Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “SLICING”

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 1,693 records · Page 94

Feature Extraction and Selection From the Perspective of Explosive Detection

Features are extractable measurements from a sample image summarizing the information content in an image and in the process providing an essential tool in image understanding. In particular, they are useful for image classification into pre-defined classes or grouping a set of image samples (also called clustering) into clusters with similar within-cluster characteristics as defined by such features. At the lowest level, features may be the intensity levels of a pixel in an image. The intensity levels of the pixels in an image may be derived from a variety of sources. For example, it can be the temperature measurement (using an infra-red camera) of the area representing the pixel or the X-ray attenuation in a given volume element of a 3-d image or it may even represent the dielectric differential in a given volume element obtained from an MIR image. At a higher level, geometric descriptors of objects of interest in a scene may also be considered as features in the image. Examples of such features are: area, perimeter, aspect ratio and other shape features, or topological features like the number of connected components, the Euler number (the number of connected components less the number of 'holes'), etc. Occupying an intermediate level in the feature hierarchy are texture features which are typically derived from a group of pixels often in a suitably defined neighborhood of a pixel. These texture features are useful not only in classification but also in the segmentation of an image into different objects/regions of interest. At the present state of our investigation, we are engaged in the task of finding a set of features associated with an object under inspection ( typically a piece of luggage or a brief case) that will enable us to detect and characterize an explosive inside, when present. Our tool of inspection is an X-Ray device with provisions for computed tomography (CT) that generate one or more (depending on the number of energy levels used) digitized 3-dimensional attenuation images with a voxel resolution of the order of one quarter of a milimeter. In the task of feature extraction and subsequent selection of an appropriate subset thereof, several important factors need to be considered. Foremost among them are: (1) Definition of the sampling unit from which the features will be extracted for the purpose of detection/ identification of the explosives. (2) The choice of features ( given the sampling unit) to be extracted that can be used to signal the existence / identity of the explosive. (3) Robustness of the computed features under different inspection conditions. To attain robustness, invariance under the transformations of translation, scaling, rotation and change of orientation is highly desirable. (4) The computational costs in the process of feature extraction, selection and their use in explosive detection/ identification In the search for extractable features, we have done a thorough literature survey with the above factors in mind and come out with a list of features that could possibly help us in meeting our objective. We are assuming that features will be based on sampling units that are single CT slices of the target. This may however change when appropriate modifications should be made to the feature extraction process. We indicate below some of the major types of features in 2- or 3-dimensional images that have been used in the literature on application of pattern recognition (PR) techniques in image understanding and are possibly pertinent to our study. In the following paragraph, we briefly indicate the motivation that guided us in the choice of these features, and identify the nature of the constraints. The principal feature types derivable from an image will be discussed in section 2. Once the features are extracted, one must select a subset of this feature set that will retain the most useful information and remove any redundant and irrelevant information that may have a detrimental effect on the classifier performance. This is discussed in section 3. Section 4 provides a brief summary.

42 ENGINEERING↗

Reference guide to WPP version 2.0

WPP is a computer program for simulating seismic wave propagation on parallel machines. WPP solves the governing equations in second order formulation using a node-based finite difference approach. The basic numerical method is described in [9]. WPP implements substantial capabilities for 3-D seismic modeling, with a free surface condition on the top boundary, non-reflecting far-field boundary conditions on the other boundaries, point force and point moment tensor source terms with many predefined time dependencies, fully 3-D heterogeneous material model specification, output of synthetic seismograms in the SAC [4] format, output of GMT [11] scripts for laying out simulation information on a map, and output of 2-D slices of (derived quantites of) the solution field as well as the material model. Version 2.0 of WPP allows the free surface boundary condition to be imposed on a curved topography. For this purpose a curvilinear mesh is used near the free surface, extending into the computational domain down to a user specified level. The elastic wave equations and the free surface boundary conditions are discretized on the curvilinear mesh using the energy conserving technique described in [2]. A curvilinear mesh generator is built into WPP and the curvilinear mesh is automatically generated from the topography. Below the curvilinear grid, the elastic wave equation is discretized on Cartesian meshes, which leads to a more computationally efficient algorithm. In version 2.0 of WPP, Cartesian local mesh refinement can be used to make the computational mesh finer near the free surface, where more resolution often is needed to resolve short wave lenghts in the solution, for example in sedimentary basins. The mesh refinement is performed in the vertical direction and each Cartesian grid is constructed from user specified refinement levels. In this approach, the grid size in all three spatial directions is doubled across each mesh refinement interface, leading to substantial savings in memory and computational effort. The energy conserving mesh refinement coupling method described in [10] is used to handle the hanging nodes along the refinement interface. The examples subdirectory of the WPP source distribution contains several examples and validation tests. Many Matlab/octave scripts are provided in the tools directory.

58 GEOSCIENCES↗

IMPACT-T User Document Version 1.6

IMPACT-T is a fully three-dimensional program to track relativistic particles taking into account space charge forces and short-range longitudinal and transverse wakenelds. IMPACT-T is one of the few codes used in the photoinjector community that has a parallel implementation, making it very useful for high statistics simulations of beam halos and beam diagnostics. It has a comprehensive set of beamline elements, and furthermore allows arbitrary overlap of their fields, which gives the IMPACT-T a capability to model both the standing wave structure and traveling wave structure. It is also unique in its use of space-charge solvers based on an integrated Green function to efficiently and accurately treat beams with large aspect ratio, and a shifted Green function to efficiently treat image charge effects of a cathode. It is also unique in its inclusion of energy binning in the space-charge calculation to model beams with large energy spread. IMPACT-T has a flexible data structure that allows particles to be stored in containers with common characteristics; for photoinjector simulations the containers represent multiple slices, but in other applications they could correspond, e.g., to particles of different species. Together, all these features make IMPACT-T a powerful and versatile tool for modeling beams in photoinjectors and other systems.

99 GENERAL AND MISCELLANEOUS↗

X-Ray Tomographic Reconstruction

Tomographic scans have revolutionized imaging techniques used in medical and biological research by resolving individual sample slices instead of several superimposed images that are obtained from regular x-ray scans. X-Ray fluorescence computed tomography, a more specific tomography technique, bombards the sample with synchrotron x-rays and detects the fluorescent photons emitted from the sample. However, since x-rays are attenuated as they pass through the sample, tomographic scans often produce images with erroneous low densities in areas where the x-rays have already passed through most of the sample. To correct for this and correctly reconstruct the data in order to obtain the most accurate images, a program employing iterative methods based on the inverse Radon transform was written. Applying this reconstruction method to a tomographic image recovered some of the lost densities, providing a more accurate image from which element concentrations and internal structure can be determined.

Schmittberger, Bonnie↗

Coherence Properties of the LCLS

The LINAC Coherent Light Source (LCLS), an X-Ray free-electron laser(FEL) based on the self amplified spontaneous emission principle, has recently come on-line. For many users it is desirable to have an idea of the level of transverse coherence of the X-Ray beam produced. In this paper, we analyze the output of GENESIS simulations of electrons traveling through the FEL. We first test the validity of an approach that ignores the details of how the beam was produced, and instead, by assuming a Gaussian-Schell model of transverse coherence, predicts the level of transverse coherence simply through looking at the beam radius at several longitudinal slices. We then develop a Markov chain Monte Carlo approach to calculating the degree of transverse coherence, which offers a {approx}100-fold speedup compared to the brute-force algorithm previously in use. We find the beam highly coherent. Using a similar Markov chain Monte Carlo approach, we estimate the reasonability of assuming the beam to have a Gaussian-Schell model of transverse coherence, with inconclusive results.

Ocko, Samuel↗

The Readout Electronics of the Mu2e Electromagnetic Calorimeter

The Mu2e electromagnetic calorimeter has been designed to measure ~100 MeV electrons with energy resolution σE/E <10%, time resolution σt < 500ps and position resolution σx < 1cm. The detector is composed of 1348 un-doped CsI crystals coupled to two large area Silicon Photomultipliers (SiPMs). Each SiPM is connected to a Front End Electronics (FEE) chip which hosts the shaping amplifier and the high voltage linear regulator. A group of 20 FEE is controlled by one Mezzanine Board (MB) which transmits the amplified signals to one Digitizer ReAdout Controller board (DiRAC). The DiRAC samples the waveforms at 200 MHz with 12-bit ADCs, packs the data according to the Mu2e custom format and transmits them to the event builder through an optical transceiver. To limit the number of pass-through connectors and the length of the cables, the readout and digitization electronics is located inside the detector cryostat and close to the interaction target. The boards will have to sustain a neutron fluence of about 5x10 10 n/cm 2 @ 1 MeVeq (Si)/y and a Total Ionizing Dose of about 12 krad, while working into a 1T magnetic field and a vacuum of 10 (-4) Torr. This harsh operational environment has made the electronics design challenging and required an extended campaign of tests to select and qualify the employed electronic components. In this paper we report on the board architecture and design, on the qualification of the prototypes, as well as on the results of the first vertical slice test of the Mu2e calorimeter.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

The Mu2e crystal calorimeter

The Mu2e experiment at Fermilab will search for the charged-lepton flavour violating conversion of negative muons into electrons in the coulomb field of an Al nucleus, planning to reach a single event sensitivity of about $3\cdot10^{−17}$, four orders of magnitude beyond the current best limit.The conversion electron has a clear monoenergetic signature at 104.967 MeV, slightly below the muon rest mass, and will be identified by a complementary measurement carried out by a high-resolution tracker and an electromagnetic calorimeter (EMC). The calorimeter is composed of 1348 pure CsI crystals, each read by two custom UV-extended SiPMs, that are arranged in two annular disks. The EMC should achieve better than 10% energy resolution and 500 ps timing resolution for 100 MeV electrons and maintain extremely high levels of reliability and stability and in a harsh operating environment with high vacuum, 1 T B-field and radiation exposures up to 100 krad and $10^{12} \rm{n}_\rm{1MeVeq}/\rm{cm}^{2}$.The calorimeter technological choice, along with the design of the custom front-end electronics, cooling and mechanical systems were validated through an electron beam test on a large-scale 51-crystals prototype (Module-0) and extensive test campaigns that characterised and verified the performance of crystals, photodetectors, analogue and digital electronics. This included hardware stress tests and irradiation campaigns with neutrons, protons, and photons.The production and QC phases of all calorimeter components is completed apart for the digital electronics that has been revised for improving its resilience to SEU and SEL. A series of vertical slice tests with the final electronics is being carried out on the Module-0 at LNF along with the implementation and validation of the calibration procedures. The first disk has been assembled in 2022 while the second disk is under assembly at the moment of writing. Status of construction will be summarised, along with plans for commissioning and first calibration of the fully assembled disks.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Dynamically Downscaled Hourly Future Weather Data with 12-km Resolution Covering Most of North America

This is an hourly future weather dataset for energy modeling applications. The dataset is primarily based on the output of a regional climate model (RCM), i.e., the Weather Research and Forecasting (WRF) model version 3.3.1. The WRF simulations are driven by the output of a general circulation model (GCM), i.e., the Community Climate System Model version 4 (CCSM4). This dataset is in the EPW format, which can be read or translated by more than 25 building energy modeling programs (e.g., EnergyPlus, ESP-r, and IESVE), energy system modeling programs (e.g., System Advisor Model (SAM)), indoor air quality analysis programs (e.g., CONTAM), and hygrothermal analysis programs (e.g., WUFI). It contains 13 weather variables, which are the Dry-Bulb Temperature, Dew Point Temperature, Relative Humidity, Atmospheric Pressure, Horizontal Infrared Radiation Intensity from Sky, Global Horizontal Irradiation, Direct Normal Irradiation, Diffuse Horizontal Irradiation, Wind Speed, Wind Direction, Sky Cover, Albedo, and Liquid Precipitation Depth. The weather data is created for two emissions scenarios: RCP4.5 and RCP8.5 and spans two 10-year time slices in the future: 2045 - 2054 and 2085 - 2094. It offers a spatial resolution of 12 km by 12 km with extensive coverage across most of North America. Due to the enormous size of the entire dataset, in the first stage of its distribution, we provide 20 years of future weather data for the centroid of each Public Use Microdata Area (PUMA), excluding Hawaii. PUMAs are non-overlapping, statistical geographic areas that partition each state or equivalent entity into geographic areas containing no fewer than 100,000 people each. The 2,378 PUMAs as a whole cover the entirety of the U.S. The weather data can be utilized alongside the large-scale energy analysis tools, ResStock and ComStock, developed by National Renewable Energy Laboratory, whose smallest resolution is at the PUMA scale. The data for RCP4.5 is still being processed and will be published soon.

Array↗

Full-physics 3D heterogeneous simulations of electromagnetic induction fields on level and deformed sea ice

In this article we explore simulated responses of electromagnetic (EM) signals relative to in situ field surveys and quantify the effects that different values of conductivity in sea ice have on the EM fields. We compute EM responses of ice types with a three-dimensional (3-D) finite-volume discretization of Maxwell's equations and present 2-D sliced visualizations of their associated EM fields at discrete frequencies. Several interesting observations result: First, since the simulator computes the fields everywhere, each gridcell acts as a receiver within the model volume, and captures the complete, coupled interactions between air, snow, sea ice and sea water as a function of their conductivity; second, visualizations demonstrate how 1-D approximations near deformed ice features are violated. But the most important new finding is that changes in conductivity affect EM field response by modifying the magnitude and spatial patterns (i.e. footprint size and shape) of current density and magnetic fields. These effects are demonstrated through a visual feature we define as 'null lines'. Null line shape is affected by changes in conductivity near material boundaries as well as transmitter location. Our results encourage the use of null lines as a planning tool for better ground-truth field measurements near deformed ice types.

58 GEOSCIENCES↗

Towards Fully Secure 5G Ultra-Low Latency Communications: A Cost-Security Functions Analysis

Future components to enhance the basic, native security of 5G networks are either complex mechanisms whose impact in the requiring 5G communications are not considered, or lightweight solutions adapted to ultra-reliable low-latency communications (URLLC) but whose security properties remain under discussion. Although different 5G network slices may have different requirements, in general, both visions seem to fall short at provisioning secure URLLC in the future. In this work we address this challenge, by introducing cost-security functions as a method to evaluate the performance and adequacy of most developed and employed non-native enhanced security mechanisms in 5G networks. We categorize those new security components into different groups according to their purpose and deployment scope. We propose to analyze them in the context of existing 5G architectures using two different approaches. First, using model checking techniques, we will evaluate the probability of an attacker to be successful against each security solution. Second, using analytical models, we will analyze the impact of these security mechanisms in terms of delay, throughput consumption, and reliability. Finally, we will combine both approaches using stochastic cost-security functions and the PRISM model checker to create a global picture. Our results are first evidence of how a 5G network that covers and strengthened all security areas through enhanced, dedicated non-native mechanisms could only guarantee secure URLLC with a probability of ~55%.

5G networks↗

Simulation Assisted Design for an Additively Manufactured Autoclave Tool Accounting for an Anisotropic Expansion

Carbon fiber reinforced polymer composites have been used in Big Area Additive Manufacturing (BAAM) to decrease the distortion during the printing process and increase functional stiffness. These materials are also important for additively manufactured autoclave tooling which expands when exposed to the high temperatures of the operational cycle, causing the dimensions of the mold to differ from the targeted design. Since the reinforcing fibers generally align during the extrusion process, the thermal expansion of the composite along the deposition direction is restrained by fibers, whereas the thermal expansion perpendicular to the bead is largely unconstrained. This leads to an anisotropic expansion of the material that is dependent upon the local deposition path, which may be tortuous and complex. To obtain an accurate final part geometry during the autoclave process, a computational prediction of the thermal expansion of a tool is required to account for the complex extrusion deposition directions. A multi-step approach is presented that accounts for (1) anisotropic thermal expansion of the extruded bead, (2) the complex deposition directions, and (3) internal geometry determined by slicing software. The thermal expansion coefficient in the deposition direction and perpendicular to the deposition direction were measured at multiple locations in the test specimen. A revised model geometry was generated to achieve the target dimensions when accounting for thermal expansion.

Hassen, Ahmed↗

X-ray chemical imaging for assessing redox microsites within soils and sediments

Redox reactions underlie several biogeochemical processes and are typically spatiotemporally heterogeneous in soils and sediments. However, redox heterogeneity has yet to be incorporated into mainstream conceptualizations and modeling of soil biogeochemistry. Anoxic microsites, a defining feature of soil redox heterogeneity, are non-majority oxygen depleted zones in otherwise oxic environments. Neglecting to account for anoxic microsites can generate major uncertainties in quantitative assessments of greenhouse gas emissions, C sequestration, as well as nutrient and contaminant cycling at the ecosystem to global scales. However, only a few studies have observed/characterized anoxic microsites in undisturbed soils, primarily, because soil is opaque and microsites require µm-cm scale resolution over cm-m scales. Consequently, our current understanding of microsite characteristics does not support model parameterization. To resolve this knowledge gap, we demonstrate through this proof-of-concept study that X-ray fluorescence (XRF) 2D mapping can reliably detect, quantify, and provide basic redox characterization of anoxic microsites using solid phase “forensic” evidence. First, we tested and developed a systematic data processing approach to eliminate false positive redox microsites, i.e., artefacts, detected from synchrotron-based multiple-energy XRF 2D mapping of Fe (as a proxy of redox-sensitive elements) in Fe-“rich” sediment cores with artificially injected microsites. Then, spatial distribution of Fe II and Fe III species from full, natural soil core slices (over cm-m lengths/widths) were mapped at 1–100 µm resolution. These investigations revealed direct evidence of anoxic microsites in predominantly oxic soils such as from an oak savanna and toeslope soil of a mountainous watershed, where anaerobicity would typically not be expected. We also revealed preferential spatial distribution of redox microsites inside aggregates from oak savanna soils. We anticipate that this approach will advance our understanding of soil biogeochemistry and help resolve “anomalous” occurrences of reduced products in nominally oxic soils.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Accelerated fission rate irradiation design, pre-irradiation characterization, and adaptation of conventional PIE methods for U-10Mo and U-17Mo

Metallic U alloys have high U density and thermal conductivity and thus have been explored since the beginning of nuclear power research. Alloys of U with modest amounts of Mo, such as U-10 wt % Mo (U-10Mo), are of particular interest because the γ-U crystal structure in this alloying addition shows prolonged stability in reactor service. Historically, radiation data on U-10Mo fuels were collected in Na fast reactors or lower temperature research reactor conditions, but little is known about irradiation behavior, particularly swelling and creep, at irradiation temperatures between 250 and 500°C. This work discusses the methodology and pre-irradiation characterization results from a U-Mo irradiation campaign performed in the High Flux Isotope Reactor at Oak Ridge National Laboratory. U-10Mo and U-17Mo samples irradiations are being completed at temperatures ranging from 250 to 500°C to three targeted fission densities between 2 × 10 20 and 1.5 × 10 21 fissions per cubic centimeter. Swelling measurement of the specimen sizes studied here required development and assessment of new methods for volume determination before and after irradiation. Laser profilometry and X-ray computation tomography (XCT) were used to provide preirradiation characterization of samples to determine the error and applicability of each to determine swelling following irradiation. These outcomes are contextualized through use of BISON simulations performed to assess the predicted expansion of U-Mo fuels subjected to the irradiation conditions of this work. Use of existing BISON fuel performance models predicted a maximum of 7% swelling under the irradiation conditions of this study. Pre-irradiation characterization revealed the as-cast U-Mo fuel samples were uniformly large-grained fully cubic U crystals with small U-C/N bearing precipitates and pores distributed throughout. Samples were found to contain a bulk porosity between .4 and 3% because of the casting process. Local porosity in areas far from large, interconnected pores was found by Slice-and-View to be under .2%. Nanometer-sized precipitates rich in C and N were identified in all samples, likely because of impurities during the fabrication process. Dendritic bands were also observed throughout the samples. These bands were characterized by variable Mo content that deviated from the overall Mo content by 2–3 wt %. No other microstructural features were correlated to these bands. Mechanical properties were found to be slightly strengthened compared to literature reports of bulk U-Mo fuels due to the nano-scale precipitates throughout the sample.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Nitric Oxide Production from Nitrite plus Ascorbate during Ischemia upon Hippocampal Glutamate NMDA Receptor Stimulation

Nitric oxide (•NO), a diffusible free radical, is an intercellular messenger, playing a crucial role in several key brain physiological processes, including in neurovascular coupling (NVC). In the brain, glutamatergic activation of the neuronal nitric oxide synthase (nNOS) enzyme constitutes its main synthesis pathway. However, when oxygen (O2) supply is compromised, such as in stroke, ischemia, and aging, such •NO production pathway may be seriously impaired. In this context, evidence suggests that, as already observed in the gastric compartment, the reduction of nitrite by dietary compounds (such as ascorbate and polyphenols) or by specific enzymes may occur in the brain, constituting an important rescuing or complementary mechanism of •NO production. Here, using microsensors selective for •NO, we show that nitrite enhanced the •NO production in a concentration-dependent manner and in the presence of ascorbate evoked by N-methyl-D-aspartate (NMDA) and glutamate stimulation of rat hippocampal slices. Additionally, nitrite potentiated the •NO production induced by oxygen-glucose deprivation (OGD). Overall, these observations support the notion of a redox interaction of ascorbate with nitrite yielding •NO upon neuronal glutamatergic activation and given the critical role of NO as the direct mediator of neurovascular coupling may represents a key physiological mechanism by which •NO production for cerebral blood flow (CBF) responses to neuronal activation is sustained under hypoxic/acidic conditions in the brain.

Nunes, Carla (ORCID:0000000274521592)↗

Adenosine A2A Receptor Up-Regulation Pre-Dates Deficits of Synaptic Plasticity and of Memory in Mice Exposed to Aβ1–42 to Model Early Alzheimer’s Disease

The intracerebroventricular (icv) injection of amyloid peptides (Aβ) models Alzheimer’s disease (AD) in mice, as typified by the onset within 15 days of deficits of memory and of hippocampal long-term potentiation (LTP) that are prevented by the blockade of adenosine A2A receptors (A2AR). Since A2AR overfunction is sufficient to trigger memory deficits, we tested if A2AR were upregulated in hippocampal synapses before the onset of memory deficits to support the hypothesis that A2AR overfunction could be a trigger of AD. Six to eight days after Aβ-icv injection, mice displayed no alterations of hippocampal dependent memory; however, they presented an increased excitability of hippocampal synapses, a slight increase in LTP magnitude in Schaffer fiber-CA1 pyramid synapses and an increased density of A2AR in hippocampal synapses. A2AR blockade with SCH58261 (50 nM) normalized excitability and LTP in hippocampal slices from mice sacrificed 7–8 days after Aβ-icv injection. Fifteen days after Aβ-icv injection, mice displayed evident deficits of hippocampal-dependent memory deterioration, with reduced hippocampal CA1 LTP but no hyperexcitability and a sustained increase in synaptic A2AR, which blockade restored LTP magnitude. This shows that the upregulation of synaptic A2AR precedes the onset of deterioration of memory and of hippocampal synaptic plasticity, supporting the hypothesis that the overfunction of synaptic A2AR could be a trigger of memory deterioration in AD.

Lopes, Cátia R.↗

Shaping Micro-Bunched Electron Beams for Compact X-ray Free-Electron Lasers with Transverse Gradient Undulators

Laser-modulator-based micro-bunching of electron beams has been applied to many novel operating modes of X-ray free-electron lasers from harmonic generation to attosecond pulse production. Recently, it was also identified as a key enabling technology for the production of a compact XFEL driven by a relatively low-energy beam. In traditional laser modulator schemes with low-energy and high-current bunches, collective effects limit the possible working points that can be employed, and thus it is difficult to achieve optimal XFEL performance. We propose to utilize transverse longitudinal coupling in a transverse gradient undulator (TGU) to shape micro-bunched electron beams so as to optimize their performance in a compact X-ray free-electron laser. We show that a TGU added to a conventional laser modulator stage enables much more flexibility in the design, allowing one to generate longer micro-bunches less subject to slippage effects and even lower the slice emittance of the micro-bunches. We present a theoretical analysis of laser-based micro-bunching with an added TGU, simulation of compression with collective effects in such systems, and finally XFEL simulations demonstrating the gains in peak power enabled by the TGU. Although we focus on the application to compact XFELs, what we propose is a general phase space manipulation that may find utility in other applications as well.

eSASE↗

Predicting Mechanical Properties from Microstructure Images in Fiber-Reinforced Polymers Using Convolutional Neural Networks

Evaluating the mechanical response of fiber-reinforced composites can be extremely time-consuming and expensive. Machine learning (ML) techniques offer a means for faster predictions via models trained on existing input–output pairs and have exhibited success in composite research. This paper explores a fully convolutional neural network modified from StressNet, which was originally used for linear elastic materials, and extended here for a non-linear finite element (FE) simulation to predict the stress field in 2D slices of segmented tomography images of a fiber-reinforced polymer specimen. The network was trained and evaluated on data generated from the FE simulations of the exact microstructure. The testing results show that the trained network accurately captures the characteristics of the stress distribution, especially on fibers, solely from the segmented microstructure images. The trained model can make predictions within seconds in a single forward pass on an ordinary laptop, given the input microstructure, compared to 92.5 h to run the full FE simulation on a high-performance computing cluster. These results show promise in using ML techniques to conduct fast structural analysis for fiber-reinforced composites and suggest a corollary that the trained model can be used to identify the location of potential damage sites in fiber-reinforced polymers.

Sun, Yixuan (ORCID:0000000311093380)↗