Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “training data quality”

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 343 records · Page 19
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

A Novel Machine Learning Algorithm for Planetary Boundary Layer Height Estimation Using AERI Measurement Data

Accurately determining the height of the planetary boundary layer (PBL) is important since it can affect the climate, weather, and air quality. Ground-based infrared hyperspectral remote sensing is an effective way to obtain this parameter. Compared with radiosonde measurements, its temporal resolution is much higher. In this study, a method to retrieve the PBL height (PBLH) from the ground-based infrared hyperspectral radiance data is proposed based on machine learning. In this method, the channels that are sensitive to temperature and humidity profiles are selected as the feature vectors, and the PBLHs derived from radiosonde are taken as the true values. The support vector machine (SVM) is applied to train and test the data set, and the parameters are optimized in the process. The data set collected at the Atmospheric Radiation Measurement (ARM) program Southern Great Plains (SGP) from 2012 to 2015 is analyzed. The instruments used in this letter include Atmospheric Emitted Radiance Interferometer (AERI), Vaisala CL31 ceilometer, and radiosonde. It shows that the root mean square error (RMSE) between the PBLHs calculated by the proposed method using AERI data and those from radiosonde data can be within 370 m, and the square correlation coefficient (SCC) is greater than 0.7. Compared with the PBLHs derived from the ceilometer, it can be found that the new method is more stable and less affected by clouds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Applications of Federated Learning in Semiconductor Manufacturing [Poster]

As semiconductor manufacturers explore advanced data analytics and modeling techniques and data hungry machine learning models increase in popularity due to their accuracy in solving generalized problems and ability to learn complex relationships, federated learning emerges as a privacy preserving machine learning technique for preserving data privacy and ensuring intellectual property protection. Federated Learning is a machine learning technique focused on training models using distributed data that never needs to be centrally stored, allowing the use of advanced machine learning techniques without compromising data privacy, and in the semiconductor manufacturing industry advanced machine learning techniques can reduce cost and time, but maintaining data privacy is essential to maintaining a competitive advantage. This paper systematically reviews existing literature on applications of federated learning in the semiconductor manufacturing industry with a focus on identifying common themes, algorithms, and gaps within the literature to drive future research directions. The findings reveal five key themes, including improvements in quality assurance, virtual models, privacy preservation, reliable data practices, and emerging trends and developments. By identifying key themes in literature on federated learning and semiconductor manufacturing and analyzing gaps and discussed methodologies, this study highlights several potential future research directions to expand the application of federated learning techniques in the semiconductor manufacturing domain.

42 ENGINEERING↗
DOE OSTI2026

The Double-edged Sword of Data-driven Super-Resolution: Adversarial Super-resolution Models

Data-driven super-resolution (SR) methods are often integrated into imaging pipelines as preprocessing steps to improve downstream tasks such as classification and detection. However, these SR models introduce a previously unexplored attack surface into imaging pipelines. In this paper, we present AdvSR, a framework demonstrating that adversarial behavior can be embedded directly into SR model weights during training, requiring no access to inputs at inference time. Unlike prior attacks that perturb inputs or rely on backdoor triggers, AdvSR operates entirely at the model level. By jointly optimizing for reconstruction quality and targeted adversarial outcomes, AdvSR produces models that appear benign under standard image quality metrics while inducing downstream misclassification. We evaluate AdvSR on three SR architectures (SRCNN, EDSR, SwinIR) paired with a YOLOv11 classifier and demonstrate that AdvSR models can achieve high attack success rates with minimal quality degradation. These findings highlight a new model-level threat for imaging pipelines, with implications for how practitioners source and validate models in safety-critical applications.

Sullivan, Haley [ORNL] (ORCID:0000000274069217)↗
DOE OSTI2023

Toward DMC Accuracy Across Chemical Space with Scalable Δ-QML

In the past decade, quantum diffusion Monte Carlo (DMC) has been demonstrated to successfully predict the energetics and properties of a wide range of molecules and solids by numerically solving the electronic many-body Schrödinger equation. With O(N 3 ) scaling with the number of electrons N, DMC has the potential to be a reference method for larger systems that are not accessible to more traditional methods such as CCSD(T). Assessing the accuracy of DMC for smaller molecules becomes the stepping stone in making the method a reference for larger systems. We show that when coupled with quantum machine learning (QML)-based surrogate methods, the computational burden can be alleviated such that quantum Monte Carlo (QMC) shows clear potential to undergird the formation of high-quality descriptions across chemical space. We discuss three crucial approximations necessary to accomplish this: the fixed-node approximation, universal and accurate references for chemical bond dissociation energies, and scalable minimal amons-set-based QML (AQML) models. Numerical evidence presented includes converged DMC results for over 1000 small organic molecules with up to five heavy atoms used as amons and 50 medium-sized organic molecules with nine heavy atoms to validate the AQML predictions. Finally, numerical evidence collected for Δ-AQML models suggests that already modestly sized QMC training data sets of amons suffice to predict total energies with near chemical accuracy throughout chemical space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Fast and efficient identification of anomalous galaxy spectra with neural density estimation

ABSTRACT Current large-scale astrophysical experiments produce unprecedented amounts of rich and diverse data. This creates a growing need for fast and flexible automated data inspection methods. Deep learning algorithms can capture and pick up subtle variations in rich data sets and are fast to apply once trained. Here, we study the applicability of an unsupervised and probabilistic deep learning framework, the probabilistic auto-encoder, to the detection of peculiar objects in galaxy spectra from the SDSS survey. Different to supervised algorithms, this algorithm is not trained to detect a specific feature or type of anomaly, instead it learns the complex and diverse distribution of galaxy spectra from training data and identifies outliers with respect to the learned distribution. We find that the algorithm assigns consistently lower probabilities (higher anomaly score) to spectra that exhibit unusual features. For example, the majority of outliers among quiescent galaxies are E+A galaxies, whose spectra combine features from old and young stellar population. Other identified outliers include LINERs, supernovae, and overlapping objects. Conditional modelling further allows us to incorporate additional information. Namely, we evaluate the probability of an object being anomalous given a certain spectral class, but other information such as metrics of data quality or estimated redshift could be incorporated as well. We make our code publicly available.

Böhm, Vanessa↗
DOE OSTI2020

Inversion of Time-Lapse Seismic Reservoir Monitoring Data Using CycleGAN: A Deep Learning-Based Approach for Estimating Dynamic Reservoir Property Changes

Carbon capture and storage is being pursued globally as a geoengineering measure for reducing the emission of anthropogenic CO 2 the atmosphere. Comprehensive monitoring, verification, and accounting programs must be established for demonstrating the safe storage of injected CO 2 . One of the most commonly deployed monitoring techniques is time-lapse seismic reservoir monitoring (also known as 4-D seismic), which involves comparing 3-D seismic survey data taken at the same study site but over different times. Analyses of 4-D seismic data volumes can help improve the quality of storage reservoir characterization, track the movement of injected CO 2 plume, and identify potential CO 2 spillover/leakage from the storage reservoirblue. However, the derivation of high-resolution CO 2 saturation maps from 4-D seismic data is a highly nonlinear and ill-posed inverse problem, often requiring significant computational effort. In this research, we apply a physics-based deep learning method to facilitate the solution of both the forward and inverse problems in seismic inversion while honoring physical constraints. A cycle generative adversarial neural network (CycleGAN) model is trained to learn the bidirectional functional mappings between the reservoir dynamic property changes and seismic attribute changes, such that both forward and inverse solutions can be obtained efficiently from the trained model. We show that our CycleGAN-based approach not only improves the reliability of 4-D seismic inversion but also expedites the quantitative interpretation. Our deep learning-based workflow is generic and can be readily used for reservoir characterization and reservoir model updates involving the use of 4-D seismic data.

58 GEOSCIENCES↗
DOE OSTI2022

The Sensitivity of GPz Estimates of Photo-z Posterior PDFs to Realistically Complex Training Set Imperfections

The accurate estimation of photometric redshifts is crucial to many upcoming galaxy surveys, for example, the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). Almost all Rubin extragalactic and cosmological science requires accurate and precise calculation of photometric redshifts; many diverse approaches to this problem are currently in the process of being developed, validated, and tested. In this work, we use the photometric redshift code GPz to examine two realistically complex training set imperfections scenarios for machine learning based photometric redshift calculation: (i) where the spectroscopic training set has a very different distribution in color–magnitude space to the test set, and (ii) where the effect of emission line confusion causes a fraction of the training spectroscopic sample to not have the true redshift. By evaluating the sensitivity of GPz to a range of increasingly severe imperfections, with a range of metrics (both of photo-z point estimates as well as posterior probability distribution functions, PDFs), we quantify the degree to which predictions get worse with higher degrees of degradation. In particular, we find that there is a substantial drop-off in photo-z quality when line-confusion goes above ~1%, and sample incompleteness below a redshift of 1.5, for an experimental setup using data from the Buzzard Flock synthetic sky catalogs.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Extracting structural motifs from pair distribution function data of nanostructures using explainable machine learning

Characterization of material structure with X-ray or neutron scattering using e.g. Pair Distribution Function (PDF) analysis most often rely on refining a structure model against an experimental dataset. However, identifying a suitable model is often a bottleneck. Recently, automated approaches have made it possible to test thousands of models for each dataset, but these methods are computationally expensive and analysing the output, i.e. extracting structural information from the resulting fits in a meaningful way, is challenging. Our Machine Learning based Motif Extractor (ML-MotEx) trains an ML algorithm on thousands of fits, and uses SHAP (SHapley Additive exPlanation) values to identify which model features are important for the fit quality. We use the method for 4 different chemical systems, including disordered nanomaterials and clusters. ML-MotEx opens for a type of modelling where each feature in a model is assigned an importance value for the fit quality based on explainable ML.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Non-Intrusive Appliance Identification with Appliance-Specific Networks

The problem of noninstrusive load monitoring (NILM) is usually formulated as a single-channel blind source separation task, whose successful solution enable fast and convenient load identification and energy disaggregation. When applied at test time, NILM algorithms aim to identify the operating characteristics of individual appliances from an aggregate power measurement of the entire house. Recent advances in deep learning gave rise to many methods that mostly focus on learning a direct mapping from aggregate measurement to individual appliance power. However, these methods are not only computationally expensive, but they often suffer from overfitting and do not generalize very well. In this article, we propose a novel NILM method that leverages advances in statistical learning that have not been properly applied in this domain before. The proposed method consists of three stages: first, a Bayesian nonparametric learning-based approach for appliance state extraction; second, synthetic minority oversampling technique for data augmentation and mitigating the heavy imbalance in switching events; and third, appliance-specific lightweight long short-term memory networks for status classification for each appliance. Here, we adopt a “differential” input (the difference before and after the switching event) to reduce the complexity of network training and make the proposed method robust to multiappliance switching events. Experiments are conducted to demonstrate the effectiveness of the proposed method, achieving superior performance when compared to recent methods. An ablation study is conducted to demonstrate the effectiveness of each module of our method. Finally, we investigate the quality of generated synthetic samples.

42 ENGINEERING↗
DOE OSTI2025

SCULPT (Supervised Clustering and Uncovering Latent Patterns with Training) v1

SCULPT (Supervised Clustering and Uncovering Latent Patterns with Training) is a comprehensive data visualization and analysis application focused on working with COLTRIMS (COLd Target Recoil Ion Momentum Spectroscopy) data, which is used in atomic and molecular physics experiments. The application offers several powerful features: - Data uploading and processing capabilities for COLTRIMS files - Multiple visualization methods using UMAP (Uniform Manifold Approximation and Projection) for dimensionality reduction - Interactive selection of data points across multiple views - Feature engineering through various methods: - Manual feature selection from calculated physics parameters - Deep autoencoder for dimension reduction - Genetic programming for discovering meaningful features - Mutual information-based feature selection - Multiple clustering approaches (DBSCAN, KMeans, Agglomerative) - Quality metrics for evaluating clustering results - Export capabilities for selections and generated features

Daoud, Hazem [Lawrence Berkeley National Laborator↗
DOE OSTI2025

PAVC Gridded 20m Alaska NGEE Tier3 PFTs v1.0

These 20-meter spatial resolution gridded products provide per-pixel fractional cover (%) of Next Generation Ecosystem Experiments (NGEE) Arctic Plant Functional Types (PFTs) Tier 3 across Alaska, north of the boreal treeline. The products were developed for the NGEE Arctic project, which is improving Arctic vegetation representation and parameterization of the E3SM Land Model. This dataset includes 8 files containing fractional cover for NGEE Tier 3 PFTs (https://data.ess-dive.lbl.gov/view/doi:10.15485/2529470): (1) bryophytes; (2) lichens; (3) non-vascular plants, i.e., the sum of lichens and bryophytes; (4) deciduous shrubs, (5) evergreen shrubs, (6) forbs, (7) graminoids, and a non-PFT class, (8) litter. Each pixel contains the percent cover (expressed as a fraction of total ground cover) that was predicted by random-forest regression models. The random-forest models were trained on cover data collected at 978 plots from 2010 to 2021, of which are archived in the Pan-Arctic Vegetation Cover (PAVC) database (https://data.ess-dive.lbl.gov/datasets/doi:10.15485/2483557). The plot cover was linked to 20-meter spatial resolution, satellite-derived predictor variables: Sentinel-2 spectra and Sentinel-1 polarizations averaged over the 2019 growing season, as well as topographical features derived from ArcticDEM. Then, spatio-temporally anomalous plot data that introduced large variability to the regression outcomes were dropped using the Cook’s distance outlier detection method, and the models were re-created using high-quality plots and their associated satellite derived explanatory variables per each PFT. The correlations between plot-observed and satellite-derived fractional cover for all PFTs were well correlated (R2 = 0.69–0.95 and 0.5 for litter) and had low RMSE bias (0.02–0.11). This research was performed as a part of the NGEE Arctic project. The NGEE Arctic project was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Department of Energy’s Atmospheric System Research (ASR) Program’s Workshop on the Future of Atmospheric Large Eddy Simulation (LES): Workshop Report

Large-eddy simulation (LES) is used as a tool to understand physical processes such as turbulence, aerosols, clouds, precipitation, radiation, the interactions among all these, and their interactions with the underlying surface. Over the next 10 years, LES will drive fundamental progress in open scientific questions in these areas as LES is increasingly used to gain understanding of complex interacting physical processes involving atmospheric turbulence. This growth will be driven both by scientific demand and the expansion of computational resources needed to conduct LES, and the form that the growth takes will largely be determined by how computational resources are leveraged for scientific gain. In particular, we suggest that computational resources are likely to be leveraged in two separate but not necessarily distinct ways. On one hand, growth in computational resources will allow LES to be made more routine, that is, performed more frequently, while on the other hand, the computational expense (measured in total floating point operations) afforded to individual LES will expand dramatically, allowing simulations to increase in both domain size and resolution as well as physical detail. Current U.S. Department of Energy (DOE) projects such as LES ARM Symbiotic Simulation and Observation Activity (LASSO) are leading the way in conducting routine LES, building large, public databases that are accessible for data science, sensitivity studies, and training for machine learning. LES will also become more routine as it becomes more accessible for individual researchers to address their scientific questions of interest. Scientific questions addressed by LES over the next 10 years are likely to include cloud organization and aggregation; aerosol cloud interactions and atmospheric chemistry (including geo-engineering); urban-scale LES; atmospheric extreme events, ranging from small-scale severe weather to wildfires; and ocean-wave-atmosphere interactions. Further LES-related research will likely grow significantly in areas related to societal impact studies of air quality and extreme weather events, applications to renewable energy forecasting and resource assessment, and aid in decision-making processes. The growth in the use of LES in atmospheric science research will drive the need for better physical process representations (e.g., cloud aerosol microphysics, radiation, and atmospheric chemistry) at the scales resolved by LES. To date, many of the process representations used by LES have been taken directly from coarser-resolution models. Promising methods for LES process representations include superdroplet and quadrature methods for microphysics, 3D approaches for radiation, and better representation of chemistry and aerosol processes. At LES resolution, land-atmosphere interactions for complex terrains, land cover/types, biogeochemistry, and plant canopy models are needed as an improvement beyond traditional and widely used Monin-Obuhkov similarity theory.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Department of Energy’s Atmospheric System Research (ASR) Program’s Workshop on the Future of Atmospheric Large Eddy Simulation (LES) (Workshop Report)

Large-eddy simulation (LES) is used as a tool to understand physical processes such as turbulence, aerosols, clouds, precipitation, radiation, the interactions among all these, and their interactions with the underlying surface. Over the next 10 years, LES will drive fundamental progress in open scientific questions in these areas as LES is increasingly used to gain understanding of complex interacting physical processes involving atmospheric turbulence. This growth will be driven both by scientific demand and the expansion of computational resources needed to conduct LES, and the form that the growth takes will largely be determined by how computational resources are leveraged for scientific gain. In particular, we suggest that computational resources are likely to be leveraged in two separate but not necessarily distinct ways. On one hand, growth in computational resources will allow LES to be made more routine, that is, performed more frequently, while on the other hand, the computational expense (measured in total floating point operations) afforded to individual LES will expand dramatically, allowing simulations to increase in both domain size and resolution as well as physical detail. Current U.S. Department of Energy (DOE) projects such as LES ARM Symbiotic Simulation and Observation Activity (LASSO) are leading the way in conducting routine LES, building large, public databases that are accessible for data science, sensitivity studies, and training for machine learning. LES will also become more routine as it becomes more accessible for individual researchers to address their scientific questions of interest. Scientific questions addressed by LES over the next 10 years are likely to include cloud organization and aggregation; aerosol cloud interactions and atmospheric chemistry (including geo-engineering); urban-scale LES; atmospheric extreme events, ranging from small-scale severe weather to wildfires; and ocean-wave-atmosphere interactions. Further LES-related research will likely grow significantly in areas related to societal impact studies of air quality and extreme weather events, applications to renewable energy forecasting and resource assessment, and aid in decision-making processes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Descriptor: High Temporal Resolution Meteorological Data at Oak Ridge Reservation (ORR-HiResMet)

Access to continuous, quality assessed meteorological data is critical for understanding the climatology and atmospheric dynamics of a region. Research facilities like Oak Ridge National Laboratory (ORNL) rely on such data to assess site-specific climatology, model potential emissions, establish safety baselines, and prepare for emergency scenarios. To meet these needs, on-site towers at ORNL collect meteorological data at 15-minute and hourly intervals. However, data measurements from meteorological towers are affected by sensor sensitivity, degradation, lightning strikes, power fluctuations, glitching, and sensor failures, all of which can affect data quality. To address these challenges, we conducted a comprehensive quality assessment and processing of five years of meteorological data collected from ORNL at 15-minute intervals, including measurements of temperature, pressure, humidity, wind, and solar radiation. The time series of each variable was pre-processed and gap-filled using established meteorological data collection and cleaning techniques, i.e., the time series were subjected to structural standardization, data integrity testing, automated and manual outlier detection, and gap-filling. The data product and highly generalizable processing workflow developed in Python Jupyter notebooks are publicly accessible online. As a key contribution of this study, the evaluated 5-year data will be used to train atmospheric dispersion models that simulate dispersion dynamics across the complex ridge-and-valley topography of the Oak Ridge Reservation in East Tennessee.

Steckler, Morgan R. [Oak Ridge National Laboratory↗
DOE OSTI2024

Maven: a multimodal foundation model for supernova science

Abstract A common setting in astronomy is the availability of a small number of high-quality observations, and larger amounts of either lower-quality observations or synthetic data from simplified models. Time-domain astrophysics is a canonical example of this imbalance, with the number of supernovae observed photometrically outpacing the number observed spectroscopically by multiple orders of magnitude. At the same time, no data-driven models exist to understand these photometric and spectroscopic observables in a common context. Contrastive learning objectives, which have grown in popularity for aligning distinct data modalities in a shared embedding space, provide a potential solution to extract information from these modalities. We present Maven, the first foundation model for supernova science. To construct Maven, we first pre-train our model to align photometry and spectroscopy from 0.5 M synthetic supernovae using a contrastive objective. We then fine-tune the model on 4702 observed supernovae from the Zwicky transient facility. Maven reaches state-of-the-art performance on both classification and redshift estimation, despite the embeddings not being explicitly optimized for these tasks. Through ablation studies, we show that pre-training with synthetic data improves overall performance. In the upcoming era of the Vera C. Rubin observatory, Maven will serve as a valuable tool for leveraging large, unlabeled and multimodal time-domain datasets.

Zhang, Gemma (ORCID:0000000280198082)↗
DOE OSTI2023

Unlocking Autonomous Telescopes through Reinforcement Learning: An Offline Framework and Insights from a Case Study

Optimizing observational astronomy campaigns is becoming a complex and expensive task for next-generation telescopes, where manual planning of observations may tend to reach suboptimal results in terms of optimization.Reinforcement Learning (RL) has been well-demonstrated as a valuable approach for training autonomous systems, and it may provide the basis for self-driving telescopes capable of scanning the sky and optimizing the scheduling for astronomy campaigns.We have developed a framework for the optimization of telescope scheduling using RL techniques, based on a dataset containing data on a discrete set of sky locations that the telescope should visit, and a reward metric. We compared several RL algorithms applied to an offline simulation dataset based at the Stone Edge Observatory, considering a discrete set of sky locations to visit and using “t-effective” as a reward metric, a measure of the quality of the data.Deep Q-Networks (DQNs), belonging to the class of value-based methods, have shown remarkable success in the optimization of astronomical observations in our dataset. In the full environment, the average reward value in each state was found to be 92%±5% of the maximum possible reward, while on the test set it resulted in 87%±9% of the maximum possible reward.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Automating the Analysis of Large Language Models Responses through Zero-Shot Question Answering

Recent advancements in Large Language Models (LLMs) have shown significant potential in various applications, yet their evaluation, particularly in zero-shot question answering scenarios, remains a challenging task. In this study, our objective was to explore precision metrics for Large Language Models (LLM) and design and implement a software pipeline to automatically evaluate LLMs' outputs under zero-shot question answering. Zero-shot question answering involves a model providing answers to questions about topics it hasn't seen during training. It leverages the principles of zero-shot learning by relying on semantic understanding and generalization from related knowledge. The data used was metadata from medical databases on congenital heart disease. We explored eleven LLM metrics and selected three for our evaluation: BLEU, BERTScore, and MoverScore. BLEU calculates a score based on the overlap of n-grams (contiguous sequences of n items, typically words) between the machine-generated translation and the reference translations. Higher BLEU scores indicate better correspondence between the machine-generated and human-generated translations. BERTScore is a metric used to evaluate the quality of machine-generated text by measuring the similarity of token embeddings produced by BERT (Bidirectional Encoder Representations from Transformers) between the generated text and reference text. MoverScore is a metric that quantifies the dissimilarity between the distributions of word embeddings from machine-generated text and reference text, emphasizing semantic similarity over exact token overlap. We also introduced HBKI, a composite metric summarizing these approaches. We tested five models —GPT-3, Llama-2, Gemini 1.5 Pro, Solar 10.7B, and Mixtral-8x7b. Our software pipeline, designed and implemented using Object-Oriented Programming principles, allows users to customize the selection and extraction of features for topics of interest in their own research. Our results show that MoverScore delivered the most precise evaluation of the LLM's outputs, while Mixtral-8x7b achieved the best overall performance in extracting metadata from the databases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Unsupervised learning-enabled pulsed infrared thermographic microscopy of subsurface defects in stainless steel

Metallic structures produced with laser powder bed fusion (LPBF) additive manufacturing method (AM) frequently contain microscopic porosity defects, with typical approximate size distribution from one to 100 microns. Presence of such defects could lead to premature failure of the structure. In principle, structural integrity assessment of LPBF metals can be accomplished with nondestructive evaluation (NDE). Pulsed infrared thermography (PIT) is a non-contact, one-sided NDE method that allows for imaging of internal defects in arbitrary size and shape metallic structures using heat transfer. PIT imaging is performed using compact instrumentation consisting of a flash lamp for deposition of a heat pulse, and a fast frame infrared (IR) camera for measuring surface temperature transients. However, limitations of imaging resolution with PIT include blurring due to heat diffusion, sensitivity limit of the IR camera. We demonstrate enhancement of PIT imaging capability with unsupervised learning (UL), which enables PIT microscopy of subsurface defects in high strength corrosion resistant stainless steel 316 alloy. PIT images were processed with UL spatial–temporal separation-based clustering segmentation (STSCS) algorithm, refined by morphology image processing methods to enhance visibility of defects. The STSCS algorithm starts with wavelet decomposition to spatially de-noise thermograms, followed by UL principal component analysis (PCA), fine-tuning optimization, and neural learning-based independent component analysis (ICA) algorithms to temporally compress de-noised thermograms. The compressed thermograms were further processed with UL-based graph thresholding K-means clustering algorithm for defects segmentation. The STSCS algorithm also includes online learning feature for efficient re-training of the model with new data. For this study, metallic specimens with calibrated microscopic flat bottom hole defects, with diameters in the range from 203 to 76 µm, were produced using electro discharge machining (EDM) drilling. While the raw thermograms do not show any material defects, using STSCS algorithm to process PIT images reveals defects as small as 101 µm in diameter. To the best of our knowledge, this is the smallest reported size of a sub-surface defect in a metal imaged with PIT, which demonstrates the PIT capability of detecting defects in the size range relevant to quality control requirements of LPBF-printed high-strength metals.

36 MATERIALS SCIENCE↗