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 1,693 records · Page 94

Accelerating FEM-Based Corrosion Predictions Using Machine Learning

Atmospheric corrosion of metallic parts is a widespread materials degradation phenomena that is challenging to predict given its dependence on many factors (e.g. environmental, physiochemical, and part geometry). For materials with long expected service lives, accurately predicting the degree to which corrosion will degrade part performance is especially difficult due to the stochastic nature of corrosion damage spread across years or decades of service. The Finite Element Method (FEM) is a computational technique capable of providing accurate estimates of corrosion rate by numerically solving complex differential Eqs. characterizing this phenomena. Nevertheless, given the iterative nature of FEM and the computational expense required to solve these complex equations, FEM is ill-equipped for an efficient exploration of the design space to identify factors that accelerate or deter corrosion, despite its accuracy. In this work, a machine learning based surrogate model capable of providing accurate predictions of corrosion with significant computational savings is introduced. Specifically, this work leverages AdaBoosted Decision trees to provide an accurate estimate of corrosion current per width given different values of temperature, water layer thickness, molarity of the solution, and the length of the cathode for a galvanic couple of aluminum and stainless steel.

36 MATERIALS SCIENCE↗

Machine learning approach to trapped many-fermion systems

For this work, we apply a variational ansatz based on neural networks to the problem of spin-$^1_2$ fermions in a harmonic trap interacting through a short distance potential. We showed that standard machine learning techniques lead to a quick convergence to the ground state, especially in weakly coupled cases. Higher couplings can be handled efficiently by increasing the strength of interactions during “training”.

1-dimensional systems↗

LED Lighting: Applying Lessons Learned from the CFL Experience

Light emitting diode (LED) technology has emerged as an exciting new lighting alternative with the potential for significant energy savings. There is concern, however, that white light LEDs for general illumination could take a long, bumpy course similar to another energy-efficient lighting technology – compact fluorescent lights (CFLs). Recognizing the significant potential energy-efficient lighting has to reduce U.S. energy consumption, Congress mandated in the Energy Policy Act of 2005 that the U.S. Department of Energy (DOE) develop Solid State Lighting (SSL) through a Next Generation Lighting Initiative. DOE’s first step was to analyze the market introduction of compact fluorescent lighting to determine what lessons could be learned to smooth the introduction of SSL in the United States (Sandahl et al. 2006). This paper summarizes applicable lessons learned from the market introduction of CFLs and describe how DOE and others are applying those lessons to speed the development and market introduction of energy-efficient LED lighting for general illumination applications. A description of the current state of LED technology and compares LEDs to incandescent, fluorescent, and halogen lights is also provided.

CFLs↗

Conceptual Machine Learning Strategy for Maintenance of Molten Salt Heat Exchanger

This report addresses the requirements of Milestone M3.2 Define maintenance scenarios and benchmarks. Development of digital twins (DT) for molten salt reactor (MSR) components is crucial for reducing operating and maintenance costs (O&M) and ensuring commercial viability of these reactors. Our focus is on development of DT for MSR primary system heat exchanger (HX), a critical component, the fault in which can reduce operating efficiency and force reactor shutdown. We are investigating feasibility of a conceptual DT of HX consisting of internal distributed temperature sensing with fiber optics and machine learning (ML) algorithms to detect and localize faults.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

OPFLearnData: Dataset for Learning AC Optimal Power Flow

The datasets are resulting from OPFLearn.jl, a Julia package for creating AC OPF datasets. The package was developed to provide researchers with a standardized way to efficiently create AC OPF datasets that are representative of more of the AC OPF feasible load space compared to typical dataset creation methods. The OPFLearn dataset creation method uses a relaxed AC OPF formulation to reduce the volume of the unclassified input space throughout the dataset creation process. The dataset contains load profiles and their respective optimal primal and dual solutions. Load samples are processed using AC OPF formulations from PowerModels.jl. More information on the dataset creation method can be found in our publication, "OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets" and in the package website: https://github.com/NREL/OPFLearn.jl.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Photonics Research and Development

During the period August 2005 through October 2009, the UNLV Research Foundation (UNLVRF), a non-profit affiliate of the University of Nevada, Las Vegas (UNLV), in collaboration with UNLV's Colleges of Science and Engineering; Boston University (BU); Oak Ridge National Laboratory (ORNL); and Sunlight Direct, LLC, has managed and conducted a diverse and comprehensive research and development program focused on light-emitting diode (LED) technologies that provide significantly improved characteristics for lighting and display applications. This final technical report provides detailed information on the nature of the tasks, the results of the research, and the deliverables. It is estimated that about five percent of the energy used in the nation is for lighting homes, buildings and streets, accounting for some 25 percent of the average home's electric bill. However, the figure is significantly higher for the commercial sector. About 60 percent of the electricity for businesses is for lighting. Thus replacement of current lighting with solid-state lighting technology has the potential to significantly reduce this nation's energy consumption by some estimates, possibly as high as 20%. The primary objective of this multi-year R&D project has been to develop and advance lighting technologies to improve national energy conversion efficiencies; reduce heat load; and significantly lower the cost of conventional lighting technologies. The UNLVRF and its partners have specifically focused these talents on (1) improving LED technologies; (2) optimizing hybrid solar lighting, a technology which potentially offers the benefits of blending natural with artificial lighting systems, thus improving energy efficiency; and (3) building a comprehensive academic infrastructure within UNLV which concentrates on photonics R&D. Task researchers have reported impressive progress in (1) the development of quantum dot laser emitting diodes (QDLEDs) which will ultimately improve energy efficiency and lower costs for display and lighting applications (UNLV College of Engineering); (2) advancing green LED technology based on the Indium-Gallium-Nitride system (BU), thus improving conversion efficiencies; (3) employing unique state-of-the-art X-ray, electron and optical spectroscopies with microscopic techniques to learn more about the electronic structure of materials and contacts in LED devices (UNLV College of Science); (4) establishing a UNLV Display Lighting Laboratory staffed with a specialized team of academic researchers, students and industrial partners focused on identifying and implementing engineering solutions for lighting display-related problems; and (5) conducting research, development and demonstration for HSL essential to the resolution of technological barriers to commercialization.

30 DIRECT ENERGY CONVERSION↗

MACHINE LEARNING-ENABLED PREDICTION OF TRANSIENT INJECTION MAP IN AUTOMOTIVE INJECTORS WITH UNCERTAINTY QUANTIFICATION

Accurate prediction of injection profiles is a critical aspect of linking injector operation with engine performance and emissions. However, highly resolved injector simulations can take one to two weeks of wall-clock time, which is incompatible with engine design cycles with desired turnaround times of less than a day. Hence, it is important to reduce the time-to-solution of the internal flow simulations by several orders of magnitude to make it compatible with engine simulations. This work demonstrates a data-driven approach for tackling the computational overhead of injector simulations, whereby the transient injection profiles are emulated for a side-oriented, single-hole diesel injector using a Bayesian machine-learning framework. First, an interpretable Bayesian learning strategy was employed to understand the effect of design parameters on the total void fraction field. Then, autoencoders are utilized for efficient dimensionality reduction of the flowfields. Gaussian process models are finally used to predict the spatiotemporal void fraction field at the injector exit for unknown operating conditions. The Gaussian process models produce principled uncertainty estimates associated with the emulated flowfields, which provide the engine designer with valuable information of where the data-driven predictions can be trusted in the design space. The Bayesian flowfield predictions are compared with the corresponding predictions from a deep neural network, which has been transfer-learned from static needle simulations from a previous work by the authors. The emulation framework can predict the void fraction field at the exit of the orifice within a few seconds, thus achieving a speed-up factor of up to 38 x 10(6) over the traditional simulation-based approach of generating transient injection maps.

machine learning↗

Machine Learning-Assisted Distribution System Network Reconfiguration Problem

High penetration from volatile renewable energy resources in the grid and the varying nature of loads raise the need for frequent line switching to ensure the efficient operation of electrical distribution networks. Operators must ensure maximum load delivery, reduced losses, and the operation between voltage limits. However, computations to decide the optimal feeder configuration are often computationally expensive and intractable, making it unfavorable for real-time operations. This is mainly due to the existence of binary variables in the network reconfiguration optimization problem. To tackle this issue, we have devised an approach that leverages machine learning techniques to reshape distribution networks featuring multiple substations. This involves predicting the substation responsible for serving each part of the network. Hence, it leaves simple and more tractable Optimal Power Flow problems to be solved. This method can produce accurate results in a significantly faster time, as demonstrated using the IEEE 37-bus distribution feeder. Compared to the traditional optimization-based approaches, a feasible solution is achieved approximately ten times faster for all the tested scenarios.

deep neural networks↗

OPFLearn.jl [SWR-21-109]

OPFLearn.jl is a Julia package for creating datasets for machine learning approaches to solving AC optimal power flow (AC OPF). It was developed to provide researchers with a standardized way to efficiently create AC OPF datasets that are representative of more of the AC OPF feasible load space compared to typical dataset creation methods. The OPFLearn dataset creation method uses a relaxed AC OPF formulation to reduce the volume of the unclassified input space throughout the dataset creation process. Over time this input space tightens around the relaxed AC OPF feasible region to increase the percentage of feasible load profiles found while uniformly sampling the input space. Load samples are processed using AC OPF formulations from PowerModels.jl. More information on the dataset creation method can be found in our publication, "OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets". To use OPFLearn.jl a PowerModels network data dictionary is required (can be loaded from Matpower ".m" files) to define the network the dataset is being created for.

Joswig-Jones, Trager↗

OPFLearn.jl v0.1.2 5/18/2023 [SWR-21-109]

OPFLearn.jl is a Julia package for creating datasets for machine learning approaches to solving AC optimal power flow (AC OPF). It was developed to provide researchers with a standardized way to efficiently create AC OPF datasets that are representative of more of the AC OPF feasible load space compared to typical dataset creation methods. The OPFLearn dataset creation method uses a relaxed AC OPF formulation to reduce the volume of the unclassified input space throughout the dataset creation process. Over time this input space tightens around the relaxed AC OPF feasible region to increase the percentage of feasible load profiles found while uniformly sampling the input space. Load samples are processed using AC OPF formulations from PowerModels.jl. More information on the dataset creation method can be found in our publication, "OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets". To use OPFLearn.jl a PowerModels network data dictionary is required (can be loaded from Matpower ".m" files) to define the network the dataset is being created for.

Joswig-Jones, Trager↗

Deployment of Dynamic Neural Network Optimization to Minimize Heat Rate During Ramping for Coal Power Plants (Final Technical Report)

Much success was achieved throughout the course of this project. A successful implementation of Dynamic Neural Network Optimization (D-NNO) was coupled with Adaptive Predictive Controls (APC) and a novel hardware installation comprised of an advanced sensor network (ASN) measuring mass-weighted averages of flue gas constituents above the horizontal superheater of a coal-fired utility boiler. From 2019 through 2023 (including an extension due to COVID delays), the team was able to prototype, evaluate, deploy, iterate, and ultimately finalize an advanced closed-loop control D-NNO system which demonstrated the ability to: •improve unit efficiency ~2.0% relative to unoptimized operation (represented as total fuel fired per MWh generated) •improve unit NOx emission rates 10%+ beyond static optimization baselines •improve unit temperature stability as much as 58% and on average 12% •improve operating load stability as much as 35% The culmination of this project has generated an advanced methodology of deploying specially designed recurrent neural networks (long short-term memory, gated recurrent unit, encoder-decoder networks, transformers, etc.), customized trajectory planning and closed-loop optimization modules capable of adapting to live electric grid responses and demands, self-tuning and adaptive expert controls constantly adjusting prediction parameters to real-time unit behavior, and a hardware/software package able to reliably calculate net unit heat rate (NUHR) in real-time using flue gas constituents, machine learning, and known combustion relationships. Through this real-time NUHR value, immediate feedback on system adjustments relative to operating efficiency was available, allowing for rapid improvements to system performance. In addition to development and deployment of the advanced D-NNO system, the approach methodology has been readily commercialized through the project platform Griffin Open Systems, LLC, the D-NNO software platform host. Similar methodologies to those developed by this project have already been deployed at 5 other units across the United States, with another 6 implementations scheduled, and more expected. Over the course of the project, multiple academic papers were submitted and accepted for publication within esteemed academic journals, and PhD students were trained and graduated, as well as undergraduate students becoming involved and participating to project objectives.

01 COAL, LIGNITE, AND PEAT↗

Selecting XFEL single-particle snapshots by geometric machine learning

A promising new route for structural biology is single-particle imaging with an X-ray Free-Electron Laser (XFEL). This method has the advantage that the samples do not require crystallization and can be examined at room temperature. However, high-resolution structures can only be obtained from a sufficiently large number of diffraction patterns of individual molecules, so-called single particles. Here, we present a method that allows for efficient identification of single particles in very large XFEL datasets, operates at low signal levels, and is tolerant to background. This method uses supervised Geometric Machine Learning (GML) to extract low-dimensional feature vectors from a training dataset, fuse test datasets into the feature space of training datasets, and separate the data into binary distributions of “single particles” and “non-single particles.” As a proof of principle, we tested simulated and experimental datasets of the Coliphage PR772 virus. We created a training dataset and classified three types of test datasets: First, a noise-free simulated test dataset, which gave near perfect separation. Second, simulated test datasets that were modified to reflect different levels of photon counts and background noise. These modified datasets were used to quantify the predictive limits of our approach. Third, an experimental dataset collected at the Stanford Linear Accelerator Center. The single-particle identification for this experimental dataset was compared with previously published results and it was found that GML covers a wide photon-count range, outperforming other single-particle identification methods. Moreover, a major advantage of GML is its ability to retrieve single particles in the presence of structural variability.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Arbitrary Polynomial Separations in Trainable Quantum Machine Learning

Recent theoretical results in quantum machine learning have demonstrated a general trade-off between the expressive power of quantum neural networks (QNNs) and their trainability; as a corollary of these results, practical exponential separations in expressive power over classical machine learning models are believed to be infeasible as such QNNs take a time to train that is exponential in the model size. We here circumvent these negative results by constructing a hierarchy of efficiently trainable QNNs that exhibit unconditionally provable, polynomial memory separations of arbitrary constant degree over classical neural networks—including state-of-the-art models, such as Transformers—in performing a classical sequence modeling task. This construction is also computationally efficient, as each unit cell of the introduced class of QNNs only has constant gate complexity. We show that contextuality—informally, a quantitative notion of semantic ambiguity—is the source of the expressivity separation, suggesting that other learning tasks with this property may be a natural setting for the use of quantum learning algorithms.

Anschuetz, Eric R. [California Institute of Techno↗

Machine learning modeling and model predictive control of a closed-circuit reverse osmosis system

Closed-circuit reverse osmosis (CCRO) offers a flexible and energy-efficient alternative to conventional reverse osmosis by operating in a semi-batch mode that recycles brine, enabling higher recovery rates and reduced specific energy consumption (SEC). However, developing accurate, system-level dynamic models for CCRO remains challenging due to its nonlinear, multi-phase operation and sensitivity to variable feed water conditions. Traditional modeling approaches, such as NARMAX (nonlinear autoregressive moving average with exogenous inputs), often struggle to generalize across varying inlet feed concentrations, necessitating frequent parameter re-estimation and limiting their utility for real-time control applications. To address these limitations, we developed a long short-term memory (LSTM) neural network model trained on an extensive experimental data set from a CCRO pilot plant. The model accepts three inputs, feed flow rate, recirculation flow rate, and initial feed conductivity, and predicts three key outputs: reject conductivity, feed pump power draw, and recirculation pump power draw. We validated the LSTM model against experimental data, demonstrating its ability to distinguish between different feed conductivities and adapt to variable flow rates. Subsequently, we incorporated the LSTM model within a nonlinear model predictive control (MPC) scheme and conducted closed-loop simulations to optimize the integrated SEC (iSEC). In conclusion, the results project up to a 6% reduction in iSEC by using MPC to optimize performance over the entire experiment duration, without requiring any random excitation for data collection or parameter re-estimation.

Desalination↗

Deep reinforcement learning control of hydraulic fracturing

Hydraulic fracturing is a technique to extract oil and gas from shale formations, and obtaining a uniform proppant concentration along the fracture is key to its productivity. Recently, various model predictive control schemes have been proposed to achieve this objective. But such controllers require an accurate and computationally efficient model which is difficult to obtain given the complexity of the process and uncertainties in the rock formation properties. In this article, we design a model-free data-based reinforcement learning controller which learns an optimal control policy through interactions with the process. Deep reinforcement learning (DRL) controller is based on the Deep Deterministic Policy Gradient algorithm that combines Deep-Q-network with actor-critic framework. In addition, we utilize dimensionality reduction and transfer learning to quicken the learning process. We show that the controller learns an optimal policy to obtain uniform proppant concentration despite the complex nature of the process while satisfying various input constraints.

42 ENGINEERING↗

Parameter study of a vehicle-scale hydrogen storage system.

Sandia National Laboratories has developed a vehicle-scale prototype hydrogen storage system as part of a Work For Others project funded by General Motors. This Demonstration System was developed using the complex metal hydride sodium alanate. For the current work, we have continued our evaluation of the GM Demonstration System to provide learning to DOE's hydrogen storage programs, specifically the new Hydrogen Storage Engineering Center of Excellence. Baseline refueling data during testing for GM was taken over a narrow range of optimized parameter values. Further testing was conducted over a broader range. Parameters considered included hydrogen pressure and coolant flow rate. This data confirmed the choice of design pressure of the Demonstration System, but indicated that the system was over-designed for cooling. Baseline hydrogen delivery data was insufficient to map out delivery rate as a function of temperature and capacity for the full-scale system. A more rigorous matrix of tests was performed to better define delivery capabilities. These studies were compared with 1-D and 2-D coupled multi-physics modeling results. The relative merits of these models are discussed along with opportunities for improved efficiency or reduced mass and volume.

08 HYDROGEN↗

HBMax: Optimizing Memory Efficiency for Parallel Influence Maximization on Multicore Architectures

The goal of influence maximization is to select k most-influential vertices or seeds in a network, where influence is defined by a given diffusion process. The problem has a number of important applications such as viral marketing, information spread, and epidemic control. Although computing optimal seed set is NP-Hard, due to the submodular nature of the problem efficient approximation algorithms exist. However, even state-of-the-art parallel implementations are limited by a sampling step that incurs large memory footprints. This in turn limits the problem size reach and approximation quality. In this work, we study the memory footprint of the sampling process collecting reverse reachability information in the IMM algorithm over large real-world social networks. We present an adaptive and memory-efficient optimization approach for a state-of-the-art multi-threaded parallel influence maximization algorithm. Our approach,HuffMax, uses a portion of the reverse reachable (RR) sets collected by the algorithm to learn the characteristics of the graph. Then, it compresses the intermediate reverse reachability information with Huffman coding, and queries directly on the compressed data to preserve the memory savings obtained through compression. We also propose an efficient sampling strategy based on the distribution of RR sets, which can further reduce the computation time for typical social networks with long-tail distributions. Considering a NUMA architecture, we scale up our solution on 128-core CPUs and reduce the memory footprint by up to 45.7% with negligible time overhead (or even faster) and without perceivable loss of accuracy.

Chen, Xinyu↗

Novel usage of deep learning and high-performance computing in long-baseline neutrino oscillation experiments

Mención Internacional en el título de doctorDeep-learning methods are playing a crucial role in numerous scientific and industrialapplications. Over the past two decades, these techniques have helped in the collection,reconstruction, and analysis of large data samples in particle physics experiments. Themain topic of this PhD research is the study of deep-learning techniques in long-baselineneutrino oscillation experiments. Neutrinos are mysterious light elementary particles,and their investigation is essential to shed light on some of the remaining open questionsin physics. The work presented here describes an algorithm based on a convolutionalneural network developed to provide highly accurate and efficient selections of electronneutrino and muon neutrino interactions in the Deep Underground Neutrino Experiment(DUNE). With this algorithm, the electron neutrino (antineutrino) selection efficiencypeaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between2-5 GeV. The selection efficiency for muon neutrino (antineutrino) interactions is foundto have a maximum of 96% (97%) and exceeds 90% (95%) efficiency for reconstructedneutrino energies above 2 GeV. When considering all electron neutrino and antineutrinointeractions as signal (both those appearing from oscillations and those intrinsic tothe beam), a selection purity of 90% is achieved. These event selections are criticalto maximise the sensitivity of the experiment to CP-violating effects, key to furtherunderstand the matter-antimatter asymmetry of the Universe.In high-energy physics experiments, deep learning has also been explored for producingfast simulations and physically-motivated manipulations of simulated images. Some ofthose simulations, such as the light production and detection, are very computationallyexpensive and require novel methods to produce the necessary samples while controllingthe varied underlying physics model parameters. To do so, we invented the model-assistedgenerative adversarial network (MAGAN), first validated on simple generic case studiesand then successfully applied to the DUNE photon-detector simulation.Moreover, we also developed graph neural networks for 3D-voxel classification ofambiguities and optical crosstalk for a different particle physics experiment, most preciselyfor the proposed SuperFGD. This novel 3D-granular plastic-scintillator neutrino detectorwill be used to upgrade the near detector of the T2K neutrino oscillation experiment, and our method reports efficiencies and purities of 94-96% per event in the classificationof particle track voxels.Due to the growth and complexity of deep neural networks, researchers have beeninvestigating techniques to train those networks in a more computationally-efficient way.Many efforts have been made by the community to optimise deep-learning models byparallelising or distributing their training computation across multiple devices. In thisthesis, we study an approach based on data locality for those neural networks that cannotbenefit from scaling their computation due to a significant bottleneck in the data I/O.The research also includes a detailed study on the performance of deep neural networkson hardware accelerator boards.Los métodos de aprendizaje profundo son cada vez más utilizados en numerosas aplicacionescientíficas e industriales hoy en día. Durante las dos últimas décadas, estastécnicas se han empleado en la recolección, reconstrucción y análisis de la gran cantidadde datos generados por experimentos de física de partículas. El tema principal de estatesis doctoral es el uso de estos modelos de aprendizaje profundo en experimentos defísica de neutrinos, en concreto en los experimentos de larga distancia DUNE y T2K. Losneutrinos, partículas fundamentales neutras, de las más ligeras del Universo, pueden serclave para explicar algunas de las cuestiones todavía sin resolver en física fundamental.Entre las diferentes contribuciones que esta tesis ha hecho a su estudio, cabe destacar eldesarrollo de un algoritmo basado en una red de neuronas convolucional para seleccionarcon gran eficiencia y precisión las interacciones de neutrinos electrónicos y muónicos enel Deep Underground Neutrino Experiment (DUNE). La eficiencia de selección obtenidapara neutrinos (antineutrinos) electrónicos alcanza un máximo del 90% (94%) y supera el85% (90%) para neutrinos con energías reconstruidas en el rango 2-5 GeV. La selección deneutrinos (antineutrinos) muónicos tiene una eficiencia máxima del 96% (97%) y excedeel 90% (95%) para neutrinos con energías reconstruidas de más de 2 GeV. Considerandocomo señal todas las interacciones de neutrinos y antineutrinos electrónicos (procedentestanto de oscilaciones como intrínsecos en el haz inicial), se logra una pureza en la seleccióndel 90%. Dichas selecciones de eventos son fundamentales para maximizar la sensibilidaddel experimento a los efectos de violació...

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗