Search NASA⌕ Search

SEARCH · Search NASA

Results for “error testing”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Selection of Training Sets for 235U Source Detection Classifiers Using Gamma Signatures

The machine learning methods for classifiers to detect low level radiation sources are of interest when suitable training data sets are available. Their application and performance assessment, however, involves the aspects of over-fitting and training data selection that are somewhat uncommon in other existing methods for this task.We study U-235 gamma signatures using data sets collected by 21 NaI detectors under controlled conditions. The gamma spectra are collected by the detectors located at different distances from the source, and we study their choice as training sets for classifiers to detect a source. The detectors form the near, middle and outer groups based on the distance to source. The classifiers based on the outer group are susceptible to over-fitting, that is, they achieve low training error but incur much higher testing error in independent tests. The other two groups achieve lower training error and comparable testing error, and the near group achieves the overall lowest error. In detecting a source at an unknown distance, the farther detectors in the middle group achieve the overall lowest testing error with limited over-fitting, thereby indicating the complex dependencies between the training and classifier performance.

Rao, Nageswara↗
DOE OSTI2024

The Single Event Error (SEE) test and analysis of the CMS Endcap Timing Layer readout chip

The ETROC2, the first full size and full functionality prototype chip for the CMS Endcap Timing Layer readout, is strategically designed to meet the SEE immunity requirements of detector operation with the low power constraint. The triplicated periphery and pixel I2C configuration registers are designed with self-correction feature. The pixel readout control is centralized in the global readout and fully triplicated. The pixel readout is not triplicated, instead protected with power-efficient one-bit correction Hamming code. The TMR protection of the on-pixel threshold calibration can be turned off allowing the detection of the beam spot during the beam test by checking the bit-flips of the internal memory cells. In the initial proton beam test in January 2024, the chip readout process did not hang throughout the tests. The Hamming code correction strategy works because the error corrected TDC data were observed in the data frames. The error-injection simulation is performed to analy ze the small number of bit-flips in the configuration registers. We also performed SEE testing with a heavy ion beam in April and the data analysis is ongoing. The detailed design on the SEE immunity and the testing as well as simulation results will be presented, including follow-up SEE testing results in May and June 2024.

Gong, Datao↗
DOE OSTI2020

Drag Coefficient Analysis of Arbitrary Fragment Geometry with Emphasis on Meshing Sensitivity Studies.

This report characterizes Mach number effects in the hypersonic range from Mach 3 to Mach 7 for an arbitrary, computationally generated fragment. Force and moment coefficients in the x, y, z direction were successfully obtained and resulting trends were compared with theoretical expectations. Three orientations were tested in the form of unit vectors: [1,0,0], [0,1,0], and [0,0,1]; these represent the i, j, k principle axes. The final results ultimately showcased a trend very similar to that shown in previous literature — drag coefficients for a given orientation decreased with increasing Mach number by a very small amount in the hypersonic range. It was therefore concluded that the aerodynamic quantities used to obtain the fragment trajectory at low hypersonic Mach numbers (such as Mach 3) can be used to characterize the aerodynamic qualities at higher hypersonic Mach numbers (Mach 5, 7) with a reasonably small margin. A sensitivity study was also conducted which ultimately defined drag effects as a result of changing grid spacing and normal extrusion parameters for the unstructured tetrahedral mesh used in the simulation. Further work can be done in the form of experimental validation, specifically with regards to wind tunnels and ballistic range testing. Error can be reduced by testing more mesh variabilities and capturing a larger amount of fragment orientations. The results for force and moment characteristics dependent on meshing parameters and high Mach numbers are satisfactory and consistent with expected trends.

42 ENGINEERING↗
DOE OSTI2026

Representativity error scaling of models of the high temperature test facility

Error scaling is a critical step toward the validation of modeling capabilities for high-temperature gas-cooled reactors (HTGRs). Extensive effort is being made to bring HTGRs into the validation basis of numerous thermal-hydraulics codes. Here, this paper demonstrates how systems-level codes can be leveraged to perform error scaling analyses between an experimental facility and a plant-to-be facility. Specifically, we focus on two conduction cooldown experiments from the High Temperature Test Facility (HTTF) and the General Atomics 350 MW th modular high-temperature gas-cooled reactor (MHTGR-350). The error scaling methodology employed in this study is representativity, which in the context of this work was used to quantify how well experiments captured the physics of the plant facility by comparing sensitivity vectors between the two facilities. In addition, two different RELAP5–3D models of the HTTF were included in the comparison to determine if modeling methodologies notably impact the representativity results. The key figures of merit are the maximum block temperature and the coolant outlet temperature. The time-dependent maximum block temperature had a low representativity of below 0.1 for both models across both transients. The coolant outlet temperature had a higher representativity of around 0.6 for both models during the pressurized conduction cooldown, but it was below 0.2 for the depressurized conduction cooldown. Overall, the HTTF experiments were not representative of the transients in the MHTGR-350. However, these results can play a significant role in informing future potential experiments for HTGR systems that iterate on what the HTTF accomplished.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2022

Biomaniac

Los Alamos National Laboratory researchers are developing a machine-learning based algorithm to revolutionize how biopolymers are designed and optimized. BioManIAC is a software platform that fills the gaps in data to gain insight into new potential polymer properties without making and testing them. Polymer engineers are able to use BioManIAC software to extrapolate and tune new biopolymer properties that allow the user to create small smart libraries, rather than largescale trial and error testing. This targeted design is expected to improve both time to market and R&D expenditure, as well as the resulting mechanical properties of biopolymers, enabling for more direct competition with traditional petroleum-based polymers. Los Alamos is seeking partners to further validate our software platform.

36 MATERIALS SCIENCE↗
DOE OSTI2026

LAF-Net: A Deep Residual and Cross-Attention Framework for Day-Ahead Load Forecasting: Preprint

Accurate day-ahead load forecasting is essential for reliable power system operations and market efficiency. System operators such as the Midcontinent Independent System Operator (MISO) rely on forecasts from multiple vendors, yet combining them effectively remains a persistent challenge due to vendor-specific biases. This paper presents a novel LSTM-Attention Fusion Network with Error Representation (LAF-Net) that enhances day-ahead hourly load forecasting through deep residual learning and multi-modal cross-attention. The proposed model builds a historical error memory from past vendor performance and dynamically queries it with future hour context to generate adaptive, hour-specific trust weights for each vendor. A bounded residual correction further refines forecasts by mitigating systematic and temporally localized errors. Tested on real MISO LBA data with multi-vendor forecasts, LAF-Net consistently outperforms the best vendor baseline across all 38 LBAs, achieving more than a 40% reduction in system-level mean absolute error (MAE) during peak load hours relative to the best vendor baseline.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Parameter uncertainties for imperfect surrogate models in the low-noise regime

Abstract Bayesian regression determines model parameters by minimizing the expected loss, an upper bound to the true generalization error. However, this loss ignores model form error, or misspecification, meaning parameter uncertainties are significantly underestimated and vanish in the large data limit. As misspecification is the main source of uncertainty for surrogate models of low-noise calculations, such as those arising in atomistic simulation, predictive uncertainties are systematically underestimated. We analyze the true generalization error of misspecified, near-deterministic surrogate models, a regime of broad relevance in science and engineering. We show that posterior parameter distributions must cover every training point to avoid a divergence in the generalization error and design a compatible ansatz which incurs minimal overhead for linear models. The approach is demonstrated on model problems before application to thousand-dimensional datasets in atomistic machine learning. Our efficient misspecification-aware scheme gives accurate prediction and bounding of test errors in terms of parameter uncertainties, allowing this important source of uncertainty to be incorporated in multi-scale computational workflows.

Swinburne, Thomas D. (ORCID:0000000232554257)↗
DOE OSTI2023

Single-Point Extrapolation to the Complete Basis Set Limit through Deep Learning

Machine learning (ML) offers an attractive method for making predictions about molecular systems while circumventing the need to run expensive electronic structure calculations. Once trained on ab initio data, the promise of ML is to deliver accurate predictions of molecular properties that were previously computationally infeasible. In this work, we develop and train a graph neural network model to correct the basis set incompleteness error (BSIE) between a small and large basis set at the RHF and B3LYP levels of theory. Our results show that, when compared to fitting to the total potential, an ML model fitted to correct the BSIE is better at generalizing to systems not seen during training. We test this ability by training on single molecules while evaluating on molecular complexes. We also show that ensemble models yield better behaved potentials in situations where the training data is insufficient. However, even when only fitting to the BSIE, acceptable performance is only achieved when the training data sufficiently resemble the systems one wants to make predictions on. As a result, the test error of the final model trained to predict the difference between the cc-pVDZ and cc-pV5Z potential is 0.184 kcal/mol for the B3LYP density functional, and the ensemble model accurately reproduces the large basis set interaction energy curves on the S66x8 dataset.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Reliability, biological variability, and accuracy of multi-frequency bioelectrical impedance analysis for measuring body composition components

Introduction Bioelectrical impedance analysis (BIA) systems are gaining popularity for use in research and fitness assessments as the technology improves and becomes more affordable and easier to use. Multifrequency BIA (MF-BIA) may improve accuracy and precision using octopolar contacts for segmental analyses. Purpose Evaluate reliability, biological variability, and accuracy of component measures (total body water, mass, and composition) of commercially available MF-BIA system (InBody 770, Cerritos, California, USA). Methods Fourteen healthy military-age adults were assessed by MF-BIA in duplicate on five laboratory visits across 3 weeks (10 measures each). Participants were evaluated at the same time of day after refraining from strenuous exercise (> 48 h), alcohol consumption (> 24 h), and caffeine, nicotine, and food (> 10 h). Systematic error (test–retest reliability) and biological variability (day-to-day reliability) were summarized by intraclass correlation coefficient (ICC) values determined for body mass (fat, fat-free, total) and body water (extracellular, intracellular, total). Body composition measurements derived from BIA on the second visit were also tested for accuracy compared to dual-energy x-ray absorptiometry (DXA). Results Test–retest reliability was very high for all measurements of whole-body water and mass (ICC ≥ 0.999) and high for regional body water and mass (ICC 0.973–1.000). Biological variability was observable with very minor differences between tests (same day) for total and regional body water (0.0–0.2 L) and total and regional body mass measurements (0.0–0.2 kg); while between day differences were slightly higher (0.0–0.5 L and 0.1–0.7 kg). Compared to DXA, the MF-BIA whole-body measures showed an offset in %BF (Bias −4.0 ± 2.8%; Standard error of the estimate (SEE), 2.6%), an overprediction for total body fat-free mass (Bias 2.8 ± 2.1 kg; SEE 2.2 kg) and an underprediction of total body fat mass (Bias −2.9 ± 2.0 kg; SEE 1.9 kg). Conclusion Under controlled conditions with fit and healthy men and women, this MF-BIA system has high methodological reliability and demonstrates stable day-to-day measurements of major body composition components. Previously reported ~3% body fat offset compared to criterion methods was again confirmed. Precision of the InBody 770 shows consistency and supports further testing of this specific device as a new military standards method and suitability across a wider range of %BF.

Nutrition & Dietetics↗
DOE OSTI2023

Design Rules for Two–Dimensional Organic Semiconductor–Incorporated Perovskites (OSiP) Gleaned from Thousands of Simulated Structures

Two-dimensional (2D) halide perovskites are an attractive class of hybrid perovskites that have additional optoelectronic tunability due to their accommodation of relatively large organic ligands. Nevertheless, contemporary ligand design depends on either expensive trial-and-error testing of whether a ligand can be integrated within the lattice or conservative heuristics that unduly limit the scope of ligand chemistries. Here, the structural determinants of stable ligand incorporation within Ruddlesden-Popper (RP) phase perovskites are established by molecular dynamics (MD) simulations of over ten-thousand RP-phase perovskites and training of machine learning classifiers capable of predicting structural stability based solely on generalizable ligand features. The simulation results show near-perfect predictions of positive and negative literature examples, predict trade-offs between several ligand features and stability, and ultimately predict an inexhaustibly large 2D-compatible ligand design-space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Invertible neural networks for real-time control of extrusion additive manufacturing

Material extrusion additive manufacturing (AM) has enabled an elegant fabrication pathway for a vast material library. Nonetheless, each material requires optimization of printing parameters generally determined through significant trial-and-error testing. To eliminate arduous, iteration-based optimization approaches, many researchers have used machine learning (ML) algorithms which provide opportunities for automated process optimization. Here, in this work, we demonstrate the use of an ML-driven approach for real-time material extrusion print-parameter optimization through in-situ monitoring of printed line geometry. To do this, we use deep invertible neural networks (INNs) which can solve both forward and inverse, or optimization, problems using a single network. By combining in-situ computer vision and deep INNs, the printing parameters can be autonomously optimized to print a target line width in 1.2 s. Furthermore, defects that occur during printing can be rapidly identified and corrected autonomously. The methods developed and presented in this work eliminate user-intensive, time-consuming, and iterative parameter discovery approaches that currently limit accelerated implementation of extrusion-based AM processes. Furthermore, the presented approach can be generalized to provide real-time monitoring and optimization pathways for increasingly complex AM environments.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Monte Carlo simulation of order-disorder transition in refractory high entropy alloys: A data-driven approach

High entropy alloys (HEAs) are a series of novel materials that demonstrate many exceptional mechanical properties. To understand the origin of these attractive properties, it is important to investigate the thermodynamics and elucidate the evolution of various chemical phases. In this work, we introduce a machine learning approach to construct the effective Hamiltonian and study the thermodynamics of HEAs through canonical Monte Carlo simulation. The main characteristic of our method is to use pairwise interactions between atoms as the machine learning features and systematically improve the representativeness of the dataset using active learning from the Monte Carlo samples. We find this method produces highly robust and accurate effective Hamiltonians that give less than 0.1 mRy test error for all the three refractory HEAs: MoNbTaW, MoNbTaVW, and MoNbTaTiW. Using replica exchange to speed up the MC simulation, we calculated the specific heats and short-range order parameters in a wide range of temperatures. For all the studied materials, we find there are two major order-disorder transitions occurring respectively at T 1 and T 2 , where T 1 is near room temperature but T 2 is much higher. Further, we demonstrate that the transition at T 1 is caused by W and Nb while the one at T 2 is caused by the other elements. By comparing with experiments, the results demonstrate that the order-disorder transitions have a profound impact on the strength and ductility of HEAs.

36 MATERIALS SCIENCE↗
DOE OSTI2024

PINN surrogate of Li-ion battery models for parameter inference, Part II: Regularization and application of the pseudo-2D model

Bayesian parameter inference is useful to improve Li-ion battery diagnostics and can help formulate battery aging models. However, it is computationally intensive and cannot be easily repeated for multiple cycles, multiple operating conditions, or multiple replicate cells. To reduce the computational cost of Bayesian calibration, numerical solvers for physics-based models can be replaced with faster surrogates. A physics-informed neural network (PINN) is developed as a surrogate for the pseudo-2D (P2D) battery model calibration. For the P2D surrogate, additional training regularization was needed as compared to the PINN single-particle model (SPM) developed in Part I. Both the PINN SPM and P2D surrogate models are exercised for parameter inference and compared to data obtained from a direct numerical solution of the governing equations. A parameter inference study highlights the ability to use these PINNs to calibrate scaling parameters for the cathode Li diffusion and the anode exchange current density. By realizing computational speed-ups of ~2250x for the P2D model, as compared to using standard integrating methods, the PINN surrogates enable rapid state-of-health diagnostics. Finally, in the low-data availability scenario, the testing error was estimated to ~2 mV for the SPM surrogate and ~10 mV for the P2D surrogate which could be mitigated with additional data.

25 ENERGY STORAGE↗
DOE OSTI2023

Multifidelity Neural Network Formulations for Prediction of Reactive Molecular Potential Energy Surfaces

Here, this paper focuses on the development of multifidelity modeling approaches using neural network surrogates, where training data arising from multiple model forms and resolutions are integrated to predict high-fidelity response quantities of interest at lower cost. We focus on the context of quantum chemistry and the integration of information from multiple levels of theory. Important foundations include the use of symmetry function-based atomic energy vector constructions as feature vectors for representing structures across families of molecules and single-fidelity neural network training capabilities that learn the relationships needed to map feature vectors to potential energy predictions. These foundations are embedded within several multifidelity topologies that decompose the high-fidelity mapping into model-based components, including sequential formulations that admit a general nonlinear mapping across fidelities and discrepancy-based formulations that presume an additive decomposition. Methodologies are first explored and demonstrated on a pair of simple analytical test problems and then deployed for potential energy prediction for C 5 H 5 using B2PLYP-D3/6-311++G(d,p) for high-fidelity simulation data and Hartree–Fock 6-31G for low-fidelity data. For the common case of limited access to high-fidelity data, our computational results demonstrate that multifidelity neural network potential energy surface constructions achieve roughly an order of magnitude improvement, either in terms of test error reduction for equivalent total simulation cost or reduction in total cost for equivalent error.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Efficient Training of Deep Neural Operator Networks via Randomized Sampling

Neural operators (NOs) employ deep neural networks to learn the mappings between infinitedimensional function spaces. Deep operator network (DeepONet), a popular NO architecture, has demonstrated success in the real-time prediction of complex dynamics across various scientific and engineering applications. In this work, we introduce a random sampling technique to be adopted during the training of DeepONet, aimed at improving the generalization ability of the model, while significantly reducing the computational time. The proposed approach targets the trunk network of the DeepONet model that outputs the basis functions corresponding to the spatiotemporal locations of the bounded domain on which the physical system is defined. While constructing the loss function, DeepONet training traditionally considers a uniform grid of spatiotemporal points at which all the output functions are evaluated for each iteration. This approach leads to a larger batch size, resulting in poor generalization and increased memory demands, due to the limitations of the stochastic gradient descent (SGD) optimizer. The proposed random sampling over the inputs of the trunk net mitigates these challenges, improving generalization and reducing the memory requirements during training, resulting in significant computational gains. We validate our hypothesis through three benchmark examples, demonstrating substantial reductions in training time while achieving comparable or lower overall test errors relative to the traditional training approach. Our results indicate that incorporating randomization in the trunk network inputs during training enhances the efficiency and robustness of DeepONet, offering a promising avenue for improving the framework’s performance in modeling complex physical systems.

Karumuri, Sharmila [Department of Civil & Systems ↗
DOE OSTI2022

Automated Stellar Spectra Classification with Ensemble Convolutional Neural Network

Large sky survey telescopes have produced a tremendous amount of astronomical data, including spectra. Machine learning methods must be employed to automatically process the spectral data obtained by these telescopes. Classification of stellar spectra by applying deep learning is an important research direction for the automatic classification of high-dimensional celestial spectra. In this paper, a robust ensemble convolutional neural network (ECNN) was designed and applied to improve the classification accuracy of massive stellar spectra from the Sloan digital sky survey. We designed six classifiers which consist six different convolutional neural networks (CNN), respectively, to recognize the spectra in DR16. Then, according the cross-entropy testing error of the spectra at different signal-to-noise ratios, we integrate the results of different classifiers in an ensemble learning way to improve the effect of classification. The experimental result proved that our one-dimensional ECNN strategy could achieve 95.0% accuracy in the classification task of the stellar spectra, a level of accuracy that exceeds that of the classical principal component analysis and support vector machine model.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Hiperclust

This software leverages transfer learning to analyze atom probe tomography (APT) data. It is trained on synthetic data and then applies this knowledge to predict the optimal number of clusters for a given APT dataset. Initially, the software used preliminary clustering to estimate the general structure of the data. Based on this, it provides suggestions for key parameters like minimum cluster size and minimum number of points. These parameters are critical for algorithms like HDBSCAN, ensuring accurate cluster formation without the need for trial-and-error testing. The software runs on High-Performance computing (HPC) systems, enabling fast, scalable analysis of large APT datasets, ultimately saving time and improving the reliability of clustering outcomes.

Tang, Yalei [Idaho National Laboratory (INL), Idah↗
DOE OSTI2021

Development of High Bs Fe-Ni Based Metal Amorphous Nanocomposite by Optimization of Glass Forming Ability

A growing interest in electric vehicles challenges soft magnetic materials to improve efficiency and power density. Metal amorphous nanocomposites (MANCs) have lower coercivities and eddy current losses, allowing for greater efficiency and higher switching frequency. The later allows for high motor speeds and improved power density. However, commercially available and laboratory demonstrated MANCs have shortcomings. Fe-based MANCs, such as FINEMET have excellent magnetic properties, but mechanical properties limit their application in high speed electric motors (HSMs). Fe-Co based MANCs, such as HITPERM, have high saturation inductions and good mechanical properties, but elevated magnetostrictive losses. Co-based MANCs and more recent Fe-Ni based MANCs have low losses and good mechanical properties, but lower saturation inductions (1-1.2 T), that limit power density in HSMs. Recently, much work has explored improving saturation induction in MANCs by increasing the content of magnetic elements, which comes at the cost of glass-forming ability (GFA). These efforts where generally limited to trial and error testing. Additionally, all work to date has focused on Fe-based alloys. In this work, a method of using Thermocalc simulation to locate near-eutectic compositions has been applied to Fe-Ni based alloys. Minima in liquidus temperature and solidification range were found for a ternary composition range and used to identify compositions that retain good GFA as the percentage of magnetic elements is increased. The (Fe 70 Ni 30 ) x (B-Si-Nb) 100-x alloy system for x=82% and x=85% was explored by Thermocalc simulations. This is an increase in magnetic element content compared to previously developed x=80% alloys. 3 compositions in the x=82% system, and 1 alloy in the x=85% system where identified and successfully cast as amorphous ribbon. The amorphous nature of the ribbon was confirmed by a bend test and XRD. Magnetic testing was performed by PPMS to measure saturation induction and Curie temperature of the amorphous material. The Curie temperatures increased to 407-438 °C for the x=82% alloys, and 462 °C for the x=85% alloy. Saturation induction increased to 1.28-1.36 T for the x=82% alloy and 1.48 T for the x=85% alloy, which is a significant improvement over the ~370 °C Curie temperature and 1.2 T saturation of previous Fe-Ni alloy. Crystallization behavior was studied by XRD for the x=85% alloy, showing that crystallization process follows a 2-step process of Amorphous → BCC+FCC+Amorphous → BCC+FCC+Fe 3 B+Fe 23 B 6 . Post annealing magnetic properties were studied by strip testing, and saturation induction as high as 1.48 T was seen after optimal annealing. TEM was used to study structure of as cast and annealed material. 2 alloys with x=82% compositions were identified with an optimal crystalline size of 10-20 nm, while the x=85% alloy had this structure in the as cast state. This opens the possibility of using the alloy in the as cast state, without requiring annealing. In conclusion, alloys with good GFA and improved magnetic properties were identified by Thermocalc simulation.

Krimer, Yuval↗