SEARCH · Engineering Papers

Results for “Model error”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,279 records · Page 71

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2023

Improved Fermion Hamiltonians for Quantum Simulation

We developed a Hamiltonian inspired by ASQTAD and highly improved staggered quark (HISQ) actions and show how these Hamiltonians can be used for quantum simulations. Gate costs for the time evolution of these improved Hamiltonians are provided as well as a demonstration of the reduction of lattice spacing errors using the 1+1d lattice Schwinger model.

Gustafson, Erik↗

DOE OSTI2020

An Optimal Power Control Strategy for Grid-Following Inverters in a Synchronous Frame

This work proposes a power control strategy based on the linear quadratic regulator with optimal reference tracking (LQR-ORT) for a three-phase inverter-based generator (IBG) using an LCL filter. The use of an LQR-ORT controller increases robustness margins and reduces the quadratic value of the power error and control inputs during transient response. A model in a synchronous reference frame that integrates power sharing and voltage–current (V–I) dynamics is also proposed. This model allows for analyzing closed-loop eigenvalue location and robustness margins. The proposed controller was compared against a classical droop approach using proportional-resonant controllers for the inner loops. Mathematical analysis and hardware-in-the-loop (HIL) experiments under variations in the LCL filter components demonstrate fulfillment of robustness and performance bounds of the LQR-ORT controller. Experimental results demonstrate accuracy of the proposed model and the effectiveness of the LQR-ORT controller in improving transient response, robustness, and power decoupling.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

From Quantum Codes to Gravity: A Journey of Gravitizing Quantum Mechanics

In this note, I review a recent approach to quantum gravity that “gravitizes” quantum mechanics by emerging geometry and gravity from complex quantum states. Drawing further insights from tensor network toy models in AdS/CFT, I propose that approximate quantum error correction codes, when re-adapted into the aforementioned framework, also have promise in emerging gravity in near-flat geometries.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2023

Polarimetric Geometric Modeling for mm-VLBI Observations of Black Holes

The Event Horizon Telescope (EHT) is a millimeter very long baseline interferometry (VLBI) array that has imaged the apparent shadows of the supermassive black holes M87* and Sagittarius A*. Polarimetric data from these observations contain a wealth of information on the black hole and accretion flow properties. In this work, we develop polarimetric geometric modeling methods for mm-VLBI data, focusing on approaches that fit data products with differing degrees of invariance to broad classes of calibration errors. We establish a fitting procedure using a polarimetric “m-ring” model to approximate the image structure near a black hole. By fitting this model to synthetic EHT data from general relativistic magnetohydrodynamic models, we show that the linear and circular polarization structure can be successfully approximated with relatively few model parameters. We then fit this model to EHT observations of M87* taken in 2017. In total intensity and linear polarization, the m-ring fits are consistent with previous results from imaging methods. In circular polarization, the m-ring fits indicate the presence of event-horizon-scale circular polarization structure, with a persistent dipolar asymmetry and orientation across several days. The same structure was recovered independently of observing band, used data products, and model assumptions. Despite this broad agreement, imaging methods do not produce similarly consistent results. Our circular polarization results, which imposed additional assumptions on the source structure, should thus be interpreted with some caution. Polarimetric geometric modeling provides a useful and powerful method to constrain the properties of horizon-scale polarized emission, particularly for sparse arrays like the EHT.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2020

Reduced Complexity Model Intercomparison Project Phase 1: introduction and evaluation of global-mean temperature response

Reduced-complexity climate models (RCMs) are critical in the policy and decision making space, and are directly used within multiple Intergovernmental Panel on Climate Change (IPCC) reports to complement the results of more comprehensive Earth system models. To date, evaluation of RCMs has been limited to a few independent studies. Here we introduce a systematic evaluation of RCMs in the form of the Reduced Complexity Model Intercomparison Project (RCMIP). We expect RCMIP will extend over multiple phases, with Phase 1 being the first. In Phase 1, we focus on the RCMs' global-mean temperature responses, comparing them to observations, exploring the extent to which they emulate more complex models and considering how the relationship between temperature and cumulative emissions of CO2 varies across the RCMs. Our work uses experiments which mirror those found in the Coupled Model Intercomparison Project (CMIP), which focuses on complex Earth system and atmosphere–ocean general circulation models. Using both scenario-based and idealised experiments, we examine RCMs' global-mean temperature response under a range of forcings. We find that the RCMs can all reproduce the approximately 1°C of warming since pre-industrial times, with varying representations of natural variability, volcanic eruptions and aerosols. We also find that RCMs can emulate the global-mean temperature response of CMIP models to within a root-mean-square error of 0.2°C over a range of experiments. Furthermore, we find that, for the Representative Concentration Pathway (RCP) and Shared Socioeconomic Pathway (SSP)-based scenario pairs that share the same IPCC Fifth Assessment Report (AR5)-consistent stratospheric-adjusted radiative forcing, the RCMs indicate higher effective radiative forcings for the SSP-based scenarios and correspondingly higher temperatures when run with the same climate settings. In our idealised setup of RCMs with a climate sensitivity of 3°C, the difference for the ssp585–rcp85 pair by 2100 is around 0.23°C(±0.12°C) due to a difference in effective radiative forcings between the two scenarios. Phase 1 demonstrates the utility of RCMIP's open-source infrastructure, paving the way for further phases of RCMIP to build on the research presented here and deepen our understanding of RCMs.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Comparison of machine learning techniques to optimize the analysis of plutonium surrogate material via a portable LIBS device

The utilization of machine learning techniques has become commonplace in the analysis of optical emission spectra. These methods are often limited to variants of principal components analysis (PCA), partial-least squares (PLS), and artificial neural networks (ANNs). A plethora of other techniques exist and are well established in the world of data science, yet are seldom investigated for their use in spectroscopic problems. In this study, machine learning techniques were used to analyze optical emission spectra of laser-induced plasma from ceria pellets doped with silicon in order to predict silicon content. Additionally, a boosted regression ensemble model was created, and its predictive accuracy was compared to that of traditional PCA, PLS, and ANN regression models. Boosted regression tree ensembles yielded fits with R-squared (R2) values as high as 0.964 and mean-squared errors of prediction (MSEPs) as low as 0.074, providing the most accurate predictive model. Neural networks performed with slightly lower R2 values and higher MSEPs compared to the ensemble methods, thus indicating susceptibility to overfitting.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Barium stars as tracers of s -process nucleosynthesis in AGB stars: II. Using machine learning techniques on 169 stars

Barium (Ba) stars are characterised by an abundance of heavy elements made by the slow neutron capture process (s-process). This peculiar observed signature is due to the mass transfer from a stellar companion, bound in a binary stellar system, to the Ba star observed today. The signature is created when the stellar companion is an asymptotic giant branch (AGB) star. We aim to analyse the abundance pattern of 169 Ba stars using machine learning techniques and the AGB final surface abundances predicted by the FRUITY and Monash stellar models. We developed machine learning algorithms that use the abundance pattern of Ba stars as input to classify the initial mass and metallicity of each Ba star’s companion star using stellar model predictions. We used two algorithms. The first exploits neural networks to recognise patterns, and the second is a nearest-neighbour algorithm that focuses on finding the AGB model that predicts the final surface abundances closest to the observed Ba star values. In the second algorithm, we included the error bars and observational uncertainties in order to find the best-fit model. The classification process was based on the abundances of Fe, Rb, Sr, Zr, Ru, Nd, Ce, Sm, and Eu. We selected these elements by systematically removing s-process elements from our AGB model abundance distributions and identifying the elements whose removal had the biggest positive effect on the classification. We excluded Nb, Y, Mo, and La. Our final classification combined the output of both algorithms to identify an initial mass and metallicity range for each Ba star companion. With our analysis tools, we identified the main properties for 166 of the 169 Ba stars in the stellar sample. The classifications based on both stellar sets of AGB final abundances show similar distributions, with an average initial mass of M = 2.23 M ⊙ and 2.34 M ⊙ and an average [Fe/H] = –0.21 and –0.11, respectively. We investigated why the removal of Nb, Y, Mo, and La improves our classification and identified 43 stars for which the exclusion had the biggest effect. We found that these stars have statistically significant and different abundances for these elements compared to the other Ba stars in our sample. We discuss the possible reasons for these differences in the abundance patterns.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2020

ROM-Based Surrogate Systems Modeling of EBR-II

We report the System Analysis Module (SAM), developed and maintained by Argonne National Laboratory, is designed to provide whole-plant transient safety analysis capabilities for a number of advanced non-light water reactors, including sodium-cooled fast reactor (SFR), lead-cooled fast reactor (LFR), and molten salt reactor (MSR)/fluoride-salt-cooled high-temperature reactor (FHR) designs. SAM is primarily constructed as a systems-level analysis tool, with the potential to incorporate reduced order models from three-dimensional computational fluid dynamics (CFD) simulations to improve characterization of complex, multidimensional physics. It is recognized that the computational expense associated with CFD can be intractable for various engineering analyses, such as uncertainty quantification, inference, and design optimization. This paper explores the reducibility of a SAM model using recent advances in randomized linear algebra techniques, which attempt to find recurring patterns in the various realizations generated by a model after randomly perturbing all its input parameters. The reduction is described in terms of fewer degrees of freedom (DOFs), referred to as the active DOFs, for the model variables such as input model parameters and model responses. The results indicate that there is significant room for additional reduction that may be leveraged for additional computational gains when employing SAM for engineering-intensive analyses that require repeated model executions. Different from physics-based reduction approaches, the proposed approach allows one to estimate upper bounds on the reduction errors, which are rigorously developed in this work. Finally, different methods for surrogate model construction, such as regression and neural network-based training, are employed to correlate the input and output active DOFs, which are related back to the original variables using matrix-based linear transformations.

42 ENGINEERING↗

DOE OSTI2025

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention mechanism, which is a critical component of transformer-based LLMs. In this paper, we investigate the impact of faults on LLM training, focusing on INF, NaN, and near-INF values in the computation results with systematic fault injection experiments. We observe the propagation patterns of these errors, which can trigger non-trainable states in the model and disrupt training, forcing the procedure to load from checkpoints. To mitigate the impact of these faults, we propose ATTNChecker, the first Algorithm-Based Fault Tolerance (ABFT) technique tailored for the attention mechanism in LLMs. ATTNChecker is designed based on fault propagation patterns of LLM and incorporates performance optimization to adapt to both system reliability and model vulnerability while providing lightweight protection for fast LLM training. Evaluations on four LLMs show that ATTNChecker on average incurs on average 7% overhead on training while detecting and correcting all extreme errors. Compared with the state-of-the-art checkpoint/restore approach, ATTNChecker reduces recovery overhead by up to 49×.

Liang, Yuhang [University of Alabama - Birmingham]↗

DOE OSTI2020

Multimodel simulation of vertical gas transfer in a temperate lake

In recent decades, several lake models of varying complexity have been developed and incorporated in numerical weather prediction systems and climate models. To foster enhanced forecasting ability and verification, improvement of these lake models remains essential. This especially applies to the limited simulation capabilities of biogeochemical processes in lakes and greenhouse gas exchanges with the atmosphere. Here we present multi-model simulations of physical variables and dissolved gas dynamics in a temperate lake (Harp Lake, Canada). The five models (ALBM, FLake, LAKE, LAKEoneD, MTCR-1) considered within this most recent round of the Lake Model Intercomparison Project (LakeMIP) all captured the seasonal temperature variability well. In contrast, none of the models is able to reproduce the exact dates of ice-cover and ice-off, leading to considerable errors in the simulation of eddy diffusivity around those dates.We then conducted an additional modeling experiment with a diffusing passive tracer to isolate the effect of the eddy diffusivity on gas concentration. Remarkably, sophisticated k -" models do not demonstrate a significant difference in the vertical diffusion of a passive tracer compared to models with much simpler turbulence closures. All models simulate less intensive spring overturn compared to autumn. Reduced mixing in the models consequently leads to the accumulation of the passive tracer distribution in the water column. The lake models with a comprehensive biogeochemical module, such as ALBM and LAKE, predict dissolved oxygen dynamics adequate to the observed data. However, for the surface carbon dioxide concentration the correlation between modeled (ALBM, LAKE) and observed data is weak (~0.3). Overall our results indicate the need to improve the representation of physical and biogeochemical processes in lake models, thereby contributing to enhanced weather prediction and climate projection capabilities.

Guseva, Sofya↗

DOE OSTI2023

Efforts to enhance reproducibility in a human performance research project

Background: Ensuring the validity of results from funded programs is a critical concern for agencies that sponsor biological research. In recent years, the open science movement has sought to promote reproducibility by encouraging sharing not only of finished manuscripts but also of data and code supporting their findings. While these innovations have lent support to third-party efforts to replicate calculations underlying key results in the scientific literature, fields of inquiry where privacy considerations or other sensitivities preclude the broad distribution of raw data or analysis may require a more targeted approach to promote the quality of research output. Methods: We describe efforts oriented toward this goal that were implemented in one human performance research program, Measuring Biological Aptitude, organized by the Defense Advanced Research Project Agency's Biological Technologies Office. Our team implemented a four-pronged independent verification and validation (IV&V) strategy including 1) a centralized data storage and exchange platform, 2) quality assurance and quality control (QA/QC) of data collection, 3) test and evaluation of performer models, and 4) an archival software and data repository. Results: Our IV&V plan was carried out with assistance from both the funding agency and participating teams of researchers. QA/QC of data acquisition aided in process improvement and the flagging of experimental errors. Holdout validation set tests provided an independent gauge of model performance. Conclusions: In circumstances that do not support a fully open approach to scientific criticism, standing up independent teams to cross-check and validate the results generated by primary investigators can be an important tool to promote reproducibility of results.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Five-day track forecast skills of WRF model for the western North Pacific tropical cyclones

In this study, the characteristics of simulated tropical cyclones (TCs) over the western North Pacific by a regional model (the WRF Model) are verified. We utilize 12-km horizontal grid spacing, and simulations are integrated for 5 days from model initialization. A total of 125 forecasts are divided into five clusters through the k-means clustering method. The TCs in the cluster 1 and 2 (group 1), which includes many TCs moving northward in the subtropical region, generally have larger track errors than for TCs in cluster 3 and 4 (group 2). The optimal steering vector is used to examine the difference in the track forecast skill between these two groups. The bias in the steering vector between the model and analysis data is found to be more substantial for group 1 TCs than group 2 TCs. The larger steering vector difference for group 1 TCs indicates that environmental fields tend to be poorly simulated in group 1 TC cases. Furthermore, the residual terms, including the storm-scale process, asymmetric convection distribution, or beta-related effect, are also larger for group 1 TCs than group 2 TCs. Therefore, it is probable that the large track forecast error for group 1 TCs is a result of unreasonable simulations of environmental wind fields and residual processes in the midlatitudes.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

A Knowledge-based Framework for Building Energy Model Performance Verification

Building energy modeling (BEM) has been widely used by researchers, regulators, and engineers to quantify building energy performance. Quality assurance (QA) and quality control (QC) of the model's performance are essential parts of such analysis. Currently, QA/QC is done in a manual and ad-hoc manner, which is tedious, error-prone, and time-consuming when QA/QC a large number of models. To solve these challenges, we propose a a dAta-driveN buIlding perforMance verificATion framEwork (ANIMATE), which conducts automated output-based verification of building operations requirements (especially for time-series output-based verification of control requirements). While this framework was developed for verifying energy model performance, it can be extended for other applications such as BEM software testing and performance verification of real buildings in the field.

Chen, Yan↗

DOE OSTI2022

Evaluation of dynamic testing of full-scale wind turbine drivetrains with hardware-in-the-loop

Dynamometer testing of full-scale wind turbine drivetrains involves subjecting integrated components to extreme static loads, fatigue loads, or dynamic loads to replicate field conditions. This paper provides a detailed evaluation of the uncertainty and errors in applied loads and measured responses, and their magnitude relative to established repeatability bounds for a drivetrain subjected to static and dynamic loads on the 7.5 MW test bench at the Clemson University Wind Turbine Drivetrain Testing Facility. An ideal drivetrain simulation model is utilized to isolate the influence of load tracking errors on test article responses. It is shown that the test article response variations are mainly driven by run out and clearances inherent to the drivetrain. For the dynamic profiles, the load tracking errors are within acceptable limits. Furthermore, a frequency analysis is used to show that the test bench controller tracking performance is acceptable for profiles with frequency content up to 1.5 Hz.

17 WIND ENERGY↗

DOE OSTI2024

Archetype-based Redshift Estimation for the Dark Energy Spectroscopic Instrument Survey

We present a computationally efficient galaxy archetype-based redshift estimation and spectral classification method for the Dark Energy Survey Instrument (DESI) survey. The DESI survey currently relies on a redshift fitter and spectral classifier using a linear combination of principal component analysis–derived templates, which is very efficient in processing large volumes of DESI spectra within a short time frame. However, this method occasionally yields unphysical model fits for galaxies and fails to adequately absorb calibration errors that may still be occasionally visible in the reduced spectra. Our proposed approach improves upon this existing method by refitting the spectra with carefully generated physical galaxy archetypes combined with additional terms designed to absorb data reduction defects and provide more physical models to the DESI spectra. We test our method on an extensive data set derived from the survey validation (SV) and Year 1 (Y1) data of DESI. Our findings indicate that the new method delivers marginally better redshift success for SV tiles while reducing catastrophic redshift failure by 10%–30%. At the same time, results from millions of targets from the main survey show that our model has relatively higher redshift success and purity rates (0.5%–0.8% higher) for galaxy targets while having similar success for QSOs. These improvements also demonstrate that the main DESI redshift pipeline is generally robust. Additionally, it reduces the false-positive redshift estimation by 5%–40% for sky fibers. We also discuss the generic nature of our method and how it can be extended to other large spectroscopic surveys, along with possible future improvements.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2022

DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ${\approx}2.3$ the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.

79 ASTRONOMY AND ASTROPHYSICS↗