Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “feature reduction”

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 811 records · Page 45
All sourcesNASA NTRSDOE OSTI
DOE OSTI2017

Extreme Scale Unstructured Adaptive CFD: From Multiphase Flow to Aerodynamic Flow Control

Understanding the flow of fluid, either liquid or gas, through and around solid bodies has challenged man since the dawn of scientific inquiry. Many of the great minds of science and math have progressively built up a hierarchy of fluid models. This report is concerned with the computational modeling of turbulent flow around aerodynamic bodies such as planes and wind turbines. In this case, viscous effects near the solid bodies create very thin boundary layers that yield highly anisotropic (gradients normal to the surface may be 10^6 times larger than gradients along the surface) solutions to the governing non-linear partial differential equations (PDE); the Navier-Stokes equations. Furthermore, turbulent flows develop extremely broad ranges of length and time scales.This disparity motivates the use of discretization methods capable of employing adaptivity and implicit time integration. The combination of these features (non-linear, anisotropy, adaptivity, andimplicit) dramatically raise the complexity of the discretization, posing large challenges to efficient scalable parallel implementation. However, through careful design, the more complex algorithms can provide great reductions in computational cost relative to simpler methods (e.g., Cartesian grids with explicit time integration) that are easier to mate efficiently to hardware. In this report, we not only describe our approach but we also address the fact that while complex algorithms may never be as efficient flop-for-flop as simple methods, in the important measure of science-per-core-hour, they can still win big by making complex features like adaptivity and implicit methods as efficient and scalable as possible.

42 ENGINEERING↗
NASA NTRS1997

Altered astronaut lower limb and mass center kinematics in downward jumping following space flight

Astronauts exposed to the microgravity conditions encountered during space flight exhibit postural and gait instabilities upon return to earth that could impair critical postflight performance. The aim of the present study was to determine the effects of microgravity exposure on astronauts' performance of two-footed jump landings. Nine astronauts from several Space Shuttle missions were tested both preflight and postflight with a series of voluntary, two-footed downward hops from a 30-cm-high step. A video-based, three-dimensional motion-analysis system permitted calculation of body segment positions and joint angular displacements. Phase-plane plots of knee, hip, and ankle angular velocities compared with the corresponding joint angles were used to describe the lower limb kinematics during jump landings. The position of the whole-body center of mass (COM) was also estimated in the sagittal plane using an eight-segment body model. Four of nine subjects exhibited expanded phase-plane portraits postflight, with significant increases in peak joint flexion angles and flexion rates following space flight. In contrast, two subjects showed significant contractions of their phase-plane portraits postflight and three subjects showed insignificant overall changes after space flight. Analysis of the vertical COM motion generally supported the joint angle results. Subjects with expanded joint angle phase-plane portraits postflight exhibited larger downward deviations of the COM and longer times from impact to peak deflection, as well as lower upward recovery velocities. Subjects with postflight joint angle phase-plane contraction demonstrated opposite effects in the COM motion. The joint kinematics results indicated the existence of two contrasting response modes due to microgravity exposure. Most subjects exhibited "compliant" impact absorption postflight, consistent with decreased limb stiffness and damping, and a reduction in the bandwidth of the postural control system. Fewer subjects showed "stiff" behavior after space flight, where contractions in the phase-plane portraits pointed to an increase in control bandwidth. The changes appeared to result from adaptive modifications in the control of lower limb impedance. A simple 2nd-order model of the vertical COM motion indicated that changes in the effective vertical stiffness of the legs can predict key features of the postflight performance. Compliant responses may reflect inflight adaptation due to altered demands on the postural control system in microgravity, while stiff behavior may result from overcompensation postflight for the presumed reduction in limb stiffness inflight.

Clinical Trial↗
DOE OSTI2023

Spatiotemporally Adaptive Compression for Scientific Dataset with Feature Preservation – A Case Study on Simulation Data with Extreme Climate Events Analysis

Scientific discoveries are increasingly constrained by limited storage space and I/O capacities. For time-series simulations and experiments, their data often need to be decimated over timesteps to accommodate storage and I/O limitations. In this paper, we propose a technique that addresses storage costs while improving post-analysis accuracy through spatiotemporal adaptive, error-controlled lossy compression. We investigate the trade-off between data precision and temporal output rates, revealing that reducing data precision and increasing timestep frequency lead to more accurate analysis outcomes. Additionally, we integrate spatiotemporal feature detection with data compression and demonstrate that performing adaptive error-bounded compression in higher dimensional space enables greater compression ratios, leveraging the error propagation theory of a transformation-based compressor. To evaluate our approach, we conduct experiments using the well-known E3SM climate simulation code and apply our method to compress variables used for cyclone tracking. Our results show a significant reduction in storage size while enhancing the quality of cyclone tracking analysis, both quantitatively and qualitatively, in comparison to the prevalent timestep decimation approach. Compared to three state-of-the-art lossy compressors lacking feature preservation capabilities, our adaptive compression framework improves perfectly matched cases in TC tracking by 26.4-51.3% at medium compression ratios and by 77.3-571.1% at large compression ratios, with a merely 5–11% computational overhead.

Gong, Qian↗
DOE OSTI2023

TGA Study of the Reaction Kinetics of a CuFeMnAlO 4+δ Oxygen Carrier for Methane Chemical Looping Combustion under High Pressure and Atmospheric Pressure Conditions

Reduction and oxidation kinetics of a CuFeMnAlO 4+δ oxygen carrier for methane were studied using an atmospheric thermogravimetric analyzer (TGA) and a pressurized TGA. Important parameters such as temperature (500–900 °C), particle size distribution (150–650 μm), and partial pressures of reactants (methane and oxygen) were evaluated. Results showed that the reduction of the oxygen carrier was not affected by particle size distribution studied in this work, and that above 750 °C, the effect of the temperature on oxygen carrier reduction started to diminish. The reaction time approaches an asymptotic limit as methane partial pressure increases. For oxygen carrier oxidation, it was found that the rate of oxidation increased with increasing oxygen concentration. The effect of the oxygen concentration was more noticeable when the oxygen concentration was below 7.5%. Because of the inherent feature of the oxygen carrier, its chemical looping with oxygen uncoupling property was also assessed. A phase boundary-controlled shrinking sphere model was used to model the test data from the TGAs. Modeling results showed that the oxygen carrier reduction had a reaction order of 1 with an activation energy of ∼46 kJ/mol. Oxygen carrier oxidation demonstrated a reaction order of 1.1 with an activation energy of ∼55 kJ/mol. Additionally, the differences of the experimental results between the atmospheric pressure TGA and the pressurized TGA were discussed in detail and the limitations of the pressurized TGA were highlighted.

Hydrocarbons↗
NASA NTRS2011

Advanced Technology Subsonic Transport Study: N+3 Technologies and Design Concepts

Conceptual Research Corporation, the Science of the Possible, has completed a two-year study of concepts and technologies for future airliners in the 180-passenger class. This NASA-funded contract was primarily focused on the ambitious goal of a 70 percent reduction in fuel consumption versus the market-dominating Boeing 737-800. The study is related to the N+3 contracts awarded in 2008 by NASA s Aeronautics Research Mission Directorate to teams led by Boeing, GE Aviation, MIT, and Northrop Grumman, but with more modest goals and funding. CRC s contract featured a predominant emphasis on propulsion and fuel consumption, but since fuel consumption depends upon air vehicle design as much as on propulsion technology, the study included notional vehicle design, analysis, and parametric studies. Other NASA goals including NOx and noise reduction are of long-standing interest but were not highlighted in this study, other than their inclusion in the propulsion system provided to CRC by NASA. The B-737-800 was used as a benchmark, parametric tool, and design point of departure. It was modeled in the RDS-Professional aircraft design software then subjected to extensive parametric variations of parasitic drag, drag-due-to-lift, specific fuel consumption, and unsized empty weight. These studies indicated that the goal of a 70 percent reduction in fuel consumption could be attained with roughly a 30 percent improvement in all four parameters. The results were then fit to a Response Surface and coded for ease of use in subsequent trade studies. Potential technologies to obtain such savings were identified and discussed. More than 16 advanced concept designs were then prepared, attempting to investigate almost every possible emerging concept for application to this class airliner. A preliminary assessment of these concepts was done based on their total wetted area after design normalization of trimmed maximum lift. This assessment points towards a Tailless Airliner concept which was designed and analyzed in some detail. To make it work, a retracting canard and an all-moving chin rudder were employed, along with the use of the Active Aeroelastic Wing technology. Results indicate that a 60 percent savings in fuel burn may be credibly attained, but this depends upon a lot of technology maturation, concept development, and risk reduction. This should be expected-such a dramatic reduction in fuel consumption is a "game changer" in the world of commercial aviation. It won t be easy.

Raymer, Daniel P.↗
DOE OSTI2022

A Realistic Theory of Quantum Measurement

Abstract We propose that the ontic understanding of quantum mechanics can be extended to a fully realistic theory that describes the evolution of the wavefunction at all times, including during a measurement. In such an approach the wave equation should reduce to the standard wave equation when there is no measurement, and describe state reduction when the system is measured. The general wave equation must be nonlinear and nonlocal, and we require it to be time-symmetric; consequently, this approach is not a new interpretation but a new theory. The wave equation is an integrodifferential equation (IDE). The time symmetry requirement leads to a retrocausal approach, in which the wave equation is solved subject to initial and final conditions to determine history at intermediate times. We propose that different outcomes from (apparently) identically prepared experiments may result from uncontrolled parameters; both the nonlocality and the retrocausality of the theory imply that Bell’s Theorem cannot rule out such “hidden variables.” Beginning with Hamilton’s principle, we demonstrate the construction of such a theory by replacing the action with a functional designed to give rise to a nonlinear, nonlocal IDE as the wave equation. This IDE reduces to the standard wave equation (a differential equation) in the absence of a measurement, but exhibits state reduction to a single eigenvalue when the system interacts with another system with the properties of a measurement apparatus. We demonstrate several desirable features of this theory; for other properties we indicate their plausibility and possible avenues to a proof.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Multiscale Characterization of Additive Manufacturing Components with Computed Tomography, 3D X-ray Microscopy, and Deep Learning

Additive manufacturing (AM) facilitates the creation of complex-geometry parts, driving advancements in lightweight aerospace components, high-efficiency engine cooling channels, and customized medical implants. However, ensuring the quality and reliability of AM parts remains challenging due to internal defects, surface irregularities, porosity, and residual trapped powder, which are often inaccessible to traditional inspection methods. Recent developments in X-ray computed tomography (XCT) and 3D X-ray microscopy (XRM), particularly systems equipped with resolution-at-a-distance (RaaD™) capabilities, enable high-resolution, non-destructive evaluation of AM components across multiple scales, from sub-micrometer to macroscopic levels. This paper explores modern XCT and XRM techniques for multiscale characterization of AM parts, focusing on their ability to detect and analyze defects such as porosity, cracks, inclusions, and surface roughness, while offering insights into defect formation mechanisms, material properties, and process-induced variations. The integration of deep learning (DL) frameworks, including Simurgh, DeepRecon, and DeepScout, enhances XCT/XRM workflows by reducing scan times, improving resolution recovery, and enabling accurate defect detection even with limited projection data. These DL-based methods overcome limitations of traditional reconstruction techniques, enabling faster, more reliable characterization of dense materials like Inconel 718 and novel alloys such as AlCe. Applications include process parameter optimization, high-throughput quality control, and multistage AM process evaluation, with DL-enhanced workflows accelerating analysis times from weeks to days. Correlative imaging approaches further validate XCT and XRM data against scanning electron microscopy (SEM) images of physically sectioned samples, confirming the accuracy of DL-based reconstructions and enabling comprehensive defect analysis. While challenges remain in generalizing DL models to diverse materials and imaging conditions, improvements in resolution, noise reduction, and defect detection highlight the transformative potential of these methods. This multiscale and correlative approach enables precise identification and correlation of microstructural features with the overall performance of AM components. By integrating advanced XCT, XRM, and DL techniques, this paper demonstrates a significant leap forward in AM characterization, offering valuable insights into the relationships between processing parameters, microstructure, and part performance, and driving innovations that enhance the quality and reliability of AM products for demanding industrial applications.

Additive manufacturing↗
DOE OSTI2018

Switching of Coercivity Process in MnBi Alloys

MnBi-based alloys represent an interesting choice for developing rare earth-free permanent magnets due to the high magnetocrystalline anisotropy of their characteristic low-temperature intermetallic phase (LTIP) with hexagonal structure. In this work, we discuss the switching of coercivity mechanism in MnBi alloys by modulation of their phase distribution and microstructure. As-cast MnBi alloys obtained by suction-casting technique exhibited LTIP interspersed within Bi- and Mn-rich areas. A noticeable coercivity field of 282 kA/m was observed. The coercivity mechanism for this alloy was explained in terms of the nucleation of reverse domains after saturation, by means of the Kronmüller equation, which incorporates the detrimental effect of microstructure defects through fitting parameters associated to reduced intrinsic magnetic properties at grain size boundaries, interfaces, and local demagnetizing fields. Subsequent annealing at 583 K for 24 h produced a marked reduction of coercivity (down to 16 kA/m), reflecting a switching of coercivity process from nucleation to pinning of domain walls. The key microstructural feature determining this variation is the formation/suppression of Bi-rich areas, which promotes the nucleation and growth of the initial MnBi intermetallic phase.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2018

GOLGA2 loss causes fibrosis with autophagy in the mouse lung and liver

Highlights: • GOLGA2/GM130 loss induces autophagy with Golgi disruption in liver cells and transgenic mice. • GOLGA2/GM130 loss leads to degradation of lipid structures (LBs and LDs) by autophagy. • GOLGA2/GM130 loss causes liver and lung fibrosis. Autophagy is a biological recycling process via the self-digestion of organelles, proteins, and lipids for energy-consuming differentiation and homeostasis. The Golgi serves as a donor of the double-membraned phagophore for autophagosome assembly. In addition, recent studies have demonstrated that pulmonary and hepatic fibrosis is accompanied by autophagy. However, the relationships among Golgi function, autophagy, and fibrosis are unclear. Here, we show that the deletion of GOLGA2, encoding a cis-Golgi protein, induces autophagy with Golgi disruption. The induction of autophagy leads to fibrosis along with the reduction of subcellular lipid storage (lipid droplets and lamellar bodies) by autophagy in the lung and liver. GOLGA2 knockout mice clearly demonstrated fibrosis features such as autophagy-activated cells, densely packed hepatocytes, increase of alveolar macrophages, and decrease of alveolar surfactant lipids (dipalmitoylphosphatidylcholine). Therefore, we confirmed the associations among Golgi function, fibrosis, and autophagy. Moreover, GOLGA2 knockout mice may be a potentially valuable animal model for studying autophagy-induced fibrosis.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

A fast and accurate domain decomposition nonlinear manifold reduced order model

Here, this paper integrates nonlinear-manifold reduced order models (NM-ROMs) with domain decomposition (DD). NM ROMs approximate the full order model (FOM) state in a nonlinear-manifold by training a shallow, sparse autoencoder using FOM snapshot data. These NM-ROMs can be advantageous over linear-subspace ROMs (LS-ROMs) for problems with slowly decaying Kolmogorov n-width. However, the number of NM-ROM parameters that need to be trained scales with the size of the FOM. Moreover, for “extreme-scale” problems, the storage of high-dimensional FOM snapshots alone can make ROM training expensive. To alleviate the training cost, this paper applies DD to the FOM, computes NM-ROMs on each subdomain, and couples them to obtain a global NM-ROM. This approach has several advantages: Subdomain NM-ROMs can be trained in parallel, involve fewer parameters to be trained than global NM-ROMs, require smaller subdomain FOM dimensional training data, and can be tailored to subdomain specific features of the FOM. The shallow, sparse architecture of the autoencoder used in each subdomain NM-ROM allows application of hyper-reduction (HR), reducing the complexity caused by nonlinearity and yielding computational speedup of the NM-ROM. This paper provides the first application of NM-ROM (with HR) to a DD problem. In particular, this paper details an algebraic DD reformulation of the FOM, training a NM-ROM with HR for each sub domain, and a sequential quadratic programming (SQP) solver to evaluate the coupled global NM-ROM. Theoretical convergence results for the SQP method and a priori and a posteriori error estimates for the DD NM-ROM with HR are provided. The proposed DD NM-ROM with HR approach is numerically compared to a DD LS-ROM with HR on the 2D steady-state Burgers’ equation, showing an order of magnitude improvement in accuracy of the proposed DD NM-ROM over the DD LS-ROM.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Residential electricity conservation in response to auto-generated, multi-featured, personalized eco-feedback designed for large scale applications with utilities

While past research has shown that providing residents with feedback about their electricity usage can reduce demand and its associated environmental burdens, some questions remain regarding what makes such feedback most effective. We followed the electricity usage of 36 residents who each received 14 feedback messages over 2 months. Using approaches borrowed from Natural-Language-Processing, feedbacks were generated automatically, using 10 features in random combinations. Unlike in previous studies, each resident received varying types of messages over time. In 504 observations, the average prompted reduction in electricity usage was 11 ± 3%, compared to a control group of 89 residents who received no messages. Feedback types prompting the largest reductions were self-comparisons with one’s own earlier usage (average reduction 14%) and messages of high variety from one feedback-cycle to the next (average reduction 16%). Comparisons with neighbors did not prompt higher reductions on average. Instead, they prompted reductions only when a resident’s recent usage happened to be higher than the average usage of neighbors, and increases when the reverse was true. Finally, this behavior was exhibited by all residents and is likely explained by a norm-conforming mean reversion of residents to their neighbors’ average usage, rather than an anti-conform “boomerang” behavior previously suggested in similar contexts.

42 ENGINEERING↗
DOE OSTI2021

Amorphous complexions alter the tensile failure of nanocrystalline Cu-Zr alloys

Grain boundary-based mechanisms are known to control the plastic deformation and failure of nanocrystalline metals, with manipulation of the boundary structure a promising path for tuning this response. In this study, the role of interfacial structural disorder on plasticity and failure of nanocrystalline Cu-Zr alloys is investigated with in situ scanning electron microscopy tensile deformation experiments. Two model materials are created, one with only the typical ordered grain boundaries and another with amorphous intergranular films interspersed into the boundary network, while the microstructures are otherwise identical. Hence, the importance of complexion type on plasticity and failure is isolated by only varying complexion structure. Here, the tensile experiments show that failure of the samples containing amorphous films is significantly retarded, as evidenced by an increase in the cross-sectional area reduction, a decrease in the occurrence of shear-dominated failure, a decrease in strain localization, and fracture surfaces with more elongated dimple features. As a whole, this study provides direct evidence that structural disorder at the grain boundaries can be beneficial for improving the ductility of nanocrystalline metals.

36 MATERIALS SCIENCE↗
DOE OSTI2012

FIRST DETECTION OF NEAR-INFRARED LINE EMISSION FROM ORGANICS IN YOUNG CIRCUMSTELLAR DISKS

We present an analysis of high-resolution spectroscopy of several bright T Tauri stars using the CRIRES spectrograph on the Very Large Telescope and NIRSPEC spectrograph on the Keck Telescope, revealing the first detections of emission from HCN and C{sub 2}H{sub 2} in circumstellar disks at near-infrared wavelengths. Using advanced data reduction techniques, we achieve a dynamic range with respect to the disk continuum of {approx}500 at 3 {mu}m, revealing multiple emission features of H{sub 2}O, OH, HCN, and C{sub 2}H{sub 2}. We also present stringent upper limits for two other molecules thought to be abundant in the inner disk, CH{sub 4} and NH{sub 3}. Line profiles for the different detected molecules are broad but centrally peaked in most cases, even for disks with previously determined inclinations of greater than 20 Degree-Sign , suggesting that the emission has both a Keplerian and non-Keplerian component as observed previously for CO emission. We apply two different modeling strategies to constrain the molecular abundances and temperatures: we use a simplified single-temperature local thermal equilibrium (LTE) slab model with a Gaussian line profile to make line identifications and determine a best-fit temperature and initial abundance ratios, and we compare these values with constraints derived from a detailed disk radiative transfer model assuming LTE excitation but utilizing a realistic temperature and density structure. Abundance ratios from both sets of models are consistent with each other and consistent with expected values from theoretical chemical models, and analysis of the line shapes suggests that the molecular emission originates from within a narrow region in the inner disk (R < 1 AU).

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2015

The nuclear near-infrared spectral properties of nearby galaxies

We present spectra of the nuclear regions of 50 nearby (D = 1–92 Mpc, median = 20 Mpc) galaxies of morphological types E to Sm. The spectra, obtained with the Gemini Near-IR Spectrograph on the Gemini North telescope, cover a wavelength range of approximately 0.85–2.5 μm at R ∼ 1300–1800. There is evidence that most of the galaxies host an active galactic nucleus (AGN), but the range of AGN luminosities (log (L {sub 2−10 keV} [erg s{sup −1}]) = 37.0–43.2) in the sample means that the spectra display a wide variety of features. Some nuclei, especially the Seyferts, exhibit a rich emission-line spectrum. Other objects, in particular the type 2 Low Ionization Nuclear Emission Region galaxies, show just a few, weak emission lines, allowing a detailed view of the underlying stellar population. These spectra display numerous absorption features sensitive to the stellar initial mass function, as well as molecular bands arising in cool stars, and many other atomic absorption lines. We compare the spectra of subsets of galaxies known to be characterized by intermediate-age and old stellar populations, and find clear differences in their absorption lines and continuum shapes. We also examine the effect of atmospheric water vapor on the signal-to-noise ratio achieved in regions between the conventional NIR atmospheric windows, which are of potential interest to those planning observations of redshifted emission lines or other features affected by telluric H{sub 2}O. Further exploitation of this data set is in progress, and the reduced spectra and data reduction tools are made available to the community.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2016

Ion-acoustic Gardner solitons in a four-component nonextensive multi-ion plasma

The nonlinear propagation of ion-acoustic (IA) solitary waves (SWs) in a four-component non-extensive multi-ion plasma system containing inertial positively charged light ions, negatively charged heavy ions, as well as noninertial nonextensive electrons and positrons has been theoretically investigated. The reductive perturbation method has been employed to derive the nonlinear equations, namely, Korteweg−deVries (KdV), modified KdV (mKdV), and Gardner equations. The basic features (viz. polarity, amplitude, width, etc.) of Gardner solitons are found to exist beyond the KdV limit and these IA Gardner solitons are qualitatively different from the KdV and mKdV solitons. It is observed that the basic features of IA SWs are modified by various plasma parameters (viz. electron and positron nonextensivity, electron number density to ion number density, and electron temperature to positron temperature, etc.) of the considered plasma system. The results obtained from this theoretical investigation may be useful in understanding the basic features of IA SWs propagating in both space and laboratory plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2019

SUNDIALS Multiphysics+MPIManyVector Performance Testing

In this report we document performance test results on a SUNDIALS-based multiphysics demonstration application. We aim to assess the large-scale parallel performance of new capabilities that have been added to the SUNDIALS suite of time integrators and nonlinear solvers in recent years under funding from both the Exascale Computing Project (ECP) and the Scientific Discovery through Advanced Scientific (SciDAC) program, specifically: 1. SUNDIALS’ new MPIManyVector module, that allows extreme flexibility in how a solution "vector" is staged on computational resources. 2. ARKode’s new multirate integration module, MRIStep, allowing high-order accurate calculations that subcycle "fast" processes within "slow" ones. 3. SUNDIALS’ new flexible linear solver interfaces, that allow streamlined specification of problem-specific linear solvers. 4. SUNDIALS’ new N_Vector additions of "fused" vector operations (to increase arithmetic intensity) and separation of reduction operations into "local" and "global" versions (to reduce latency by combining multiple reductions into a single MPI_Allreduce call). We anticipate that subsequent reports will extend this work to investigate a variety of other new features, including SUNDIALS’ generic SUNNonlinearSolver interface and accelerator-enabled N Vector modules, and upcoming MRIStep extensions to support custom "fast" integrators (that leverage problem structure) and IMEX integration of the "slow" time scale (to add diffusion).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Machine Learning for Joint Quality Control

The use of lightweight material combinations has been highly demanded in manufacturing automotive structures. However, making robust dissimilar material joints of such lightweight materials is still challenging. A significant barrier to achieving high-quality and repeatable joint performance is a deficient understanding of the relationship between the welding process, joint attributes, and joint performance. In this context, welding factors refer to material, equipment, environment, and process parameters, while joint features comprise specific microstructural attributes of the weld such as nugget size, heat affected zone (HAZ) topology, intermetallic layer thickness, and sheet thickness reduction. Joint performance is quantified in terms of strength (e.g., tensile shear, coach peel, cross-tension), weld size, and hardness, among other factors. While there have been many attempts to establish this process-structure-property relationship by developing a model derived from the associated physics and first principles, the complexity of the joining processes compounded by the complex interactions with different materials in an automotive assembly line environment, has hindered the usefulness of such attempts. The complexity is further exacerbated using different stacking materials, especially comprising dissimilar material combinations. In practice, the common approach has been the laborious process of creating welds, characterizing them, and then physically testing them through experimentation. With the emergence of artificial intelligence (AI) methods, an alternative pathway to eliciting the desired process-structure-property relationship at an accelerated pace is to use a data-driven approach by employing machine-learning (ML) techniques. This approach is benefitted by the availability of large streams of data, generated through years of research and testing by original equipment manufacturers, in the form of material, process, environmental, equipment, microstructural, and bulk-scale performance information from multimodal, multiscale sensors making measurements from laboratory-scale to production-scale processes. During Phase I efforts, which ended in fiscal year (FY) 2021, the Oak Ridge National Laboratory and Pacific Northwest National Laboratory (ORNL/PNNL) team demonstrated the effectiveness of different ML/AI frameworks in modeling complex relationships between resistance spot welding (RSW) process parameters, weld attributes, and joint properties using a subset of data from General Motors (GM). In FY 2022, the project team further refined and expanded their respective ML models to analyze additional welds with new weld stack-ups and materials to enhance the ML model predictive capability. ORNL extended its unified deep neural networks (DNN) ML training and prediction framework with new data streams of process parameters, and PNNL extended its model describing RSW process parameters’ associations with weld attributes. In FY 2023, the project team completed the development of the AI/ML architecture for analyzing aluminum/steel joints manufactured by GM via RSW and transitioned into the inline welding quality monitoring task for steel/steel RSW joints provided by GM.

36 MATERIALS SCIENCE↗