SEARCH · Engineering Papers
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.
This is my Intern poster and deliverable. It is about using knowledge graphs and large language models for safety analysis in nuclear reactors.
This paper addresses the challenge of traffic monitoring and incident detection in remote areas, utilizing multimodal large language models (LLMs) deployed on edge AI devices. The key novelty of the LLM is to convert real-time video streams into descriptive texts, enabling low-bandwidth transmissions and reliable detection of anomalies and incidents in environments of intermittent connectivity. The model is developed based on fine-tuning open-source LLMs and extending it with multi-modal capabilities to analyze video frames. Our work also involves deploying this model on edge devices such as Nvidia IGX Orin and is planned to be tested in realistic environments in future work. The methodology includes data set curation, iterative model fine-tuning and compression, and hardware-based optimization. This approach aims to enhance traffic safety and response speed in remote areas, marking a significant advancement in the application of AI for traffic monitoring and safety management.
In this study, we investigated strategies to address trust issues arising from errors in large language models (LLMs). The study examined the impact of confidence scores, system capability explanations, and user feedback on trust restoration post-error. 68 participants viewed the responses of an LLM to 20 general trivia questions, with an error introduced on the third trial. Each participant was presented with one mitigation strategy. Participants rated their overall trust in the model and the reliability of the answer. Results showed an immediate drop in trust after the error; however, there were no differences across the three strategies in trust recovery. All conditions had a logarithmic trend in trust recovery following error. Differences in overall trust were predicted by perceived reliability of the answer, suggesting that participants were evaluating results critically and using that to inform their trust in the model. Qualitative data supported this finding; participants expressed lasting distrust despite the LLM’s later accuracy. Results showcase the need to prioritize accuracy in LLM deployment, because early errors may irrevocably damage user trust calibration and later adoption.
This paper explores the development and application of an investment tool designed to quantify the costs and potential savings associated with integrating large language models (LLMs) into work week management optimization (WMO) within the nuclear industry. LLMs, with their advanced natural language processing capabilities, can significantly enhance various aspects of work management, such as problem identification, prioritization, planning, scheduling, information retrieval, and information summary. Our investment tool focuses on evaluating the return on investment (ROI) for LLM applications in WMO by considering four pivotal decision factors: model selection, application, user training, and hosting options. This paper details the development and implementation of the ROI model and illustrates its application through multiple case studies, analyzing the impact of different variables, such as work time saved, number of requests, and model performance, on the computed ROI over two years. The computed ROI is also compared over different hosting solutions. Our findings indicate that ROI increases with enhanced work time savings and optimal request load but can decline with high request volumes or increased model costs. This model aids decision-makers in the nuclear industry by providing a structured approach to assessing the economic viability and potential savings from integrating LLMs into WMO processes.
This paper explores the development and application of an investment tool designed to quantify the costs and potential savings associated with integrating large language models (LLMs) into work week management optimization (WMO) within the nuclear industry. LLMs, with their advanced natural language processing capabilities, can significantly enhance various aspects of work management, such as problem identification, prioritization, planning, scheduling, information retrieval, and information summary. Our investment tool focuses on evaluating the return on investment (ROI) for LLM applications in WMO by considering four pivotal decision factors: model selection, application, user training, and hosting options. This paper details the development and implementation of the ROI model and illustrates its application through multiple case studies, analyzing the impact of different variables, such as work time saved, number of requests, and model performance, on the computed ROI over two years. The computed ROI is also compared over different hosting solutions. Our findings indicate that ROI increases with enhanced work time savings and optimal request load but can decline with high request volumes or increased model costs. This model aids decision-makers in the nuclear industry by providing a structured approach to assessing the economic viability and potential savings from integrating LLMs into WMO processes.
This study combines Graph Neural Networks (GNNs) and Large Language Models (LLMs) to improve material property predictions. By leveraging both embeddings, this hybrid approach achieves up to a 25% improvement over GNN-only model in accuracy.
Intermediate Representations (IRs) are essential in compiler design and program analysis, yet their comprehension by Large Language Models (LLMs) remains underexplored. This paper presents a pioneering empirical study to investigate the capabilities of LLMs, including GPT-4, GPT-3, Gemma 2, LLaMA 3.1, and Code Llama, in understanding IRs. We analyze their performance across four tasks: Control Flow Graph (CFG) reconstruction, decompilation, code summarization, and execution reasoning. Our results indicate that while LLMs demonstrate competence in parsing IR syntax and recognizing high-level structures, they struggle with control flow reasoning, execution semantics, and loop handling. Specifically, they often misinterpret branching instructions, omit critical IR operations, and rely on heuristic-based reasoning, leading to errors in CFG reconstruction, IR decompilation, and execution reasoning. The study underscores the necessity for IR-specific enhancements in LLMs, recommending fine-tuning on structured IR datasets and integration of explicit control flow models to augment their comprehension and handling of IR-related tasks.
Objective: To develop and evaluate an automated system for identifying healthcare barriers focusing on transportation issues in veterans’ clinical notes using large language models (LLMs) and to assess the impact of different prompting strategies on classification performance and explanation consistency. Methods: We developed a hybrid system combining pattern matching for templated notes with LLM analysis for free-text notes. Using 2000 manually annotated clinical notes, we compared four prompting strategies (dual-role short, dual-role long, analysis-first, analysis-only) across Mistral-7B and Llama-3.1 models. We evaluated classification performance using standard metrics and assessed explanation consistency through embedding similarity analysis. Results: The analysis-first strategy achieved superior performance, with Mistral-7B reaching an F1 score of 0.914, outperforming traditional machine learning approaches (GBM: 0.786, BERT: 0.811). LLMs demonstrated higher explanation consistency within models (mean cosine similarity 0.887–0.908) compared to cross-model similarities (0.767–0.872). Pattern matching successfully handled 6.7% of templated notes deterministically. Mistral-7B showed greater internal consistency but higher abstention rates compared to Llama-3.1. Conclusion: Requiring LLMs to analyze evidence before classification improves both accuracy and explanation consistency for identifying transportation barriers in clinical notes. This approach enables automated barrier detection at scale while providing clinically relevant explanations, supporting both population-level healthcare planning and individual patient care decisions.
Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.
Deep neural networks are known to be resilient to random bit-wise faults in their parameters. However, this resilience has primarily been established through evaluations of classification models. The extent to which this claim holds for large-language models remains underexplored. In this work, we conduct an extensive measurement study on the impact of random bitwise faults in commercial-scale language models. We perform an in-depth analysis of the resulting generation outputs. We first expose that these language models are not truly resilient to random bit-flips. While aggregate metrics such as accuracy may suggest resilience, an in-depth inspection of the generated outputs shows significant degradation in text quality. Our analysis also shows that tasks requiring more complex reasoning suffer more from performance and quality degradation. Moreover, we extend our analysis to models with augmented reasoning capabilities, such as Chain-of-Thought or Mixture of Experts architectures, and characterize their failure scenarios under random bit-flips.
With advances in imaging technologies, modern photovoltaic (PV) systems generate large volumes of heterogeneous image data, including visible, electroluminescence (EL), and infrared (IR) images. Existing PV image analysis models, particularly deep learning approaches, are typically task-specific and lack cross-modality generalization. To address this limitation, this paper proposes an open-source large language model (LLM)–based unified framework for heterogeneous PV image diagnostics. Through task-aware diagnostic prompting, the framework enables analysis of visible, EL, and IR images within a single pipeline, supporting both zero-shot and few-shot inference and binary and multiclass classification. It is compatible with state-of-the-art multimodal LLMs, including ChatGPT, Gemini, Claude, Qwen, and CLIP. The framework is evaluated on PV module condition classification (clean, soiling, snow, hail, and bird droppings) using visible images, cell crack detection using EL images, and hotspot detection using IR images. GPT-5.1 in few-shot mode achieves the best performance, with classification accuracy exceeding 97.3%. Open-source models such as Qwen and CLIP also deliver competitive results on visible images (around 90% accuracy), though their performance is more limited on EL and IR modalities. On the full ELPV dataset, the framework achieves 83.5% zero-shot accuracy, within 2.8% of the supervised CNN baseline, confirming scalability to larger benchmarks. Practical aspects such as reproducibility, response latency, and confidence estimation are systematically analyzed. The framework operates across PV image modalities without modality- or task-specific training, making it well suited as a rapid pre-screening tool to support downstream detailed diagnostics. A benchmark dataset of diverse labeled PV images is also released.
The unprecedented growth in artificial intelligence (AI) workloads, recently dominated by large language models (LLMs) and vision-language models (VLMs), has intensified power and cooling demands in data centers. This study benchmarks LLMs and VLMs on two HGX nodes, each with 8× NVIDIA H100 graphics processing units (GPUs), using liquid and air cooling. Leveraging GPU Burn, Weights & Biases, and IPMItool, we collect detailed thermal, power, and computation data. Results show that the liquid-cooled systems maintain GPU temperatures between 41-50$^\circ$C, while the air-cooled counterparts fluctuate between 54-72$^\circ$C under load. This thermal stability of liquid-cooled systems yields 17% higher performance (54 TFLOPs/ GPU vs. 46 TFLOPs/GPU), performance-per-watt, reduced energy overhead, and greater system efficiency than the air-cooled counterparts. These findings underscore the energy and sustainability benefits of liquid cooling, offering a compelling path forward for hyperscale data centers seeking to optimize AI infrastructure. https://github.com/iscaas/Cooling-Matters.
This research introduces a comprehensive framework for creating and deploying a digital twin platform for continuous monitoring and predictive maintenance within industrial settings. Through utilizing advanced technologies, including Unreal Engine 5, Unity 3D, the Message Queue Telemetry Transport protocol, Random Forest machine learning algorithms, and Large Language Models (LLMs), we establish a platform that digitally reproduces physical equipment and translates digital controls into real-world actions. This facilitates preventive maintenance approaches and improves operational effectiveness. The digital twin platform gathers sensor data from operational equipment, analyzes it using machine learning, and delivers practical insights to prevent potential malfunctions and enhance equipment performance. Furthermore, the incorporation of a web portal enables efficient monitoring and access to historical data, educational materials, and equipment status information. Preliminary findings indicate that digital twins can transform industrial equipment management and maintenance methodologies.
AI-assisted processes are expected to enhance operational efficiency and improve decision-making, supporting the long-term economic viability of nuclear power plants. However, detailed business analyses of AI-generated cost savings are rarely performed. Given the recent industry interest in Large Language Model (LLM), the U.S. Department of Energy (DOE) Light Water Reactor Sustainability (LWRS) Program has conducted a comprehensive business case analysis of LLM Artificial Intelligence (AI) implementation in nuclear plant engineering workflows. The research employed three complementary business case approaches to evaluate impact of an LLM, using three representative engineering processes as use-cases: Boric Acid Corrosion (BAC) Evaluations, Maintenance Rule Evaluations, and 10 CFR 50.59 Screenings. Through detailed workload analyses and structured interviews, the study quantified significant efficiency improvements ranging from 11% to 59% across these processes. The research further considers how these efficiency gains could translate into tangible reliability improvements through enhanced engineering capacity. Analysis of historical plant trip data indicates that enabling engineers to focus on proactive reliability activities could provide substantial financial benefits through avoided outages, potentially generating greater value than the direct efficiency improvements alone. By documenting successful applications, implementation challenges, and strategic opportunities, this research provides nuclear utilities with a practical framework for evaluating the value of AI technology to support long-term operations through advanced digital technologies.
Cybersecurity breaches targeting electrical substations constitute a significant threat to the integrity of the power grid, necessitating comprehensive defense and mitigation strategies. Any anomaly in information and communication technology (ICT) should be detected for secure communications between devices in digital substations. This paper proposes large language models (LLMs), e.g., ChatGPT, for the cybersecurity of IEC 61850-based communications. Multi-cast messages such as generic object oriented system events (GOOSE) and sampled values (SV) are used for case studies. The proposed LLM-based cybersecurity framework includes, for the first time, data pre-processing of communication systems and human-in-the-loop (HITL) training (considering the cybersecurity guidelines recommended by humans). The results show a comparative analysis of detected anomaly data carried out based on the performance evaluation metrics for different LLMs. A hardware-in-the-loop (HIL) testbed is used to generate and extract a dataset of IEC 61850 communications.
Extracting structured knowledge from scientific text remains a challenging task for machine learning models. Here, we present a simple approach to joint named entity recognition and relation extraction and demonstrate how pretrained large language models (GPT-3, Llama-2) can be fine-tuned to extract useful records of complex scientific knowledge. We test three representative tasks in materials chemistry: linking dopants and host materials, cataloging metal-organic frameworks, and general composition/phase/morphology/application information extraction. Records are extracted from single sentences or entire paragraphs, and the output can be returned as simple English sentences or a more structured format such as a list of JSON objects. This approach represents a simple, accessible, and highly flexible route to obtaining large databases of structured specialized scientific knowledge extracted from research papers.
Abstract We evaluate the ability of machine learning to predict whether a hypothetical crystal structure can be synthesized and explain those predictions to scientists. Fine‐tuned large language models (LLMs) trained on a human‐readable text description of the target crystal structure perform comparably to previous bespoke convolutional graph neural network methods, but better prediction quality can be achieved by training a positive‐unlabeled learning model on a text‐embedding representation of the structure. An LLM‐based workflow can then be used to generate human‐readable explanations for the types of factors governing synthesizability, extract the underlying physical rules, and assess the veracity of those rules. These explanations can guide chemists in modifying or optimizing non‐synthesizable hypothetical structures to make them more feasible for materials design.
Abstract We evaluate the ability of machine learning to predict whether a hypothetical crystal structure can be synthesized and explain those predictions to scientists. Fine‐tuned large language models (LLMs) trained on a human‐readable text description of the target crystal structure perform comparably to previous bespoke convolutional graph neural network methods, but better prediction quality can be achieved by training a positive‐unlabeled learning model on a text‐embedding representation of the structure. An LLM‐based workflow can then be used to generate human‐readable explanations for the types of factors governing synthesizability, extract the underlying physical rules, and assess the veracity of those rules. These explanations can guide chemists in modifying or optimizing non‐synthesizable hypothetical structures to make them more feasible for materials design.