Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Training Time”

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 1,549 records · Page 86
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Improved Tomographic Binning of 3 × 2 pt Lens Samples: Neural Network Classifiers and Optimal Bin Assignments

Abstract Large imaging surveys, such as the Legacy Survey of Space and Time, rely on photometric redshifts and tomographic binning for 3 × 2 pt analyses that combine galaxy clustering and weak lensing. In this paper, we propose a method for optimizing the tomographic binning choice for the lens sample of galaxies. We divide the CosmoDC2 and Buzzard simulated galaxy catalogs into a training set and an application set, where the training set is nonrepresentative in a realistic way, and then estimate photometric redshifts for the application sets. The galaxies are sorted into redshift bins covering equal intervals of redshift or comoving distance, or with an equal number of galaxies in each bin, and we consider a generalized extension of these approaches. We find that bins of equal comoving distance produce the highest dark energy figure of merit of the initial binning choices, but that the choice of bin edges can be further optimized. We then train a neural network classifier to identify galaxies that are either highly likely to have accurate photometric redshift estimates or highly likely to be sorted into the correct redshift bin. The neural network classifier is used to remove poor redshift estimates from the sample, and the results are compared to the case when none of the sample is removed. We find that the neural network classifiers are able to improve the figure of merit by ∼13% and are able to recover ∼25% of the loss in the figure of merit that occurs when a nonrepresentative training sample is used.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Automated Detection of Qubit Structures on Quantum Chips

In this study, YOLO (You Only Look Once), a well-known object detection and image segmentation model, is used to detect qubits on a quantum chip. The model is trained by exposing it to various images of objects of interest and by tweaking various training parameters to allow the model to learn from a limited and highly specialized dataset of SEM imagery. The model was provided with numerous images of qubits and various prominent features of note located on a qubit. These detections were then integrated into a simple GUI, allowing for real-time feedback alongside SEM usage. This will allow us to create various functions enabling automated functions like chip-wide scanning, auto-focusing, and image correction.

Perjuste, Ruth [Wellesley Coll.]↗
DOE OSTI2026

Enhanced Ionization Charge Identification in the Short-Baseline Neutrino Program Neutrino Detectors with Deep Neural Networks

We present a deep neural net-based region of interest detection method (DNN ROI) for signal processing in the liquid argon time projection chambers of the Short-Baseline Neutrino (SBN) Program, SBND and ICARUS. DNN ROI addresses limitations of the traditional wire-by-wire thresholding algorithm by leveraging the full two-dimensional detector readout and cross-plane matching information. To account for detector performance variations, we explore training with augmented samples. We find that DNN ROI outperforms the traditional method in both low-level ROI identification performance and high-level reconstruction metrics for high-energy cosmic and accelerator neutrino interaction products, while also being more robust against detector variations, with or without sample augmentation.

Abratenko, P. [Tufts U.]↗
DOE OSTI2024

Real Time-Optimal Power Flow-Based Distributed Energy Resource Management System (DERMS)

This project aims to promote lab-proven clean energy technology to commercially scalable versions of the technology, integrate the technology with broader systems, provide extended performance data, and validate the manufacturability and reliability of the technology. The lab-proven technology, RT-OPF DERMS, was developed and validated through previous U.S. Department of Energy-funded efforts, including Advanced Research Projects Agency-Energy funding under the Network Optimized Distributed Energy Systems program and Holy-Cross Energy High Impact Project. In the Advanced Research Projects Agency-Energy Network Optimized Distributed Energy Systems project, the RT-OPF DERMS was developed and implemented in multiple hardware platforms, demonstrating its performance and capabilities in the lab and field environments. The technology was also evaluated and matured via a participation in the U.S. Department of Energy I-Corps program, whose goal is to pair teams of researchers with industry mentors for an intensive 2-month training in which the researchers define technology value propositions, conduct customer discovery interviews, and develop viable market pathways for their technologies. These activities indicate the high technology maturity and Technology Readiness Level of the RT-OPF DERMS.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

A neural-network-enhanced parameter-varying framework for multi-objective model predictive control applied to buildings

Management of the electrical grid is becoming more complex due to the increased penetration of alternative energy generation technologies and a broadening diversity of electric loads. This complexity creates challenges in balancing demand and generation that can increase the potential for grid instabilities. One effective way to address this issue is to leverage previously unexploited demand flexibility through advanced control strategies. In this work, we propose an advanced control method, called adaptive neural parameter-varying model predictive control (ANPV-MPC), to control the temperature and energy consumption of a building via its Heating, Ventilation, and Air Conditioning system. ANPV-MPC combines key ideas in parameter-varying control, adaptive control, and online learning strategies to bridge the gap between computationally efficient linear model predictive control and more accurate nonlinear model predictive control. The novelty in ANPV-MPC is the use of a physics-inspired Bayesian neural network to estimate the coefficients of the parameter-varying linear control model. The Bayesian neural network additionally provides uncertainty estimates, triggering online training to capture evolving building system conditions. We show that ANPV-MPC can approximate the building system dynamics with a 28.39% higher accuracy than traditional linear model predictive control, resulting in 36.23% better control performance without increasing complexity of the optimal control problem. ANPV-MPC also adapts in real time to previously unseen conditions using online learning, further improving its performance.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

An investigation on machine learning predictive accuracy improvement and uncertainty reduction using VAE-based data augmentation

The confluence of ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and the availability of large datasets place multiple engineering fields at the threshold of dramatic progress. However, a unique challenge in nuclear engineering is data scarcity because experimentation on nuclear systems is usually more expensive and time-consuming than most other disciplines. One potential way to resolve the data scarcity issue is deep generative learning, which uses certain ML models to learn the underlying distribution of existing data and generate synthetic samples that resemble the real data. In this way, one can significantly expand the dataset to train more accurate predictive ML models. In this study, our objective is to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. We investigated whether the data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, the DNN prediction uncertainties are quantified using Bayesian Neural Networks (BNN) and conformal prediction (CP) to assess the impact on predictive uncertainty reduction. To test the proposed methodology, we used TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. Here, we found that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved the prediction confidence intervals, and reduced the prediction uncertainties.

Bayesian neural network↗
DOE OSTI2024

Uncertainty-aware particle segmentation for electron microscopy at varied length scales

Electron microscopy is indispensable for examining the morphology and composition of solid materials at the sub-micron scale. To study the powder samples that are widely used in materials development, scanning electron microscopes (SEMs) are increasingly used at the laboratory scale to generate large datasets with hundreds of images. Parsing these images to identify distinct particles and determine their morphology requires careful analysis, and automating this process remains challenging. In this work, we enhance the Mask R-CNN architecture to develop a method for automated segmentation of particles in SEM images. We address several challenges inherent to measurements, such as image blur and particle agglomeration. Moreover, our method accounts for prediction uncertainty when such issues prevent accurate segmentation of a particle. Recognizing that disparate length scales are often present in large datasets, we use this framework to create two models that are separately trained to handle images obtained at low or high magnification. By testing these models on a variety of inorganic samples, our approach to particle segmentation surpasses an established automated segmentation method and yields comparable results to the predictions of three domain experts, revealing comparable accuracy while requiring a fraction of the time. These findings highlight the potential of deep learning in advancing autonomous workflows for materials characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Monte Carlo Event Generation with Continuous Normalizing Flows

We apply continuous normalizing flows trained with the flow matching method to the problem of phase-space sampling in Monte Carlo event generation for high-energy collider physics. Focusing on lepton-pair and top-quark pair production with multiple jets, the two computationally most expensive processes at the Large Hadron Collider, we train helicity-conditioned continuous normalizing flows to remap the random numbers used in matrix element evaluation. Compared to standard methods, we achieve unweighting efficiency improvements by factors of up to 184 and 25 for the two processes at their respective highest jet number, at the cost of an increased evaluation time. When combining the advantages of continuous normalizing flows with the fast evaluation times of coupling-layer-based flows, using the RegFlow approach, we find parton-level unweighted event generation walltime gains of about a factor of 10 at the highest jet numbers. These substantial gains highlight the promise of samplers based on machine learning for next-generation collider experiments.

Bothmann, Enrico [CERN; Gottingen U.] (ORCID:00000↗
DOE OSTI2026

PowerMappeR: Power-Optimized Mapping of SNNs onto ReRAM Crossbars coupled via Packet-Switched NoCs

Many recent efforts in developing hardware-accelerated spiking neural networks (SNNs) are characterized by deep co-design between algorithms, architectures, and devices. Architectural advances overcome device constraints by coupling together many small resistive-RAM (ReRAM) crossbars via a network-on-chip (NoC) for neuromorphic component operation. Concurrently, improved SNN training methods increase accuracy and structural sparsity in networks despite growing problem sizes. Finally, compilers leverage these attributes to minimize area and inter-crossbar communication while mapping large SNNs to sophisticated architectures. However, for compiler-driven co-design to realize increasingly complex and profitable optimizations, a compile-time view of power consumption is critical. We present PowerMappeR to express and optimize over mapping-, architecture-, and device-specific power consumption information. By modeling the dynamic power of well-established components, we develop an integer linear programming (ILP)-based, encoding-agnostic, parametric power estimation model. Using this model, we demonstrate practical improvements in area and inter-crossbar communication by 0%–9.5% and 1.4%–5.1%, respectively. We also limit hotspot formation during optimization, achieving comparable or better results in targeted metrics with up to 96.4%–97.1% restriction of hotspot magnitude. Finally, we introduce profile-guided formulations to reduce worst-case and expected-case hotspot magnitude by 40.7%–69.5% and 40.6%–56.3%, respectively. Optimizing worst-case hotspot magnitude incidentally improves expected-case magnitude by 10.85%–33.45%. Reciprocally, optimizing expected-case magnitude incidentally improves worst-case magnitude by 4.33%–39.87%. Validation against hardware simulators confirms that PowerMappeR can decrease dynamic power consumption by 12.6%–27.3%.

Pohl, Devin [ORNL] (ORCID:0009000040149027)↗
DOE OSTI2025

Sparse measurement medical CT reconstruction using multi-fused block matching denoising priors

A major challenge for medical X-ray CT imaging is reducing the number of X-ray projections to lower radiation dosage and reduce scan times without compromising image quality. However these under-determined inverse imaging problems rely on the formulation of an expressive prior model to constrain the solution space while remaining computationally tractable. Traditional analytical reconstruction methods like Filtered Back Projection (FBP) often fail with sparse measurements, producing artifacts due to their reliance on the Shannon-Nyquist Sampling Theorem. Consensus Equilibrium, which is a generalization of Plug and Play, is a recent advancement in Model-Based Iterative Reconstruction (MBIR), has facilitated the use of multiple denoisers are prior models in an optimization free framework to capture complex, non-linear prior information. However, 3D prior modelling in a Plug and Play approach for volumetric image reconstruction requires long processing time due to high computing requirement. Instead of directly using a 3D prior, this work proposes a BM3D Multi Slice Fusion (BM3D-MSF) prior that uses multiple 2D image denoisers fused to act as a fully 3D prior model in Plug and Play reconstruction approach. Our approach does not require training and are thus able to circumvent ethical issues related with patient training data and are readily deployable in varying noise and measurement sparsity levels. In addition, reconstruction with the BM3D-MSF prior achieves similar reconstruction image quality as fully 3D image priors, but with significantly reduced computational complexity. We test our method on clinical CT data and demonstrate that our approach improves reconstructed image quality.

Hossain, Maliha [ORNL]↗
DOE OSTI2025

A Linear-Complexity Tensor Butterfly Algorithm for Compressing High-Dimensional Oscillatory Integral Operators

This paper presents a multilevel tensor compression algorithm called tensor butterfly algorithm for efficiently representing large-scale and high-dimensional oscillatory integral operators, including Green's functions for wave equations and integral transforms such as Radon transforms and Fourier transforms. The proposed algorithm leverages a tensor extension of the so-called complementary low-rank property of existing matrix butterfly algorithms. The algorithm partitions the discretized integral operator tensor into subtensors of multiple levels and factorizes each subtensor at the middle level as a Tucker-type interpolative decomposition, whose factor matrices are formed in a multilevel fashion. For a d-dimensional (d > 1) integral operator discretized into a 2d-mode tensor with n2d entries, the overall CPU time and memory requirement scale as O(nd), in stark contrast to the O(nd log n) complexity of existing matrix algorithms such as matrix butterfly algorithms and fast Fourier transforms (FFTs), where n is the number of points per direction. When comparing with other tensor algorithms such as quantized tensor train (QTT), the proposed algorithm also shows superior CPU and memory performance for tensor contraction. Remarkably, the tensor butterfly algorithm can efficiently model high-frequency Green's function interactions between two unit cubes, each spanning 512 wavelengths per direction, which represents problems of scale over 512× larger than that existing butterfly algorithms can handle, with the same amount of computation resources. On the other hand, for a problem representing 64 wavelengths per direction, which is the largest size existing algebraic matrix algorithms can handle, our tensor butterfly algorithm exhibits 200x speedups and 30× memory reduction compared with existing ones. Moreover, the tensor butterfly algorithm also permits O(nd)-complexity FFTs and Radon transforms up to d = 6 dimensions.

Kielstra, P Michael↗
DOE OSTI2022

SolarAPP+ Pilot Analysis: Performance and Impact of Instant, Online Solar Permitting

The National Renewable Energy Laboratory (NREL) led a collaborative effort to develop the Solar Automated Permit Processing Plus (SolarAPP+), a no-cost solar permitting software solution to address residential solar photovoltaic (PV) permitting resource constraints and streamline solar adoption processes among authorities having jurisdiction (AHJs). The SolarAPP+ is an online portal that automates permit plan review, enabling an instant permit approval process for code-compliant residential PV systems. Based on national model building, electrical, and fire codes, the SolarAPP+ automatically performs a compliance check of permit inputs against code requirements and produces an inspection checklist that can be used to verify installation practices, workmanship, and adherence to the approved design. NREL conducted a two-phase pilot with five participating AHJs and 16 solar contractors, spanning from November 2020 through December 2021, evaluating the ability of SolarAPP+ to deliver instant permits and its impact on four critical areas within each AHJ: permit review timelines; solar adoption timelines; AHJ time saved; and inspection results. The pilot confirmed that SolarAPP+ reduced permit review times to less than one day, reduced solar adoption timelines by an average of 12 days, saved an estimated 2,067 staff hours, and had comparable inspection results to those found in traditional permitting. The pilot further identified key lessons for improving SolarAPP+, including ways to streamline SolarAPP+ adoption, development of training resources, and expansion of supported products.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Data Science and Machine Learning for Genome Security

This report describes research conducted to use data science and machine learning methods to distinguish targeted genome editing versus natural mutation and sequencer machine noise. Genome editing capabilities have been around for more than 20 years, and the efficiencies of these techniques has improved dramatically in the last 5+ years, notably with the rise of CRISPR-Cas technology. Whether or not a specific genome has been the target of an edit is concern for U.S. national security. The research detailed in this report provides first steps to address this concern. A large amount of data is necessary in our research, thus we invested considerable time collecting and processing it. We use an ensemble of decision tree and deep neural network machine learning methods as well as anomaly detection to detect genome edits given either whole exome or genome DNA reads. The edit detection results we obtained with our algorithms tested against samples held out during training of our methods are significantly better than random guessing, achieving high F1 and recall scores as well as with precision overall.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

NSA Site Science: Use of ARM Observations from Northern Alaska to Evaluate and Improve Prediction Capabilities

The Arctic is warming at a rate nearly double that of the rest of the planet, leading to profound changes in atmospheric, oceanic, and ice processes. The U.S. Department of Energy's (DOE) Atmospheric Radiation Measurement (ARM) user facility has played a significant role in Arctic research, operating observatories in Alaska's North Slope for over 25 years. These observatories provide a rich, and wide-reaching dataset that offers insight into atmospheric processes in northern Alaska. This report details the results of a nine-year research project (2015–2024) supported by the DOE Atmospheric Systems Research (ASR) program, that leverages data from ARM’s deployment of observing facilities at Utqiaġvik (known as the North Slope of Alaska, or NSA, site) and Oliktok Point, Alaska. The project was conducted in two phases: - Phase 1 (2015–2019): Focused on understanding key atmospheric processes at Oliktok Point, including cloud formation, high-latitude precipitation, aerosol-cloud interactions, and cloud properties. - Phase 2 (2019–2024): Extended the research to the broader North Slope region, using data from both Oliktok Point and Utqiaġvik. Topics explored included surface energy budgets, atmospheric stability, ice nucleation processes, and microphysics in Arctic clouds. The project resulted in numerous research products, including 50 peer-reviewed publications and dissertations, 169 presentations, and 10 data products. These products cover a variety of topics, including: - Cloud Macro- and Microphysical Properties: Arctic clouds play a crucial role in energy transfer, and accurate representation in models is critical. The study explored cloud transitions, ice crystal shapes, and dual-wavelength radar data to understand ice crystal habits and size distributions. - Aerosol Properties and Processes: The team examined aerosol sources in the Arctic, including industrial emissions and natural sources. Observations showed significant spatial gradients in aerosol concentrations due to human activities and wildfire smoke. The influence of aerosols on cloud formation and the surface energy budget was also assessed. - Aerosol-Cloud Interactions: Research revealed that aerosols might suppress cloud ice production, affecting cloud radiative forcing and precipitation. The impact of local industrial emissions on cloud properties was also investigated. - Contextualizing the North Slope of Alaska in the context of the broader Arctic: To understand broader trends, the project evaluated large-scale circulation patterns and the influence of weather systems on the Arctic. Studies indicated that large-scale processes play a significant role in temperature patterns and the timing of snowmelt. - Advancing ARM Observational and Modeling Capabilities: The project developed new radar data products and advanced measurement techniques, including clutter mitigation and drizzle detection. Uncrewed aerial systems (UAS) and tethered balloon systems (TBS) were deployed to gather detailed atmospheric data. Additionally, the project supported 10 early career scientists, providing training and mentorship to undergraduate interns, graduate students, postdoctoral researchers, and early career researchers. These efforts contributed to the advancement of ARM research capabilities and fostered a new generation of scientists skilled in Arctic atmospheric research. Ultimately, this ASR-supported project has provided valuable insights into Arctic atmospheric processes and their broader climate implications. Recommendations for future work include continuing support for long-term observing at Arctic locations to foster additional research, further exploration of aerosol-cloud interactions and the potential impacts of enhanced industrialization of the Arctic, and expanded use of uncrewed systems to gather data in this remote and harsh environment. Additionally, the data products developed by this work, and the data products developed through the ARM infrastructure, leave a treasure-trove of additional information that should be explored for many years to come to gain additional insight into physical processes in the Arctic atmosphere that drive the rapid changes occurring in at high latitudes and their global impact.

58 GEOSCIENCES↗
DOE OSTI2021

Mining and Validating Social Media Data for COVID-19–Related Human Behaviors Between January and July 2020: Infodemiology Study

Background: Health authorities can minimize the impact of an emergent infectious disease outbreak through effective and timely risk communication, which can build trust and adherence to subsequent behavioral messaging. Monitoring the psychological impacts of an outbreak, as well as public adherence to such messaging, is also important for minimizing long-term effects of an outbreak. Objective: We used social media data from Twitter to identify human behaviors relevant to COVID-19 transmission, as well as the perceived impacts of COVID-19 on individuals, as a first step toward real-time monitoring of public perceptions to inform public health communications. Methods: We developed a coding schema for 6 categories and 11 subcategories, which included both a wide number of behaviors as well codes focused on the impacts of the pandemic (eg, economic and mental health impacts). We used this to develop training data and develop supervised learning classifiers for classes with sufficient labels. Classifiers that performed adequately were applied to our remaining corpus, and temporal and geospatial trends were assessed. We compared the classified patterns to ground truth mobility data and actual COVID-19 confirmed cases to assess the signal achieved here. Results: We applied our labeling schema to approximately 7200 tweets. The worst-performing classifiers had F1 scores of only 0.18 to 0.28 when trying to identify tweets about monitoring symptoms and testing. Classifiers about social distancing, however, were much stronger, with F1 scores of 0.64 to 0.66. We applied the social distancing classifiers to over 228 million tweets. We showed temporal patterns consistent with real-world events, and we showed correlations of up to –0.5 between social distancing signals on Twitter and ground truth mobility throughout the United States. Conclusions: Behaviors discussed on Twitter are exceptionally varied. Twitter can provide useful information for parameterizing models that incorporate human behavior, as well as for informing public health communication strategies by describing awareness of and compliance with suggested behaviors.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Assessing shellfish water exposure to fecal bacteria pollution in Salish Sea: three-dimensional modeling and implications for monitoring

Fecal bacteria (FB) contamination poses significant risks to shellfish safety and management in coastal and estuarine waters. Despite extensive pollution identification and correction efforts, FB contamination in shellfish-growing areas persists in the Salish Sea, highlighting the need to identify overlooked sources and better understand FB transport from riverine and shoreline inputs to shellfish beds. To address this, a high-resolution three-dimensional hydrodynamic model coupled with FB kinetics was developed and applied to a case study site in Salish Sea—Portage Bay—to simulate freshwater plume circulation, flushing dynamics, and bacterial transport. Daily FB loading from the major freshwater inflow—Nooksack River was generated by both linear interpolation and integrating a machine learning approach (XGBoost), trained on historical hydrological and meteorological data. The model successfully reproduced both the magnitude and seasonal variation of FB concentrations in Portage Bay for the year of 2021, demonstrating that simplified FB kinetics with first-order decay due to mortality was effective in this dynamic coastal environment with short flushing time. Model results identified the Nooksack River as the dominant far-field FB source, while scenario simulations showed that near-field coastal stormwater outfalls elevated local FB levels following rainfall, particularly under low-flow conditions. The XGBoost prediction provided comparable or superior accuracy to linear interpolation, particularly during periods of missing observational data, by capturing short-term variability and event-driven loading more effectively. Integrating data-driven riverine FB inputs with mechanistic coastal numerical modeling provides a robust framework for operational forecasting of shellfish bed exposure risk and supports adaptive monitoring and management of shellfish growing areas in the Salish Sea and similar coastal systems.

Salish Sea↗
DOE OSTI2021

Practical CO2—WAG Field Operational Designs Using Hybrid Numerical-Machine-Learning Approaches

Machine-learning technologies have exhibited robust competences in solving many petroleum engineering problems. The accurate predictivity and fast computational speed enable a large volume of time-consuming engineering processes such as history-matching and field development optimization. The Southwest Regional Partnership on Carbon Sequestration (SWP) project desires rigorous history-matching and multi-objective optimization processes, which fits the superiorities of the machine-learning approaches. Although the machine-learning proxy models are trained and validated before imposing to solve practical problems, the error margin would essentially introduce uncertainties to the results. In this paper, a hybrid numerical machine-learning workflow solving various optimization problems is presented. By coupling the expert machine-learning proxies with a global optimizer, the workflow successfully solves the history-matching and CO2 water alternative gas (WAG) design problem with low computational overheads. The history-matching work considers the heterogeneities of multiphase relative characteristics, and the CO2-WAG injection design takes multiple techno-economic objective functions into accounts. This work trained an expert response surface, a support vector machine, and a multi-layer neural network as proxy models to effectively learn the high-dimensional nonlinear data structure. The proposed workflow suggests revisiting the high-fidelity numerical simulator for validation purposes. The experience gained from this work would provide valuable guiding insights to similar CO2 enhanced oil recovery (EOR) projects.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Sensitivity Study of Mini-Batch Size on a Long Short-Term Memory Network for In-situ Sensing of Core-to-shell Ratio of Microencapsulated Phase Change Materials

Microencapsulated phase change materials are being studied for applications for thermal energy storage in concentrated solar fields. During fabrication, the thickness of the encapsulation cannot be readily measured for real-time control. Therefore, a machine learning network, specifically a Long Short-Term Memory network, is being developed to estimate the ratio of the shell radius to core radius based on a one second temperature history. The mini-batch size determines how often the algorithm weights are updated during network training, and shuffle indicates whether the training data is shuffled during training. A general factorial design is used to analyze the effects of varying mini-batch size and shuffle, along with the core-to-shell ratio, on the RMSE of the response from the Long Short-Term Memory network. It was found that the network performed better for smaller core to shell ratios (less than 0.6) and had the lowest RMSE when the minibatch size was 128. The minimum RMSE found was 0.00501.

Shannon, Rebecca↗