Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “GPT”

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.

139 records · Page 8
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph with ChatGPT

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) concept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze requirements within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗
NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph With ChatGPT - Poster

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗
NASA NTRSDate not supplied

Emulating Nature: The Future of Sustainable Design with BIDARA

BIDARA (Bio-inspired Design and Research Assistant) is a GPT-4o chatbot that was instructed to help scientists and engineers understand, learn from, and emulate the strategies used by living things to create sustainable designs and technologies. BIDARA can guide users through the Biomimicry Institute’s Design Process, a step-by-step method to propose biomimetic solutions to challenges. This process includes defining the problem, biologizing the challenge, discovering natural models, abstracting design strategies, and emulating nature's lessons.

Brandon Ruffridge↗
DOE OSTI2022

E-Beam Irradiation Beamline at Jefferson Lab for Wastewater Treatment

Electron beam (e-beam) irradiation is an advanced method for removing the emerging organic contaminants in wastewater, such as 1,4-dioxane, and per- and polyfluoroalkyl sub?stances (PFAS), which have the potential to be regulated in the near future but are difficult to degrade by conventional treatment methods. This dissertation was based on a collabo?rating study between Jefferson Lab (Jlab) and Hampton Roads Sanitation District (HRSD) to evaluate the impacts of e-beam irradiation on the degradation of 1,4-dioxane and PFAS. It presents the detailed design of an e-beam irradiation beamline, the beamline simulation using general particle tracer (GPT), the installation, and the successful commissioning. The beamline is an extended section to the Upgraded Injector Test Facility (UITF) at Jlab, which is a continuous wave (CW), superconducting radio frequency (SRF) linear accelerator with an energy up to 10 MeV. To let the sample volume receive a significant and uniform dose distribution, the sample target was designed by investigating the dose distribution simulated with a Monte-Carlo code, FLUKA. The optimized beam energy was 8 MeV and the beam current for irradiation was ? 100 nA. With the use of a solenoid and a raster, the electron beam was expanded to the optimized size, 1? ? 15 mm, at the sample target. This dis?sertation also presents the irradiation experiments for 64 1,4-dioxane samples and 48 PFAS samples in different water matrices, including real wastewater, which were prepared and an?alyzed by HRSD. The absorbed doses of samples were obtained by designing a new method that combines the FLUKA simulation and dose mapping experiments. The irradiation re?sults showed that around 95% of 1,4-dioxane was removed at a low dose of ? 2 kGy, and PFAS was possibly removed at a lower dose compared to similar research. This work is a first implementation of SRF technology for wastewater irradiation. It pro?vides a valuable new research platform for wastewater remediation. This will be in support of future industrial applications of advanced SRF technologies and better understanding of the effect of e-beam irradiation on wastewater or water treatment.

Li, Xi↗
DOE OSTI2023

Modeling the CEBAF Injector at 200 kV: Investigating K-Long Beam Conditions with and without Wien Filter

The upcoming K-Long experiment [1] ain Hall D at Jefferson Lab presents unique beam requirements, featuring a significantly low bunch repetition rate and an unusually high bunch charge. This experiment, which utilizes the CEBAF accelerator in conjunction with the GlueX experimental setup, aims to study strange hadron spectroscopy by measuring the differential cross section and polarizations of produced hyperons such as Λ, Σ, Ξ, and Ω. By directing an intense K-Long beam towards the LD2/LH2 target, new and valuable data can be obtained. To optimize the CEBAF injector specifically for this experiment, we employed Multi-Objective Genetic Optimization (MGO) using General Particle Tracer (GPT) simulations. Through this approach, we determined the optimal magnetic elements and radiofrequency (RF) settings required to achieve a K-Long bunch charge of 0.64 pC at an energy of 200 kV. We conducted simulations with both the Wien Filter turned on and off to examine its impact on the beam. Furthermore, we investigated the transmission efficiency and beam characteristics of electron beams with varying charge per bunch through the injector, considering the simultaneous operation of all four CEBAF Halls. The results of our study offer valuable insights and guidance for optimizing the CEBAF injector not only for the Jefferson Lab K-Long experiment but also for other experiments that entail similar beam conditions.

Pokharel, Sunil↗
DOE OSTI2016

CE TSUNAMI-3D Algorithm Improvements in SCALE 6.2

The TSUNAMI (Tools for Sensitivity and Uncertainty Analysis Methodology Implementation) capabilities within the SCALE code system make use of sensitivity coefficients for an extensive number of criticality safety applications such as quantifying the data-induced uncertainty in the eigenvalue of critical systems, assessing the neutronic similarity between different systems, quantifying computational biases, and guiding nuclear data adjustment studies. The continuous-energy (CE) TSUNAMI-3D code is a new tool included in SCALE 6.2 that allows for eigenvalue and generalized response sensitivity calculations using high-fidelity CE Monte Carlo methods. This paper describes several improvements to CE TSUNAMI-3D beyond those previously published. These improvements primarily consist of - A multi-response capability for the CE TSUNAMI generalized response sensitivity calculation mode; and - Efficiency improvements in CE TSUNAMI's Iterated Fission Probability (IFP)-based algorithms. This paper documents several improvements to the CE TSUNAMI-3D sensitivity algorithms included in the SCALE 6.2 release. These improvements have enabled the simulation of multiple GPT responses within a single CE TSUNAMI simulation, a feature that increases the memory footprint of the simulations by approximately 1-3% per response and the runtime by approximately 1-2%, per response. These algorithmic improvements have also significantly improved the computational efficiency of CE TSUNAMI IFP-based sensitivity calculations, reducing the memory footprints approximately by a factor of 3 and the simulation runtimes by 10-70%. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

GOLEM: GOld standard for Learning and Evaluation of Motifs

Motifs are distinctive, recurring, widely used idiom-like words or phrases, often originating from folklore, whose meaning is anchored in a narrative and have a significance as communicative devices across a wide range of media, including news, literature, and propaganda. Many motifs concisely imply a large constellation of culturally relevant information, and their broad usage suggests their cognitive importance as touchstones of cultural knowledge. As such, their detection is a step towards culturally aware natural language processing. We present GOLEM (GOld standard for Learning and Evaluation of Motifs) a dataset of English news articles, opinion pieces, and broadcast transcripts annotated for motific information. The dataset identifies 25,737 motif candidates across 34 motif types drawn from three cultural or national groups: Jewish, Irish, and Puerto Rican. The dataset contains 2,024,141 words split into 25,737 text snippets drawn from 8,073 articles. Each motif candidate is labeled according to a scheme which identifies the type of usage (motific, referential, eponymic, or unrelated), resulting in 1,743 actual motific instances in the data. Annotation was performed by individuals identifying as members of each group and achieved a Fleiss’ kappa (?) of > 0.55. In addition to the data, we demonstrate that classification of the candidate type is a challenging task for Large Language Models (LLMs) using a few-shot approach; recent models such as T5, FLAN-T5, GPT-2, and Llama 2 (7B) achieved a performance of 41% accuracy at best, where the majority class accuracy is 41% and the average chance accuracy is 27%. These data will support development of new models and approaches for detecting (and reasoning about) motific information in text.

motif, culture, natural language, artificial intel↗
DOE OSTI2025

Large Language Model Integration for Knowledge Retrieval and Interaction for the DUNE Experiment

The Deep Underground Neutrino Experiment (DUNE) is a next-generation neutrino experiment that will generate an unprecedented volume of heterogeneous information-from documentation and technical notes to experimental data and reconstruction pipelines. Efficient knowledge retrieval and contextual understanding are increasingly critical for collaboration-wide productivity and onboarding. In this work, we present DUNE-GPT, a prototype framework that leverages large language models (LLMs) and retrieval-augmented generation (RAG) to enable natural-language querying of DUNE's internal documentation and technical resources. The system provides an intelligent interface for DUNE collaborators to interact with experiment-specific knowledge while maintaining data privacy and infrastructure compliance within Fermilab computing resources.

Rafique, A. [Argonne (main)]↗
DOE OSTI2024

Protein–Protein Interaction Networks Derived from Classical and Machine Learning-Based Natural Language Processing Tools

The study of protein-protein interactions (PPIs) provides insight into various biological mechanisms, including the binding of antibodies to antigens, enzymes to inhibitors or promoters, and receptors to ligands. Recent studies of PPIs have led to significant biological breakthroughs. For example, the study of PPIs involved in the human:SARS-CoV-2 viral infection mechanism aided in the development of the SARS-CoV-2 vaccines. Though several databases exist for the manual curation of PPI networks, text mining methods have been routinely demonstrated as useful alternatives for newly studied or understudied species where databases are incomplete. Here, the relationship extraction (RE) performance of several open-source classical text processing, machine learning (ML)-based natural language processing (NLP), and large language model (LLM)-based NLP tools were compared. Overall, our results indicated that networks derived from classical methods tend to have high true positive rates at the expense of having overconnected-networks, ML-based NLP methods have lower true positive rates but networks with the closest structures to the target network, and LLM-based NLP methods tend to exist in-between the two other approaches, with variable performances. Finally, the selection of a specific NLP approach should be tied to the needs of a study and text availability, as models varied in performance due to the amount of text provided.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

LLM-Based Adaptive Distribution Voltage Regulation Under Frequent Topology Changes: An In-Context MPC Framework

This paper proposes a large language model (LLM) based adaptive inverter control for distribution voltage regulation under frequent topology changes. We leverage the ability of the LLM to perform in-context learning and create a topology-adaptive surrogate model for power flow calculation. The surrogate model is then integrated with a long short-term memory-based load forecaster and a model predictive control (MPC) scheme to achieve the optimal inverter control that adapts to frequent topology changes. Unlike many existing works that assume fixed-topology grids or require the knowledge of all possible topologies when training a model, the proposed in-context MPC method tackles the distribution voltage control problem under various topologies and adapts to unknown topologies with limited data requirement for fine-tuning. The effectiveness of our method is demonstrated on a modified IEEE 123-bus test system.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

A Preferences Corpus and Annotation Scheme for Human-Guided Alignment of Time-Series GPTs

The process of time-series forecasting such as predicting trajectories of silicon content in blast furnaces is a difficult task. Most time-series approaches today focus on scalar-type MSE loss optimization. This optimization approach, while widely common, could benefit from the use of human expert or process-level preferences. In this paper, we introduce a novel alignment and fine-tuning approach that involves learning from a corpus of preferred and dis-preferred time-series prediction trajectories. Our contributions include (1) a preference annotation pipeline for time-series forecasts, (2) the application of Score-based Preference Optimization (SPO) to train decoder-only transformers from preferences, and (3) results showing improvements in forecast quality. The approach is validated on both proprietary blast furnace data and the UCI Appliances Energy dataset. The proposed preference corpus and training strategy offer a new option for fine-tuning sequence models in industrial settings.

DPO↗
DOE OSTI2014

CONTINUOUS-ENERGY MONTE CARLO METHODS FOR CALCULATING GENERALIZED RESPONSE SENSITIVITIES USING TSUNAMI-3D

This work introduces a new approach for calculating sensitivity coefficients for generalized neutronic responses to nuclear data uncertainties using continuous-energy Monte Carlo methods. The approach presented in this paper, known as the GEAR-MC method, allows for the calculation of generalized sensitivity coefficients for multiple responses in a single Monte Carlo calculation with no nuclear data perturbations or knowledge of nuclear covariance data. The theory behind the GEAR-MC method is presented here, and proof of principle is demonstrated by using the GEAR-MC method to calculate sensitivity coefficients for responses in several 3D, continuous-energy Monte Carlo applications.

CLUTCH↗