training samples from 20 to 100.

surrogate modeling; convolutional neural networks;↗
DOE OSTI2023

Comparative Study on Deep Learning Methods for Defect Identification and Classification in Composite Aerostructure Material

Aircraft structures are required to have a high level of quality to satisfy their need for light weight, efficient flight, and withstanding high loads over their lifespan. These aerostructures are typically made from composite material due to their good tensile strength and resistance to compression. To ensure their structural integrity, the composite material requires inspection for common flaws such as porosity, delaminations, voids, foreign object debris, and other defects. Ultrasonic testing (UT) is a popular non-destructive inspection (NDI) technique used for effectively evaluating composite material. Current inspection methods rely heavily on human experience and are extremely time consuming. Therefore, there is a need for the development of techniques to reduce the manual inspection time. This work compares the performance of different deep learning-based methods in the identification and classification of defects. Deep learning has shown great promise in numerous fields, and we show its effectiveness in the evaluation of composite aerostructure material. Furthermore, the methods developed here are both highly reliable with a top recall value of 98.63% as well as extremely efficient requiring an average of 4 seconds during the inferencing stage to evaluate new composites.

composites↗
DOE OSTI2016

Radiation-induced bistable centers with deep levels in silicon n{sup +}–p structures

The method of deep level transient spectroscopy is used to study electrically active defects in p-type silicon crystals irradiated with MeV electrons and α particles. A new radiation-induced defect with the properties of bistable centers is determined and studied. After keeping the irradiated samples at room temperature for a long time or after their short-time annealing at T ∼ 370 K, this defect does not display any electrical activity in p-type silicon. However, as a result of the subsequent injection of minority charge carriers, this center transforms into the metastable configuration with deep levels located at E{sub V} + 0.45 and E{sub V} + 0.54 eV. The reverse transition to the main configuration occurs in the temperature range of 50–100°C and is characterized by the activation energy ∼1.25 eV and a frequency factor of ∼5 × 10{sup 15} s{sup –1}. The determined defect is thermally stable at temperatures as high as T ∼ 450 K. It is assumed that this defect can either be a complex of an intrinsic interstitial silicon atom with an interstitial carbon atom or a complex consisting of an intrinsic interstitial silicon atom with an interstitial boron atom.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Layer-Parallel Training of Deep Residual Neural Networks

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Synchrophasor Measurements-based Events Detection Using Deep Learning

Deep learning algorithms have been developed for phasor measurement units (PMUs) analysis aiming at providing grid operators to observe and react to significant real-time changes in the grid associated with multiple factors (e.g., power generation and load variations, different type of faults, and equipment mailfunction), or for offline post-event system diagnostics. In this study, a Long Short-Term Memory (LSTM)-based deep neural network (DNN) is adopted and evaluated to identify the most appropriate model configurations for event detection and longer-term anomalous pattern extraction. The proposed DNN model shows the potential on long-term predictions with the ability to capture nonlinear and nonstationary mixture complex patterns in PMU datasets. Real-world PMU in the WECC system were used for model development and validation.

deep learning↗
DOE OSTI2025

TorchBraid: High-Performance Layer-Parallel Training of Deep Neural Networks with MPI and GPU Acceleration

TorchBraid is a high-performance implementation of layer-parallel training for deep neural networks (DNNs) supporting MPI-based parallelism and GPU acceleration. Layer-parallel training has been developed to overcome the serialization inherent in forward and backward propagation of DNNs that limits utilization of computational resources in the strong scaling limit. To achieve this, TorchBraid integrates the PyTorch neural network framework with the state-of-the-art XBraid time-parallel library. Furthermore, this article presents the use and performance of TorchBraid, in addition to solutions for overcoming the algorithmic challenges inherent in combining automatic differentiation with layer-parallel. Results are presented with and without GPU acceleration for the Tiny ImageNet and MNIST image classification data sets, as well as recurrent neural networks. Overall, TorchBraid enables fast training of DNNs, both in a strong and weak scaling context. In addition to the TorchBraid software, several new advances in applying layer-parallel algorithms are detailed. Integration of layer-parallel with data-parallel algorithms is presented for the first time, showing the computational advantages of the combination. Standard deep learning techniques, like batch-normalization, are developed for layer-parallel training. Finally, a new approach combining layer-parallel with spatial coarsening in order to accelerate training for 3D image classification shows roughly a 10× speedup over serial execution.

Layer-parallel↗
DOE OSTI2020

Deep convolutional neural networks for multi-scale time-series classification and application to disruption prediction in fusion devices

The multi-scale, mutli-physics nature of fusion plasmas makes predicting plasma events challenging. Recent advances in deep convolutional neural network architectures (CNN) utilizing dilated convolutions enable accurate predictions on sequences which have long-range, multi-scale characteristics, such as the time-series generated by diagnostic instruments observing fusion plasmas. Here we apply this neural network architecture to the popular problem of disruption prediction in fusion tokamaks, utilizing raw data from a single diagnostic, the Electron Cyclotron Emission imaging (ECEi) diagnostic from the DIII-D tokamak. ECEi measures a fundamental plasma quantity (electron temperature) with high temporal resolution over the entire plasma discharge, making it sensitive to a number of potential pre-disruptions markers with different temporal and spatial scales. Promising, initial disruption prediction results are obtained training a deep CNN with large receptive field ({$\sim$}30k), achieving an $F_1$-score of {$\sim$}91\% on individual time-slices using only the ECEi data.

convolutional neural networks↗
DOE OSTI2020

Deep machine learning-assisted multiphoton microscopy to reduce light exposure and expedite imaging

Two-photon excitation fluorescence (2PEF) allows imaging of tissue up to about one millimeter in thickness. Typically, reducing fluorescence excitation exposure reduces the quality of the image. However, using deep learning super resolution techniques, these low-resolution images can be converted to high-resolution images. This work explores improving human tissue imaging by applying deep learning to maximize image quality while reducing fluorescence excitation exposure. We analyze two methods: a method based on U-Net, and a patch-based regression method. Both methods are evaluated on a skin dataset and an eye dataset. The eye dataset includes 1200 paired high power and low power images of retinal organoids. The skin dataset contains multiple frames of each sample of human skin. High-resolution images were formed by averaging 70 frames for each sample and low-resolution images were formed by averaging the first 7 and 15 frames for each sample. The skin dataset includes 550 images for each of the resolution levels. We track two measures of performance for the two methods: mean squared error (MSE) and structural similarity index measure (SSIM). For the eye dataset, the patches method achieves an average MSE of 27,611 compared to 146,855 for the U-Net method, and an average SSIM of 0.636 compared to 0.607 for the U-Net method. For the skin dataset, the patches method achieves an average MSE of 3.768 compared to 4.032 for the U-Net method, and an average SSIM of 0.824 compared to 0.783 for the U-Net method. Despite better performance on image quality, the patches method is worse than the U-Net method when comparing the speed of prediction, taking 303 seconds to predict one image compared to less than one second for the U-Net method.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2020

WRF Modelling of Deep Convection and Hail for Wind Power Applications

Deep convection and the related occurrence of hail, intense precipitation and wind gusts represent a hazard to a range of energy infrastructure including wind turbine blades. Wind turbine blade leading edge erosion (LEE) is caused by the impact of falling hydrometeors onto rotating wind turbine blades. It is a major source of wind turbine maintenance costs and energy losses from wind farms. In the United States Southern Great Plains (SGP), where there is widespread wind energy development, deep convection and hail events are common, increasing the potential for precipitation-driven LEE. A 25-day Weather Research and Forecasting (WRF) model simulation conducted at convection-permitting resolution and using a detailed microphysics scheme is carried out for the SGP to evaluate the effectiveness in modelling the wind and precipitation conditions relevant to LEE potential. WRF output for these properties is evaluated using radar observations of precipitation (including hail) and reflectivity, in situ wind speed measurements and wind power generation. This research demonstrates some skill for the primary drivers of LEE. Wind speeds, rainfall rates and precipitation totals show good agreement with observations. Here, the occurrence of precipitation during power producing wind speeds is also shown to exhibit fidelity. Hail events frequently occur during periods when wind turbines are rotating and are especially important to LEE in the SGP. The presence of hail is modelled with a mean proportion correct of 0.77 and an odds ratio 4.55. Further research is needed to demonstrate sufficient model performance to be actionable for the wind energy industry and there is evidence for positive model bias in cloud reflectivity.

17 WIND ENERGY↗
DOE OSTI2022

A resilient network recovery framework against cascading failures with deep graph learning

Because of the increasing importance and dependencies of infrastructure networks and the potential for massive cascading failures in real-world network systems, maintenance optimization to effectively reduce system performance loss caused by diverse disruptions is of significant interest among researchers and practitioners. In this work, a new recovery framework was developed to rapidly identify important system components for maintenance to improve network resilience against cascading failures. Here this work provides distinct advantages to determine an optimal maintenance priority by combining real-time network structure importance with other maintenance prioritization based on customer preference. This approach adopts structural graph embedding and deep reinforcement learning to extract real-time network topology information (such as minimum vertex cover) to update the maintenance priority during the recovery process. Based on the case studies on synthetic networks and a US airport network, the proposed recovery framework with real-time network topology awareness shows better performance than other maintenance prioritization strategies regarding resilience enhancement. This work improves the understanding of how the changing network structure influences maintenance effects. It also provides insights of the practical usefulness of advanced deep learning on helping optimal maintenance prioritization to effectively reduce the intensity and extent of cascading failures.

42 ENGINEERING↗
DOE OSTI2021

DeepDist: real-value inter-residue distance prediction with deep residual convolutional network

Abstract Background Driven by deep learning, inter-residue contact/distance prediction has been significantly improved and substantially enhanced ab initio protein structure prediction. Currently, most of the distance prediction methods classify inter-residue distances into multiple distance intervals instead of directly predicting real-value distances. The output of the former has to be converted into real-value distances to be used in tertiary structure prediction. Results To explore the potentials of predicting real-value inter-residue distances, we develop a multi-task deep learning distance predictor (DeepDist) based on new residual convolutional network architectures to simultaneously predict real-value inter-residue distances and classify them into multiple distance intervals. Tested on 43 CASP13 hard domains, DeepDist achieves comparable performance in real-value distance prediction and multi-class distance prediction. The average mean square error (MSE) of DeepDist’s real-value distance prediction is 0.896 Å 2 when filtering out the predicted distance ≥ 16 Å, which is lower than 1.003 Å 2 of DeepDist’s multi-class distance prediction. When distance predictions are converted into contact predictions at 8 Å threshold (the standard threshold in the field), the precision of top L/5 and L/2 contact predictions of DeepDist’s multi-class distance prediction is 79.3% and 66.1%, respectively, higher than 78.6% and 64.5% of its real-value distance prediction and the best results in the CASP13 experiment. Conclusions DeepDist can predict inter-residue distances well and improve binary contact prediction over the existing state-of-the-art methods. Moreover, the predicted real-value distances can be directly used to reconstruct protein tertiary structures better than multi-class distance predictions due to the lower MSE. Finally, we demonstrate that predicting the real-value distance map and multi-class distance map at the same time performs better than predicting real-value distances alone.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Achieving robust somatic mutation detection with deep learning models derived from reference data sets of a cancer sample

Accurate detection of somatic mutations is challenging but critical in understanding cancer formation, progression, and treatment. We recently proposed NeuSomatic, the first deep convolutional neural network-based somatic mutation detection approach, and demonstrated performance advantages on in silico data. In this study, we use the first comprehensive and well-characterized somatic reference data sets from the SEQC2 consortium to investigate best practices for using a deep learning framework in cancer mutation detection. Using the high-confidence somatic mutations established for a cancer cell line by the consortium, we identify the best strategy for building robust models on multiple data sets derived from samples representing real scenarios, for example, a model trained on a combination of real and spike-in mutations had the highest average performance. The strategy identified in our study achieved high robustness across multiple sequencing technologies for fresh and FFPE DNA input, varying tumor/normal purities, and different coverages, with significant superiority over conventional detection approaches in general, as well as in challenging situations such as low coverage, low variant allele frequency, DNA damage, and difficult genomic regions.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

GEOPHIRES Simulations for Deep Direct Use (DDU) Projects

This folder contains the GEOPHIRES codes and input files for running the base case scenarios for the six deep direct-use (DDU) projects. The six DDU projects took place during 2017-2020 and were funded by the U.S. Department of Energy Geothermal Technologies Office. They investigated the potential of geothermal deep direct-use at six locations across the country. The projects were conducted by Cornell University, West Virginia University (WVU), University of Illinois (U of IL), Sandia National Laboratory (SNL), Portland State University (PSU), and National Renewable Energy Laboratory (NREL). Four projects (Cornell, WVU, U of IL, SNL) investigated geothermal for direct heating of a local campus or community, the project by PSU considered seasonal subsurface storage of solar heating, and the NREL project investigated geothermal heating for turbine inlet cooling using absorption chillers. To allow comparison of techno-economic results across the six DDU projects, GEOPHIRES simulations were set up and conducted for each project. The GEOPHIRES code was modified for each project to simulate the local application and incorporate project-specific assumptions and results such as reservoir production temperature or financing conditions. The base case input file is included which simulates the base case conditions assumed by each project team. The levelized cost of heat (LCOH) is calculated and matches the base case LCOH reported by the project teams.

15 GEOTHERMAL ENERGY↗
DOE OSTI2024

Generalization of Deep-Learning Models for Classification of Local Distance Earthquakes and Explosions across Various Geologic Settings

Although accurately classifying signals from earthquakes and explosions at local distance (<250 km) remains an important task for seismic network operations, the growing volume of available seismic data presents a challenge for analysts using traditional source discrimination techniques. In recent years, deep-learning models have proven effective at discriminating between low-magnitude earthquakes and explosions measured at local distances, but it is not clear how well these models are capable of generalizing across different geological settings. To address the issue of generalization between regions, we train deep-learning models (convolutional neural networks [CNNs]) on time–frequency representations (scalograms) of three-component earthquake and explosion signals from eight different regions in the continental United States. We explore scenarios where models are trained on data from all regions, individual regions, or all but one region. We find that although CNN models trained on individual regions do not necessarily generalize well across different settings, models trained on multiple regions that include diverse path coverage generalize to new regions, with station-level accuracy of up to 90% or more for data sets from unseen regions. In general, CNN-based discrimination models significantly outperform models based on uncorrected P/S ratio (measured in the 10–18 Hz frequency band), even when CNN models are tested on data from entirely unseen regions.

58 GEOSCIENCES↗
DOE OSTI2013

Prediction of Peak Hydrogen Concentrations for Deep Sludge Retrieval in Tanks AN-101 and AN-106 from Historical Data of Spontaneous Gas Release Events

Radioactive and chemical wastes from nuclear fuel processing are stored in large underground storage tanks at the Hanford Site. The Tank Operations Contractor is continuing a program of moving solid wastes from single-shell tanks (SSTs) to double-shell tanks (DSTs) and preparing for waste feed delivery (WFD). A new mechanism for a large spontaneous gas release event (GRE) in deep sludge sediments has been postulated. The creation of this potential new GRE hazard, deep sludge gas release events (DSGREs), is the retrieval of sludge waste into a single DST that results in a sediment depth greater than operating experience has demonstrated is safe. The Tank Operations Contractor program of moving solid wastes from SSTs to DSTs and preparing for WFD is being negatively impacted by this sediment depth limit.

Deep sludge retrieval↗
DOE OSTI2016

Phased Retrofits in Existing Homes in Florida Phase I: Shallow and Deep Retrofits

The U.S. Department of Energy (DOE) Building America program, in collaboration with Florida Power and Light (FPL), conducted a phased residential energy-efficiency retrofit program. This research sought to establish impacts on annual energy and peak energy reductions from the technologies applied at two levels of retrofit - shallow and deep, with savings levels approaching the Building America program goals of reducing whole-house energy use by 40%. Under the Phased Deep Retrofit (PDR) project, we have installed phased, energy-efficiency retrofits in a sample of 56 existing, all-electric homes. End-use savings and economic evaluation results from the phased measure packages and single measures are summarized in this report.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗