Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Traditional Machine Learning Models”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Transfer learning driven design optimization for inertial confinement fusion

Transfer learning is a promising approach to create predictive models that incorporate simulation and experimental data into a common framework. In this technique, a neural network is first trained on a large database of simulations and then partially retrained on sparse sets of experimental data to adjust predictions to be more consistent with reality. Previously, this technique has been used to create predictive models of Omega [Humbird et al., IEEE Trans. Plasma Sci. 48, 61–70 (2019)] and NIF [Humbird et al., Phys. Plasmas 28, 042709 (2021); Kustowski et al., Mach. Learn. 3, 015035 (2022)] inertial confinement fusion (ICF) experiments that are more accurate than simulations alone. Here, in this work, we conduct a transfer learning driven hypothetical ICF campaign in which the goal is to maximize experimental neutron yield via Bayesian optimization. The transfer learning model achieves yields within 5% of the maximum achievable yield in a modest-sized design space in fewer than 20 experiments. Furthermore, we demonstrate that this method is more efficient at optimizing designs than traditional model calibration techniques commonly employed in ICF design. Such an approach to ICF design could enable robust optimization of experimental performance under uncertainty.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Active anomaly detection for time-domain discoveries

Aims. We present the first evidence that adaptive learning techniques can boost the discovery of unusual objects within astronomical light curve data sets. Methods. Our method follows an active learning strategy where the learning algorithm chooses objects which can potentially improve the learner if additional information about them is provided. This new information is subsequently used to update the machine learning model, allowing its accuracy to evolve with each new information. For the case of anomaly detection, the algorithm aims to maximize the number of scientifically interesting anomalies presented to the expert by slightly modifying the weights of a traditional Isolation Forest (IF) at each iteration. In order to demonstrate the potential of such techniques, we apply the Active Anomaly Discovery (AAD) algorithm to 2 data sets: simulated light curves from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) and real light curves from the Open Supernova Catalog. We compare the AAD results to those of a static IF. For both methods, we performed a detailed analysis for all objects with the ~2% highest anomaly scores. Results. We show that, in the real data scenario , AAD was able to identify ~80% more true anomalies than the IF. This result is the first evidence that AAD algorithms can play a central role in the search for new physics in the era of large scale sky surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection

Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety of traditional machine learning tasks, e.g., speech recognition, image classification, and segmentation. The ability of DNNs to efficiently approximate high-dimensional functions has also motivated their use in scientific applications, e.g., to solve partial differential equations and to generate surrogate models. In this paper, we consider the supervised training of DNNs, which arises in many of the above applications. We focus on the central problem of optimizing the weights of the given DNN such that it accurately approximates the relation between observed input and target data. Devising effective solvers for this optimization problem is notoriously challenging due to the large number of weights, nonconvexity, data sparsity, and nontrivial choice of hyperparameters. To solve the optimization problem more efficiently, we propose the use of variable projection (VarPro), a method originally designed for separable nonlinear least-squares problems. Our main contribution is the Gauss--Newton VarPro method (GNvpro) that extends the reach of the VarPro idea to nonquadratic objective functions, most notably cross-entropy loss functions arising in classification. These extensions make GNvpro applicable to all training problems that involve a DNN whose last layer is an affine mapping, which is common in many state-of-the-art architectures. In our four numerical experiments from surrogate modeling, segmentation, and classification, GNvpro solves the optimization problem more efficiently than commonly used stochastic gradient descent (SGD) schemes. Finally, GNvpro finds solutions that generalize well, and in all but one example better than well-tuned SGD methods, to unseen data points.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Application of physics-informed neural networks (PINNs) solution to coupled thermal and hydraulic processes in silty sands

Abstract The accurate modeling of water and heat transport in soils is crucial for both geo-environmental and geothermal engineering. Traditional modeling methods are problematic because they require well-defined boundaries and initial conditions. Recently, physics-informed neural networks (PINNs), which incorporate partial differential equations (PDEs) to solve forward and inverse problems, have attracted increasing attention in machine learning research. In this study, we applied PINNs to tackle hydraulic and thermal transport coupling forward problems in silty sands. A fully connected deep neural network was utilized for training. This neural network model leverages automatic differentiation to apply the governing equations as constraints, based on the mathematical approximations established by the neural network itself. We conducted forward problems and compared the solutions derived from PINNs with those from Finite Element Method (FEM) simulations. The forward problem results demonstrate the PINNs model’s capability in predicting hydraulic transport, heat transport, and thermal–hydraulic coupling in silty sands under various boundary conditions. The PINNs exhibited great performance in simulating the thermal–hydraulic coupling problem. The accuracy of the PINNs solutions shows its potential for simulation in geotechnical engineering.

Feng, Yuan↗
DOE OSTI2023

Machine Learning Enabled Sensor Fusion for In-Situ Defect Detection in Laser Powder Bed Fusion

Laser Powder Bed Fusion (L-PBF) Additive Manufacturing (AM) is among the metal 3D printing technologies most broadly adopted by the manufacturing industry. The current industry qualification paradigm for critical-application L-PBF parts relies heavily on expensive non-destructive inspection techniques such as X-Ray Computed Tomography (XCT), which significantly limits the use-cases of L-PBF. In situ monitoring of the process promises a less expensive alternative to ex situ testing, but existing sensor technologies and data analysis techniques struggle to detect sub-surface flaws (e.g., porosity and cracking) on production-scale L-PBF printers. RTX Technologies Research Center (RTRC) has licensed ORNL’s Peregrine software package – a printer- and camera-agnostic data analytics tool designed specifically for detecting process anomalies using in situ data collected during powder bed printing. The goal of this project was to feed temporally rich, multi-modal sensor data, including visible light, integrated near infrared (NIR), and spatially mapped co-axial melt pool thermal emission data into Peregrine to enable detection of subsurface flaws. XCT data was used as ground truth training data to allow Peregrine’s deep learning algorithms to recognize anomalies in these complex data streams in both test artifacts and industrially relevant geometries. Completion of this program has seen the successful implementation of multi-modal, multi-layer sensor data footprints for training of machine learning models in Peregrine. Flaws detected in XCT data have been successfully detected directly from this in situ data footprint, and initial analyses of the in situ probability-of-detection has been conducted, showing performance levels commensurate with traditional non-destructive evaluation (NDE) methods. The in situ monitoring methodology was then applied to an industrially relevant component that was using post-build NDE, highlighting the utility of the proposed method for hard-to-inspect AM components. As a direct result of this program, two journal manuscripts [1], [2] have been published in Additive Manufacturing, with additional manuscripts planned following program completion.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Building a DFT+U machine learning interatomic potential for uranium dioxide

Despite uranium dioxide (UO 2 ) being a widely used nuclear fuel, fuel performance models rely extensively on empirical correlations of material behavior, leveraging the historical operating experience of UO 2 . Mechanistic models that consider an atomistic understanding of the processes governing fuel performance (such as fission gas release and creep) will enable a better description of fuel behavior under non-prototypical conditions such as in new reactor concepts or for modified UO 2 fuel compositions. To this end, molecular dynamics simulation is a powerful tool for rapidly predicting physical properties of proposed fuel candidates. However, the reliability of these simulations depends largely on the accuracy of the atomic forces. Traditionally, these forces are computed using either a classical force field (FF) or density functional theory (DFT). While DFT is relatively accurate, the computational cost is burdensome, especially for f-electron elements, such as actinides. By contrast, classical FFs are computationally efficient but are less accurate. For these reasons, we report a new accurate machine learning interatomic potential (MLIP) for UO 2 that provides high-fidelity reproduction of DFT forces at a similar low cost to classical FFs. We employ an active learning approach that autonomously augments the DFT training data set to iteratively refine the MLIP. To further improve the quality of our predictions, we utilize transfer learning to retrain our MLIP to higher-accuracy DFT+U data. We validate our MLIPs by comparing predicted physical properties (e.g., thermal expansion and elastic properties) with those from existing classical FFs and DFT/DFT+U calculations, as well as with experimental data when available.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2026

Automated ICRF heating surrogate modeling via machine learning

This work introduces automated machine learning workflows that address critical bottlenecks in surrogate model development for Ion Cyclotron Range of Frequencies (ICRF) heating applications. The automated framework includes data analysis tools that transform raw datasets into actionable insights in seconds, replacing weeks of manual exploratory effort and ensuring consistent, reproducible dataset characterization. By integrating advanced hyperparameter optimization (HPO) methods including Bayesian optimization via BoTorch and Tree-structured Parzen Estimators (TPE), the framework significantly reduces model development time from weeks to hours, decreasing computational cost and required expertise, while enabling high-accuracy surrogate models. Compared to traditional hyperparameter scanning (HPS) techniques such as methodical, randomized, and grid searches, HPO methods achieve superior convergence and predictive performance, even when compared to already well-tuned reference models. On NSTX High Harmonic Fast Wave (HHFW) heating datasets, both Random Forest Regressor (RFR) and neural network surrogates demonstrate improved accuracy, achieving R 2 values beyond 0.97 and 0.98, respectively. The results show that while HPO gains are modest for robust architectures like RFR, they become essential for more sensitive models such as neural networks, highlighting the trade-offs across optimization strategies. Through automated workflows that eliminate manual hyperparameter tuning and require minimal ML expertise, this work enables widespread adoption of high-fidelity surrogate models across the fusion community for real-time plasma control, uncertainty quantification, rapid experimental scenario development, and integrated system optimization.

Sanchez-Villar, Alvaro [Princeton Plasma Physics L↗
DOE OSTI2022

HPC Analytics of Fused Thermal Plants Data to Optimize Operating Envelope

In this project, ORNL extensively reviewed the ORAP RAM data, and it guided us to develop machine learning models that can predict time to next failures and forecast failure trends, which will be useful for optimizing power plant operation strategies. More specifically, we trained multiple random forest models and evaluated the model accuracy to validate with 10+ years of historical data. In addition, we implemented a web-based graphical user interface system for the models to show how our models can be used in more intuitive ways. This proof of concept allowed exploration of model use with power plant operators in mind. Developed machine learning models will be helpful for managing risks, planning maintenance and operation, ultimately reducing the down time and increasing the service hours. For future work, there are several interesting research topics including but not limited to model enhancement, creating synergy with traditional failure modeling approaches, and data-driven actionable recommendation and suggestions.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2023

Connecting Large‐Scale Meteorological Patterns to Extratropical Cyclones in CMIP6 Climate Models Using Self‐Organizing Maps

Abstract Extratropical cyclones (ETCs) are responsible for the majority of cool‐season extreme events in the northeastern United States (NEUS), often leading to high‐impact weather conditions that can have wide‐ranging socioeconomic impacts. Evaluating the ability of climate models to adequately simulate ETC dynamics is essential for improving model performance and increasing confidence in future projections used by stakeholders and policymakers. ETCs are traditionally studied using techniques such as case studies and synoptic typing, however, these approaches can be time‐consuming, require subjective analysis, and do not necessarily identify the coincident large‐scale meteorological patterns (LSMPs). Here, we apply self‐organizing maps (SOMs) as an automated machine‐learning approach to characterize the LSMPs and associated frequency and intensity of discrete ETC events over NEUS. The dominant patterns of geopotential height variability are identified through SOM analysis of five reanalysis products during the last four decades. ETC events are tracked using TempestExtremes and are integrated with SOMs to classify the accumulated cyclone activity (ACA) associated with each pattern. We then evaluate the skill of CMIP6 historical experiments in simulating the LSMPs and ETC events identified in the SOM. Our results identify a robust bias toward more zonal patterns, with models struggling to reproduce the more amplified patterns typically associated with the highest cyclone activity. While model resolution has some impact on simulation credibility, model configuration appears to be more important in LSMP representation. The vast majority of CMIP6 models produce too few ETCs, although model errors are distributed around historical reanalyses when ACA is normalized by storm frequency.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Predicting wind-driven spatial deposition through simulated color images using deep autoencoders

Abstract For centuries, scientists have observed nature to understand the laws that govern the physical world. The traditional process of turning observations into physical understanding is slow. Imperfect models are constructed and tested to explain relationships in data. Powerful new algorithms can enable computers to learn physics by observing images and videos. Inspired by this idea, instead of training machine learning models using physical quantities, we used images, that is, pixel information. For this work, and as a proof of concept, the physics of interest are wind-driven spatial patterns. These phenomena include features in Aeolian dunes and volcanic ash deposition, wildfire smoke, and air pollution plumes. We use computer model simulations of spatial deposition patterns to approximate images from a hypothetical imaging device whose outputs are red, green, and blue (RGB) color images with channel values ranging from 0 to 255. In this paper, we explore deep convolutional neural network-based autoencoders to exploit relationships in wind-driven spatial patterns, which commonly occur in geosciences, and reduce their dimensionality. Reducing the data dimension size with an encoder enables training deep, fully connected neural network models linking geographic and meteorological scalar input quantities to the encoded space. Once this is achieved, full spatial patterns are reconstructed using the decoder. We demonstrate this approach on images of spatial deposition from a pollution source, where the encoder compresses the dimensionality to 0.02% of the original size, and the full predictive model performance on test data achieves a normalized root mean squared error of 8%, a figure of merit in space of 94% and a precision-recall area under the curve of 0.93.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Data-driven Quasi-static Surrogate Model for Nuclear-powered Integrated Energy Systems

The integration of nuclear power into energy systems presents a promising avenue to address the growing global energy demands while minimizing greenhouse gas emissions. In this paper, we introduce a data-driven quasi-static surrogate model for nuclear-powered Integrated Energy Systems (IES) that comprises various components, including a small modular reactor (SMR), energy manifold (EM), balance of plant (BOP), high-temperature steam electrolysis (HTSE), and district heating (DH) system. Traditional physics-based models for these components often entail significant computational overhead and time consumption, necessitating the development of efficient surrogate models. The development of a complete surrogate model for the IES involves the creation of individual surrogate models for each component, leveraging machine learning techniques and simulated data. These isolated surrogate models are subsequently integrated, enabling a holistic view of the IES and reducing the computational burden associated with detailed physics-based simulations. This paper outlines the development process, validation, and the performance evaluation of the surrogate models. The findings shed light on the accuracy and applicability of the surrogate models in practical scenarios, demonstrating their potential to expedite the analysis of nuclear-powered IES and inform future research and development efforts.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Data-driven Quasi-static Surrogate Models for Nuclear-powered Integrated Energy Systems

The integration of nuclear power into energy systems presents a promising avenue to address the growing global energy demands while minimizing greenhouse gas emissions. In this paper, we introduce a data-driven quasi-static surrogate model for nuclear-powered Integrated Energy Systems (IES) that comprises various components, including a small modular reactor (SMR), steam manifold, balance of plant (BOP), high-temperature steam electrolysis (HTSE), and district heating (DH) system. Traditional physics-based models for these components often entail significant computational resource and time consumption, necessitating the development of efficient surrogate models. The development of a complete surrogate model for the IES involves the creation of individual surrogate models for each component, leveraging machine learning techniques and simulated data. These isolated surrogate models are subsequently integrated, enabling a holistic view of the IES and reducing the computational burden associated with detailed physics-based simulations. This paper outlines the development process, validation, and the performance evaluation of the surrogate models. The exceptional performance, with low root-mean-squared errors and R-squared scores of at least 99.8% across all individual surrogate models, underscores their accuracy and practical applicability. These results demonstrate the potential of these models to expedite the analysis of nuclear-powered IES, offering insights that can shape future research and development efforts.

08 HYDROGEN↗
DOE OSTI2024

Accelerating Computational Materials Discovery with Machine Learning and Cloud High-Performance Computing: from Large-Scale Screening to Experimental Validation

High-throughput computational materials discovery has promised significant acceleration of the design and discovery of new materials for many years. Despite a surge in interest and activity, the constraints imposed by large-scale computational resources present a significant bottleneck. Furthermore, examples of large-scale computational discovery carried through experimental validation remain scarce, especially for materials with product applicability. In this paper, we demonstrate how this vision became reality by first combining state-of-the-art artificial intelligence (AI) models and traditional physics-based models on cloud high performance computing (HPC) resources to quickly navigate through more than 32 million candidates and predict around half a million potentially stable materials. Focusing on solid-state electrolytes for battery applications, our discovery pipeline further identified 18 promising candidates with new compositions and rediscovered a decade’s worth of collective knowledge in the field as a byproduct. By employing around one thousand virtual machines in the cloud, this process took less than 80 hours. We then synthesized and experimentally characterized the structures and conductivities of our top candidates, the Na x Li 3-x YCl 6 (0.5 ≤ x ≤ 2.5) series, demonstrating the potential of these compounds to serve as solid electrolytes. Additional candidate materials are currently under experimental investigation that could offer more examples of the computational discovery of new phases of Li- and Na-conducting solid electrolytes. We believe this unprecedented approach of synergistically integrating AI models and cloud HPC not only accelerates materials discovery but also showcases the potency of AI-guided experimentation in unlocking transformative scientific breakthroughs with real-world applications.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Neural Network‐Based Methods for Ocean Surface Wave Measurement Using Submarine Distributed Acoustic Sensing (DAS)

Two new data-driven models for estimating ocean surface waves from distributed acoustic sensing (DAS) submarine cable strain rate are developed using supervised machine learning on a 10-day data set collected offshore of Oliktok Point, Alaska. The new models were trained on target data from seafloor pressure moorings at three sites spaced evenly along 27.1 km of cable and were benchmarked against an empirical transfer function method previously used to estimate waves from DAS. A model which uses convolutional neural networks to transform 2-km frequency-wavenumber strain spectra to seafloor pressure spectra outperforms the benchmark in wave height prediction (RMSE of 0.15 vs. 0.41 m) and period prediction (0.29 vs. 0.37 s) when evaluated on a held-out test data set. When applied to a DAS data set collected on the same cable 2 years prior, the CNN-based model maintained similar significant wave height performance (RMSE = 0.23 m) relative to available satellite altimetry data. A two-hidden-layer, fully connected neural network which transforms 1-D strain spectra to seafloor pressure spectra also outperforms the benchmark in wave height prediction (RMSE of 0.19 vs. 0.41 m), but does not generalize as well to the prior data. Regression-based machine learning is useful for estimating waves from DAS data when the pressure-strain relationship varies temporally and spatially across different wave conditions. Models can be applied to DAS data to measure waves with higher spatial resolution and longer temporal coverage than traditional methods, which often measure waves only at a single point.

Davis, Jacob R. [Univ. of Washington, Seattle, WA ↗
NASA NTRSDate not supplied

Detecting Risk and Anomalies in Airplane Dynamics Through Entropic Analysis of Time Series Data

Despite recent efforts to move away from traditional threshold exceedance detection methods for aircraft state monitoring, modern aircraft still rely on safety thresholds to communicate to pilots the identification of an anomaly in the aircraft when a threshold is surpassed. Current anomaly detection methods mainly depend on uninterpretable machine learning models to learn complex patterns and relationships contained in the time series data of aircraft. Although these methods are capable of identifying known anomalies, their deficiency in interpretability presents a challenge when translating them to different aircraft. To overcome this deficiency, entropic analysis of aircraft dynamics seeks to characterize the complexity, or lack thereof, of the aircraft dynamics prior to the development of a risk scenario. This complexity characterization provides a more straightforward summary of state changes in the dynamics of flight variables. To build a foundation for entropic analysis, we analyzed the complexity of unstable approaches, an anomalous event present in many of today’s aviation accidents. The analysis revealed a statistically significant difference in the complexity distribution of flight variables under a stable approach versus an unstable approach. These differences in complexity were especially notable minutes before an approach was identified as unstable. Moreover, the multiscale entropic analysis revealed the presence of signal complexity at multiple time scales across multiple time windows before landing. By capturing state changes and corrections in the aircraft dynamics using entropy, advanced, yet still interpretable, sensor systems based on entropic frameworks from this study can be constructed in the future using classical machine learning approaches.

Risk detection↗
DOE OSTI2024

Enhanced Detection of Primary Biological Aerosol Particles Using Machine Learning and Single-Particle Measurement

Accurately identifying primary biological aerosol particles (PBAPs) using analytical techniques poses inherent challenges due to their resemblance to other atmospheric carbonaceous particles. Here, we present a study of an enhanced method for detecting PBAPs by combining single-particle measurement with advanced supervised machine learning (SML) techniques. We analyzed ambient particles from a variety of environments and lab-generated standards, focusing on chemical composition for traditional rule-based and clustering approaches and incorporating morphological features into the SML approaches, neural networks and XGBoost, for improved accuracy. This study demonstrates that SML methods outperform traditional methods in quantifying PBAPs, achieving significant improvements in precision, recall, F1-score, and accuracy, leading to an increased number of detected PBAPs by at least 19%. The adaptability of the proposed XGBoost-based SML model is showcased in comparison to traditional methods in categorizing PBAPs for blind data sets from different geographical locations. Two field case studies were investigated, over agricultural land and Amazonia rain forest, representing relatively low and high concentrations of PBAPs, respectively, where XGBoost consistently detected up to 3.5 times more PBAPs than traditional methods. Precise detection of PBAPs in the atmosphere could significantly improve the prediction of climatic impacts by them.

42 ENGINEERING↗
NASA NTRSDate not supplied

Developing Concepts of Operations Using Multi-Step Tool Techniques With Large Language Models

The National Aeronautics and Space Administration (NASA) Air Mobility Pathfinders (AMP) project is developing and evaluating concepts of operations (ConOps) for safe, secure, and scalable Urban Air Mobility (UAM) operations. The AMP project’s Operational Concepts, Architecture, and Requirements Integration (OCARI) Team is using a Model Based System Engineering (MBSE) approach for integration, interoperability, and traceability of Advanced Air Mobility (AAM) ecosystems centered around urban air taxi services. The team’s goal is to define structures and behaviors needed for system feasibility, readiness, and interoperability, establish a UAM knowledge base, and trace and validate assumptions and requirements relevant to AAM. NASA Langley Research Center (LaRC) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of multi-modal transportation systems. The Knowledge-based Digital Platform (KbDP) is a concept being developed that ties the workflows of Project Managers (PM), Principal Investigators (PI), and System Engineers together across organizational boundaries. It does so through the management of an information database defined by mathematical, data science, and system engineering principles. Machine Learning (ML) algorithms play a key role in this concept by extracting meaningful knowledge from relational and graph databases, document repositories, and system artifacts, which the human user leverages to greatly improve the efficiency and effectiveness of their research. Recent advancements in the field of Large Language Models (LLMs), specifically models trained for tool use, such as Command-R , now allow for the reliable implementation of single-step and multi-step tool-centric systems. These techniques provide the LLM with a set of tools, in our case Python functions, that can be called on to answer a much wider range of questions compared to LLMs implemented using a traditional single-source or Retrieval Augmented Generation (RAG) approach. Through this method, the LLM can pull information from multiple data sources, such as relational or graph databases, document repositories, application programming interfaces (APIs), and SysML artifacts depending on the user’s question. The LLM can also output the information in a variety of different formats, using output generation tools, such as CSV, UML, or SysML artifacts. Additionally, tools can be assigned roles and can work together to provide answers to queries in an “agent” like approach, similar to that implemented by Microsoft’s AutoGen framework where different agents can converse with each other to accomplish tasks. Previously, our team developed a chatbot system with “agent like” functionality in the form of different “modes” the user could select from a user interface (UI), this architecture can be seen on the left in figure 1. Three different modes were implemented, the first mode allowed the LLM to utilize the structures and algorithms within a graph database to trace UAM requirements. The second mode gave the LLM access to a vector search capable of providing relevant information from thousands of document pages related to UAM ConOps and requirements. The third mode served as a general assistant where users could enter open-ended questions and custom prompts to utilize the LLM for different use-cases. This system improved the process surrounding generating and analyzing information related to UAM requirements, however, the implementation provided a clunky user experience. Users were required to know what mode to select within the UI in advance before entering their question to the selected tool. Moreover, the different tools were isolated from each other, they lacked bidirectional links that would allow for tools to collaborate to generate better responses. Our team is working on a new architecture, seen on the right in the below figure, with the goal to address many of the UX shortcomings of our original system while improving the accuracy and depth of responses from the LLM. This new system will automatically select the appropriate tool to use based off the user’s question. Each tool will be capable of calling on any of the other tools available to the LLM, resulting in a collaborative pipeline where tools can pass data between other tools until enough data is received to generate an answer to the user’s question. Using a locally deployed, open-source, LLM, the NASA OCARI team, in collaboration with Collins Aerospace, will implement a prototype application that will bridge knowledge across multiple sources to assist System Engineers (SEs) with requirements discovery and tracing, research question and use case identification, and assumption validation. Such a system will also allow SEs to more easily, and intuitively, explore the AAM ecosystem, ultimately improving the efficiency and effectiveness of the SE's research and decision-making processes surrounding ConOps development and validation. In this session, our team will provide a video demonstration of our new prototype architecture in action. We will also present an overview of our prototype system architecture and talk about its advantages over traditional LLM deployments along with how those advantages can provide additional value to the field of System Engineering.

systems engineering↗
DOE OSTI2025

Defect Detection Model Development for Large Scale Thermoplastic Printing

Large-format additive manufacturing (LFAM) offers several advantages, including high throughput, cost-effective pellet-fed extrusion, and the capability to produce large-scale structures. The main pain points of LFAM include start and stops during the printing process, warpage, long layer times that lead to bead freezing, and bead separation due to shrinkage. These issues can lead to overfill, underfill and buildup of material in different sections of a print. This can lead to hidden defects embedded within the printed layers, or even ultimate failure of the printed structure. This ensures these defects can only be identified through nondestructive testing (NDT) inspection methods after printing, which can be timely and costly. Aligned Vision work specializes in 2D projectors with visual inspection systems and machine learning. Traditionally system is used for composite layup and layup inspections. In this work we used the LFAM system at Oak Ridge National Laboratory to create defect rich samples. The Aligned Vision inspection system then performed in-situ monitoring of the print process after each part was printed. This in-situ vision inspection system was used to develop a layer-by-layer inspection model that looks for overfill, underfill, and the buildup of defects using only a camera-based vision system. This leads to the assurance of high-quality production components.

36 MATERIALS SCIENCE↗