Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Transformer model”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

SigTime: Learning and Visually Explaining Time Series Signatures

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve diagnosis, risk assessment, and patient outcomes. However, existing methods for time series pattern discovery face major challenges, including high computational complexity, limited interpretability, and difficulty in capturing meaningful temporal structures. Here, to address these gaps, we introduce a novel learning framework that jointly trains two Transformer models using complementary time series representations: shapelet-based representations to capture localized temporal structures and traditional feature engineering to encode statistical properties. The learned shapelets serve as interpretable signatures that differentiate time series across classification labels. Additionally, we develop a visual analytics system—SigTime—with coordinated views to facilitate exploration of time series signatures from multiple perspectives, aiding in useful insights generation. We quantitatively evaluate our learning framework on eight publicly available datasets and one proprietary clinical dataset. Additionally, we demonstrate the effectiveness of our system through two usage scenarios along with the domain experts: one involving public ECG data and the other focused on preterm labor analysis.

97 MATHEMATICS AND COMPUTING↗
NASA NTRSDate not supplied

Harnessing Artificial Intelligence for Medical Diagnosis and Treatment During Space Exploration Missions

From May 8th to June 9th, 2023, I had the opportunity to participate in an experiential learning experience at Johnson Space Center in Houston, TX with Exploration Medical Capability (ExMC), an element of the NASA Human Research Program. During this research experience, I was not only able to work on the above titled research project, but also gain an immense exposure to the field of aerospace medicine, make numerous connections within the field, tour NASA facilities, as well as travel to the Aerospace Medical Association Annual Conference (AsMA) in New Orleans. To briefly introduce my project, it is well understood that the medical capabilities available to crew medical officers (CMOs) on the International Space Station will be different than the capabilities available and needed during deep space exploration missions to the Moon, Mars, and beyond. Ground support is particularly limited due to distance, communication delays (or lack of communication), and lack of resupply. Therefore, to support medical care by CMOs on these missions, robust clinical decision support systems (CDSSs) must be designed. The recent publication and public launch of generative artificial intelligence (AI) tools based upon large language models (LLM) such as ChatGPT provides the opportunity to create a smart assistant for onboard triage, diagnosis, and treatment of medical conditions. Ultimately, the overall purpose of the project was to research what AI tools currently exist or are in development, and to see how they might be implemented onboard during exploration class spaceflights of the future. The ExMC element is actively developing several tools to be used in preparation for and during deep space exploration missions. One of those tools, known as IMPACT, is a probabilistic risk assessment model which can be used to propose a desired medical system (based on mass and volume) and suggest the clinical outcomes likely to occur for a design reference mission (DRM). The group recently presented the IMPACT model and a DRM of interest titled “Modified Long Duration Lunar Orbital and Lunar Surface” (mLDLOLS) at the recent AsMA conference. The mLDLOLS mock mission is a 9 month and 6-day deep space exploration mission consisting of time in Moon’s orbit (3 months on the Gateway space station), on the lunar surface (3 months within habitat), and another 3 months on Gateway before return to Earth. For this DRM, IMPACT ultimately outlined a preferred medical system that was then associated with medical conditions considered to be most likely based on frequency, most likely to cause astronaut task time loss (TTL), most likely to cause return to definitive care (RTDC), and most likely cause loss of crew life (LOCL). IMPACT also highlighted the medical capabilities/skills that would be required to care for those medical conditions, such as performing a history of present illness or musculoskeletal exam with ultrasound. The primary objective of the project was to perform a survey of the AI tools and systems applicable to the conditions outlined for the proposed mLDLOLS mission. Using PubMed (including most relevant MeSH terms) and Google Scholar, we then created a robust annotated bibliography organized by condition. The 56-page and over 500 reference annotated bibliography was subsequently used to create a review outline that would become the basis for drafting of a future publication. For the review outline, we took those medical conditions researched within the annotated bibliography (condition-based approach) and deployed a systems-based approach, combining those medical conditions and related tools into ten categories. These categories included general/all-purpose CDSSs, tools to diagnose or manage respiratory, dermatologic, neurologic, auditory and vestibular, ophthalmic, musculoskeletal, infection-associated, and gynecologic conditions, as well as tools that could be deployed in the setting of trauma/emergency. With the completion of the 30-page outline, we then began drafting the review paper. To conclude the research experience, I presented the findings from our survey to the ExMC Clinical and Science team. With these objectives, I ultimately learned about the number of AI tools that exist today to assist medical professionals with the triage, diagnosis, and management of several medical conditions. These tools can span from chatbot assistants to help triage knee pain to vision transformer models that can identify ophthalmic conditions based on ocular surface images captured with a cell phone. We also highlighted the current gaps that exist in the literature alongside the advancements that are needed to make the desired CDSS for deep space exploration missions. With this experience, I certainly confirmed an existing career goal and identified several additional skills needed to become an aerospace medical doctor including knowledge of critical care in an extreme medicine setting, aerospace engineering and human integration systems, artificial intelligence, machine learning, and risk models. I also identified numerous transferable skills for this career goal including the basic knowledge of medicine (MD), deployment of the scientific method for critical thought about new scientific questions (PhD), review of published literature, including creating an annotated bibliography (PhD), as well as detailed scientific writing (PhD). The results of my research will likely guide the design of an all-encompassing onboard medical assistant for use during deep space exploration missions of the future. I plan on sharing the outcomes from this experience with my peers at a student seminar in the Fall semester on August 30th. During the seminar, I will detail the project, my experience at NASA and AsMA, as well as offer best practice guidelines for students entertaining similar experiences or careers. In conclusion, I would like to thank the WVU School of Medicine, Research and Graduate Education office, as well as NASA ExMC for the unwavering support of this life-changing experience.

Ryan A. Lacinski↗
DOE OSTI2022

Determining the kinetic rate constants of Fe 3 O 4 -to-Fe and FeO-to-Fe reduction by H 2

Steel production using coal accounts for ~ 8% of global carbon emissions. “Green Steel” is a new grand concept proposed recently to make steel from iron ores using renewable derived “Green Hydrogen” to achieve zero carbon emission. The kinetics and rate-limiting steps of iron ore reduction into iron with H 2 as a reducing agent is critically important to the success of this new technology. While reduction of Fe 2 O 3 into Fe by H 2 follows multiple steps, the past research on this topic mainly deals with the overall averaged kinetics, giving little information on the elemental and rate-limiting steps. In this work, we report a kinetic study specifically design to attain kinetic rate constants of one-step reduction of Fe 3 O 4 -to-Fe and FeO-to-Fe. Guided by thermodynamics, we show first how to create in situ the desirable starting oxide phases, i.e., Fe 3 O 4 and FeO, with precisely controlled the ratio of partial pressures of H 2 O and H 2 . We then show time-dependent raw H 2 O content data collected by a mass spectrometer and the processed reduction data to extract kinetic rate constants. We found that the kinetics of the two one-step reduction reactions follows nicely the Johnson-Mehl-Avrami (JMA) phase transformation model. The one-step reduction mechanisms and activation energy are also discussed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Design-controlled synthesis of IrO 2 sub-monolayers on Au nanoflowers: marrying plasmonic and electrocatalytic properties

We develop herein plasmonic–catalytic Au–IrO 2 nanostructures with a morphology optimized for efficient light harvesting and catalytic surface area; the nanoparticles have a nanoflower morphology, with closely spaced Au branches all partially covered by an ultrathin (1 nm) IrO 2 shell. This nanoparticle architecture optimizes optical features due to the interactions of closely spaced plasmonic branches forming electromagnetic hot spots, and the ultra-thin IrO 2 layer maximizes efficient use of this expensive catalyst. This concept was evaluated towards the enhancement of the electrocatalytic performances towards the oxygen evolution reaction (OER) as a model transformation. The OER can play a central role in meeting future energy demands but the performance of conventional electrocatalysts in this reaction is limited by the sluggish OER kinetics. We demonstrate an improvement of the OER performance for one of the most active OER catalysts, IrO 2 , by harvesting plasmonic effects from visible light illumination in multimetallic nanoparticles. We find that the OER activity for the Au–IrO 2 nanoflowers can be improved under LSPR excitation, matching best properties reported in the literature. Our simulations and electrocatalytic data demonstrate that the enhancement in OER activities can be attributed to an electronic interaction between Au and IrO 2 and to the activation of Ir–O bonds by LSPR excited hot holes, leading to a change in the reaction mechanism (rate-determinant step) under visible light illumination.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Novel Power-Hardware-in-the-Loop Interface Method for Grid-Forming Inverter Systems

Power-hardware-in-the-loop (PHIL) simulations of grid-forming (GFM) inverter systems facilitate the testing of drastic scenarios, such as on-grid to off-grid transitions and islanded microgrid operations without a stiff grid. To the authors’ best knowledge, most studies in the literature focus on PHIL simulations for grid-following inverter systems. Only a few studies focus on GFM inverters, and those are challenging and problematic, especially for high-power applications. This article proposes a novel PHIL simulation platform that enables interfacing high-power GFM inverter systems. The paper proposes the concept of a virtual GFM inverter as a part of the proposed PHIL interface. This addition of a virtual GFM inverter in the PHIL interface expands the conventional ideal transformer model (ITM) method and enables it to overcome the issues of instability of existing ITM methods. In the validation stage, a PHIL experiment is conducted on a three-phase, 480-V, 125-kVA GFM inverter system with the proposed interfacing method. The results corroborate that the proposed PHIL simulation method performs well and is stable for GFM inverter systems.

droop control↗
DOE OSTI2026

Energy–Performance Trade-offs in Privacy-Preserving Federated Learning on SmartNIC-Enabled HPC Systems

Federated learning (FL) is increasingly deployed on accelerator-rich high-performance computing (HPC) systems, yet the system-level energy cost of privacy-aware FL remains poorly understood, particularly across heterogeneous networking and server-placement options. We present a measurement-driven study of energy–performance trade-offs for FL on GH200-class nodes across three deployment configurations: CPU-Ethernet, CPU-InfiniBand (RDMA-capable), and a DPU-hosted FL server over InfiniBand using a BlueField-3 SmartNIC/DPU. Using NVIDIA FLARE (NVFLARE), we align node-level power telemetry with per-round timing extracted from NVFLARE logs to quantify time-to-solution (TTS), energy-to-solution (ETS), energy-delay product (EDP), and synchronization behavior for three transformer models (ALBERT, DistilBERT, BERT), trained with and without differential privacy (DP). We find that interconnect choice is the dominant driver of runtime and energy: host-managed InfiniBand consistently reduces communication overhead versus Ethernet, yielding lower TTS/ETS/EDP. In contrast, in our NVFLARE deployment, placing the FL server on the DPU does not consistently match CPU-InfiniBand performance and can be slower—especially for larger models—highlighting that server placement alone is not sufficient to guarantee end-to-end gains. Finally, under our fixed-round protocol, DP increases per-round cost and runtime variance; ETS increases largely in proportion to TTS because average node power remains relatively stable across configurations.

Kotevska, Olivera [ORNL] (ORCID:0000000316772243)↗
DOE OSTI2023

Resilient Inverter-Driven Black Start with Collective Parallel Grid-Forming Operation

As modern power systems are experiencing exceptional changes with increasing penetrations of inverter-based resources (IBRs), system restoration using IBRs has received attention. Using local grid-forming (GFM) assets near consumers, engineered to establish grid voltages in the absence of a stiff grid, i.e., bottom-up restoration, a distribution system could obtain high system resilience by not relying on the bulk power system restoration, which requires significant human intervention and procedure. This paper studies the technical feasibility of the novel approach with detailed electromagnetic transient (EMT) simulations. To thoroughly evaluate the potential of GFM inverters and the technical challenges in IBR-driven black start, a detailed three-phase inverter model is developed, including negative-sequence control for voltage balance and a phase-by- phase current limiter to sustain momentary overloading during the black start. To examine dynamic aspects of the black-start process, the EMT simulation also models transformer and motor dynamics to emulate their inrush and startup behaviors as well as network dynamics. In addition, active involvement of grid- following distributed energy resources is also studied to facilitate the black-start process. By allowing multiple GFM inverters to collectively black start without leader-follower coordination, we demonstrate that a system can achieve high resilience even with a fraction of assets lost. Two test cases of inverter-driven black start, using two and one GFM inverters, respectively, for a heavily unbalanced 2-MVA distribution feeder are demonstrated. Takeaways for further study and field deployment are provided.

grid-forming inverter↗
DOE OSTI2026

Secondary-Side Active Rectifier Synchronization and Control in LCC-LC Compensated Inductive Power Transfer Systems

This paper proposes a communication-less synchronization and output power control strategy for LCC-LC compensated inductive power transfer systems with a secondaryside active rectifier. By replacing the passive rectifier with an active bridge, the proposed architecture eliminates the need for a separate secondary-side DC-DC converter and enables direct regulation of battery power. The key challenge in such a system is achieving robust synchronization of the secondary active bridge with the primary inverter without access to primary-side signals. To address this issue, the secondary-side variables are analyzed and the current through the secondary series inductor is identified as a load-independent synchronization variable with a fixed phase relationship to the primary excitation. A fixed-frequency second order generalized (SOGI)-based phase locked loop (PLL) is used to estimate the switching phase and frequency, and a phase-shift-based output power controller is developed using a phasor-transformer model of the active bridges. A modified control formulation is further introduced to remove phase-dependent loop-gain variation and simplify controller design. Simulation results validate the proposed method under both fixed and varying switching-frequency conditions, demonstrating successful frequency tracking from 82 kHz to 88 kHz and accurate output power regulation over a wide operating range. The proposed method offers a compact and effective solution for high-power IPT systems by enabling secondary-side synchronization and control without wireless communication or an additional DC-DC conversion stage.

Fernandes, Arnold Anthony [ORNL] (ORCID:0009000631↗
DOE OSTI2024

CoVTransformer

The code is a transformer model to forecast SARS-CoV-2 lineage frequencies in the future.

Feng, Yinan↗
DOE OSTI2026

Transform-Your-World

Machine learning library for developing scientific transformer models, particularly chemical language models, at scale

Salij, Andrew↗
DOE OSTI2023

Prediction of the influence of strain magnitude and strain path on the resulting microstructure and post-forming mechanical behavior of RA containing high formability steels

In third generation advanced high strength steels (AHSS) there is considerable potential to alter the transformation characteristics through variation of process parameters and through changes in chemical composition. This proposal aims to utilize this known phenomenon to develop microstructure-based transformation models to predict austenite stability as a function of chemical composition, strain level, deformation mode. The ultimate intent is to predict microstructure and performance during room temperature forming to produce automotive structural components with superior strength and failure resistance.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Transformer Analysis with ANSYS Maxwell and COMSOL

This is an extension of work described by Rodriguez et al . (2021). It continues analyses of a generic transformer design by Wes Greenwood. In this report, we summarize that work and add comparable results using the ANSYS Maxwell software (henceforward, “ANSYS”), and with COMSOL . We found the ANSYS and COMSOL calculations of inductance agreed well with previous results for simplified coils in air, and with a ferromagnetic core. We then describe the ANSYS and COMSOL approach and show results for a full transformer model based on magnetic field analyses. Finally, we present electrostatic analyses of E field enhancement, once again resolving individual wires. The purpose is to assess the electrostatic fields in order to locate where electric breakdown is likely to originate. We found the maximum enhancement between the secondary and either the primary or the tertiary at the end of the windings with a large potential difference.

42 ENGINEERING↗
NASA NTRS1987

Automated rectification and geocoding of SAR imagery

An automated post-processing system has been developed for rectification and geocoding of SAR (Synthetic Aperture Radar) imagery. The system uses as input a raw uncorrected image from the operational SAR correlator, and produces as a standard output a rectified and geocoded product. The accurate geolocation of SAR image pixels is provided by a spatial transformation model which maps the slant range-azimuth SAR image pixels into their location on a prespecified map grid. This model predicts the geodetic location of each pixel by utilizing: the sensor platform position; a geoid model; the parameters of the data collection system and the processing parameters used in the SAR correlator. Based on their geodetic locations, the pixels are mapped by using the desired cartographic projection equations. This rectification and geocoding technique has been tested with Seasat and SIR-B images. The test results demonstrate absolute location uncertainty of less than 50 m and relative distortion (scale factor and skew) of less than 0.1 percent relative to local variations from the assumed geoid.

Kwok, R.↗
NASA NTRS1991

Development of a computer algorithm for the analysis of variable-frequency AC drives: Case studies included

The development of computer software for performance prediction and analysis of voltage-fed, variable-frequency AC drives for space power applications is discussed. The AC drives discussed include the pulse width modulated inverter (PWMI), a six-step inverter and the pulse density modulated inverter (PDMI), each individually connected to a wound-rotor induction motor. Various d-q transformation models of the induction motor are incorporated for user-selection of the most applicable model for the intended purpose. Simulation results of selected AC drives correlate satisfactorily with published results. Future additions to the algorithm are indicated. These improvements should enhance the applicability of the computer program to the design and analysis of space power systems.

Kankam, M. David↗
NASA NTRSDate not supplied

Downwelling Far-Infrared Emission Spectra Measured by FIRST at Cerro Toco, Chile and Table Mountain Facility, CA

The Far-Infrared Spectroscopy of the Troposphere (FIRST) instrument is a fourier transform spectrometer developed to measure the far-infrared portion of the Earth's longwave spectrum. Specifically, the purpose is measurement of the important, yet under-investigated 100 to 1000 cm-1 band. Presented here are measurements made by FIRST at two successful deployments in a ground-based configuration to measure downwelling longwave radiation. The initial deployment was to Cerro Toco, Chile. FIRST operated from August to October, 2009 as part of the Radiative Heating in Underexplored Bands Campaign (RHUBC-II) campaign. After recalibration, FIRST was deployed to the Table Mountain Facility from August to October, 2012. Dry days for both campaigns were chosen for analysis ? 09/24/2009 and 10/19/2012. Also available from both deployments are coincident radiosonde temperature and water vapor vertical profiles used as inputs to radiance calculations performed by two platforms, the AER Line-by-Line Radiative Transform Model (using the AER line database), and a research platform, MRTA utilizing HITRAN 2012. Thus, we have three streams of data for the closure studies, and results of the comparisons are presented showing good agreement in the optically thick regions of 200-400 cm-1 and 600-800 cm-1. Differences between measured and coincident calculated spectra between 400 and 600 cm-1 are less than 10 mW/m^2/sr/cm-1. Uncertainties accounted for in this study include uncertainty from multiple detectors, water vapor, temperature, line strength and width as presented in HITRAN 2012, and due to internal heating caused by black bodies. The residuals fall within the root-sum-square envelope of the uncertainties.

J Mast↗
NASA NTRSDate not supplied

Advancing Air Mobility: Few-Shot Learning in Airspace Research and Development

The advancement of Air Mobility, particularly in the context of Advanced Air Mobility (AAM) and Urban Air Mobility (UAM), represents a transformative shift in aviation's role in modern society. A comprehensive understanding of requirement consistency is paramount for fostering interoperability, standardization, and cost-effectiveness within airspace systems. This paper introduces a novel approach utilizing a pretrained Sentence Transformers model and few-shot learning to address this crucial aspect task of flagging potentially inconsistent requirements. Few-shot learning supports the development of this future through ensuring the accuracy and consistency of identified requirements with little human oversight. This approach offers a promising solution to the challenges of requirement consistency identification in airspace systems. By harnessing the power of advanced NLP techniques with fine-tuned models, stakeholders can enhance efficiency, accuracy, and scalability; ultimately fostering improved interoperability, standardization, and cost-effectiveness in airspace management.

Natural Language Processing↗
NASA NTRSDate not supplied

Contextualizing Air Traffic Management Conversations using Natural Language Understanding

Efficient management of air traffic and mitigation of delays depend on extracting actionable information from unstructured data, such as dialogues from the Federal Aviation Administration’s (FAA’s) Air Traffic Control System Command Center (ATCSCC) telecons. This study presents a pipeline utilizing Natural Language Processing (NLP) methods for Intent Classification (IC) and Slot Filling (SF) to identify and extract Traffic Management Initiatives (TMIs) from aviation-specific dialogues. We leveraged DeBERTa, a pre-trained transformer model, and fine-tuned it to the nuances of the aviation domain. Despite challenges posed by annotation complexities, the IC model achieved promising results with a weighted average F1-score of 0.81. Our results are close to those of human annotators, which demonstrates the model’s strong alignment with human-level performance. The SF model also showed strong performance, achieving a weighted F1-score of 0.97, which demonstrates its effectiveness in accurately predicting key slots. Our analysis revealed limitations in handling less frequent intents and slot labels due to data sparsity, motivating future efforts to adopt joint IC-SF modeling and data augmentation strategies. This research highlights the potential of domain-specific NLP to streamline decision-making in the aviation industry and improve the management of TMIs.

Air Traffic Control Management↗