Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep energy method”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Load Profile Inpainting for Missing Load Data Restoration and Baseline Estimation

This paper introduces a Generative Adversarial Nets (GAN) based, Load Profile Inpainting Network (Load-PIN) for restoring missing load data segments and estimating the baseline for a demand response event. The inputs are time series load data before and after the inpainting period together with explanatory variables (e.g., weather data). Here, we propose a Generator structure consisting of a coarse network and a fine-tuning network. The coarse network provides an initial estimation of the data segment in the inpainting period. The fine-tuning network consists of self-attention blocks and gated convolution layers for adjusting the initial estimations. Loss functions are specially designed for the fine-tuning and the discriminator networks to enhance both the point-to-point accuracy and realisticness of the results. We test the Load-PIN on three real-world data sets for two applications: patching missing data and deriving baselines of conservation voltage reduction (CVR) events. We benchmark the performance of Load-PIN with five existing deep-learning methods. Our simulation results show that, compared with the state-of-the-art methods, Load-PIN can handle varying-length missing data events and achieve 15-30% accuracy improvement.

14 SOLAR ENERGY↗
DOE OSTI2022

Sensitivity analysis of generic deep geologic repository with focus on spatial heterogeneity induced by stochastic fracture network generation

Geologic Disposal Safety Assessment Framework is a state-of-the-art simulation software toolkit for probabilistic post-closure performance assessment of systems for deep geologic disposal of nuclear waste developed by the United States Department of Energy. This paper presents a generic reference case and shows how it is being used to develop and demonstrate performance assessment methods within the Geologic Disposal Safety Assessment Framework that mitigate some of the challenges posed by high uncertainty and limited computational resources. Variance-based global sensitivity analysis is applied to assess the effects of spatial heterogeneity using graph-based summary measures for scalar and time-varying quantities of interest. Behavior of the system with respect to spatial heterogeneity is further investigated using ratios of water fluxes. This analysis shows that spatial heterogeneity is a dominant uncertainty in predictions of repository performance which can be identified in global sensitivity analysis using proxy variables derived from graph descriptions of discrete fracture networks. New quantities of interest defined using water fluxes proved useful for better understanding overall system behavior.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

Efficient and assured reinforcement learning-based building HVAC control with heterogeneous expert-guided training

Abstract Building heating, ventilation, and air conditioning (HVAC) systems account for nearly half of building energy consumption and $$20\%$$ of total energy consumption in the US. Their operation is also crucial for ensuring the physical and mental health of building occupants. Compared with traditional model-based HVAC control methods, the recent model-free deep reinforcement learning (DRL) based methods have shown good performance while do not require the development of detailed and costly physical models. However, these model-free DRL approaches often suffer from long training time to reach a good performance, which is a major obstacle for their practical deployment. In this work, we present a systematic approach to accelerate online reinforcement learning for HVAC control by taking full advantage of the knowledge from domain experts in various forms . Specifically, the algorithm stages include learning expert functions from existing abstract physical models and from historical data via offline reinforcement learning, integrating the expert functions with rule-based guidelines, conducting training guided by the integrated expert function and performing policy initialization from distilled expert function. Moreover, to ensure that the learned DRL-based HVAC controller can effectively keep room temperature within the comfortable range for occupants, we design a runtime shielding framework to reduce the temperature violation rate and incorporate the learned controller into it. Experimental results demonstrate up to 8.8 X speedup in DRL training from our approach over previous methods, with low temperature violation rate.

Xu, Shichao↗
DOE OSTI2026

Federated learning for 2D synchrotron x-ray diffractometry: a cross-institutional approach for phase quantification of Ti–6Al–4V alloy

High-energy Two dimensional (2D) synchrotron x-ray diffractometry provides important insights into the atomistic structure and phase evolution of materials, yet traditional analysis methods remain complex, knowledge-intensive, and computationally demanding. Deep-learning models offer a powerful alternative for automating their analysis. Institutions that hold these datasets may be unwilling to share their data due to privacy and security policies, as well as the challenges associated with large-scale data transfer. As a result, models trained on local datasets often perform well only on their own data but exhibit bias and poor generalization across different instruments or facilities. To overcome these limitations, we explore federated learning (FL) for 2D synchrotron diffractograms, enabling collaborative model training without exchanging raw data. In this study, 2D synchrotron diffractograms of Ti–6Al–4V alloy collected from two independent facilities are used to train convolutional neural networks for predicting the β-phase volume fraction. Experimental results show that federated global models significantly outperform locally trained models in terms of generalization and achieve accuracy comparable to centralized trained models. These findings demonstrate the potential of FL to enable secure, cross-institutional collaboration and enhance the scalability of deep-learning-based materials characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Astronomaly at scale: searching for anomalies amongst 4 million galaxies

ABSTRACT Modern astronomical surveys are producing data sets of unprecedented size and richness, increasing the potential for high-impact scientific discovery. This possibility, coupled with the challenge of exploring a large number of sources, has led to the development of novel machine-learning-based anomaly detection approaches, such as astronomaly. For the first time, we test the scalability of astronomaly by applying it to almost 4 million images of galaxies from the Dark Energy Camera Legacy Survey. We use a trained deep learning algorithm to learn useful representations of the images and pass these to the anomaly detection algorithm isolation forest, coupled with astronomaly’s active learning method, to discover interesting sources. We find that data selection criteria have a significant impact on the trade-off between finding rare sources such as strong lenses and introducing artefacts into the data set. We demonstrate that active learning is required to identify the most interesting sources and reduce artefacts, while anomaly detection methods alone are insufficient. Using astronomaly, we find 1635 anomalies among the top 2000 sources in the data set after applying active learning, including eight strong gravitational lens candidates, 1609 galaxy merger candidates, and 18 previously unidentified sources exhibiting highly unusual morphology. Our results show that by leveraging the human–machine interface, astronomaly is able to rapidly identify sources of scientific interest even in large data sets.

Astronomy & Astrophysics↗
DOE OSTI2025

Topology-Aware Reinforcement Learning for Voltage Control: Centralized and Decentralized Strategies

Volt-VAR control (VVC) methods based on deep reinforcement learning (DRL) can effectively control distribution grid voltage and minimize power loss by implementing corrective and preventive control measures on the reactive power output of inverter-based distributed energy resources (DERs). However, model-free DRL-based VVC approaches usually cannot capture the important topological feature of the power system since they use a fully-connected network (FCN) to deliver the action. Therefore, this paper proposes a graph convolutional network (GCN)-based DRL approach that can employ the topological information of the network to take better control action for regulating the voltage. Our implementation allows for both centralized and decentralized configurations, utilizing a single agent and multiple agents respectively. Although the centralized GCN-based DRL approach has its advantages of minimizing voltage fluctuation and power loss, it is not suitable for large scale power systems due to its challenges in terms of scalability, computation speed and potential single points of failure. Therefore, these problems can be resolved using the decentralized GCN-based DRL approach. Moreover, to ensure the safe operation of the model, our proposed approach incorporates an exponential barrier function while formulating the reward function for each agent. To validate performance of the proposed approaches, the proposed model is tested on modified IEEE test systems and the performances are measured in terms on voltage fluctuation reduction, minimization of power loss and computational speed. Finally, the results show that the proposed topology-aware approach outperforms the FCN-based DRL approach in terms of reducing voltage fluctuation and minimizing power loss of the network. Moreover, it is shown that the decentralized GCN-based DRL has faster computational speed than other approaches.

42 ENGINEERING↗
DOE OSTI2020

AI for Science: Report on the Department of Energy (DOE) Town Halls on Artificial Intelligence (AI) for Science

The report documents the DOE Town Halls held during 2019 at Argonne National Laboratory, Oak Ridge National Laboratory, Lawrence Berkeley National Laboratory, and in Washington, DC. From July to October 2019, the Argonne, Oak Ridge, and Berkeley National Laboratories hosted a series of four town hall meetings attended by more than 1,000 U.S. scientists and engineers. The goal of the town hall series was to examine scientific opportunities in the areas of artificial intelligence (AI), Big Data, and high-performance computing (HPC) in the next decade, and to capture the big ideas, grand challenges, and next steps to realizing these opportunities. In this report and in the Department of Energy (DOE) laboratory community, we use the term “AI for Science” to broadly represent the next generation of methods and scientific opportunities in computing, including the development and application of AI methods (e.g., machine learning, deep learning, statistical methods, data analytics, automated control, and related areas) to build models from data and to use these models alone or in conjunction with simulation and scalable computing to advance scientific research. The AI for Science town hall discussions focused on capturing the transformational uses of AI that employ HPC and/or data analysis, leveraging data sets from HPC simulations or instruments and user facilities, and addressing scientific challenges unique to DOE user facilities and the agency’s wide-ranging fundamental and applied science enterprise.

36 MATERIALS SCIENCE↗
DOE OSTI2021

The Binary INformation from Open Clusters Using SEDs (BINOCS) Project: Reliable Photometric Mass Determinations of Binary Star Systems in Clusters

We introduce a new binary detection technique, Binary INformation from Open Clusters using SEDs (binocs), which we show is able to determine reliable stellar multiplicity and masses over a much larger mass range than current approaches. This new technique determines accurate component masses of binary and single systems of the open clusters’ main sequence by comparing observed magnitudes from multiple photometric filters to synthetic star spectral energy distributions (SEDs), allowing us to systematically probe the binary population for low-mass stars in clusters for eight well-studied open clusters. We provide new deep, infrared photometric catalogs (1.2–8.0 μm) for the key open clusters NGC 1960 (M36), NGC 2099 (M37), NGC 2420, and NGC 2682 (M67), using observations from NOAO/NEWFIRM and Spitzer/IRAC. Using these deep multiwavelength catalogs, the binocs method is applied to these clusters to determine accurate component masses for unresolved cluster binaries. We explore binary fractions as a function of cluster age, Galactic location, and metallicity.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Cross-Market Price Difference Forecast Using Deep Learning for Electricity Markets

Price forecasting is in the center of decision making in electricity markets. Many researches have been done in forecasting energy prices while little research has been reported on forecasting price difference between day-ahead and realtime markets due to its high volatility, which however plays a critical role in virtual trading. To this end, this paper takes the first attempt to employ novel deep learning architecture with Bidirectional Long-Short Term Memory (LSTM) units to forecast the price difference between day-ahead and real-time markets for the same node. The raw data is collected from PJM market, processed and fed into the proposed network. The Root Mean Squared Error (RMSE) and customized performance metric are used to evaluate the performance of the proposed method. Case studies show that it outperforms the traditional statistical models like ARIMA, and machine learning models like XGBoost and SVR methods in both RMSE and the capability of forecasting the sign of price difference. Additionally, to cross-market price difference forecast, the proposed approach has the potential to be applied to solve other forecasting problems such as price spread forecast in DA market for Financial Transmission Right (FTR) trading purpose.

DA/RT price difference↗
DOE OSTI2023

The Variable Continuous Bimaterial Interface in the San Jacinto Fault Zone Revealed by Dense Seismic Array Analysis of Fault Zone Head Waves

Key factors controlling earthquake ruptures include fault geometry, continuity, and seismic velocity structure around the fault. We present a novel tool that better informs deep bimaterial fault geometry embedded in distributed damage and seismicity, associated velocity contrasts across the fault, and their correlations with surface complexities. The method employs fault zone head and direct body waves and is applied to recordings from five spatiotemporally different seismic arrays along the complex San Jacinto fault zone (SJFZ) in southern California. We detect and distinguish these signals based on instantaneous phase coherence and relative energy in a cascading manner from one scale array to another. The analysis reveals a >70-km long continuous bimaterial interface within the SJFZ with several deep northeast dipping fault segments. The northern SJFZ, for instance, locates ~7 km northeast of its surface expression at 18-km depth. P-wave velocity contrasts range from near 0% to >15%, consistent with other bimaterial faults, and differ by a few % depending on fault-array azimuth, implying directional-dependent velocity contrasts. S-wave head waves and velocity contrasts are also imaged for the first time at the southern SJFZ, averaging to 2.9% in agreement with tomography results. The imaged geometry and continuity suggest the SJFZ initiated along remnant tectonic structures and translates to a rupture potential of M > 7.2, i.e., the sizes of its largest paleo-earthquakes. The P and S contrasts, and their ratios, have important implications for earthquake rupture speed, mode, directivity, and frictional heating along the SJFZ and other major faults globally.

58 GEOSCIENCES↗
DOE OSTI2024

Using the Principals of Electrochemistry to Understand and Overcome the Complicated Degradation Mechanisms of Silicon Anodes in Lithium-Ion Batteries [Slides]

Battery technology is the most significant problem facing widespread market adoption of battery electric vehicles (BEVs). The low energy density of state-of-the-art lithium-ion electrode materials leaves BEV owners and prospective buyers with lower ranges than a comparable internal combustion engine (ICE) vehicle, and vulnerable to a nascent fast charging network. Silicon has the potential to increase the anode energy density by nearly ten times compared to the incumbent material (graphite) and make BEVs a more competitive transportation option. However, lithiated silicon is extremely reactive towards components of the electrolyte and forms a heterogeneous, complicated, and dynamic solid at its surface known as the solid electrolyte interphase (SEI). Ideally, the SEI would passivate the silicon surface, but continuous chemical degradation persists even when the battery is not operating. This reactivity reduces silicon anode lifetimes well below the necessary standards for BEVs. The NREL-led Silicon Consortium Project is dedicated to understanding and solving these mechanisms of degradation. Here, I will discuss an electrochemical method that provides deep insights into the silicon interface during battery operation. I will link these observations to fundamental electrochemical principals and how they translate into actionable strategies that extend the lifetime of silicon anodes.

25 ENERGY STORAGE↗
DOE OSTI2023

Two-Stage Deep Reinforcement Learning for Distribution System Voltage Regulation and Peak Load Management

The growing integration of distributed solar photovoltaic (PV) in distribution systems could result in adverse effects during grid operation. This paper develops a two-agent soft actor critic-based deep reinforcement learning (SAC-DRL) solution to simultaneously control PV inverters and battery energy storage systems for voltage regulation and peak demand reduction. The novel two-stage framework, featured with two different control agents, is applied for daytime and nighttime operations to enhance control performance. Comparison results with other control methods on a real feeder in Western Colorado demonstrate that the proposed method can provide advanced voltage regulation with modest active power curtailment and reduce peak load demand from feeder's head.

deep reinforcement learning↗
DOE OSTI2023

Ising-Traffic: Using Ising Machine Learning to Predict Traffic Congestion under Uncertainty

This paper addresses the challenges in accurate and realtime traffic congestion prediction with uncertainty by proposing Ising-Traffic, a novel quantum-inspired dual-model Ising based traffic prediction framework which delivers higher accuracy and lower latency than SOTA solutions. While traditional and deep learning methods face the trade-off between algorithm complexity and computational efficiency, our Ising-based method leverages Ising’s inherent and unique capability of finding the state of a system with the lowest energy and applying it to traffic prediction. In this work, traffic prediction under uncertainty is formulated into two separate Ising models: Reconstruct-Ising and Predict-Ising. Reconstruct-Ising is mapped onto modern Ising machine and handles uncertainty in traffic accurately with negligible latency and energy consumption, while Predict-Ising is mapped onto traditional processors and predicts future congestion precisely with only at most 1.8% computational demands of existing solutions. Our evaluation shows Ising-Traffic delivers on average 98× speedups and 5% accuracy improvement over SOTA.

traffic flow control, Ising↗
DOE OSTI2025

Machine Learning-Based Energy Estimation for Sterile Neutrino Searches in the NOνA Experiment

This dissertation presents a search for sterile neutrinos using Monte Carlo datasets and experimental data from the NOνA experiment. This work introduces novel machine learning techniques for energy reconstruction in neutral current events. A deep learning-based energy estimator was developed and integrated into the analysis framework. Using this new energy estimator, the sensitivity to sterile neutrino-induced oscillations is evaluated and presented. Furthermore, the dissertation explores potential methods for further improvement of the analysis.

43 PARTICLE ACCELERATORS↗
DOE OSTI2023

Two-Stage Deep Reinforcement Learning for Distribution System Voltage Regulation and Peak Load Management: Preprint

The growing integration of distributed solar photovoltaic (PV) in distribution systems could result in adverse effects during grid operation. This paper develops a soft actor critic-based deep reinforcement learning (SAC-DRL) solution to simultaneously control PV inverters and battery energy storage systems for voltage regulation and peak load demand shaving. The novel two-stage framework, featured with two different control agents, is applied for daytime and nighttime operation to enhance the control performance. Comparison results with other control methods on a real feeder in Western Colorado demonstrate that the proposed method can provide advanced voltage regulation with modest active power curtailment for peak demand reduction.

deep reinforcement learning↗
DOE OSTI2024

HDBind: encoding of molecular structure with hyperdimensional binary representations

Traditional methods for identifying “hit” molecules from a large collection of potential drug-like candidates rely on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug and its protein target. These approaches have a significant limitation in that they require exceptional computing capabilities for even relatively small collections of molecules. Increasingly large and complex state-of-the-art deep learning approaches have gained popularity with the promise to improve the productivity of drug design, notorious for its numerous failures. However, as deep learning models increase in their size and complexity, their acceleration at the hardware level becomes more challenging. Hyperdimensional Computing (HDC) has recently gained attention in the computer hardware community due to its algorithmic simplicity relative to deep learning approaches. The HDC learning paradigm, which represents data with high-dimension binary vectors, allows the use of low-precision binary vector arithmetic to create models of the data that can be learned without the need for the gradient-based optimization required in many conventional machine learning and deep learning methods. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated in a range of application areas (computer vision, bioinformatics, mass spectrometery, remote sensing, edge devices, etc.). To the best of our knowledge, our work is the first to consider HDC for the task of fast and efficient screening of modern drug-like compound libraries. We also propose the first HDC graph-based encoding methods for molecular data, demonstrating consistent and substantial improvement over previous work. We compare our approaches to alternative approaches on the well-studied MoleculeNet dataset and the recently proposed LIT-PCBA dataset derived from high quality PubChem assays. We demonstrate our methods on multiple target hardware platforms, including Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs), showing at least an order of magnitude improvement in energy efficiency versus even our smallest neural network baseline model with a single hidden layer. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools. We make our code publicly available at https://github.com/LLNL/hdbind.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Vehicle to Grid Frequency Regulation Capacity Optimal Scheduling for Battery Swapping Station Using Deep Q-Network

Battery swapping stations (BSSs) are ideal candidates for fast frequency regulation services (FFRS) due to their large battery stock capacity. In addition, BSSs can precharge batteries for customers and the batteries that are not in charging can provide a stable regulation capacity to the market. However, uncertainties, such as ACE signals and the EV per-hour visit counts, introduce stochastic nonlinear dynamics into the operation of a BSS-based FFRS. Currently, there is no quantification method to ensure its optimal economical operation. To close this gap, in this article, we propose a novel deep Q-learning-based FFRS capacity dynamic scheduling strategy. This method can autonomously schedule the hourly regulation capacity in real time to maximize the BSSx0027;s revenue for providing FFRS. Case studies using real-world data verify the efficacy of the proposed work.

25 ENERGY STORAGE↗
DOE OSTI2026

Semi-inclusive deep-inelastic scattering on a polarized spin-1 target. II. Deuteron and spectator nucleon tagging

We develop the theoretical framework for semi-inclusive deep-inelastic scattering on a polarized spin-1 target and apply it to scattering on the polarized deuteron with spectator nucleon tagging. In Part I (previous article), we present the general form of the semi-inclusive cross section and polarization observables for the spin-1 target. In Part II (this article), we consider deep-inelastic scattering on the polarized deuteron with spectator nucleon tagging as a special case of target fragmentation. Methods of light-front quantization are employed to separate nuclear and hadronic structure in the high-energy process and achieve a composite description. The light-front wave function of the polarized deuteron is obtained from a rotationally covariant three-dimensional wave function in the center-of-mass frame of the proton-neutron system. The tagged structure functions are computed in the impulse approximation. The momentum and spin distribution of the active nucleon are controlled by the deuteron polarization and the detected spectator momentum (𝐷/𝑆 wave ratio). The cross section and spin asymmetries are evaluated for general deuteron polarization (vector and tensor, longitudinal and transverse) as functions of the spectator momentum. Tensor-polarized spin asymmetries of order unity are achieved for spectator momenta of approximately 300 MeV, which select configurations with a large 𝐷 wave. Sum rules for the tagged spin structure functions are derived. The results can be used for simulations of spectator tagging in future polarized fixed-target experiments (Jefferson Lab) or at the Electron-Ion Collider.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗