Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning efficiency”

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 1,495 records · Page 83

Computing chemical potentials with machine-learning-accelerated simulations to accurately predict thermodynamic properties of molten salts

The successful design and deployment of next-generation nuclear technologies heavily rely on thermodynamic data for relevant molten salt systems. However, the lack of accurate force fields and efficient methods has limited the quality of thermodynamic predictions from atomistic simulations. Here we propose an efficient free energy framework for computing chemical potentials, which is the central free energy quantity behind many thermodynamic properties. We accelerate our simulations without sacrificing accuracy by using machine learning interatomic potentials trained on density functional theory (DFT) data. Using lithium chloride as our model system, we compute chemical potentials with DFT-accuracy for solid and liquid phases by transmuting ions into noninteracting particles. Notably, in the liquid phase, we demonstrate consistency whether we transmute one ion pair or the entire system into ideal gas particles. By locating the temperature where the chemical potential of solid and liquid phases cross, we predict a melting point of 880 ± 18 K for lithium chloride, which is remarkably close to the experimental value of 883 K. With this successful demonstration, we lay the foundation for high-throughput thermodynamic predictions of many properties that can be derived from the chemical potentials of the minority and majority components in molten salts.

Gibson, Luke D. [Oak Ridge National Laboratory (OR↗

Operator inference for non-intrusive model reduction with quadratic manifolds

This paper proposes a novel approach for learning a data-driven quadratic manifold from high-dimensional data, then employing this quadratic manifold to derive efficient physics-based reduced-order models. The key ingredient of the approach is a polynomial mapping between high-dimensional states and a low-dimensional embedding. This mapping consists of two parts: a representation in a linear subspace (computed in this work using the proper orthogonal decomposition) and a quadratic component. The approach can be viewed as a form of data-driven closure modeling, since the quadratic component introduces directions into the approximation that lie in the orthogonal complement of the linear subspace, but without introducing any additional degrees of freedom to the low-dimensional representation. Combining the quadratic manifold approximation with the operator inference method for projection-based model reduction leads to a scalable non-intrusive approach for learning reduced-order models of dynamical systems. Further, applying the new approach to transport-dominated systems of partial differential equations illustrates the gains in efficiency that can be achieved over approximation in a linear subspace.

42 ENGINEERING↗

Occupancy prediction through machine learning and data fusion of environmental sensing and Wi-Fi sensing in buildings

Occupancy information is crucial to building facility design, operation, and energy efficiency. Many studies propose the use of environmental sensors (such as carbon dioxide, air temperature, and relative humidity sensors) and radio-frequency sensors (Wi-Fi networks) to monitor, assess, and predict occupancy information for buildings. As many methods have been developed and a variety of sensory data sources are available, establishing a proper selection of model and data source is critical to the successful implementation of occupancy prediction systems. This study compared three popular machine learning algorithms, including k-nearest neighbors (kNN), support vector machine (SVM), and artificial neural network (ANN), combined with three data sources, including environmental data, Wi-Fi data, and fused data, to optimize the occupancy models’ performance in various scenarios. Three error measurement metrics, the mean average error (MAE), mean average percentage error (MAPE), and root mean squared error (RMSE), have been employed to compare the models’ accuracies. Examined with an on-site experiment, the results suggest that the ANN-based model with fused data has the best performance, while the SVM model is more suitable with Wi-Fi data. The results also indicate that, comparing with independent data sources, the fused data set does not necessarily improve model accuracy but shows a better robustness for occupancy prediction.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A backward SDE method for uncertainty quantification in deep learning

Here, we develop a backward stochastic differential equation based probabilistic machine learning method, which formulates a class of stochastic neural networks as a stochastic optimal control problem. An efficient stochastic gradient descent algorithm is introduced with the gradient computed through a backward stochastic differential equation. Convergence analysis for stochastic gradient descent optimization and numerical experiments for applications of stochastic neural networks are carried out to validate our methodology in both theory and performance.

97 MATHEMATICS AND COMPUTING↗

Machine Learning-Accelerated First-Principles Molecular Dynamics Explains Anomalous Lattice Thermal Expansion in BaZr 0.78 Y 0.22 O 3-δ

Fuel cells are a vital clean energy technology that converts chemical energy directly into electricity with high efficiency, making them a cornerstone of a sustainable energy future. Herein we investigate the thermal and chemical lattice expansion behavior of hydrated BaZr 0.78 Y 0.22 O 3-δ using machine learning-accelerated ab initio molecular dynamics simulations. Here, our results reproduce the experimentally observed non-monotonic and anomalous temperature dependence of lattice expansion, which we attribute to the competing effects of thermal expansion and dehydration—two mechanisms that influence the lattice expansion in opposite directions. The importance of this work lies in its detailed demonstration of how advanced computational techniques can accurately capture complex environmental effects, providing a valuable framework for modeling similar phenomena in a variety of material systems and applications.

Proton conducting fuel cell↗

Analytic continuation of noisy data using Adams Bashforth residual neural network

We propose a data-driven learning framework for the analytic continuation problem in numerical quantum many-body physics. Designing an accurate and efficient framework for the analytic continuation of imaginary time using computational data is a grand challenge that has hindered meaningful links with experimental data. The standard Maximum Entropy (MaxEnt)-based method is limited by the quality of the computational data and the availability of prior information. Also, the MaxEnt is not able to solve the inversion problem under high level of noise in the data. Here we introduce a novel learning model for the analytic continuation problem using a Adams-Bashforth residual neural network (AB-ResNet). Additionally, the advantage of this deep learning network is that it is model independent and, therefore, does not require prior information concerning the quantity of interest given by the spectral function. More importantly, the ResNet-based model achieves higher accuracy than MaxEnt for data with higher level of noise. Finally, numerical examples show that the developed AB-ResNet is able to recover the spectral function with accuracy comparable to MaxEnt where the noise level is relatively small.

97 MATHEMATICS AND COMPUTING↗

DP-TwoLevel: two-stage gradient subspace learning for differentially private federated learning

Federated learning (FL) enables collaborative model training across distributed data sources without sharing raw data, but faces fundamental challenges in communication efficiency and privacy. Differentially private (DP) training mitigates information leakage but introduces noise that degrades model performance, especially in high-dimensional settings. We propose DP-TwoLevel, a hierarchical gradient projection method that improves utility under fixed DP constraints by exploiting low-dimensional structure in model updates. Our approach learns a two-level PCA-based representation of gradients and applies DP noise in a reduced-dimensional subspace, thereby lowering the effective noise magnitude while preserving dominant signal components. We evaluate the method across three datasets (MNIST, Fashion-MNIST, CIFAR-10) and three privacy regimes (ϵ∈0.5, 1.0, 2.0). Across nine experimental settings, DP-TwoLevel consistently outperforms DP-FedAvg, achieving an average accuracy improvement of 9.44%, with larger gains observed in lower ϵ(higher-noise) regimes (up to +22.31%). We further analyze scalability across models ranging from 100K to 1.49M parameters and identify a variance-based success criterion: performance remains strong when the projection preserves more than 75% of gradient variance, degrades in a marginal regime (65–75%), and fails below this threshold. Our results demonstrate that structure-aware dimensionality reduction can significantly improve the privacy–utility tradeoff in FL without modifying formal privacy guarantees. We also provide empirical evidence of scaling limitations for global projections and motivate per-layer extensions for larger models.

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

Generalized and Mechanistic PV Module Performance Prediction From Computer Vision and Machine Learning on Electroluminescence Images

Electroluminescence (EL) imaging of photovoltiac (PV) modules offers high-speed, high-resolution information about device performance, affording opportunities for greater insight and efficiency in module characterization across manufacturing, research and development, and power plant operations and management. Predicting module electrical properties from EL image features is a critical step toward these applications. In this article, we demonstrate quantification of both generalized and performance mechanism-specific EL image features, using pixel intensity-based and machine learning classification algorithms. From EL image features, we build predictive models for PV module power and series resistance, using time-series current-voltage (I-V) and EL data obtained stepwise on five brands of modules spanning three Si cell types through two accelerated exposures: damp heat (DH) (85°C/85% RH) and thermal cycling (TC) (IEC 61215). Overall, 195 pairs of EL images and I-V characteristics were analyzed, yielding 11700 individual PV cell images. A convolutional neural network was built to classify cells by the severity of busbar corrosion with high accuracy (95%). Generalized power predictive models estimated the maximum power of PV modules from EL images with high confidence and an adjusted-R 2 of 0.88, across all module brands and cell types in extended DH and TC exposures. Mechanistic degradation prediction was demonstrated by quantification of busbar corrosion in EL images of three module brands in DH, and subsequent modeling of series resistance using these mechanism-specific EL image features. For modules exhibiting busbar corrosion, we demonstrated series resistance predictive models with adjusted-R 2 of up to 0.73.

14 SOLAR ENERGY↗

FLEET: Flexible Efficient Ensemble Training for Heterogeneous Deep Neural Networks

Parallel training of an ensemble of Deep Neural Networks (DNN) on a cluster of nodes is an effective approach to shorten the process of neural network architecture search and hyper-parameter tuning for a given learning task. Prior efforts have shown that data sharing, where the common preprocessing operation is shared across the DNN training pipelines, saves computational resources and improves pipeline efficiency. Data sharing strategy, however, performs poorly for a heterogeneous set of DNNs where each DNN has varying computational needs and thus different training rate and convergence speed. This paper proposes FLEET, a flexible ensemble DNN training framework for efficiently training a heterogeneous set of DNNs. We build FLEET via several technical innovations. We theoretically prove that an optimal resource allocation is NP-hard and propose a greedy algorithm to efficiently allocate resources for training each DNN with data sharing. We integrate data-parallel DNN training into ensemble training to mitigate the differences in training rates and introduce checkpointing into this context to address the issue of different convergence speeds. Experiments show that FLEET significantly improves the training efficiency of DNN ensembles without compromising the quality of the result.

Guan, Hui↗

Randomized Federated Learning Methods for Nonsmooth, Nonconvex, and Hierarchical Optimization (Final Technical Report)

This final technical report summarizes the outcomes of a DOE-funded project on federated scientific machine learning (FL) under nonsmooth, nonconvex, and hierarchical optimization settings. The project develops new mathematical models, algorithms, and theoretical guarantees for decentralized stochastic, bilevel, and minimax optimization problems arising in DOE mission-relevant applications. A unified framework of randomized and zeroth-order federated optimization methods is introduced, providing provable convergence, communication efficiency, and sample-complexity guarantees. The report documents algorithmic design, theoretical analysis, and empirical validation of the proposed federated learning methods. The project also contributes to workforce development through graduate training and dissemination of results via publications and seminars.

97 MATHEMATICS AND COMPUTING↗

How Should Machine Learning Be Successfully Used for Wind Speed Vertical Extrapolation?

An accurate characterization of the wind resource available at hub-height is required for an efficient and bankable wind farm project. However, direct measurement of wind speed at the constantly increasing height of the hub of commercial wind turbines is oftentimes challenging and expensive, so that it is common practice to vertically extrapolate the wind resource from lower and more easily accessible levels. Conventional techniques for wind speed vertical extrapolation include the use of a power law and a logarithmic profile. While simple, the limits in accuracy of these methods have been shown in various studies. Recently, machine learning has been proposed as a new method to vertically extrapolate winds. All the published studies on the topic assess the performance of machine learning techniques in vertically extrapolating the wind resource at the same location where the algorithm has been trained. However, in real-world applications, the wind resource is measured at the instrument location, but it then needs to be extrapolated at hub height at the location of the wind turbines within the find farm. To be able to fully recommend the use of machine learning techniques over the simple power law and logarithmic law, the spatial variability of the performance improvements of the machine learning approaches needs to be assessed. Here, we propose a round-robin validation of a machine learning-based method for wind speed extrapolation. We use 20 months of observations at four locations spanning a 100 km wide region at the Southern Great Plains (SGP) atmospheric observatory, in north-central Oklahoma. At each location, we train a random forest to predict 30-min average wind speed at 143 m AGL. We use as input features lidar wind speed at 65 m AGL, time of day, sonic anemometer wind speed at 4 m AGL, turbulent kinetic energy, and Obukhov length. First, we perform a same-site comparison of the performance of the proposed random forest against the conventional techniques for wind speed extrapolation (namely power law and logarithmic profile, with widely accepted stability corrections). We find that the random forest outperforms the power law in vertically extrapolating wind speed in all the considered stability regimes, with a 33% reduction in MAE for stable conditions, and a 31% reduction in unstable conditions. Similar results are found when comparing predictions of extrapolated winds from the logarithmic profile and the random forest with the observed values. Next, we propose a round-robin validation, to use the random forest trained at each site to extrapolate wind speed at the remaining three sites. We find that the performance of the random forest approach degrades when the algorithm is tested at a site different than the training one. However, even under those circumstances, the machine learning-based approach still outperforms the conventional techniques for wind speed extrapolation, with, on average, a reduction in mean absolute error between 15 and 20% over the conventional methods, with the largest benefits obtained under stable conditions.

Monte Carlo↗

Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia

Cost versus accuracy trade-offs are frequently encountered in materials science and engineering, where a particular property of interest can be measured/computed at different levels of accuracy or fidelity. Naturally, the most accurate measurement is also the most resource and time intensive, while the inexpensive quicker alternatives tend to be noisy. In such situations, a number of machine learning (ML) based multifidelity information fusion (MFIF) strategies can be employed to fuse information accessible from varying sources of fidelity and make predictions at the highest level of accuracy. In this work, we perform a comparative study on traditionally employed single-fidelity and three MFIF strategies, namely, (1) Δ-learning, (2) low-fidelity as a feature, and (3) multifidelity cokriging (CK) to compare their relative prediction accuracies and efficiencies for accelerated property predictions and high throughput chemical space explorations. We perform our analysis using a dopant formation energy data set for hafnia, which is a well-known high- k material and is being extensively studied for its promising ferroelectric, piezoelectric, and pyroelectric properties. We use a dopant formation energy data set of 42 dopants in hafnia—each studied in six different hafnia phases—computed at two levels of fidelities to find merits and limitations of these ML strategies. The findings of this work indicate that the MFIF based learning schemes outperform the traditional SF machine learning methods, such as Gaussian process regression and CK provides an accurate, inexpensive and flexible alternative to other MFIF strategies. While the results presented here are for the case study of hafnia, they are expected to be general. Furthermore, materials discovery problems that involve huge chemical space explorations can be studied efficiently (or even made feasible in some situations) through a combination of a large number of low-fidelity and a few high-fidelity measurements/computations, in conjunction with the CK approach.

36 MATERIALS SCIENCE↗

Digital Real-Time Simulation and Power Quality Analysis of a Hydrogen-Generating Nuclear-Renewable Integrated Energy System

This paper investigates the challenges and solutions associated with integrating a hydrogen-generating nuclear-renewable integrated energy system (NR-IES) under a transactive energy framework. The proposed system directs excess nuclear power to hydrogen production during periods of low grid demand while utilizing renewables to maintain grid stability. Using digital real-time simulation (DRTS) in the Typhoon HIL 404 model, the dynamic interactions between nuclear power plants, electrolyzers, and power grids are analyzed to mitigate issues such as harmonic distortion, power quality degradation, and low power factor caused by large non-linear loads. A three-phase power conversion system is modeled using the Typhoon HIL 404 model and includes a generator, a variable load, an electrolyzer, and power filters. Active harmonic filters (AHFs) and hybrid active power filters (HAPFs) are implemented to address harmonic mitigation and reactive power compensation. The results reveal that the HAPF topology effectively balances cost efficiency and performance and significantly reduces active filter current requirements compared to AHF-only systems. During maximum electrolyzer operation at 4 MW, the grid frequency dropped below 59.3 Hz without filtering; however, the implementation of power filters successfully restored the frequency to 59.9 Hz, demonstrating its effectiveness in maintaining grid stability. Future work will focus on integrating a deep reinforcement learning (DRL) framework with real-time simulation and optimizing real-time power dispatch, thus enabling a scalable, efficient NR-IES for sustainable energy markets.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Electrical Load Forecasting Over Multihop Smart Metering Networks With Federated Learning

Electric load forecasting is essential for power management and stability in smart grids. This is mainly achieved via advanced metering infrastructure, where smart meters (SMs) record household energy data. Traditional machine learning (ML) methods are often employed for load forecasting, but require data sharing, which raises data privacy concerns. Federated learning (FL) can address this issue by running distributed ML models at local SMs without data exchange. However, current FL-based approaches struggle to achieve efficient load forecasting due to imbalanced data distribution across heterogeneous SMs. Here, this article presents a novel personalized FL (PFL) method for high-quality load forecasting in metering networks. A meta-learning-based strategy is developed to address data heterogeneity at local SMs in the collaborative training of local load forecasting models. Moreover, to minimize the load forecasting delays in our PFL model, we study a new latency optimization problem based on optimal resource allocation at SMs. A theoretical convergence analysis is also conducted to provide insights into FL design for federated load forecasting. Extensive simulations from real-world datasets show that our method outperforms existing approaches regarding better load forecasting and reduced operational latency costs.

Rahman, Ratun [Univ. of Alabama, Huntsville, AL (U↗

An AI-Based 3D Bat Movement Tracking System at Wind Energy Facilities Using Multi-Thermal Video Cameras

The talk at the NAWEA Wind Tech 2024 conference discusses how to leverage the potential of real-time thermal-imaging methodologies in quantifying nocturnal bat activities at wind turbines, using 3D computer vision techniques within a deep learning framework. This innovation enables the automatic detection and classification of bats, birds, and insects in thermal-imaging videos captured at wind turbine sites, facilitating efficient and accurate data analysis for enhanced understanding and mitigation of bat-wind turbine interactions.

AI↗

Toyota Prius Plug-In HEV: A Plug-In Hybrid Electric Car in NREL's Advanced Technology Vehicle Fleet (Fact Sheet)

This fact sheet highlights the Toyota Prius plug-in HEV, a plug-in hybrid electric car in the advanced technology vehicle fleet at the National Renewable Energy Laboratory (NREL). In partnership with the University of Colorado, NREL uses the vehicle for grid-integration studies and for testing new hardware and charge-management algorithms. NREL's advanced technology vehicle fleet featurespromising technologies to increase efficiency and reduce emissions without sacrificing safety or comfort. The fleet serves as a technology showcase, helping visitors learn about innovative vehicles that are available today or are in development. Vehicles in the fleet are representative of current, advanced, prototype, and emerging technologies.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Flame stability analysis of flame spray pyrolysis by artificial intelligence

Flame spray pyrolysis (FSP) is a process used to synthesize nanoparticles through the combustion of an atomized precursor solution; this process has applications in catalysts, battery materials, and pigments. Current limitations revolve around understanding how to consistently achieve a stable flame and the reliable production of nanoparticles. Machine learning and artificial intelligence algorithms that detect unstable flame conditions in real time may be a means of streamlining the synthesis process and improving FSP efficiency. In this study, the FSP flame stability is first quantified by analyzing the brightness of the flame's anchor point. This analysis is then used to label data for both unsupervised and supervised machine learning approaches. The unsupervised learning approach allows for autonomous labeling and classification of new data by representing data in a reduced dimensional space and identifying combinations of features that most effectively cluster it. The supervised learning approach, on the other hand, requires human labeling of training and test data but is able to classify multiple objects of interest (such as the burner and pilot flames) within the video feed. The accuracy of each of these techniques is compared against the evaluations of human experts. Both the unsupervised and supervised approaches can track and classify FSP flame conditions in real time to alert users of unstable flame conditions. This research has the potential to autonomously track and manage flame spray pyrolysis as well as other flame technologies by monitoring and classifying the flame stability.

42 ENGINEERING↗

The EGS Collab Project: Learnings from Experiment 1

The primary objective of the EGS Collab Project sponsored by DOE is to increase the understanding needed to efficiently implement enhanced geothermal systems (EGS). One goal of the EGS Collab project is to create a collaborative research environment in which to study stimulation of crystalline rock at the 10 meter scale. Key to this effort is the collection of high quality data to allow comparison to numerical coupled process models in an effort to build confidence in the codes and modeling techniques used. In response to this, the EGS Collab team has created an underground test bed at the Sanford Underground Research Facility (SURF) in Lead SD at a depth of approximately 1.5 km to examine hydraulic fracturing (Experiment 1). We are currently designing a second test bed aimed at investigating shear stimulation (Experiment 2). At the Experiment 1 location, we have characterized our host rock using laboratory testing and numerous field-based geophysical and geological techniques, and created a well-instrumented test bed to allow us to carefully monitor stimulation events and flow tests. In addition to the installed geophysical sensors, we have used tracer tests, differences in the ambient microbial communities at flow collection locations, and cold water injection to inform us about dynamic flow pathways. In Experiment 1, we have hydraulically stimulated the host rock in a number times at several locations in one well, creating new fractures that connect to existing fractures between the injection and production boreholes. We have performed long-term ambient and chilled water injection tests as an analog to EGS, and have monitored system changes resulting from these water injections through geophysical monitoring, flow and pressure measurements, tracer tests, and microbiology. Here, we summarize the tests performed, issues identified including poroelastic and thermoelastic effects, Joule-Thomson effects, restarting effects, indications of flow channeling, and the primary learnings from Experiment 1.

Enhanced Geothermal Systems, EGS Collab, stimulati↗