SEARCH · Engineering Papers

Results for “learning rate”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 199 records · Page 11

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Automated control and optimization of laser-driven ion acceleration

The interaction of relativistically intense lasers with opaque targets represents a highly non-linear, multi-dimensional parameter space. This limits the utility of sequential 1D scanning of experimental parameters for the optimization of secondary radiation, although to-date this has been the accepted methodology due to low data acquisition rates. High repetition-rate (HRR) lasers augmented by machine learning present a valuable opportunity for efficient source optimization. Here, an automated, HRR-compatible system produced high-fidelity parameter scans, revealing the influence of laser intensity on target pre-heating and proton generation. A closed-loop Bayesian optimization of maximum proton energy, through control of the laser wavefront and target position, produced proton beams with equivalent maximum energy to manually optimized laser pulses but using only 60% of the laser energy. This demonstration of automated optimization of laser-driven proton beams is a crucial step towards deeper physical insight and the construction of future radiation sources.

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

Transfer learning for probabilistic localization of hidden cracks in concrete structures

Abstract The utility of discriminative supervised learning models built using multiple training-data sources is investigated for hidden crack localization in concrete. Feed-forward neural network (FFNN) is chosen as the model architecture, and transfer learning is used to assimilate the information obtained from different sources (computational physics simulations and laboratory experiments). The labeled training data consists of values of a damage index and the known locations of hidden cracks. The classification models need to learn how the presence of damage (hidden cracks) affects the damage index at different sensors for different test conditions. To this end, diagnostic FFNN models are built by sequentially adding and training new hidden layers to assimilate labeled information from computer models (different model geometries, test conditions, crack lengths, crack locations) and laboratory experiments on a plain cement slab. These transfer learning-based models are then used to localize damage in concrete specimens that reflect real-world conditions (i.e., specimens with steel reinforcement and randomly distributed aggregate). The actual damage state in these specimens is determined by extracting cores and performing petrographic studies on the extracted cores. The damage probability estimated by transfer learning-based models is compared with the petrographic damage rating index (DRI) to identify the most suitable approach to train the diagnostic models. The transfer learning-based diagnostic methodology shows promise and could be used in various structural health monitoring applications, where sufficient labeled data are typically not available from a single data source.

Miele, S.↗

DOE OSTI2022

Using machine-learning to understand complex microstructural effects on the mechanical behavior of Ti-6Al-4V alloys

Structural materials properties are highly dependent on their microstructure. Their microstructure is in turn affected by multiple fabrication and thermo-mechanical treatment parameters, all of which conform a highly-dimensional parametric space with often hidden correlations that are difficult to extract by experimentation alone. This is particularly true for alloys of the dual-phase Ti-6Al-4V family, with their greatly complex and rich microstructures, which combine several intrinsic length scales associated with multiple grain and subgrain structures, grains with different crystal lattices (α and β phases), and complex chemistry. In this paper we use a comprehensive set of machine learning techniques to develop predictive tools relating the yield strength and hardening rate of these alloys to a set of input parameters covering extensive ranges. The data generator is a finite-element crystal plasticity model for polycrystal deformation that takes into account slip anisotropy and employs standard dislocation evolution models for the α and β phases of Ti-based alloys. Our dataset includes over two thousand independent simulations and is used to train the machine learning models, which are then used to establish correlations between microstructural parameters and the alloys’ mechanical response. Our results point to the most influential parameters affecting yield strength and hardening rate, information that can then be used to guide experimental synthesis and characterization efforts to save time and resources.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Learning heterogeneous reaction kinetics from X-ray movies pixel-by-pixel

Reaction rates at spatially heterogeneous, unstable interfaces are notoriously difficult to quantify, yet are essential in engineering many chemical systems, such as batteries 1 and electrocatalysts 2. Experimental characterizations of such materials by operando microscopy produce rich image datasets 3–6, but data-driven methods to learn physics from these images are still lacking because of the complex coupling of reaction kinetics, surface chemistry and phase separation 7. Here we show that heterogeneous reaction kinetics can be learned from in situ scanning transmission X-ray microscopy (STXM) images of carbon-coated lithium iron phosphate (LFP) nanoparticles. Combining a large dataset of STXM images with a thermodynamically consistent electrochemical phase-field model, partial differential equation (PDE)-constrained optimization and uncertainty quantification, we extract the free-energy landscape and reaction kinetics and verify their consistency with theoretical models. We also simultaneously learn the spatial heterogeneity of the reaction rate, which closely matches the carbon-coating thickness profiles obtained through Auger electron microscopy (AEM). Across 180,000 image pixels, the mean discrepancy with the learned model is remarkably small (<7%) and comparable with experimental noise. Our results open the possibility of learning nonequilibrium material properties beyond the reach of traditional experimental methods and offer a new non-destructive technique for characterizing and optimizing heterogeneous reactive surfaces.

Chueh, William↗

DOE OSTI2025

Particle Markov Chain Monte Carlo Approach to Inference in Transient Surface Kinetics

Here, in this work, we develop a novel Bayesian approach to study the adsorption and desorption of CO onto a Pd(111) surface, a process of great importance in natural sciences. The motivation for this work comes from the recent availability of time-resolved infrared spectroscopy data and the need for model interpretability and uncertainty quantification in chemical processes. The objective is to learn the relevant parameters that characterize the process: coverage with time, rate constants, activation energies, and pre-exponential factors. Our approach consists of three main schemes: (i) a problem design and probabilistic model for the whole system, (ii) a particle Markov chain Monte Carlo sampler to learn the hidden coverages and rate constant parameters, and (iii) two Bayesian formulations to infer the activation energies and pre-exponential factors. The flexibility of the Bayesian framework allows for uncertainty quantification where possible and integration of mathematical constraints in the model to reflect the system physically. We found that our results for the activation energies and pre-exponential factor are in agreement with those reported in the experimental literature, independently, and we provide discussions on the advantages and disadvantages as well as applicability to other systems.

36 MATERIALS SCIENCE↗

DOE OSTI2025

ChatPORT: Fine-Tuned LLM for Easy Code {PORT}ing

Fine-tuning existing LLMs for specialized tasks has become a very attractive alternative due to its low cost and quick development cycle. With many pre-trained LLMs available, it is an increasingly complex task to choose the correct model as the starting point or base model. In this work we discuss ChatPORT - a specialized fine-tuned LLM geared towards providing correctly translated codes from one programming model to another. We evaluate a number of base models and compare and contrast their features and characteristics that make them a viable starting point. In this paper, we focus on the OpenMP offload porting capabilities of ChatPORT. We build our training data using kernels from the Heterogeneous Computing Benchmarks (HeCBench) [12] and the OpenMP Validation and Verification suite [5] to fine-tune the base models. We then test the model using unseen kernels extracted from the HeCBench benchmark suite. Our results show that: (1) not all open LLMs geared towards HPC are aware of programming models like OpenMP, (2) although all base models benefit from fine-tuning they learn differently and produce different correctness rates, (3) depending on the memory size and compute resource available, different base models can be used for fine-tuning without significantly affecting the quality of transpiled code they generate, (4) fine-tuning improved the correctness rate of the LLM by an average of 43.2%, and (5) feedback-based training data further increased the correctness rate by an average of 6% over the LLMs tested.

Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗

DOE OSTI2026

Predictive Chemical Kinetic Modeling: Where We Succeed, Where We Struggle, and What Comes Next

Chemical kinetic modeling plays a foundational role in fields ranging from energy to environmental science, pharmaceuticals, and advanced materials. The past two decades have seen remarkable progress, particularly in modeling gas-phase reactions for thermochemical processes, leading to impactful industrial applications such as steam cracking and air quality management. However, new challenges are emerging. The successful development of systematic methodologies for the description of gas-phase kinetics opens the possibility to apply the same approach to the study of more challenging systems. Here, we review recent advances, including ab initio transition state theory-based master equation estimation of elementary rates, automated mechanism generation, machine-learning-assisted kinetics, and uncertainty quantification, and discuss the advances needed to apply the same methodological approach in areas such as heterogeneous catalysis, electrochemistry, liquid-phase and solid-state reactivity, and multiscale model integration. We advocate for the development of targeted tools, especially methods that go beyond empirical tuning toward first-principles-based predictions. We highlight the need for accessible software and AIaugmented workflows to democratize modeling for industry and academia alike. In this perspective, we call attention to not only what has worked but also what remains unsolved, advocating to avoid overemphasizing successes in scientific works at the expense of realism. The next decade should focus on predictive capability, physical accuracy, and community infrastructure (e.g., databases and services) to enable innovation across diverse fields. We argue that kinetic modeling, properly equipped, can accelerate discovery far beyond its traditional domains.

ab initio calculations↗

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 ↗

DOE OSTI2021

Cric searchable image database as a public platform for conventional pap smear cytology data

Amidst the current health crisis and social distancing, telemedicine has become an important part of mainstream of healthcare, and building and deploying computational tools to support screening more efficiently is an increasing medical priority. The early identification of cervical cancer precursor lesions by Pap smear test can identify candidates for subsequent treatment. However, one of the main challenges is the accuracy of the conventional method, often subject to high rates of false negative. While machine learning has been highlighted to reduce the limitations of the test, the absence of high-quality curated datasets has prevented strategies development to improve cervical cancer screening. The Center for Recognition and Inspection of Cells (CRIC) platform enables the creation of CRIC Cervix collection, currently with 400 images (1,376 × 1,020 pixels) curated from conventional Pap smears, with manual classification of 11,534 cells. This collection has the potential to advance current efforts in training and testing machine learning algorithms for the automation of tasks as part of the cytopathological analysis in the routine work of laboratories.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy

Recent advances in detectors for imaging and spectroscopy have afforded in situ, rapid acquisition of hyperspectral data. While electron energy loss spectroscopy (EELS) data acquisition speeds with electron counting are regularly reaching 400 frames per second with near-zero read noise, signal to noise ratio (SNR) remains a challenge owing to fundamental counting statistics. In order to advance understanding of transient materials phenomena during rapid acquisition EELS, trustworthy analysis of noisy spectra must be demonstrated. In this study, we applied machine learning techniques to denoise high frame rate spectra, benchmarking with slower frame rate “ground truths”. The results provide a foundation for reliable use of low SNR data acquired in rapid, in-situ spectroscopy experiments. Such a tool-set is a first step toward both automation in microscopy as well as use of these methods to interrogate otherwise poorly understood transformations.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Importance learning estimator for the site-averaged turnover frequency of a disordered solid catalyst

For disordered catalysts such as atomically dispersed “single-atom” metals on amorphous silica, the active sites inherit different properties from their quenched-disordered local environments. The observed kinetics are site-averages, typically dominated by a small fraction of highly active sites. Standard sampling methods require expensive ab initio calculations at an intractable number of sites to converge on the siteaveraged kinetics. We present a new method that efficiently estimates the site-averaged turnover frequency (TOF). The new estimator uses the same importance learning algorithm [Vandervelden et al., React. Chem. Eng. 5, 77 (2020)] that we previously used to compute the siteaveraged activation energy. We demonstrate the method by computing the site-averaged TOF for a simple disordered lattice model of an amorphous catalyst. The results show that with the importance learning algorithm, the site-averaged TOF and activation energy can now be obtained concurrently with orders of magnitude reduction in required ab initio calculations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Computational design of high entropy alloy coating for hydrogen turbine applications

This project aims to develop novel high entropy alloy (HEA)-based coatings to protect critical components in hydrogen-fueled turbine power system. The HEA-coatings will demonstrate superior performance in hydrogen combustion environment to commercial NiCoCrAlY coating in current natural gas turbine system. The HEA coating facilitates the formation of a protective scale of alpha-alumina to slow down the inward diffusion of oxidizing species and the outward diffusion of metal elements, and possesses ultrahigh corrosion and spallation resistance to prolong the service lifetime of critical components in hydrogen turbine power system. Aimed to accelerate the discovery of novel HEA coating compositions, high throughput computational modeling including CALPHAD and density functional theory and machine learning are performed to predict phase stability, oxygen permeability, oxidation rate constant, coefficient of thermal expansion, and mechanical properties. Based on the modeling and machine learning prediction, experimental validation is performed. Preliminary results will be presented and approaches to minimize oxidation will be discussed.

alloy design↗

NASA NTRS2007

Development of the J-2X Engine for the Ares I Crew Launch Vehicle and the Ares V Cargo Launch Vehicle: Building on the Apollo Program for Lunar Return Missions

The United States (U.S.) Vision for Space Exploration has directed NASA to develop two new launch vehicles for sending humans to the Moon, Mars, and beyond. In January 2006, NASA streamlined its hardware development approach for replacing the Space Shuttle after it is retired in 2010. Benefits of this approach include reduced programmatic and technical risks and the potential to return to the Moon by 2020 by developing the Ares I Crew Launch Vehicle (CLV) propulsion elements now, with full extensibility to future Ares V Cargo Launch Vehicle (CaLV) lunar systems. The Constellation Program selected the Pratt & Whitney Rocketdyne J-2X engine to power the Ares I Upper Stage Element and the Ares V Earth Departure Stage (EDS). This decision was reached during the Exploration Systems Architecture Study and confirmed after the Exploration Launch Projects Office performed a variety of risk analyses, commonality assessments, and trade studies. This paper narrates the evolution of that decision; describes the performance capabilities expected of the J-2X design, including potential commonality challenges and opportunities between the Ares I and Ares V launch vehicles; and provides a current status of J-2X design, development, and hardware testing activities. This paper also explains how the J-2X engine effort mitigates risk by testing existing engine hardware and designs; building on the Apollo Program (1961 to 1975), the Space Shuttle Program (1972 to 2010); and consulting with Apollo era experts to derive other lessons learned to deliver a human-rated engine that is on an aggressive development schedule, with its first demonstration flight in 2012.

Greene, WIlliam↗

NASA NTRS2010

Planning for Plume Diagnostics for Ground Testing of J-2X Engines at the SSC

John C. Stennis Space Center (SSC) is the premier test facility for liquid rocket engine development and certification for the National Aeronautics and Space Administration (NASA). Therefore, it is no surprise that the SSC will play the most prominent role in the engine development testing and certification for the J-2X engine. The Pratt & Whitney Rocketdyne J-2X engine has been selected by the Constellation Program to power the Ares I Upper Stage Element and the Ares V Earth Departure Stage in NASA s strategy of risk mitigation for hardware development by building on the Apollo program and other lessons learned to deliver a human-rated engine that is on an aggressive development schedule, with first demonstration flight in 2010 and human test flights in 2012. Accordingly, J-2X engine design, development, test, and evaluation is to build upon heritage hardware and apply valuable experience gained from past development and testing efforts. In order to leverage SSC s successful and innovative expertise in the plume diagnostics for the space shuttle main engine (SSME) health monitoring,1-10 this paper will present a blueprint for plume diagnostics for various proposed ground testing activities for J-2X at SSC. Complete description of the SSC s test facilities, supporting infrastructure, and test facilities is available in Ref. 11. The A-1 Test Stand is currently being prepared for testing the J-2X engine at sea level conditions. The A-2 Test Stand is currently being used for testing the SSME and may also be used for testing the J-2X engine at sea level conditions in the future. Very recently, ground-breaking ceremony for the new A-3 rocket engine test stand took place at SSC on August 23, 2007. A-3 is the first large - scale test stand to be built at the SSC since the A and B stands were constructed in the 1960s. The A-3 Test Stand will be used for testing J-2X engines under vacuum conditions simulating high altitude operation at approximately 30,480 m (100,000 ft). To achieve the simulated altitude environment, chemical steam generators using isopropyl alcohol, LOX, and RELEASED - Printed documents may be obsolete; validate prior to use. water would run for the duration of the test and would generate approximately 2096 Kg/s of steam to reduce pressure in the test cell and downstream of the engine. The testing at the A-3 Test Stand is projected to begin in late 2010, meanwhile the J-2X component testing on A-1 is scheduled to begin later this year.

SaintCyr, William W.↗

DOE OSTI2024

Third-integer Resonant Extraction Regulation System for Mu2e

A third-integer resonant slow extraction system is being developed for Fermilab's Delivery Ring to deliver protons to the upcoming Mu2e experiment. The timescale of the extraction (or spill) duration is 43 milliseconds, which is extremely short and unprecedented. Additionally, the experiment's strict and challenging requirements on the quality of the spill at this time scale has led to the development of a new Spill Regulation System (SRS) design. The SRS primarily consists of three components - slow regulation, fast regulation, and harmonic content suppressor. Contributions to the first two components of the SRS, i.e., Slow Regulation and Fast Regulation subsystems, will be presented in which new adaptive learning algorithm schemes for the slow regulation of the spill -- validated using particle tracking simulations -- shall be described. In addition to these novel methods for the enhancement of the spill regulation system, results of employing Machine Learning in enhancing the performance of the resonant extraction are also presented. At the forefront of applying ML techniques to solve non-linear accelerator control problems, this work includes optimizing the PID gains as well as the replacement of the traditional PID controller using Recurrent Neural Networks and Gated Recurrent Unit (GRU) ML models to achieve efficiencies greater than a PID controller. Cutting-edge on-going Reinforcement Learning efforts, including an actor-critic family of learning algorithms, to regulate the spill rate will be reviewed, as well as present analytical calculations pertaining the transit time of particles in a third-integer resonant extraction. Detailed numerical investigations and validations of such calculations, the model of which could be exported and reliably used in future analytical modeling of any resonant extraction, are discussed.

43 PARTICLE ACCELERATORS↗

DOE OSTI2022

Modeling Subsurface Performance of a Geothermal Reservoir Using Machine Learning

Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells—increasing or decreasing the fluid flow rates across the wells—and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. In this study, we describe a new approach combining reservoir modeling and machine learning to produce models that enable such a strategy. Our computational approach allows us, first, to translate sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy, and second, to find optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an “open-source” reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 h, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 s. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs.

15 GEOTHERMAL ENERGY↗

DOE OSTI2025

Deep learning-based spatio-temporal fusion for high-fidelity ultra-high-speed X-ray radiography

Full-field ultra-high-speed (UHS) X-ray imaging experiments have been well established to characterize various processes and phenomena. However, the potential of UHS experiments through the joint acquisition of X-ray videos with distinct configurations has not been fully exploited. In this paper, we investigate the use of a deep learning-based spatio-temporal fusion (STF) framework to fuse two complementary sequences of X-ray images and reconstruct the target image sequence with high spatial resolution, high frame rate and high fidelity. We applied a transfer learning strategy to train the model and compared the peak signal-to-noise ratio (PSNR), average absolute difference (AAD) and structural similarity (SSIM) of the proposed framework on two independent X-ray data sets with those obtained from a baseline deep learning model, a Bayesian fusion framework and the bicubic interpolation method. The proposed framework outperformed the other methods with various configurations of the input frame separations and image noise levels. With three subsequent images from the low-resolution (LR) sequence of a four times lower spatial resolution and another two images from the high-resolution (HR) sequence of a 20 times lower frame rate, the proposed approach achieved average PSNRs of 37.57 dB and 35.15 dB, respectively. When coupled with the appropriate combination of high-speed cameras, the proposed approach will enhance the performance and therefore the scientific value of UHS X-ray imaging experiments.

deep learning↗

DOE OSTI2022

Peak Prediction Using Multi Layer Perceptron (MLP) for Edge Computing ASICs Targeting Scientific Applications

High data rate detectors play an integral part in scientific research and their development is actively pursued at High Energy Physics (HEP) facilities around the world. Edge Machine Learning (ML) offers the ability to reduce data rates by integrating ML algorithms into Application Specific Integrated Circuits (ASICs) on the front end electronics. In this work, we explore a set of neural network architectures for predicting the peak amplitudes in the detector's sensor response. We have designed and synthesized several MLP based neural networks comparing their inference accuracy, power consumption, and area targeting for minimal latency. The neural networks are synthesized in a commercial 65nm process. The effect of quantizing the network's weights and biases on hardware performance and area is reported. We also conduct design space exploration to compare between design alternatives

47 OTHER INSTRUMENTATION↗