Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “CLASSIFICATION”

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 1,387 records · Page 77
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Structure of LARP7 Protein p65–telomerase RNA Complex in Telomerase Revealed by Cryo-EM and NMR

La-related protein 7 (LARP7) are a family of RNA chaperones that protect the 3'-end of RNA and are components of specific ribonucleoprotein complexes (RNP). Here, in Tetrahymena thermophila telomerase, LARP7 protein p65 together with telomerase reverse transcriptase (TERT) and telomerase RNA (TER) form the core RNP. p65 has four known domains—N-terminal domain (NTD), La motif (LaM), RNA recognition motif 1 (RRM1), and C-terminal xRRM2. To date, only the xRRM2 and LaM and their interactions with TER have been structurally characterized. Conformational dynamics leading to low resolution in cryo-EM density maps have limited our understanding of how full-length p65 specifically recognizes and remodels TER for telomerase assembly. Here, we combined focused classification of Tetrahymena telomerase cryo-EM maps with NMR spectroscopy to determine the structure of p65–TER. Three previously unknown helices are identified, one in the otherwise intrinsically disordered NTD that binds the La module, one that extends RRM1, and another preceding xRRM2, that stabilize p65–TER interactions. The extended La module (αN, LaM and RRM1) interacts with the four 3' terminal U nucleotides, while LaM and αN additionally interact with TER pseudoknot, and LaM with stem 1 and 5' end. Our results reveal the extensive p65–TER interactions that promote TER 3'-end protection, TER folding, and core RNP assembly and stabilization. The structure of full-length p65 with TER also sheds light on the biological roles of genuine La and LARP7 proteins as RNA chaperones and core RNP components.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

A contextual sensor system for non-intrusive machine status and energy monitoring

Event-driven contexts in manufacturing occur pervasively as a result of interactions among involved entities such as machines, workers, materials, and environment. One of the primary tasks in smart manufacturing is to derive a context-aware system conveniently incorporating worker knowledge for generating timely actionable intelligence for workers on factory floor and supervisors to respond. In this paper, we propose to design a human-and-machine interaction recognition framework by using a causality concept to collect contextual data for classifications of normal and abnormal machine operations. The causes and effects are between workers and machines for this initial research. To apply the causality to recognize worker interactions, initially a reliable way to identify the states of machines is necessary. The proposed contextual sensor system, consisting of a power meter for measuring machine operation conditions, a visual camera for capturing worker and machine interactions via a finite state machine model, and an algorithm for determining power signatures of individual components via energy disaggregation is implemented on semiconductor fabrication machines (manual or PLC controlled) each with multiple components. The experiment results demonstrate its context extraction capability such as components states and their corresponding energy usage in real time as well as its ability to identify anomalous operation conditions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Uranium Oxide Synthetic Pathway Discernment through Unsupervised Morphological Analysis

We present a novel unsupervised machine learning method for quantitative representation of scanning electron micrographs and its applications and performance for nuclear forensic analysis of uranium ore concentrates. The method uses a vector quantizing variational autoencoder followed by a histogram operation to encode a micrograph into a single dimensional representation, called the latent vector. The method requires no extant labeling of the data and can be applied over large datasets of micrographs with minimal human interaction. The representations generated are broadly descriptive of each micrograph and the microstructure of the material imaged. In the case of uranium ore concentrate analysis, the representations were amenable to processing reagent and ore concentrate species classification with accuracy of 81:8%, which is competitive with state-of-the-art supervised networks. The representations were also used to classify previously unseen processing routes, were able to classify imaging parameters such as magnification (to 76:0% accuracy), were able to classify fine grained process parameters such as calcining temperature (to 74:4% accuracy), and their informatic properties indicate that they are generally descriptive of the image represented. This method can be applied across microstructure analysis fields to perform quantitative analysis without the need for labor intensive and possibly biased human analysis.

Scanning Electron Microscopy, Vector Quantizing Va↗
DOE OSTI2022

Battery aging mode identification across NMC compositions and designs using machine learning

A comprehensive understanding of lithium-ion battery (LiB) lifespan is the key to designing durable batteries and optimizing use protocols. Although battery lifetime prediction methods are flourishing, diagnosis of the root causes of aging and degradation have not yet been well developed nor studied for a broad mixture of designs and use cases. Here, we create a machine-learning (ML)-based framework that distinguishes aging modes using multiple electrochemical signatures recorded cycle-by-cycle. The predominant aging behaviors include a combination of loss of active materials in cathode (LAMPE) and a loss of Li inventory (LLI) in Li plating or solid electrolyte interphase (SEI) formation, manifested from 44 batteries representing two cathode chemistries, two electrode loadings, and five charging rates. Here, the aging mode classification accuracy is 86% using features within the first 50 cycles and increases to 88% beyond 225 cycles. The same features can quantify the percentage of end-of-life LAMPE with only 4.3% of error.

25 ENERGY STORAGE↗
DOE OSTI2022

Avoiding thermal runaway in lithium-ion batteries using ultrasound detection of early failure mechanisms

Thermal runaway leading to catastrophic failure has slowed the adoption of lithium-ion batteries, highlighting the need for early warning systems. In this work, ultrasound is used to detect physical changes in 0.950 Ah Li-ion battery cells by inducing conditions associated with thermal runaway. Ultrasound signal features are extracted as the batteries are cycled under baseline conditions and subsequently subjected to constant current and voltage overcharges. Two conditions identifying failure are defined: a warning to detect the start of overcharge and an emergency stop (E-stop), to immediately take the battery out of service. Using changes in ultrasound signal features, consistent warning and stopping classifications are applied to all failure experiments. On average, a warning notification was issued after 15% of the overcharge time and an E-stop was triggered after 35% of total overcharge duration before failure. Further testing suggests that it is possible to avoid thermal runaway by reacting to intermediate, warning notifications prior to an immediate E-stop. In other words, not only can detection derived by ultrasound identify battery failure before a catastrophic event, but can also provide early, actionable warnings so that overcharges can be detected and corrected quickly enough so the battery does not need to be decommissioned.

25 ENERGY STORAGE↗
DOE OSTI2023

Identifying common stored product insects using automated deep learning methods

Monitoring stored product insect pests is a common practice for post-harvest management of stored grain and grain-based commodities, which helps ensure product quality from harvest to final consumer. Current methods of sampling and monitoring can be time-consuming, labor-intensive, expensive and require expertise in insect identification. Therefore, this study aims to develop an image-based automated identification system for common stored product insect species using deep-learning methods. Top-down images of the common stored product adult insect species of Rhyzopertha dominica, Cryptolestes ferrugineus, Tribolium castaneum, Sitophilus oryzae, and Oryzaephilus surinamensis were acquired and analyzed. Deep learning-based, state-of-the-art Convolutional Neural Networks (CNN) models (ResNet-50, MobileNet-v2, DarkNet-53, and EfficientNet-b0) were fine-tuned with a transfer learning approach to classify the insect species. All models were able to correctly identify the insect species with at least 96% accuracy and with few misclassifications. One issue with trained CNNs is that they do not explain the reasoning for the classification and are often called a “black box”. Therefore, visualization methods called Gradient-weighted Class Activation Mapping (Grad-CAM) were implemented to explore the black box network. The Grad-CAM uses heat maps to highlight the major image features that the network focused on to make insect species predictions. The Grad-CAM verifies the network's prediction and also helps improve network performance. This study contributes to the overall goal of developing a camera-based system for monitoring stored grain insects. As a result, the developed system would empower warehouse, flour mills, and other food facilities with a tool to quickly and accurately identify insect species in stored product environments and could be implemented as part of a close to real-time monitoring system.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

An automated procedure built on MTEX for reconstructing deformation twin hierarchies from electron backscattered diffraction datasets of heavily twinned microstructures

Here we present a set of algorithms built on the MTEX and MATLAB graph toolboxes for automatic reconstruction of deformation twin hierarchies from Electron Backscatter Diffraction (EBSD) datasets with a focus on developing methods for heavily twinned microstructures (twin fractions >0.5). The algorithms address key issues arising at large strains, mainly: missing twin relationships, grouping of heavily deformed grain fragments into families of similar orientation originating from a single initial grain, identification of parent fragments for large twin volume fractions, and classification of families having twin relationships with multiple families. To facilitate the development of these algorithms, large-grained ultra-high purity α-Ti deformed in compression along two directions is investigated. Graphs are utilized to handle non-local geometric merging and to represent relationships throughout the reconstruction process. When determining if a grain fragment is from the undeformed microstructure, the combined metrics of the fragment's orientation volume fraction in the initial texture and the directed graph centrality measure of out-closeness (the number of nodes reached in a graph from a given node) are essential. To address automation in reconstructing the sequence of twinning and relating fragments originating from a single grain in the initial microstructure, the twin family tree is formulated as a minimum spanning tree emanating from the initial grain family. A scheme constructing the distances associated with twin relationship comprising the spanning tree is developed, and a novel quasi-directional Prim spanning tree algorithm is used to determine the twin family tree. The procedure is demonstrated to significantly improve the level of automation in reconstructing twin hierarchies in heavily twinned microstructure compared to other methodologies in literature. The procedure can readily be applied to analyses of twinning in metals, as well as provide an approach for routinely extracting twin statistics at larger deformation levels than previously possible. Significantly, the procedure is demonstrated to be capable of identifying third generation twinning in α-Ti microstructures.

36 MATERIALS SCIENCE↗
DOE OSTI2026

RU-net for automatic characterization of TRISO fuel cross sections

During irradiation, phenomena such as kernel swelling and buffer densification may impact the performance of tristructural isotropic (TRISO) particle fuel. Post-irradiation microscopy is often used to identify these irradiation-induced morphologic changes. However, each fuel compact generally contains thousands of TRISO particles. Manually performing the work to get statistical information on these phenomena is cumbersome and subjective. Here, to reduce the subjectivity inherent in that process and to accelerate data analysis, we used convolutional neural networks (CNNs) to automatically segment cross-sectional images of microscopic TRISO layers. CNNs are a class of machine-learning algorithms specifically designed for processing structured grid data. They have gained popularity in recent years due to their remarkable performance in various computer vision tasks, including image classification, object detection, and image segmentation. In this research, we generated a large irradiated TRISO layer dataset with more than 2,000 microscopic images of cross-sectional TRISO particles and the corresponding annotated images. Based on these annotated images, we used different CNNs to automatically segment different TRISO layers. These CNNs include RU-Net (developed in this study), as well as three existing architectures: U-Net, Residual Network (ResNet), and Attention U-Net. The preliminary results show that the model based on RU-Net performs best in terms of Intersection over Union (IoU). Using CNN models, we can expedite the analysis of TRISO particle cross sections, significantly reducing the manual labor involved and improving the objectivity of the segmentation results.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

Machine learning-enabled multiscale modeling of mechanical deformation of aluminum and Al-SiC nanocomposites

A machine learning-enabled multiscale framework is developed for modeling the mechanical response of both pure metal and nanoparticle-reinforced metal matrix nanocomposites (MMNCs). Using aluminum–silicon carbide (Al-SiC) as an example MMNC, atomistic simulations reveal three distinct deformation mechanisms (i.e., defect-free, dislocation-based, and interface separation) governed by the interfaces between the Al matrix and SiC nanoparticles. As compared with single crystal Al, the lattice undergoes a more abrupt failure once the dislocation network becomes extensive and void nucleation initiates, whereas in Al-SiC, nanoparticle interfaces enable a more gradual progression of damage. These mechanisms are captured through a combined classification-regression neural network surrogate model that bridges atomic-scale insights with continuum-scale finite element analysis. Machine learning-enabled multiscale modeling of pure Al accurately predicted strain localization and confirmed by in-situ scanning electron microscopic tensile testing on perforated Al specimens. This study underscores the promise of integrating physics-informed machine learning with hierarchical modeling to capture the interface dominated phenomena and guide the design of advanced MMNCs.

Al-SiC↗
DOE OSTI2022

Intrinsically stretchable neuromorphic devices for on-body processing of health data with artificial intelligence

For leveraging wearable technologies to advance precision medicine, personalized and learning-based analysis of continuously acquired health data is indispensable, for which neuromorphic computing could provide the most efficient implementation of artificial intelligence (AI) data processing. For realizing on-body neuromorphic computing, skin-like stretchability is required, but yet to be combined with the suite of desired neuromorphic metrics, including linear, symmetric weight update, and sufficient state retention, for achieving high computing efficiency. Here, we report an intrinsically stretchable neuromorphic device based on an electrochemical transistor, which provides a large number (>800) of states, linear/symmetric weight update, excellent switching endurance (>100 million), good state retention (>10 4 s), together with high stretchability of 100% strain. Further integration into a prototype array successfully realized the implementation of vector-matrix multiplication even at 100% strain. Finally, we demonstrate the feasibility of implementing AI-based classification of health signals (as exemplified by electrocardiograms) with a high accuracy that is minimally influenced by the stretched state of the neuromorphic hardware. Finally, this work breaks the ground for combining AI data analysis into skin-like wearable electronics for achieving human-integrated/mimetic intelligent systems.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Site specific porosity-thermal performance correlations in neutron irradiated U-10Zr fuel

In this work, we present a site-specific three-dimensional analysis of porosity evolution in neutron-irradiated U–10Zr metallic fuel using high-resolution synchrotron X-ray tomography. Focused ion beam cubic lift-outs from four radial positions—fuel center, middle, edge, and fuel-cladding interaction (FCCI) zones—were imaged, reconstructed, and segmented to quantify pore volume, density, morphology, and pore connectivity. Porosity increased modestly from 5.5% at the center to 10.5% at the edge, yet pore number density increased by over two orders of magnitude in the fuel portion near the FCCI interface (from 4.8 x 10 4 to 6.0 x 10 6 pores/mm 3 ). Morphological classification revealed a progression from small spherical pores at the center to equiaxed and tortuous networks at the periphery, with enhanced orientation along the radial direction. Connectivity and permeability analysis reveal that the FCCI region maintains dense, highly interconnected pores despite a moderate volume fraction, enabling rapid fission gas transport and lanthanide migration. Effective thermal conductivity models incorporating sodium logging confirm that these site-specific pore features critically influenced heat transport during reactor irradiation. These findings demonstrate that pore topology—not just porosity fraction—controls thermal performance and thermal pathways in U–10Zr fuels, impacting fuel thermal performance in a reactor.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

Hierarchical median narrow band for level set segmentation of cervical cell nuclei

This paper presents a novel hierarchical nuclei segmentation algorithm for isolated and overlapping cervical cells based on a narrow band level set implementation. Our method applies a new multiscale analysis algorithm to estimate the number of clusters in each image region containing cells, which turns into the input to a narrow band level set algorithm. We assess the nuclei segmentation results on three public cervical cell image databases. Overall, our segmentation method outperformed six state-of-the-art methods concerning the number of correctly segmented nuclei and the Dice coefficient reached values equal to or higher than 0.90. We also carried out classification experiments using features extracted from our segmentation results and the proposed pipeline achieved the highest average accuracy values equal to 0.89 and 0.77 for two-class and three-class problems, respectively. Furthermore, these results demonstrated the suitability of the proposed segmentation algorithm to integrate decision support systems for cervical cell screening.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Data-driven acoustic measurement of moisture content in flowing biomass

Measuring the moisture content in flowing biomass is critical to processes such as liquid biofuel conversion, such as biogasoline, biodiesel, bio jet kerosene, etc. However, biomass tends to flow in aggregates, which results in significant inhomogeneities in the amount of biomass flowing in front of a sensor at a given time, and there can be significant overlap in the material properties of dry vs wet biomass, leading to poor signal-to-noise ratio. We present a technique for identifying biomass moisture content using a series of acoustic pitch-catch measurements to quantify the sound speed and acoustic amplitude through the biomass, in conjunction with classical machine learning techniques, including Naive Bayes, Random Forest, and K-Nearest Neighbors classification. We amplify the differences between the acoustic measurements in different moisture levels by collecting a series of pulse-echo measurements, which we sort in order of ascending sound speed. We test the accuracy of the technique on experimentally-prepared batches of corn stover biomass with specified moisture levels and measure the average error in the estimated moisture level as a function of the number of pitch-catch measurements used. We observe average estimation errors as low as 6.7% by increasing the number of measurements and optimizing the hyperparameters. This work presents a novel method determining moisture content in flowing biomass with inhomogeneous flow. Additionally, this technique has application in optimizing biomass conversion processes, as well as other fields including, paper production, natural fiber processing, and mineral extraction.

09 BIOMASS FUELS↗
DOE OSTI2022

Actinides in complex reactive media: A combined ab initio molecular dynamics and machine learning analytics study of transuranic ions in molten salts

The predominant ionic chemistry and the similarity in ionic radius of actinides make it very difficult to structurally distinguish them in liquids. In this work, while ab initio molecular dynamics shows that the f-states clearly affects the electronic properties, their impact on structural properties is not obvious. For the series of trivalent actinides U 3+ , Pu 3+ , Cm 3+ , Cf 3+ , Fm 3+ in molten NaCl and FLiBe, actinide ligand bonds have a higher degree of covalency in NaCl (than in FLiBe), and a higher degree of ionicity in FLiBe. Furthermore, a machine learned classification model can distinguish atomic environments of chemically similar actinides, as long as atoms beyond the first solvation shells are considered. Our work shows that only two types of descriptors are necessary to account for all the fluctuations in heavy metal/molten salt mixtures: The first descriptor represents the electronic state of the heavy metal, while the second encompasses the local coordination environment.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Tunable high spin Chern-number insulator phases in strained Sb monolayer

High spin Chern-number insulators (HSCI) have emerged as a novel 2D topological phase of condensed matter that is beyond the classification of topological quantum chemistry. The HSCI phase with two pairs of gapless helical edge states is robust even in the presence of spin–orbit coupling due to the protection of a “hidden” feature spectrum topology. Here, in this work, we report the observation of a semimetallic Sb monolayer carrying the same band topology as HSCI with the spin Chern number equal to 2. Our calculations further indicate a moderate lattice strain can make Sb monolayer an insulator or a semimetal with a tunable spin Chern number from 0 to 3. The results suggest strained Sb monolayers as a promising platform for exploring exotic properties of the HSCI topological matter.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Stochasticity and robustness in spiking neural networks

Despite drawing inspiration from biological systems which are inherently noisy and variable, artificial neural networks have been shown to require precise weights to carry out the task which they are trained to accomplish. This creates a challenge when adapting these artificial networks to specialized execution platforms which may encode weights in a manner which restricts their accuracy and/or precision.Reflecting back on the non-idealities which are observed in biological systems, we investigated the effect these properties have on the robustness of spiking neural networks under perturbations to weights. First, we examined techniques extant in conventional neural networks which resemble noisy processes, and postulated they may produce similar beneficial effects in spiking neural networks. Second, we evolved a set of spiking neural networks utilizing biological non-idealities to solve a pole-balancing task, and estimated their robustness. We showed it is higher in networks using noisy neurons, and demonstrated that one of these networks can perform well under the variance expected when a hafnium-oxide based resistive memory is used to encode synaptic weights. Lastly, we trained a series of networks using a surrogate gradient method on the MNIST classification task. We confirmed that these networks demonstrate similar trends in robustness to the evolved networks. We discuss these results and argue that they display empirical evidence supporting the role of noise as a regularizer which can increase network robustness.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness

We report the accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory answers to the problems of approximation and optimization, much less is known about the theory of generalization. Most existing theoretical works for generalization fail to explain the performance of neural networks in practice. To derive a meaningful bound, we study the generalization error of neural networks for classification problems in terms of data distribution and neural network smoothness. We introduce the cover complexity (CC) to measure the difficulty of learning a data set and the inverse of the modulus of continuity to quantify neural network smoothness. A quantitative bound for expected accuracy/error is derived by considering both the CC and neural network smoothness. Although most of the analysis is general and not specific to neural networks, we validate our theoretical assumptions and results numerically for neural networks by several data sets of images. The numerical results confirm that the expected error of trained networks scaled with the square root of the number of classes has a linear relationship with respect to the CC. We also observe a clear consistency between test loss and neural network smoothness during the training process. In addition, we demonstrate empirically that the neural network smoothness decreases when the network size increases whereas the smoothness is insensitive to training dataset size.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers

Dynamic graph embedding has emerged as a very effective technique for addressing diverse temporal graph analytic tasks (i.e., link prediction, node classification, recommender systems, anomaly detection, and graph generation) in various applications. Such temporal graphs exhibit heterogeneous transient dynamics, varying time intervals, and highly evolving node features throughout their evolution. Hence, incorporating long-range dependencies from the historical graph context plays a crucial role in accurately learning their temporal dynamics. In this paper, we develop a graph embedding model with uncertainty quantification, TransformerG2G, by exploiting the advanced transformer encoder to first learn intermediate node representations from its current state (t) and previous context (over timestamps [t–1,t–l], l is the length of context). Moreover, we employ two projection layers to generate lower-dimensional multivariate Gaussian distributions as each node's latent embedding at timestamp t. We consider diverse benchmarks with varying levels of "novelty" as measured by the TEA (Temporal Edge Appearance) plots. Here, our experiments demonstrate that the proposed TransformerG2G model outperforms conventional multi-step methods and our prior work (DynG2G) in terms of both link prediction accuracy and computational efficiency, especially for high degree of novelty. Furthermore, the learned time-dependent attention weights across multiple graph snapshots reveal the development of an automatic adaptive time stepping enabled by the transformer. Importantly, by examining the attention weights, we can uncover temporal dependencies, identify influential elements, and gain insights into the complex interactions within the graph structure. For example, we identified a strong correlation between attention weights and node degree at the various stages of the graph topology evolution.

97 MATHEMATICS AND COMPUTING↗