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.
Over time, multiple information repositories, access controls, and management practices created disparate information silos. Gaining accurate insights from lab information had become overly burdensome especially for new employees and collaborators
This report outlines the synergy between human decision making and generative artificial intelligence (GenAI), where GenAI supports power system operators by analyzing procedures, suggesting actions, simulating scenarios with physics-based digital twins, and recommending optimal decisions. This report is the first research effort to apply large language models (LLMs), a type of GenAI, in the power grid control room. The authors describe the Electric Grid Generative Pretrained Transformer (eGridGPT), an LLM that virtually assists system operators. Developed with cybersecurity and regulatory requirements in mind, eGridGPT represents an opportunity to responsibly evolve control room technologies to meet the needs of a rapidly changing grid. As an innovative concept, eGridGPT seeks to spearhead productive discussions about the advanced technologies in the control room of the future amid the transition to clean energy.
We propose a near-data approach to reduce the buffered supernova data on the DUNE DAQ front-end computers using ML techniques. Based on simulations, we are able to reduce the data by 5 orders of magnitude to 0(100)MB which can then be transferred quickly over ethernet to a single server that executes a full reconstruction and pointing analysis to determine the SN direction. The entire process of reducing the data and executing reconstruction and pointing analysis pipeline takes less time than that required to transfer all the data back to Fermilab before performing more processing to determine the direction of the supernova, which was the baseline plan for DUNE.
Electronic logbooks contain valuable information about activities and events concerning their associated particle accelerator facilities. However, the highly technical nature of logbook entries can hinder their usability and automation. As natural language processing (NLP) continues advancing, it offers opportunities to address various challenges that logbooks present. This work explores jointly testing a tailored Retrieval Augmented Generation (RAG) model for enhancing the usability of particle accelerator logbooks at institutes like DESY, BESSY, Fermilab, BNL, SLAC, LBNL and CERN. The RAG model uses a corpus built on logbook contributions and aims to unlock insights from these logbooks by leveraging retrieval over facility datasets, including discussion about potential multimodal sources. Our goals are to increase the FAIR-ness (findability, accessibility, interoperability, and reusability) of logbooks by exploiting their information content to streamline everyday use, to enable macro-analysis for root cause analysis, and to facilitate problem-solving automation.
The integration of power electronics-based interfaces presents challenges due to the absence of detailed models and the high computational complexity. Generic models used in system studies lack accuracy in capturing converter dynamics. This paper proposes a data-driven approach developed from experimental setup data. This approach enhances accuracy in photovoltaic inverter modeling. We used two types of PV inverters in the experiment. The recorded experimental data undergo processing through a machine learning model. Results from the model trained through machine learning is also presented.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
This document contains all relevant material generated during the authors' summer internship at NREL in 2024. This report shows how to improve energy efficiency of a few code samples by using low-precision data types combined with mixed-precision algorithms. The main applications considered here are (i) linear system solvers using mixed precision, and (ii) neural networks using mixed precision. This report also discusses how programming languages affect energy consumption of algorithms, energy metrics for a code and tools, and the available current software and hardware infrastructure.
Modern high energy physics experiments are faced not only with the challenge of having to deal with extremely high data rates but with the need to process data quickly to meet real time constraints. At Fermilab, we explore the use of novel computing technologies and techniques to address these challenges. I will discuss my R&D efforts in applying such computing solutions to enhance the multi-messenger astronomy capabilities and improve the overall physics performance of large-scale LArTPC based neutrino experiments. These efforts offer excellent opportunities for fruitful collaboration.
Explore the source record for details and available documents.
The main deliverable of this proposal was to publish data from high energy physics experiments in a FAIR format so that non-specialists could develop machine learning technologies using our data. The Minnesota team of Profs. Cushman, Furmanski and Rusack, from the high energy experiments CDMS, Micro-Boone and CMS, respectively, and Prof J. Sun from Computer Science worked to organize the data, to provide code to access the data, and where relevant provide documentation describing the data. The FAIR4HEP collaboration was formed with groups from UC San Diego, MIT, and the University of Illinois, with the principal investigator was Dr. Huerta. Collectively we collaborated on the publication of datasets from the LHC experiments. Members of the Minnesota group contributed to the common papers published by the collaboration
The use of benchmark datasets has become an important engine of progress in machine learning (ML) over the past 15 years. Recently there has been growing interest in utilizing machine learning to drive advances in research-level mathematics. However, off-the-shelf solutions often fail to deliver the types of insights required by mathematicians. This suggests the need for new ML methods specifically designed with mathematics in mind. The question then is: what benchmarks should the community use to evaluate these? On the one hand, toy problems such as learning the multiplicative structure of small finite groups have become popular in the mechanistic interpretability community whose perspective on explainability aligns well with the needs of mathematicians. While toy datasets are a useful benchmark for initial work, they lack the scale, complexity, and sophistication of many of the principal objects of study in modern mathematics. To address this, we introduce a new collection of benchmark datasets, Algebraic Combinatorics Benchmarks (ACBench), representing either classic or open problems in algebraic combinatorics, a subfield of mathematics that studies discrete structures arising from abstract algebra. After describing the datasets, we discuss the challenges involved in constructing “good” mathematics benchmarks, describe baseline model performance, and discuss some of the insights these datasets can provide that may be of interest even to those who are not interested in mathematics research itself.
Poster presentation for AGU 2024, presenting research approach to identify the natural hydrogen occurrence and to assess resource potential.
Poster presenting NETL's geologic hydrogen project at the 2024 AGU Annual Meeting.
Explore the source record for details and available documents.
During the development of high-consequence items, test systems should be capable of differentiating between test failures resulting from narrowly missing requirements versus those indicating potentially catastrophic faults. In many instances, classifying the data corresponds to simply identifying whether measured waveforms have approximately the anticipated shape. Cast in this light, the problem reduces to converting raw data into a form optimal for use with neural network classifiers. This manuscript investigates different means of representing raw data for image classification. Raw data plots and Short Time Fourier Transform (STFT) spectrograms are classified by both custom built, small-scale, Convolution Neural Networks (CNN) and open-source, multi-million parameter, pre-trained deep CNNs. In the case of time varying frequency content, the STFTs provide images with greater detail and can be accurately classified with simpler networks. This requires less memory and runs faster than classifying the raw data using the more sophisticated options—making STFTs optimal for applications with memory constraints. STFTs are not a panacea. In some cases the time-domain signal contains useful information that should not be discarded. Rather than using raw data or STFTs, the images can be constructed from both by using red and green channels of an RGB image to visualize the real and imaginary components of the transform, with the raw data occupying the blue channel.
Explore the source record for details and available documents.