Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “parameter sampling”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Use of Graph Theory and Neural Networks for Microstructural Classification

Recent advances in materials data analytics have provided new avenues for determining process-structure-property (PSP) linkages in a variety of materials. Machine learning techniques including few-shot learning have increased the efficiency of classifying microscopy images for the purposes of material characterization. Modifications in segmentation also show potential in improving the accuracy of our current pyCHIP classifier. Replacing previous encoders trained on ImageNet with those trained on microscopy images like MicroNet has initially shown better performance at classifying images of irradiated samples. Additionally, different normalization approaches were tested to show no discernable effect on classification. The Louvain method for community detection is analyzed on a set of irradiated samples with different parameters to determine which proved beneficial under what circumstances. We suggest that microscopy experiments be automated in the future using a combination of these techniques to enable high-throughput analyses.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Toward Accelerated Nuclear-physics Parameter Estimation from Binary Neutron Star Mergers: Emulators for the Tolman–Oppenheimer–Volkoff Equations

Abstract Gravitational-wave observations of binary neutron-star (BNS) mergers have the potential to revolutionize our understanding of the nuclear equation of state (EOS) and the fundamental interactions that determine its properties. However, Bayesian parameter estimation frameworks do not typically sample over microscopic nuclear-physics parameters that determine the EOS. One of the major hurdles in doing so is the computational cost involved in solving the neutron-star structure equations, known as the Tolman–Oppenheimer–Volkoff (TOV) equations. In this paper, we explore approaches to emulating solutions for the TOV equations: multilayer perceptrons (MLPs), Gaussian processes, and a data-driven variant of the reduced basis method (RBM). We implement these emulators for three different parameterizations of the nuclear EOS, each with a different degree of complexity represented by the number of model parameters. We find that our MLP-based emulators are generally more accurate than the other two algorithms, whereas the RBM results in the largest speedup with respect to the full high-fidelity TOV solver. We employ these emulators for a simple parameter inference using a potentially loud BNS observation and show that the posteriors predicted by our emulators are in excellent agreement with those obtained from the full TOV solver.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Predicting Solar Energetic Particles Using SDO/HMI Vector Magnetic Data Products and a Bidirectional LSTM Network

Solar energetic particles (SEPs) are an essential source of space radiation, and are hazardous for humans in space, spacecraft, and technology in general. In this paper, we propose a deep-learning method, specifically a bidirectional long short-term memory (biLSTM) network, to predict if an active region (AR) would produce an SEP event given that (i) the AR will produce an M- or X-class flare and a coronal mass ejection (CME) associated with the flare, or (ii) the AR will produce an M- or X-class flare regardless of whether or not the flare is associated with a CME. The data samples used in this study are collected from the Geostationary Operational Environmental Satellite's X-ray flare catalogs provided by the National Centers for Environmental Information. We select M- and X-class flares with identified ARs in the catalogs for the period between 2010 and 2021, and find the associations of flares, CMEs, and SEPs in the Space Weather Database of Notifications, Knowledge, Information during the same period. Each data sample contains physical parameters collected from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory. Experimental results based on different performance metrics demonstrate that the proposed biLSTM network is better than related machine-learning algorithms for the two SEP prediction tasks studied here. We also discuss extensions of our approach for probabilistic forecasting and calibration with empirical evaluation

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Determining Stellar Elemental Abundances from DESI Spectra with the Data-driven Payne

Abstract Stellar abundances for a large number of stars provide key information for the study of Galactic formation history. Large spectroscopic surveys such as the Dark Energy Spectroscopic Instrument (DESI) and LAMOST take median-to-low-resolution (R≲ 5000) spectra in the full optical wavelength range for millions of stars. However, the line-blending effect in these spectra causes great challenges for elemental abundance determination. Here we employDD-Payne, a data-driven method regularized by differential spectra from stellar physical models, to the DESI early data release spectra for stellar abundance determination. Our implementation delivers 15 labels, including effective temperatureT eff , surface gravity log g , microturbulence velocityv mic , and the abundances for 12 individual elements, namely C, N, O, Mg, Al, Si, Ca, Ti, Cr, Mn, Fe, and Ni. Given a spectral signal-to-noise ratio of 100 per pixel, the internal precisions of the label estimates are about 20 K forT eff , 0.05 dex for log g , and 0.05 dex for most elemental abundances. These results agree with the theoretical limits from the Crámer–Rao bound calculation within a factor of 2. The majority of the accreted halo stars contributed by the Gaia–Enceladus–Sausage are discernible from the disk and in situ halo populations in the resultant [Mg/Fe]–[Fe/H] and [Al/Fe]–[Fe/H] abundance spaces. We also provide distance and orbital parameters for the sample stars, which spread over a distance out to ∼100 kpc. The DESI sample has a significantly higher fraction of distant (or metal-poor) stars than the other existing spectroscopic surveys, making it a powerful data set for studying the Galactic outskirts. The catalog is publicly available.

Astronomy & Astrophysics↗
DOE OSTI2021

Do LIGO/Virgo Black Hole Mergers Produce AGN Flares? The Case of GW190521 and Prospects for Reaching a Confident Association

The recent report of an association of the gravitational-wave (GW) binary black hole (BBH) merger GW190521 with a flare in the active galactic nuclei (AGNs) J124942.3 + 344929 has generated tremendous excitement. However, GW190521 has one of the largest localization volumes among all of the GW events detected so far. The 90% localization volume likely contains 7400 unobscured AGNs brighter than g ≤ 20.5 AB mag, and it results in a ≳70% probability of chance coincidence for an AGN flare consistent with the GW event. We present a Bayesian formalism to estimate the confidence of an AGN association by analyzing a population of BBH events with dedicated follow-up observations. Depending on the fraction of BBHs arising from AGNs, counterpart searches of $\mathcal{O}(1) - \mathcal{O}(100)$ GW events are needed to establish a confident association, and more than an order of magnitude more for searches without follow-up (i.e., using only the locations of AGN and GW events). Follow-up campaigns of the top ~5% (based on volume localization and binary mass) of BBH events with total rest-frame mass ≥50 M ⊙ are expected to establish a confident association during the next LIGO/Virgo/KAGRA observing run (O4), as long as the true value of the fraction of BBHs giving rise to AGN flares is >0.1. Our formalism allows us to jointly infer cosmological parameters from a sample of BBH events that include chance coincidence flares. Until the confidence of AGN associations is established, the probability of chance coincidence must be taken into account to avoid biasing astrophysical and cosmological constraints.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

New Materials and an Efficient Processing Approach for Materials for Harsh Environments – Continuous Electric Field Assisted Sintering

Electric-field assisted sintering (EFAS) is an advanced manufacturing method for the consolidation and processing of ceramic and metal materials. It is a particularly excellent candidate for efficient materials processing as it has greater than 90% energy cost savings and improved CO2 emissions compared to traditional sintering in a furnace. This is due to direct rapid heating of the materials and molds leveraging an electrification phenomenon called Joule heating where electrical current is passed through the sample/mold assemblies causing direct heating. The technique does have limitations though as it is traditionally a batch-process and suffers from scale up difficulties. To overcome this, researchers at Idaho National Laboratory changed the form factor of traditional EFAS instruments to develop and construct a continuous rolling electric-field assisted sintering (CEFAS) device. Its unique design creates highly localized electrical, thermal, and mechanical process parameters for continuous samples of limitless length. Advanced core shell powder materials were also created using fluidized powder bed atomic layer deposition of core/shell solid oxide electrochemical electrode/electrolyte BaCe0.7Zr0.1Y0.1Yb0.1O3 (BCZYYb) and yttrium doped BaZrO3 (BZY) to be a feedstock for the new CEFAS instrument. The innovative core/shell powder is hypothesized to have high protonic conductivity with enhanced environmental resistance. The completed project covers innovations in process control and design enabled by control theory, finite element modeling and mechanical design, three dimensionally printed carbon-carbon composite manufacturing and utilization, and green materials processing techniques.

36 MATERIALS SCIENCE↗
DOE OSTI2025

A machine-learning approach to measure 3D sample properties from 2D Transmission Electron Microscopy images

Transmission Electron Microscopy (TEM) is a powerful tool for the characterization of materials at the nanoscale; however, its inherent two-dimensional (2D) nature poses significant challenges to accurately measure three-dimensional (3D) properties. We introduce a supervised machine-learning model that predicts 3D structural information, such as sample thickness and curvature, from a series of conventional 2D TEM images. The model, a U-Net convolutional neural network, is trained on a large synthetic dataset generated from dynamical diffraction simulations that model TEM’s complex, nonlinear image formation, accounting for sample thickness and curvature. This physically realistic framework enables exploration of a broad parameter space impractical to sample experimentally. We demonstrate that the trained model has accurate predictions for experimental single-crystal silicon samples, achieving performance comparable to established measurement techniques. This work highlights the critical role of robust, simulation-based training in overcoming the limitations of real-world imaging artifacts and inconsistent sample geometries. By integrating machine learning with numerical simulations, we offer an efficient and scalable framework for quantitative TEM analysis, paving the way for more sophisticated 3D characterization of complex materials.

Dynamical diffraction↗
DOE OSTI2023

BeyondPlanck: VII. Bayesian estimation of gain and absolute calibration for cosmic microwave background experiments

We present a Bayesian calibration algorithm for cosmic microwave background (CMB) observations as implemented within the global end-to-end BEYONDPLANCK framework and applied to the Planck Low Frequency Instrument (LFI) data. Following the most recent Planck analysis, we decomposed the full time-dependent gain into a sum of three nearly orthogonal components: one absolute calibration term, common to all detectors, one time-independent term that can vary between detectors, and one time-dependent component that was allowed to vary between one-hour pointing periods. Each term was then sampled conditionally on all other parameters in the global signal model through Gibbs sampling. The absolute calibration is sampled using only the orbital dipole as a reference source, while the two relative gain components were sampled using the full sky signal, including the orbital and Solar CMB dipoles, CMB fluctuations, and foreground contributions. We discuss various aspects of the data that influence gain estimation, including the dipole-polarization quadrupole degeneracy and processing masks. Comparing our solution to previous pipelines, we find good agreement in general, with relative deviations of -0.67% (-0.84%) for 30 GHz, 0.12% (-0.04%) for 44 GHz and -0.03% (-0.64%) for 70 GHz, compared to Planck PR4 and Planck 2018, respectively. We note that the BEYONDPLANCK calibration was performed globally, which results in better inter-frequency consistency than previous estimates. Additionally, WMAP observations were used actively in the BEYONDPLANCK analysis, which both breaks internal degeneracies in the Planck data set and results in an overall better agreement with WMAP. Finally, we used a Wiener filtering approach to smoothing the gain estimates. We show that this method avoids artifacts in the correlated noise maps as a result of oversmoothing the gain solution, which is difficult to avoid with methods like boxcar smoothing, as Wiener filtering by construction maintains a balance between data fidelity and prior knowledge. Although our presentation and algorithm are currently oriented toward LFI processing, the general procedure is fully generalizable to other experiments, as long as the Solar dipole signal is available to be used for calibration.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Cold Spray Technology Applications for SRF Cavity Thermal and Mechanical Stabilization

The overall objective of the project is the development of a method allowing increased thermal and mechanical stabilization of SRF cavities by depositing a thick layer on the outer surface by cold-spray. Coating and testing of bi-metallic Nb/Cu and Nb/CuW samples were carried out to optimize the process parameters. The process developed on samples was applied to a single cell SRF cavity for proof-of-principle demonstration of improved thermal and mechanical stability.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Enhanced Monte Carlo Simulations for Electron Energy Loss Mitigation in Real-Space Nanoimaging of Thick Biological Samples and Microchips

High-resolution imaging using Transmission Electron Microscopy (TEM) is essential for applications such as grain boundary analysis, microchip defect characterization, and biological imaging. However, TEM images are often compromised by electron energy spread and other factors. In TEM mode, where the objective and projector lenses are positioned downstream of the sample, electron–sample interactions cause energy loss, which adversely impacts image quality and resolution. This study introduces a simulation tool to estimate the electron energy loss spectrum (EELS) as a function of sample thickness, covering electron beam energies from 300 keV to 3 MeV. Leveraging recent advances in MeV-TEM/STEM technology, which includes a state-of-the-art electron source with 2-picometer emittance, an energy spread of 3 × 10 -5 , and optimized beam characteristics, we aim to minimize energy spread. By integrating EELS capabilities into the BNL Monte Carlo (MC) simulation code for thicker samples, we evaluate electron beam parameters to mitigate energy spread resulting from electron–sample interactions. Based on our simulations, we propose an experimental procedure for quantitively distinguishing between elastic and inelastic scattering. The findings will guide the selection of optimal beam settings, thereby enhancing resolution for nanoimaging of thick biological samples and microchips.

36 MATERIALS SCIENCE↗
DOE OSTI2023

The Dark Energy Survey Year 3 and eBOSS: constraining galaxy intrinsic alignments across luminosity and colour space

ABSTRACT We present direct constraints on galaxy intrinsic alignments (IAs) using the Dark Energy Survey Year 3 (DES Y3), the Extended Baryon Oscillation Spectroscopic Survey (eBOSS), and its precursor, the Baryon Oscillation Spectroscopic Survey (BOSS). Our measurements incorporate photometric red sequence (redMaGiC) galaxies from DES with median redshift z ∼ 0.2–1.0, luminous red galaxies from eBOSS at z ∼ 0.8, and also an SDSS-III BOSS CMASS sample at z ∼ 0.5. We measure two-point IA correlations, which we fit using a model that includes lensing, magnification, and photometric redshift error. Fitting on scales 6 Mpc h−1 < rp < 70 Mpc h−1, we make a detection of IAs in each sample, at 5σ–22σ (assuming a simple one-parameter model for IAs). Using these red samples, we measure the IA–luminosity relation. Our results are statistically consistent with previous results, but offer a significant improvement in constraining power, particularly at low luminosity. With this improved precision, we see detectable dependence on colour between broadly defined red samples. It is likely that a more sophisticated approach than a binary red/blue split, which jointly considers colour and luminosity dependence in the IA signal, will be needed in future. We also compare the various signal components at the best-fitting point in parameter space for each sample, and find that magnification and lensing contribute $\sim 2\!-\!18~{{\ \rm per\ cent}}$ of the total signal. As precision continues to improve, it will certainly be necessary to account for these effects in future direct IA measurements. Finally, we make equivalent measurements on a sample of emission-line galaxies from eBOSS at z ∼ 0.8. We constrain the non-linear alignment amplitude to be $A_1=0.07^{+0.32}_{-0.42}$ (|A1| < 0.78 at 95 per cent CL).

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

High-Field One-Dimensional and Two-Dimensional 27Al Magic-Angle Spinning Nuclear Magnetic Resonance Study of ?-, d-, and ?-Al2O3 Dominated Aluminum Oxides: Toward Understanding the Al Sites in ?-Al2O3

Herein, a detailed analysis was carried out using high-field (19.9 T) 27Al magic-angle spinning (MAS) nuclear magnetic resonance (NMR) on three specially prepared aluminum oxide samples where the ?-, d-, and ?-Al2O3 phases are dominantly expressed through careful control of the synthesis conditions. Specifically, two-dimensional (2D) multiquantum (MQ) MAS 27Al was used to obtain high spectral resolution, which provided a guide for analyzing quantitative 1D 27Al NMR spectra. Six aluminum sites were resolved in the 2D MQ MAS NMR spectra, and seven aluminum sites were required to fit the 1D spectra. A set of octahedral and tetrahedral peaks with well-defined quadrupolar line shapes was observed in the ?-phase dominant sample and was unambiguously assigned to the ?-Al2O3 phase. The distinct line shapes related to the ?-Al2O3 phase provided an opportunity for effectively deconvoluting the more complex spectrum obtained from the d-Al2O3 dominant sample, allowing the peaks/quadrupolar parameters related to the d-Al2O3 phase to be extracted. The results show that the d-Al2O3 phase contains three distinct AlO sites and three distinct AlT sites. This detailed Al site structural information offers a powerful way of analyzing the most complex ?-Al2O3 spectrum. It is found that the ?-Al2O3 phase consists of Al sites with local structures similar to those found in the d-Al2O3 and ?-Al2O3 phases albeit with less ordering. Spin–lattice relaxation time measurement further confirms the disordering of the lattice. Collectively, this study uniquely assigns 27Al features in transition aluminas, offering a simplified method to quantify complex mixtures of aluminum sites in transition alumina samples.

Xu, Suochang↗
DOE OSTI2021

Application of machine learning in the determination of impact parameter in the 132 Sn+ 124 Sn system

Here, 132 Sn + 124 Sn collisions at a beam energy of 270 MeV/nucleon were performed at the Radioactive Isotope Beam Factory (RIBF) in RIKEN to investigate the nuclear equation of state. Reconstructing the impact parameter is one of the important tasks in the experiment as it relates to many observable. In this work, we employ three commonly used algorithms in machine learning, the artificial neural network (ANN), the convolutional neural network (CNN), and the light gradient boosting machine (LightGBM), to determine the impact parameter by analyzing either the charged particle spectra or several features simulated with events from the ultrarelativistic quantum molecular dynamics (UrQMD) model. To closely imitate experimental data and investigate the generalizability of the trained machine learning algorithms, incompressibility of nuclear equation of state and the in-medium nucleon-nucleon cross sections are varied in the UrQMD model to generate the training data. The mean absolute error Δb between the true and the predicted impact parameter is smaller than 0.45 fm if training and testing sets are sampled from the UrQMD model with the same parameter set. However, if training and testing sets are sampled with different parameter sets, Δb would increase to 0.8 fm. The generalizability of the trained machine learning algorithms suggests that these machine learning algorithms can be used reliably to reconstruct the impact parameter in experiment.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

MultiPEM Toolbox: User Manual [Rev. 2]

This document explains use of the Multi-Phenomenology Explosion Monitoring (Multi PEM) Toolbox, a collection of R scripts for estimating the unknown device parameters of a new event with uncertainty quantification. The methodology and application used for illustration in this user manual are fully documented in a Los Alamos National Laboratory technical report hereafter designated “WPA” for reference. Additional details on the application are found in a recent journal article. Two assessment types are available: rapid and complete. Rapid assessments are conducted in two stages, as described in Section 2. In the first stage, calibration data are used to estimate forward and error model parameters (WPA, §5.1) and (if relevant) errors-in-variables yield values for calibration sources (WPA, §3, Equation (3)). In the second stage, new event data are used to estimate the unknown new event device parameters (WPA, §5.2) with uncertainty quantification. Two options for treating the inferred first stage parameters in second stage Bayesian analysis are available: fixing them at their maximum likelihood estimate (default), or multiple imputation. Multiple imputation involves utilizing several posterior samples (imputations) of the first stage parameters as fixed values in the second stage posterior sampling of the new event device parameters. Second stage sampling is conducted across imputations in parallel to improve computational efficiency. This method produces improved uncertainty quantification of the new event device parameters compared with the default treatment of the first stage parameters, at the expense of additional computation. Complete assessments are conducted in a single stage, as described in Section 3. Calibration and (if relevant) new event data are used simultaneously to estimate all forward model, error model, and (if relevant) new event device parameters with uncertainty quantification on the latter. As the name suggests, rapid assessments generally run substantially faster than complete assessments (even with multiple imputation), because the results of first stage analysis can be stored and incorporated into estimating a relatively low-dimensional space of new event device parameters whenever relevant new event data becomes available. On the other hand, complete assessments must be run on the full set of model and device parameters with calibration and new event data every time the latter becomes available.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Characterization of multi-material 316L-Hastelloy X fabricated via laser powder-bed fusion

The aim of this work is to provide firsthand knowledge of 316 L stainless steel (316 L) and Hastelloy X (HX) multi-material processing via laser powder bed fusion (PBF). Specifically, microstructure of the interface is studied using scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS), and X-ray diffraction (XRD). Surface metrology is performed to characterize the resulting surface roughness at the interface followed by tensile and flexural testing of multi-material samples to characterize the mechanical properties of the interfaces. Results showed that use of proper process parameters for each individual material led to formation of a compositional gradient at the interface that stretched for 240 μm (10–12 layers) with no evidence of cracking or porosity. The interface exhibited higher surface roughness compared to 316 L or HX as measured by arithmetic mean height, Sa, and maximum valley depth, Sv, parameters. During tensile testing, samples failed in the 316 L region away from the interface, with comparable yield strength, ultimate strength, and ductility. Finally, it was concluded that the “naturally” formed interface created a compositional gradient which was defect free due to similar values of coefficient of thermal expansion, input energy density, and different Marangoni numbers of the materials.

316L stainless Steel↗
DOE OSTI2021

The Impala's horn applied to posterior samples of Ti-6Al-4V strength model parameters

We have generated strength model parameters for the Preston-Tonks-Wallace (PTW) model of plastic deformation based on a collection of Ti-6Al-4V alloy data and a Bayesian framework. This data collected from the literature includes different chemistries and processes. The experiments include quasistatic compression, Split Hopkinson Pressure Bar (SHPB) compression, and Taylor cylinders. Here we use posterior parameter distributions applied to a hypothetical impact referred to as the Impala's horn. The Impala's horn is like a Taylor cylinder, but modified to have a conical pro le that is truncated before coming to a point. The smaller diameter at the impact end results in higher calculated strain rates and strains than the same velocity impact with the traditional Taylor profile. The modified geometry exercises the behavior of the strength model outside the range of conditions found in the calibration data. Here we sort posterior strength models based on their flow stress at characteristic values for this hypothetical deformation. Then we compare the performance of these posterior models based on two simple observable final state properties of the Impala's horn.

36 MATERIALS SCIENCE↗
DOE OSTI2025

What more can be done with XPS? Highly informative but underused approaches to XPS data collection and analysis

Because of the importance of surfaces and interfaces in many scientific and technological areas, the use of x-ray photoelectron spectroscopy (XPS) has been growing exponentially. Although XPS is being used to obtain useful information about the surface composition of samples, much more information about materials and their properties can be extracted from XPS data than commonly obtained. This paper describes some of the areas where alternative analysis methods or experimental design can obtain information about the near-surface region of a sample, often information not available in other ways. Experienced XPS analysts are familiar with many of these methods, but they may not be known to new or casual XPS users, and sometimes, they have not been used because of an inappropriately assumed complexity. The information available includes optical, electronic, and electrical properties; nanostructure; expanded chemical information; and enhanced analysis of biological materials and solid/liquid interfaces. Many of these analyses can be conducted on standard laboratory XPS systems, with either no or relatively minor system alterations. Topics discussed include (1) considerations beyond the “traditional” uniform surface layer composition calculation, (2) using the Auger parameter to determine a sample property, (3) use of the D parameter to identify sp 2 and sp 3 carbon information, (4) information from the XPS valence band, (5) using cryocooling to expand range of samples that can be analyzed and minimize damage, and (6) using electrical potential effects on XPS signals to extract chemically resolved electrical measurements including band alignment and electrical property information.

Baer, Donald R. [Pacific Northwest National Labora↗
DOE OSTI2022

Deep Learning for In-Situ Layer Quality Monitoring during Laser-Based Directed Energy Deposition (LB-DED) Additive Manufacturing Process

Defects are a leading issue for the rejection of parts manufactured through the Directed Energy Deposition (DED) Additive Manufacturing (AM) process. In an attempt to illuminate and advance in situ quality monitoring and control of workpieces, we present an innovative data-driven method that synchronously collects sensing data and AM process parameters with a low sampling rate during the DED process. The proposed data-driven technique determines the important influences that individual printing parameters and sensing features have on prediction at the inter-layer qualification to perform feature selection. Three Machine Learning (ML) algorithms including Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) are used. During post-production, a threshold is applied to detect low-density occurrences such as porosity sizes and quantities from CT scans that render individual layers acceptable or unacceptable. This information is fed to the ML models for training. Training/testing are completed offline on samples deemed “high-quality” and “low-quality”, utilizing only features recorded from the build process. CNN results show that the classification of acceptable/unacceptable layers can reach between 90% accuracy while training/testing on a “high-quality” sample and dip to 65% accuracy when trained/tested on “low-quality”/“high-quality” (respectively), indicating over-fitting but showing CNN as a promising inter-layer classifier.

36 MATERIALS SCIENCE↗