Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Missing data problem”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Subspace-Driven Learning for Anomaly Detection in Process Transients

Nuclear power plant (NPP) monitoring and diagnostic centers are actively investigating and implementing automated anomaly detection algorithms to help plants catch anomalies sooner, thereby preventing or reducing the duration of unexpected shutdowns. Current machine learning-based anomaly detection methods are expected to be highly effective during stable, full-power operations because NPPs typically operate as baseload power generators, meaning there are extensive operating data available from plant equipment. However, it is expected that anomaly detection methods will face significant challenges during transient conditions (i.e., when power output falls below full power) because plants only occasionally operate at these lower power levels, generating sparse transient operational data, and resulting in false alarms or missed detections. Here, to address this issue, transfer learning is used, which for this problem leverages knowledge (in the form of learned features) from stable, full-power operations to improve detection accuracy during transient conditions, even with limited data. In this effort, a novel subspace approach is developed to transfer a subset of the data features from full power operation to transients. This approach is validated through experiments using synthetic data and was found to outperform two baseline transfer learning approaches in anomaly detection performance across a range of amounts of transient data used in the training process.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
DOE OSTI2026

Inverse problem in the large momentum effective theory framework

One proposal to compute parton distributions from first principles is the large momentum effective theory (LaMET), which requires the Fourier transform of matrix elements computed nonperturbatively. Lattice quantum chromodynamics (QCD) provides calculations of these matrix elements over a finite range of Fourier harmonics that are often noisy or unreliable in the largest computed harmonics. It has been suggested that enforcing an exponential decay of the missing harmonics helps alleviate this issue. Using nonperturbative data, we show that the uncertainty introduced by this inverse problem in a realistic setup remains significant without very restrictive assumptions, and that the importance of the exact asymptotic behavior is minimal for values of 𝑥 where the framework is currently applicable. We show that the crux of the inverse problem lies in harmonics of the order of 𝜆 = 𝑧⁢𝑃 𝑧 ∼ 5–15, where the signal in the lattice data is often barely existent in current studies, and the asymptotic behavior is not firmly established. We stress the need for more sophisticated techniques to account for this inverse problem, whether in the LaMET or related frameworks like the short-distance factorization. We also address a misconception that, with available lattice methods, the LaMET framework allows a “direct” computation of the 𝑥-dependence, whereas the alternative short-distance factorization only gives access to moments or fits of the 𝑥-dependence.

Dutrieux, Hervé [Aix-Marseille Université, Marseil↗
DOE OSTI2024

Underground hydrogen storage leakage detection and characterization based on machine learning of sparse seismic data

Underground hydrogen storage (UHS) is considered as a scalable approach for massive storage and seasonal extraction of hydrogen (H 2 ). Although conventional leakage detection and characterization methods based on time-lapse seismic imaging and inversion generally apply to H 2 leakage detection problem, a high-fidelity yet cost effective geophysics approach is still missing to reliably inform leakage location and properties based on very sparse data. In response, we develop a novel supervised machine learning method to detect and characterize H 2 leakage from UHS. The input to our neural network are sparse time-lapse seismic waveforms, while the output from the neural network includes the spatial location and physical properties of a H 2 leakage. Here, we generate high-quality time-lapse waveforms using the elastic-wave equations to train the neural network. We train and validate our machine learning model and find that it attains high accuracy in using extremely sparse time-lapse seismic data to detect and characterize H 2 leakage. Our investigation is the first systematic study that focuses on applying machine learning to subsurface H 2 leakage detection and characterization and could potentially serve as a cost-effective geophysical tool for underground hydrogen leakage detection and characterization with high fidelity.

08 HYDROGEN↗
DOE OSTI2024

Short-term Electricity Price Forecasting with Constrained Regressors

The volatility of electricity price presents a challenge to market participants as their decision-making process are highly depend on the accuracy of price forecasts. However, there is growing empirical evidence of increasing price volatility and price spikes in electricity markets as a result of variable renewable energy generation, extreme weather events, and other factors. The distribution shift caused by spikes in electricity price data differentiates the forecasting tasks from other renewable energy sources. Moreover, the observations may be compromised by cyberattacks and thus not available in the testing phase. To this end, we propose a Similarity-Enhanced Electricity Decomposition Forecasting model (SEED-Forecaster) to address the missing response problem and spikes capturing in short-term electricity price forecasting. The effectiveness of the proposed framework is tested on real-world electricity price data from California Independent System Operator (CAISO). Numerical results of case studies show that the proposed SEED-Forecsater can enhance forecasting performance, particularly in capturing electricity spikes, even under conditions without regressors during testing stage.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Glass Refraction Distortion Object Detection via Abstract Features

Glass reflection and refraction lead to missing and distorted object feature data, affecting the accuracy of object detection. In order to solve the above problems, this paper proposed a glass refraction distortion object detection via abstract features. The number of parameters of the algorithm is reduced by introducing skip connections and expansion modules with different expansion rates. The abstract feature information of the object is extracted by binary cross-entropy loss. Meanwhile, the abstract feature distance between the object domain and source domain is reduced by a loss function, which improves the accuracy of object detection under glass interference. To verify the effectiveness of the algorithm in this paper, the GRI dataset is produced and made public on GitHub. The algorithm of this paper is compared with the current state-of-the-art Deep Face, VGG Face, TBE-CNN, DA-GAN, PEN-3D, LMZMPM, and the average detection accuracy of our algorithm is 92.57% at the highest, and the number of parameters is only 5.13 M.

Cai, Lei↗
DOE OSTI2024

TNet: A Model-Constrained Tikhonov Network Approach for Inverse Problems

Deep learning (DL), in particular deep neural networks, by default is purely data-driven and in general does not require physics. This is the strength of DL but also one of its key limitations when applied to science and engineering problems in which underlying physical properties—such as stability, conservation, and positivity—and accuracy are required. DL methods in their original forms are often not capable of respecting the underlying mathematical models or achieving desired accuracy even in big-data regimes. On the other hand, many data-driven science and engineering problems, such as inverse problems, typically have limited experimental or observational data, and DL would overfit the data in this case. Leveraging information encoded in the underlying mathematical models, we argue, not only compensates for missing information in low data regimes but also provides opportunities to equip DL methods with the underlying physics, hence promoting better generalization. This paper develops a model-constrained DL approach and its variant TNet—a Tikhonov neural network—which are capable of learning not only information hidden in the training data but also in the underlying mathematical models to solve inverse problems governed by partial differential equations in low data regimes. We provide the constructions and some theoretical results for the proposed approaches for both linear and nonlinear inverse problems. Since TNet is designed to learn inverse solutions with Tikhonov regularization, it is interpretable: in fact it recovers Tikhonov solutions for linear cases while potentially approximating Tikhonov solutions for nonlinear inverse problems. We also prove that data randomization can enhance not only the smoothness of the networks but also their generalizations. Comprehensive numerical results confirm the theoretical findings and show that with even as little as 1 training data sample for one-dimensional (1D) deconvolution, 5 for an inverse 2D heat conductivity problem, 100 for inverse initial conditions for a time-dependent 2D Burgers’s equation, and 50 for inverse initial conditions for 2D Navier–Stokes equations, TNet solutions can be as accurate as Tikhonov solutions while being several orders of magnitude faster. Furthermore, this is possible owing to the model-constrained term, replications, and randomization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Isomeric yield ratios of fission products: A missing piece in reactor antineutrino summation calculations

The calculation of the spectrum of antineutrinos ($\bar{v}_e$) from a reactor is a complicated problem requiring several nuclear data and physics inputs. Many of these have been investigated thoroughly to improve calculations and properly account for uncertainties. One input which has heretofore escaped consideration is the fission-yield distribution between ground and isomeric states. Here, in this work, we explore the effect of incorporating newly evaluated isomeric yield ratios (IYR) for 43 fission products into summation calculations and identify the disproportionate importance of certain isotopes, particularly at higher energies. Our analysis indicates that updated IYRs contribute to a significant increase in the $\bar{v}_e$ spectrum around and above 7 MeV, with increases of more than 50% at higher energies. Through a detailed sensitivity study, we highlight a number of isotopes for which the IYR has a substantial effect on the $\bar{v}_e$ spectrum. This work stresses the critical role of isomeric yields in calculations of reactor $\bar{v}_e$ spectra and points to the necessity for their accurate experimental determination, especially for key fission products, in order to refine our understanding and address the observed anomalies between measured and calculated $\bar{v}_e$ spectra.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

Isomeric Yield Ratios of fission products: a missing piece in reactor antineutrino summation calculations

The calculation of the spectrum of antineutrinos ( $\overline{V}$ e ) from a reactor is a complicated problem requiring several nuclear data and physics inputs. Many of these have been investigated thoroughly to improve calculations and properly account for uncertainties. One input which has heretofore escaped consideration is the fission yield distribution between ground and isomeric states. In this work, we explore the effect of incorporating newly evaluated isomeric yield ratios (IYR) for 43 fission products into summation calculations and identify the disproportionate importance of certain isotopes, particularly at higher energies. Our analysis indicates that updated IYRs contribute to a significant increase in the $\overline{V}$ e spectrum around and above 7 MeV, with increases of more than 50% at higher energies. Through a detailed sensitivity study, we highlight a number of isotopes for which the IYR has a substantial effect on the $\overline{V}$ e spectrum. This work stresses the critical role of isomeric yields in calculations of reactor $\overline{V}$ e spectra and points to the necessity for their accurate experimental determination, especially for key fission products, in order to refine our understanding and address the observed anomalies between measured and calculated $\overline{V}$ e spectra.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2020

Examining the order-of-limits problem and lattice constant performance of the Tao–Mo functional

In their recent communication a semi-local density functional derived from the density matrix expansion of the exchange hole localised by a general coordinate transformation. We show that the order-of-limits problem present in the functional, dismissed as harmless in the original publication, causes severe errors in predicted phase transition pressures. We also show that the claim that lattice volume prediction accuracy exceeds that of existing similar functionals was based on comparison to reference data that misses anharmonic zero-point expansion and consequently overestimates accuracy. Here, by highlighting these omissions, we give a more accurate assessment of the Tao-Mo functional and show a possible direction for resolving the order-of-limits problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Coordinate-Based Seismic Interpolation in Irregular Land Survey: A Deep Internal Learning Approach

Physical and budget constraints often result in irregular sampling, which complicates accurate subsurface imaging. Preprocessing approaches, such as missing trace or shot interpolation, are typically employed to enhance seismic data in such cases. Recently, deep learning has been used to address the trace interpolation problem at the expense of large amounts of training data to adequately represent typical seismic events. Nonetheless, most research in this area has focused on trace reconstruction, with little attention having been devoted to shot interpolation. Furthermore, existing methods assume regularly spaced receivers/sources failing in approximating seismic data from real (irregular) surveys. This work presents a novel shot gather interpolation approach which uses a continuous coordinate-based representation of the acquired seismic wavefield parameterized by a neural network. The proposed unsupervised approach, which we call coordinate-based seismic interpolation (CoBSI), enables the prediction of specific seismic characteristics in irregular land surveys without using external data during neural network training. Importantly, experimental results on real and synthetic 3-D data validate the ability of the proposed method to estimate continuous smooth seismic events in the time-space and frequency-wavenumber domains, improving sparsity or low-rank-based interpolation methods.

58 GEOSCIENCES↗
DOE OSTI2020

Reversible structural transformations in supercooled liquid water from 135 to 245 K

Water has many anomalous properties compared to “simple” liquids, and these anomalies are typically enhanced in supercooled water.1-3 While numerous models have been proposed, including the liquid-liquid critical point,4,5 the singularity-free scenario,6 and the stability limit conjecture,1 a molecular-level understanding remains elusive. The main difficulty in determining which, if any, of these models is correct is the limited amount of data in the relevant temperature and pressure ranges. For water at ambient pressures, which is the focus of this work, data is largely missing from 160 – 232 K (“No Man’s Land”) due to rapid crystallization.2,3 Whether rapid crystallization is just an experimental obstacle, or a fundamental problem signaling the inability of water to thermally equilibrate prior to crystallization is also a major unanswered question.5,7 Here, we investigate the structural transformations of transiently-heated, supercooled water with nanosecond time resolution using infrared vibrational spectroscopy. The experiments demonstrate three key results. First, water’s structure relaxes from its initial configuration to a “steady-state” configuration prior to the onset of crystallization over a wide temperature range. Second, water’s steady-state structure can be reproduced by a linear combination of two, temperature-independent structures that correspond to a “high-temperature liquid” and a “low-temperature liquid.” Third, the observed structural changes are reversible over the full temperature range. Taken together, these results show that supercooled water can equilibrate prior to crystallization for temperatures from the homogeneous nucleation temperature, TH ~232 K,3 down to the glass transition temperature (Tg ~ 136 K). Second, the results provide support for the hypothesis that supercooled water can be described as a mixture of two, structurally-distinct, interconvertible liquids from 135 K to 245 K.5,8-18

Kringle, Loni M.↗
DOE OSTI2022

Industry Level Feasibility of LiDAR Data into Fire Modeling Using Fire Risk Investigation in 3D (FRI3D)

Many evaluation, assessment, and modeling tasks at nuclear power plants require spatial information this often requires physical visits to locations within the facility because the 2D or 3D schematics and current models do not contain enough detail or do not capture as-built and real-world conditions. These visits require extensive manual labor for not only the requesting party, but support groups such as security. LIDAR mapping is trying to solve that problem by providing very detailed 3D models for low costs. However, the use of these models can be very limited because either component reference information is missing and too costly to add, or there is no way to extract specific spatial data needed for other tools. This report presents Idaho National Lab's work with Environmental Intellect (Ei) covering two main efforts. First, to reduce the effort of "tagging" data in large 3D models. By using both existing plant database information, and artificial intelligence (AI) to find and read equipment labels. This research explores the ability of to provide a simple way for the user to tag items and verify plant data, capturing both the speed of AI and human verification. The second part of the work is the development of an interface for importing pieces needed for Modeling & Simulation. Analysis work such as that for fire, flood, or physical security all require spatial or 3D models in various levels of detail. This interface will allow for the retrieval of item location or boundaries, enabling the auto generation of models for varying tools. The application program interface (API) of the fire risk investigation in 3D (FRI3D) was used to test feasibility of exporting the LiDAR tagged spatial information. Outcomes from this work provide preliminary data to determine if the tools and methods could provide substantial industry benefit if fully matured.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Towards AI Based Data Classification for Decision Making During Testing

During the development of high-consequence items, test systems should be capable of differentiating between test failures resulting from narrowly missing requirements versus those indicating potentially catastrophic faults. In many instances, classifying the data corresponds to simply identifying whether measured waveforms have approximately the anticipated shape. Cast in this light, the problem reduces to converting raw data into a form optimal for use with neural network classifiers. This manuscript investigates different means of representing raw data for image classification. Raw data plots and Short Time Fourier Transform (STFT) spectrograms are classified by both custom built, small-scale, Convolution Neural Networks (CNN) and open-source, multi-million parameter, pre-trained deep CNNs. In the case of time varying frequency content, the STFTs provide images with greater detail and can be accurately classified with simpler networks. This requires less memory and runs faster than classifying the raw data using the more sophisticated options—making STFTs optimal for applications with memory constraints. STFTs are not a panacea. In some cases the time-domain signal contains useful information that should not be discarded. Rather than using raw data or STFTs, the images can be constructed from both by using red and green channels of an RGB image to visualize the real and imaginary components of the transform, with the raw data occupying the blue channel.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

ORNL Neutron Cross Section Measurements of 90 Zr

Nuclear criticality modeling and simulations rely on the quality of the existing evaluated nuclear data libraries such as Evaluated Nuclear Data File (ENDF)/B, the Joint Evaluated Fission and Fusion (JEFF) nuclear data library, or the Japanese Evaluated Nuclear Data Library (JENDL). In some cases, the cross-section evaluations of those libraries were found to be deficient in describing criticality benchmarks accurately. More than two decades ago, the US Nuclear Criticality Safety Program (NCSP) established a Nuclear Data (ND) task which encompassed experiments and evaluations. In response to this, the Oak Ridge National Laboratory (ORNL) formed a Nuclear Criticality and Data group which performed ND experiments, data analysis, and evaluations to produce ENDF files for the ND libraries as identified in the NCSP Five-Year Plan. Before being submitted to the ENDF library, files were processed and tested for performance by running benchmark calculations. This procedure was centralized in the ORNL group and is now often referred to as the ND pipeline. NCSP collaborates with the Joint Research Center (JRC) of the European Commission in Geel, Belgium, to perform high-resolution neutron-induced cross section measurements at the Geel Linear Accelerator (GELINA). The objective is to address emerging ND problems in criticality calculations. Difficulties with ND include insufficient neutron energy range, missing covariances, and previously unrecognized inaccuracies with experiments. New neutron total and capture cross sections of 90 Zr in the neutron energy range from 100 eV to several hundred keV were recently performed. These measured data will be used, together with existing high-resolution transmission data from a metallic 90 Zr sample, to improve representation of the cross sections.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elements

Multiphysics problems that are characterized by complex interactions among fluid dynamics, heat transfer, structural mechanics, and electromagnetics, are inherently challenging due to their coupled nature. While experimental data on certain state variables may be available, integrating these data with numerical solvers remains a significant challenge. Physics-informed neural networks (PINNs) have shown promising results in various engineering disciplines, particularly in handling noisy data and solving inverse problems in partial differential equations (PDEs). However, their effectiveness in forecasting nonlinear phenomena in multiphysics regimes, particularly involving turbulence, is yet to be fully established. Here, this study introduces NeuroSEM, a hybrid framework integrating PINNs with the highfidelity Spectral Element Method (SEM) solver, Nektar++. NeuroSEM leverages the strengths of both PINNs and SEM, providing robust solutions for multiphysics problems. PINNs are trained to assimilate data and model physical phenomena in specific subdomains, which are then integrated into the Nektar++ solver. We demonstrate the efficiency and accuracy of NeuroSEM for thermal convection in cavity flow and flow past a cylinder. The framework effectively handles data assimilation by addressing those subdomains and state variables where the data is available. We applied NeuroSEM to the Rayleigh-B´enard convection system, including cases with missing thermal boundary conditions and noisy datasets. Finally, we applied the proposed NeuroSEM framework to real particle image velocimetry (PIV) data to capture flow patterns characterized by horseshoe vortical structures. Our results indicate that NeuroSEM accurately models the physical phenomena and assimilates the data within the specified subdomains. The framework’s plug-and-play nature facilitates its extension to other multiphysics or multiscale problems. Furthermore, NeuroSEM is optimized for efficient execution on emerging integrated GPU-CPU architectures. This hybrid approach enhances the accuracy and efficiency of simulations, making it a powerful tool for tackling complex engineering challenges in various scientific domains.

42 ENGINEERING↗
DOE OSTI2021

Verification and Validation Tests of Gamma Library of MC2-3 for Coupled Neutron and Gamma Heating Calculation

For the accurate assessment of the heat generation rate in fast reactors, the gamma library of MC2 -3 and the MC2 -3 + GAMSOR procedure employing the coupled neutron and gamma heating calculation has been thoroughly verified against Monte Carlo results and validated using the ZPPR-15D gamma dose measurement data. NJOY outputs are post-processed in a consistent way with the NJOY procedure to avoid any missing data or double counting of data. Prompt heating for 379 out of 391 isotopes in the gamma library was verified against MCNP6.2 to within 1% relative error in total heating for most isotopes. For both a simple one-dimensional slab problem representing a sodium cooled fast reactor and the Experimental Breeder Reactor II (EBR-II) benchmark problem, the root-mean-square values of assembly power error were less than 0.5% for fuel assemblies, ~1% in blankets and ~1 to ~3% in reflectors compared to MCNP6.2 results. The most plausible cause for the 3% error in a reflector assembly is believed to be the error in the multigroup neutron cross sections for the reflector assembly. For validation, gamma doses measured with thermoluminiscent dosimeters (TLDs) in the ZPPR-15D experiment were calculated using GAMSOR. Due to the uncertainty in the TLD measurement with regards to the energy deposition of photons and neutrons, the validation data leads to a 12.7% uncertainty on the experimental measurement. With this uncertainty bound, the calculated doses all fell within one standard deviation of the measured value. Combined with the accurate calculation of reaction rate distributions and neutron spectrum measurements, these results indicate good agreement for the neutron and gamma heating calculations that were performed.

coupled neutron and gamma heating↗
DOE OSTI2021

Investigating Application of LiDAR for Nuclear Power Plants

Many evaluation, assessment, and modeling tasks at nuclear power plants require spatial in-formation; this often requires physical visits to locations within the facility because the 2D or 3D schematics and current models do not contain enough detail or do not capture as-built and real-world conditions. These visits require extensive manual labor for not only the requesting party, but also support groups, such as security. Light Detection and Ranging (LiDAR) mapping is trying to solve that problem by providing very detailed 3D models for low costs. However, the use of these models can be very limited because either component reference information is missing and too costly to add or there is no way to extract specific spatial data needed for other tools. This report outlines two main efforts. First, to reduce the effort of “Tagging” data in large 3D models, a general Application Programming Interface (API) was developed to import a variety of existing plant database information into a 3D-visualization engine. Filters allow the user to have only zone-specific items listed; then, they can simply click and assign the information to a specific spot or component in the 3D model. The second part of the work is the development of an interface for importing pieces from the3D-LiDAR model into other systems needed for modeling and simulation, outlined around fire modeling. This interface allows for the retrieval of item location and boundaries, enabling the auto generation of models for varying tools.

3D Modelling↗