Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “fast machine learning”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Annular Metallic Nuclear Fuel Informatics at 50 nm Resolution

U-10wt.% Zr (U-10Zr) based metallic fuel is the leading candidate for next-generation sodium cooled fast reactor in United States. Advanced post-irradiation characterization (from sub-nanometer to micrometer) helps to understand fuel microstructure and property change during irradiation, benefiting fuel qualification for commercial application. With high velocity image data generating method, an automatic way to extract the microstructural information quantitively can better serve the needs from post irradiation characterization. A trained machine learning model, named Decision Tree, is employed to categorize pores caused by fission gas release and to aid phase identification. This work presents a showcase of this approach on different irradiated U-10Zr metallic fuels. This quantitative data offers insights into the fission product migration and potentially thermal conductivity degradation. This information from machine learning will be fed into fuel design code for better prediction of fuel performance.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2023

Using Co-Optimized Machine Learned Manifolds for Modeling Chemically Reacting Flows

Chemically reacting flows play a key role in a wide range of engineered systems, from chemical and polymer processing to combustion-based energy conversion technologies. Simulations of these flows involve solving a coupled set of partial differential equations for mass, momentum, energy, and all relevant chemical species in the system. Chemical reaction pathways may be extremely complex and involve hundreds or more intermediate species, with reactions that occur over timescales varying by several orders of magnitude - presenting a significant numerical stiffness challenge. The combination of these factors makes simulation of chemically reacting flows vastly more expensive than nonreactive simulations, and often makes direct solution of the governing equations intractable. It is necessary to apply lower-fidelity models in place of the detailed governing equations in order to reduce computational cost to enable reacting flow simulation tools to be used in the engineering design process. Many of the models employed for this purpose are based on reducing the dimension of the thermochemical state, motivated by the observation that the observed thermochemical states in a system lie on a low-dimensional manifold in thermochemical state space. This behavior occurs due to the fast equilibration of certain reactive and transport processes, and physics-based manifold models rely on idealized assumptions about the balance of timescales and the way in which chemistry and transport are coupled. In this work, we apply a novel method for data-driven manifold-based modeling that can leverage data from high-fidelity reacting flow simulations to improve model accuracy in cases where the physics-based modeling assumptions break down. The approach is designed to be broadly applicable across chemically reacting flow systems but is applied here to turbulent combustion modeling.

machine learning↗
DOE OSTI2022

Prediction of local concentration fields in porous media with chemical reaction using a multi scale convolutional neural network

The study of solute transport in porous media is of interest in many chemical engineering systems. Some example applications include packed bed catalytic reactors, filtration devices, and batteries. The pore scale modeling of these systems is time consuming and may require large computing resources, for this reason computational fluid dynamics (CFD) simulations are not practical if a large number of simulations is required, like in multiscale modeling, where a model at a large scale calls for pore scale simulations. It has been shown that neural networks can be trained with a dataset of flow simulations and then predict fields orders of magnitude faster, and with less computational resources, in new domains. However, it is crucial to provide the neural network with an effective description of the domain and the undergoing operating conditions to be able to train models that generalize accurately in unseen samples. Therefore, research is needed to employ neural networks in new complex systems. The appropriate training of a network for predicting coupled flow and solute transport processes is an outstanding problem due to the complex interplay between geometry and operating conditions. In this work, we train a multi scale convolutional neural network (MSNet) with a diverse dataset of simulations of transport and chemical reaction in porous media to predict the local concentration fields in images of porous media. Our dataset contains a wide diversity of sphere pack arrangements under different operating conditions (Péclet and Reynolds numbers). Further, we train a robust model by employing different input descriptors that represent the medium and the different operating conditions of each system. Our trained model is able to provide nearly instantaneous predictions, compared to around twenty hours of the CFD workflow, with less than 3.5% error on new geometries and transport conditions. Thus the model could be easily integrated in a multiscale workflow where fast response is needed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Latent space mapping: Revolutionizing predictive models for divertor plasma detachment control

The inherent complexity of boundary plasma, characterized by multi-scale and multi-physics challenges, has historically restricted high-fidelity simulations to scientific research due to their intensive computational demands. Consequently, routine applications such as discharge control and scenario development have relied on faster but less accurate empirical methods. This work introduces DivControlNN, a novel machine-learning-based surrogate model designed to address these limitations by enabling quasi-real-time predictions (i.e., ~ 0.2 ms) of boundary and divertor plasma behavior. Trained on over 70,000 2D UEDGE simulations from KSTAR tokamak equilibria, DivControlNN employs latent space mapping to efficiently represent complex divertor plasma states, achieving a computational speed-up of over 10 8 compared to traditional simulations while maintaining a relative error below 20% for key plasma property predictions. During the 2024 KSTAR experimental campaign, a prototype detachment control system powered by DivControlNN successfully demonstrated detachment control on its first attempt, even for a new tungsten divertor configuration and without any fine-tuning. These results highlight the transformative potential of DivControlNN in overcoming diagnostic challenges in future fusion reactors by providing fast, robust, and reliable predictions for advanced integrated control systems.

Artificial neural networks↗
DOE OSTI2022

Finding quadruply imaged quasars with machine learning – I. Methods

ABSTRACT Strongly lensed quadruply imaged quasars (quads) are extraordinary objects. They are very rare in the sky and yet they provide unique information about a wide range of topics, including the expansion history and the composition of the Universe, the distribution of stars and dark matter in galaxies, the host galaxies of quasars, and the stellar initial mass function. Finding them in astronomical images is a classic ‘needle in a haystack’ problem, as they are outnumbered by other (contaminant) sources by many orders of magnitude. To solve this problem, we develop state-of-the-art deep learning methods and train them on realistic simulated quads based on real images of galaxies taken from the Dark Energy Survey, with realistic source and deflector models, including the chromatic effects of microlensing. The performance of the best methods on a mixture of simulated and real objects is excellent, yielding area under the receiver operating curve in the range of 0.86–0.89. Recall is close to 100 per cent down to total magnitude i ∼ 21 indicating high completeness, while precision declines from 85 per cent to 70 per cent in the range i ∼ 17–21. The methods are extremely fast: training on 2 million samples takes 20 h on a GPU machine, and 108 multiband cut-outs can be evaluated per GPU-hour. The speed and performance of the method pave the way to apply it to large samples of astronomical sources, bypassing the need for photometric pre-selection that is likely to be a major cause of incompleteness in current samples of known quads.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Deep Learning Based Superconducting Radio-Frequency Cavity Fault Classification at Jefferson Laboratory

This work investigates the efficacy of deep learning (DL) for classifying C100 superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a large, high-power continuous wave recirculating linac that utilizes 418 SRF cavities to accelerate electrons up to 12 GeV. Recent upgrades to CEBAF include installation of 11 new cryomodules (88 cavities) equipped with a low-level RF system that records RF time-series data from each cavity at the onset of an RF failure. Typically, subject matter experts (SME) analyze this data to determine the fault type and identify the cavity of origin. This information is subsequently utilized to identify failure trends and to implement corrective measures on the offending cavity. Manual inspection of large-scale, time-series data, generated by frequent system failures is tedious and time consuming, and thereby motivates the use of machine learning (ML) to automate the task. This study extends work on a previously developed system based on traditional ML methods (Tennant and Carpenter and Powers and Shabalina Solopova and Vidyaratne and Iftekharuddin, Phys. Rev. Accel. Beams, 2020, 23, 114601), and investigates the effectiveness of deep learning approaches. The transition to a DL model is driven by the goal of developing a system with sufficiently fast inference that it could be used to predict a fault event and take actionable information before the onset (on the order of a few hundred milliseconds). Because features are learned, rather than explicitly computed, DL offers a potential advantage over traditional ML. Specifically, two seminal DL architecture types are explored: deep recurrent neural networks (RNN) and deep convolutional neural networks (CNN). We provide a detailed analysis on the performance of individual models using an RF waveform dataset built from past operational runs of CEBAF. In particular, the performance of RNN models incorporating long short-term memory (LSTM) are analyzed along with the CNN performance. Furthermore, comparing these DL models with a state-of-the-art fault ML model shows that DL architectures obtain similar performance for cavity identification, do not perform quite as well for fault classification, but provide an advantage in inference speed.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1997

A Low-Power High-Speed Smart Sensor Design for Space Exploration Missions

A low-power high-speed smart sensor system based on a large format active pixel sensor (APS) integrated with a programmable neural processor for space exploration missions is presented. The concept of building an advanced smart sensing system is demonstrated by a system-level microchip design that is composed with an APS sensor, a programmable neural processor, and an embedded microprocessor in a SOI CMOS technology. This ultra-fast smart sensor system-on-a-chip design mimics what is inherent in biological vision systems. Moreover, it is programmable and capable of performing ultra-fast machine vision processing in all levels such as image acquisition, image fusion, image analysis, scene interpretation, and control functions. The system provides about one tera-operation-per-second computing power which is a two order-of-magnitude increase over that of state-of-the-art microcomputers. Its high performance is due to massively parallel computing structures, high data throughput rates, fast learning capabilities, and advanced VLSI system-on-a-chip implementation.

Fang, Wai-Chi↗
DOE OSTI2023

Can a deep-learning model make fast predictions of vacancy formation in diverse materials?

The presence of point defects, such as vacancies, plays an important role in materials design. Here, we explore the extrapolative power of a graph neural network (GNN) to predict vacancy formation energies. We show that a model trained only on perfect materials can also be used to predict vacancy formation energies (E vac ) of defect structures without the need for additional training data. Such GNN-based predictions are considerably faster than density functional theory (DFT) calculations and show potential as a quick pre-screening tool for defect systems. To test this strategy, we developed a DFT dataset of 530 E vac consisting of 3D elemental solids, alloys, oxides, semiconductors, and 2D monolayer materials. We analyzed and discussed the applicability of such direct and fast predictions. We applied the model to predict 192 494 E vac for 55 723 materials in the JARVIS-DFT database. Our work demonstrates how a GNN-model performs on unseen data.

2D materials↗
DOE OSTI2024

Dimensionally Aligned Signal Projection Algorithms Library

Dimensionally aligned signal projection (DASP) algorithms are used to analyze fast Fourier transforms (FFTs) and generate visualizations that help focus on the harmonics for specific signals. At a high level, these algorithms extract the FFT segments around each harmonic frequency center, and then align them in equally sized arrays ordered by increasing distance from the base frequency. This allows for a focused view of the harmonic frequencies, which, among other use cases, can enable machine learning algorithms to more easily identify salient patterns. This work seeks to provide an effective open-source implementation of the DASP algorithms proposed by Vann et al. (2018) as well as functionality to help explore and test how these algorithms work with an interactive dashboard and signal-generation tool. The DASP library is implemented in Python and contains four types of algorithms for implementing these feature engineering techniques: fixed harmonically aligned signal projection (HASP), decimating HASP, interpolating HASP, and frequency aligned signal projection (FASP). Each algorithm returns a numerical array, which can be visualized as an image. The HASP algorithms are variations of the algorithms originally presented by Vann et al. (2018). For consistency, FASP, which is the terminology used for the short-time Fourier transform (STFT), has been implemented as part of the library to provide a similar interface to the STFT of the raw signal. Additionally, the library contains an algorithm to generate artificial signals with basic customizations such as the base frequency, sample rate, duration, number of harmonics, noise, and number of signals. Finally, the library provides multiple interactive visualizations, each of which is implemented using IPyWidgets and works in a Jupyter environment. A dashboard-style visualization is provided, which contains some common signal-processing visual components (signal, FFT, spectogram) updating in unison with the HASP functions (see Figure 1 below). Separate from the dashboard, an independent visualization is provided for each of the DASP algorithms as well as for the artifical signal generator. These visualizations are included in the library to aid in developing an intuitive understanding how the algorithms are affected by different input signals and parameter selections.

harmonics↗
DOE OSTI2022

Machine-learning from Pseudomonas putida KT2440 transcriptomes reveals its transcriptional regulatory network

Bacterial gene expression is orchestrated by numerous transcription factors (TFs). Elucidating how gene expression is regulated is fundamental to understanding bacterial physiology and engineering it for practical use. In this study, a machine-learning approach was applied to uncover the genome-scale transcriptional regulatory network (TRN) in Pseudomonas putida KT2440, an important organism for bioproduction. We performed independent component analysis of a compendium of 321 high-quality gene expression profiles, which were previously published or newly generated in this study. We identified 84 groups of independently modulated genes (iModulons) that explain 75.7% of the total variance in the compendium. With these iModulons, we (i) expand our understanding of the regulatory functions of 39 iModulon associated TFs (e.g., HexR, Zur) by systematic comparison with 1993 previously reported TF-gene interactions; (ii) outline transcriptional changes after the transition from the exponential growth to stationary phases; (iii) capture group of genes required for utilizing diverse carbon sources and increased stationary response with slower growth rates; (iv) unveil multiple evolutionary strategies of transcriptome reallocation to achieve fast growth rates; and (v) define an osmotic stimulon, which includes the Type VI secretion system, as coordination of multiple iModulon activity changes. Taken together, this study provides the first quantitative genome-scale TRN for P. putida KT2440 and a basis for a comprehensive understanding of its complex transcriptome changes in a variety of physiological states.

09 BIOMASS FUELS↗
DOE OSTI2025

Motion Dynamics of Motile Microbes in Pore-Networks and its Implications for Reactive Transport Processes

This report outlines new methods to improve simulations of microbial transport and microbially mediated reactions in porous media. A range of experimental, modeling, and machine learning tools are introduced to make these simulations faster, more reliable, and useful for real-world applications. At the microscopic level, the study investigates how different types of bacteria move through confined spaces. A new artificial intelligence tool called DeepTrackStat, is introduced to track motions dynamics as observed in videos of particles migrating through pore networks. This tool is especially helpful for studying fast-moving microbes and requires less computing power than traditional tracking methods. At larger scales, the research looks at how microbes and chemicals interact in zones where surface water and groundwater meet. To connect the small- and large-scale findings, the study presents a neural network model called STAMNet. This tool helps scale up detailed small-scale microbial motion behaviors to predict large-scale environmental changes more efficiently. By combining lab experiments, computer models, and artificial intelligence, the research presented supports smarter environmental decision-making, especially in bioremediation of contaminated groundwater and protection of water quality.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Low-latency Jet Tagging for HL-LHC Using Transformer Architectures

Transformers are the state-of-the-art model architectures and widely used in application areas of machine learning. However the performance of such architectures is less well explored in the ultra-low latency domains where deployment on FPGAs or ASICs is required. Such domains include the trigger and data acquisition systems of the LHC experiments. We present a transformer-based algorithm for jet tagging built with the HGQ2 framework, which is able to produce a model with heterogeneous bitwidths for fast inference on FPGAs, as required in the trigger systems at the LHC experiments. The bitwidths are acquired during training by minimizing the total bit operations as an additional parameter. By allowing a bitwidth of zero, the model is pruned in-situ during training. Using this quantization-aware approach, our algorithm achieves state-of-the-art performance while also retaining permutation invariance which is a key property for particle physics applications. Due to the strength of transformers in representation learning, our work also serves as a stepping stone for the development of a larger foundation model for trigger applications.

Laatu, Lauri [Imperial Coll., London]↗
DOE OSTI2023

Reactivity Coefficient Measurements to Aid in Reducing Compensating Errors in Plutonium Nuclear Data

Compensating errors between several nuclear data observables in a nuclear data library can adversely impact application simulations. The primary goal of the EUCLID project (Experiments Underpinned by Computational Learning for Improvements in Nuclear Data) is to reduce compensating errors between fast (0.1–5 MeV) 239Pu nuclear data for prompt fission neutron spectra (PFNS), average prompt fission neutron multiplicities, and neutron induced fission, capture, elastic, and inelastic cross sections. This work will focus on the design and execution of void reactivity coefficient measurements in the EUCLID experiment, performed on the Planet vertical lift critical assembly machine at the National Criticality Experiments Research Center (NCERC). Two different base configurations were designed and measured, one with high neutron leakage, and one with low neutron leakage. Both were primarily made up of plutonium metal (Zero Power Physics Reactor plates) without interstitial moderators and reflected by half-inch aluminum. Design optimization showed that void reactivity coefficient measurements in three locations per configuration was most impactful to reduce nuclear data uncertainties due to the varying impacts from elastic and inelastic scattering, as well as fission and capture. The locations for measurements were chosen based on preliminary studies which balanced measurement uncertainty and measurement practicality. The measurements were also selected to have sensitivities maximally complementary to previous arrangements. Comparisons across nuclear data libraries highlight the potential impact.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

When more data hurts: Optimizing data coverage while mitigating diversity-induced underfitting in an ultrafast machine-learned potential

Machine-learned interatomic potentials (MLIPs) are becoming an essential tool in materials modeling. However, optimizing the generation of training data used to parametrize the MLIPs remains a significant challenge. This is because MLIPs can fail when encountering local environments too different from those present in the training data. The difficulty of determining a priori the environments that will be encountered during molecular dynamics simulation necessitates diverse, high-quality training data. Here, this study investigates how training data diversity affects the performance of MLIPs using the Ultra-Fast force field (UF 3 ) to model amorphous silicon nitride. We employ expert and autonomously generated data to create the training data and fit four force field variants to subsets of the data. Our findings reveal a critical balance in training data diversity: insufficient diversity hinders generalization, while excessive diversity can exceed the MLIP's learning capacity, reducing simulation accuracy. Specifically, we found that the UF 3 variant trained on a subset of the training data, in which nitrogen-rich structures were removed, offered vastly better prediction and simulation accuracy than any other variant. By comparing these UF 3 variants, we highlight the nuanced requirements for creating accurate MLIPs, emphasizing the importance of application-specific training data to achieve optimal performance in modeling complex material behaviors.

ab initio molecular dynamics↗
DOE OSTI2024

Utilizing a Virtual Sodium-Cooled Fast Reactor Digital Twin to Aid in Diversion Pathway Analysis for International Safeguards Applications

We report digital twin technology has the potential to improve the effectiveness of international safeguards inspectors by providing a tool which can: first, perform an accurate diversion path analysis, identify their indicators, and required sensors to detect them; and second, monitor facilities in real-time using critical data streams that benefit from this safeguards-by-design approach. Safeguards inspectors are required to visit facilities and verify the nuclear material to ensure no diversion has taken place and detect misuse of the facility; however, this analysis and verification effort is time consuming, and with limited funding it is imperative that time spent at a nuclear facility is focused on key areas. A virtual digital twin of three prototypic sodium fast reactors was developed, where diversion and misuse scenarios were explored to determine how a digital twin could provide inspectors with an understanding of how proliferation may occur and where the most likely areas for proliferation would be. For each of the three reactors, an optimization algorithm was able to find core designs which would be difficult to detect via sensors alone; however, the use of a machine learning adapter provided by the digital twin was able to show general trends in where proliferation as likely to take place.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning

Applications of machine learning (ML) are growing by the day for many unique and challenging scientific applications. However, a crucial challenge facing these applications is their need for ultra low-latency and on-detector ML capabilities. Given the slowdown in Moore's law and Dennard scaling, coupled with the rapid advances in scientific instrumentation that is resulting in growing data rates, there is a need for ultra-fast ML at the extreme edge. Fast ML at the edge is essential for reducing and filtering scientific data in real-time to accelerate science experimentation and enable more profound insights. To accelerate real-time scientific edge ML hardware and software solutions, we need well-constrained benchmark tasks with enough specifications to be generically applicable and accessible. These benchmarks can guide the design of future edge ML hardware for scientific applications capable of meeting the nanosecond and microsecond level latency requirements. To this end, we present an initial set of scientific ML benchmarks, covering a variety of ML and embedded system techniques.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Bayesian Optimization of a Free-Electron Laser

The Linac Coherent Light Source X-ray free-electron laser is a complex scienti c apparatus which changes con gurations multiple times per day, necessitating fast tuning strategies to reduce setup time for successive experiments. To this end, we employ a Bayesian approach to maximizing X- ray laser pulse energy by controlling groups of quadrupole magnets. A Gaussian process model provides probabilistic predictions for the machine response with respect to control parameters, enabling a balance of exploration and exploitation in the search for the global optimum. We show that the model parameters can be learned from archived scans, and correlations between devices can be extracted from the beam transport. Furthermore, the result is a sample-e cient optimization routine, combining both historical data and knowledge of accelerator physics to signi cantly outperform existing optimizers.

47 OTHER INSTRUMENTATION↗