Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “optimal accuracy”

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 793 records · Page 44

DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning

Machine learning models are increasingly applied across scientific disciplines, yet their effectiveness often hinges on heuristic decisions—such as data transformations, training strategies, and model architectures—that are not learned by the models themselves. Automating the selection of these heuristics and analyzing their sensitivity is crucial for building robust and efficient learning workflows. DeepHyper addresses this challenge by democratizing hyperparameter optimization, providing accessible tools to streamline and enhance machine learning workflows from a laptop to the largest supercomputer in the world. Building on top of hyperparameter optimization, it unlocks new capabilities around ensembles of models for improved accuracy and uncertainty quantification. All of these organized around efficient parallel computing.

ensemble↗

Tribological behavior prediction of friction materials for ultrasonic motors using Monte Carlo‐based artificial neural network

ABSTRACT In this article, the relationship of complexity, diversity, and uncertainty between components and tribological properties of friction materials based on a Monte Carlo‐based artificial neural network (MC‐ANN) model was predicted precisely. Meanwhile, the grey relational analysis was applied to figure out weight of factors, optimize formulation design, and calculate nonlinear dependency of ingredients. The accuracy of model was studied by comparing experimental and simulated values on the basis of statistical methods (root‐mean‐squared error). It was found that the model exhibited an excellent performance in predicting and fitting effect. Moreover, comprehensive analysis of weight indicated that nano‐SiO 2 and mica exerted a significant role in improving the friction stability and wear resistance. According to different contents of each ingredient, the corresponding friction coefficient and specific wear rate could be obtained by virtue of a well‐trained MC‐ANN model without experiments, which saved a lot of time and money. It can be expected that the results of this work will extend the current research and pave a route for further in‐depth studies of friction materials. © 2018 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136 , 47157.

Li, Song↗

Efficiency Improvement in a Busy Radiology Practice: Determination of Musculoskeletal Magnetic Resonance Imaging Protocol Using Deep-Learning Convolutional Neural Networks

The purposes of this study are to evaluate the feasibility of protocol determination with a convolutional neural networks (CNN) classifier based on short-text classification and to evaluate the agreements by comparing protocols determined by CNN with those determined by musculoskeletal radiologists. Following institutional review board approval, the database of a hospital information system (HIS) was queried for lists of MRI examinations, referring department, patient age, and patient gender. These were exported to a local workstation for analyses: 5258 and 1018 consecutive musculoskeletal MRI examinations were used for the training and test datasets, respectively. The subjects for pre-processing were routine or tumor protocols and the contents were word combinations of the referring department, region, contrast media (or not), gender, and age. The CNN Embedded vector classifier was used with Word2Vec Google news vectors. The test set was tested with each classification model and results were output as routine or tumor protocols. The CNN determinations were evaluated using the receiver operating characteristic (ROC) curves. The accuracies were evaluated by a radiologist-confirmed protocol as the reference protocols. The optimal cut-off values for protocol determination between routine protocols and tumor protocols was 0.5067 with a sensitivity of 92.10%, a specificity of 95.76%, and an area under curve (AUC) of 0.977. The overall accuracy was 94.2% for the ConvNet model. All MRI protocols were correct in the pelvic bone, upper arm, wrist, and lower leg MRIs. Deep-learning-based convolutional neural networks were clinically utilized to determine musculoskeletal MRI protocols. CNN-based text learning and applications could be extended to other radiologic tasks besides image interpretations, improving the work performance of the radiologist.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Facets of hydro power and future trends in a Nordic Context

Hydropower technologies bolster high penetration of variable renewable energies (VREs) in the net zero emissions scenarios. Nevertheless, there are various challenges to meeting the ambitious goal, such as stability, reliability, resiliency, security, lack of reactive power, voltage support and inertia, large-scale storage deployment and coordination, interconnectedness, demand-side response, higher thermal cycles with increased start/stops, and inadequate Levelized Cost of Energy (LCOE) for system-wise VRE integration and profitability. This survey conducts a bottom-up analysis to unveil the opportunities to utilize hydropower facilities and disentangle the nested problem for intertwining design features, control algorithms, operation, optimization approaches, incentives, services, and market mechanisms using a three-pillar framework perspective: grid owners, power producers, and machine designers. The survey identified emerging trends in real-time and capacity markets, flexible power systems, and enhanced grid capabilities, including advanced voltage support and updated grid codes. These developments present significant opportunities for hydropower, such as achieving super-flexibility through hybridization, expanded reactive power capabilities, and advanced operational modes like a synchronous condenser and power adequator functionalities. These opportunities require novel design philosophies — including new winding, stator, and rotor configurations, optimized ventilation, and active cooling systems — to enhance performance under stressed grid and climate conditions. Finally, integrating climate and energy models for multi-basin optimization with finer spatial and temporal granularity enhances the planning accuracy for water management of hydropower while addressing environmental challenges. The review delivers helpful prospective suggestions and tools that would serve researchers, power engineers, and stakeholders in making decisions about hydropower technologies and services in 2050 and beyond.

13 HYDRO ENERGY↗

A second-order distributed memory parallel fast sweeping method for the Eikonal equation

The Eikonal equation is used to calculate wave propagation and distance fields, and due to its complexity requires numerical treatment for its solution. In this work, we present a second-order distributed memory parallel fast sweeping method. The second-order solution switches on a two-point stencil when two upwind points are available, and reverts to first-order otherwise. In all examples, the second-order method improves the solution over the first-order, allowing for significant savings in memory while achieving the same accuracy. Parallelization over distributed memory saw good weak scaling with optimal convergence. The computational time for second-order was approximately 2.5 times slower than first-order, where the largest amount of mesh points ran on 144 cores (512 GB) was ≈20 billion. The savings in memory from the second-order method combined with the distributed memory algorithm result in the ability to solve problems much larger than are possible with the serial first-order method.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field ($B^{+}_{1}$) inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate $B^{+}_{1}$ inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 ​× ​speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel $B^{+}_{1}$ fields. Next, we train a Residual Network (ResNet) to map $B^{+}_{1}$ fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.

Deep learning↗

Development and assessment of hierarchical multi-reward reinforcement learning based potential for silicene with state-of-the-art models

We develop a new interatomic force field for Silicene, a 2D material with a buckled hexagonal lattice structure with high polymorphism. We introduce new parameterizations of a Tersoff model using a hierarchical multi-reward reinforcement learning (RL) methodology coupled with a continuous Monte Carlo Tree Search optimization. Our model significantly outperforms existing methods by enhancing the accuracy of predictions for the structural and thermodynamic properties of seven silicene polymorphs-including structure, energy, equation of state, elasticity, and phonon dispersion-when compared to established models. We further make a comprehensive comparison of the various models in predicting the mechanical and thermal properties of silicene. We trace the origin of the improved performance to the description of the angular dependence in the bond-order term, suggesting that modifying the angular terms in short-range models is essential to capture the structural diversity in low dimensional systems.

2D materials↗

Arrays of Si vacancies in 4 H -SiC produced by focused Li ion beam implantation

Point defects in SiC are an attractive platform for quantum information and sensing applications because they provide relatively long spin coherence times, optical spin initialization, and spin-dependent fluorescence readout in a fabrication-friendly semiconductor. The ability to precisely place these defects at the optimal location in a host material with nano-scale accuracy is desirable for integration of these quantum systems with traditional electronic and photonic structures. Here, we demonstrate the precise spatial patterning of arrays of silicon vacancy (${V}_{Si}$) emitters in an epitaxial 4H -SiC (0001) layer through mask-less focused ion beam implantation of Li + . We characterize these arrays with high-resolution scanning confocal fluorescence microscopy on the Si-face, observing sharp emission lines primarily coming from the ${V1}^{{\prime}}$ zero-phonon line (ZPL). The implantation dose is varied over 3 orders of magnitude, leading to ${V}_{Si}$ densities from a few per implantation spot to thousands per spot, with a linear dependence between ZPL emission and implantation dose. Optically-detected magnetic resonance (ODMR) is also performed, confirming the presence of V2 ${V}_{Si}$. Our investigation reveals scalable and reproducible defect generation.

36 MATERIALS SCIENCE↗

Terahertz wave generation from gas plasma using a phase compensator with attosecond phase-control accuracy

We report the use of a precise phase compensator for the generation of intense terahertz waves from laser-induced gas plasma excited by a femtosecond pulse ({omega}) and its second harmonic (2{omega}) at both close contact and standoff distances. The attosecond accuracy phase-control capability of the device enables further optimization of the terahertz emission from gas plasma and elimination of the temporal walkoff between the {omega} and 2{omega} pulses traveling in dispersive media, resulting in intense terahertz generation at a distance of over 100 m by sending the optical beams far away and focusing them locally.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Stochastic self-tuning hybrid algorithm for reaction-diffusion systems

Many biochemical phenomena involve reactants with vastly different concentrations, some of which are amenable to continuum-level descriptions, while the others are not. We present a hybrid self-tuning algorithm to model such systems. The method combines microscopic (Brownian) dynamics for diffusion with mesoscopic (Gillespie-type) methods for reactions and remains efficient in a wide range of regimes and scenarios with large variations of concentrations. Furthermore, its accuracy, robustness, and versatility are balanced by redefining propensities and optimizing the mesh size and time step. We use a bimolecular reaction to demonstrate the potential of our method in a broad spectrum of scenarios: from almost completely reaction-dominated systems to cases where reactions rarely occur or take place very slowly. The simulation results show that the number of particles present in the system does not degrade the performance of our method. This makes it an accurate and computationally efficient tool to model complex multireaction systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Model Residuals as Shields: A Two-Level Formulation to Defend Smart Grids From Poisoning Attacks

The advancement of smart grids presents both vast opportunities and heightened cybersecurity risks. Data-driven defense mechanisms, though designed as a shield against these threats, can fall prey to poisoning attacks. We delve into regression settings, underscoring the imperative to fortify defenses against a spectrum of poison ratios, notably those above 0.5—an issue scarcely addressed in prior studies. Recognizing the susceptibilities of smart grids and their manipulable sensors, we exploit the very intent of poisoning attacks, compromising model accuracy, as our defense mechanism. Our proposed two-level optimization framework discerns between poisoned and authentic data based on model residuals, outperforming or matching existing methods in 72% to 77% of precision and 75% to 80% of recalls across various poisoning attacks, poison ratios, and datasets. Once the authentic data are identified, the trained model is adaptable for a variety of applications. Comprehensive evaluations on different smart grid datasets, pitted against myriad poisoning schemes, validate our methodology’s edge over existing methods. Here, we also shed light on the implications of model misspecification originating from temporal auto-correlation, a common feature in Internet of Things and smart grid data.

Adversarial machine learning (ML)↗

FedEFsz: Fair Cross-Silo Federated Learning System With Error-Bounded Lossy Compression

Cross-Silo federated learning systems have been identified as an efficient approach to scaling DNN training across geographically-distributed data silos to preserve the privacy of the training data. Communication efficiency and fairness are two major issues that need to be both satisfied when federated learning systems are deployed in practice. Simultaneously guaranteeing both of them, however, is exceptionally difficult because simply combining communication reduction and fairness optimization approaches often causes non-converged training or drastic accuracy degradation. Here, to bridge this gap, we propose FedEFsz. On the one hand, it integrates the state-of-the-art error-bounded lossy compressor SZ3 into cross-silo federated learning systems to significantly reduce communication traffic during the training. On the other hand, it achieves a high fairness (i.e., rather consistent model accuracy and performance across different clients) through a carefully designed heuristic algorithm that can tune the error-bound of SZ3 for different clients during the training. Extensive experimental results based on a GPU cluster with 65 GPU cards show that FedEFsz improves the fairness across different benchmarks by up to 60.88% and meanwhile reduces the communication traffic by up to 315×.

Cross-Silo Federated Learning Systems↗

TH-EF-BRB-10: Dosimetric Validation of a Trajectory Based Cranial SRS Treatment Technique On a Varian TrueBeam Linac

Purpose: This work investigates the dosimetric accuracy of a trajectory based delivery technique in which an optimized radiation beam is delivered along a Couch-Gantry trajectory that is formed by simultaneous rotation of the linac gantry and the treatment couch. Methods: Nine trajectory based cranial SRS treatment plans were created using in-house optimization software. The plans were calculated for delivery on the TrueBeam STx linac with 6MV photon beam. Dose optimization was performed along a user-defined trajectory using MLC modulation, dose rate modulation and jaw tracking. The pre-defined trajectory chosen for this study is formed by a couch rotation through its full range of 180 degrees while the gantry makes four partial arc sweeps which are 170 degrees each. For final dose calculation, the trajectory based plans were exported to the Varian Eclipse Treatment Planning System. The plans were calculated on a homogeneous cube phantom measuring 18.2×18.2×18.2 cm3 with the analytical anisotropic algorithm (AAA) using a 1mm3 calculation voxel. The plans were delivered on the TrueBeam linac via the developer’s mode. Point dose measurements were performed on 9 patients with the IBA CC01 mini-chamber with a sensitive volume of 0.01 cc. Gafchromic film measurements along the sagittal and coronal planes were performed on three of the 9 treatment plans. Point dose values were compared with ion chamber measurements. Gamma analysis comparing film measurement and AAA calculations was performed using FilmQA Pro. Results: The AAA calculations and measurements were in good agreement. The point dose difference between AAA and ion chamber measurements were within 2.2%. Gamma analysis test pass rates (2%, 2mm passing criteria) for the Gafchromic film measurements were >95%. Conclusion: We have successfully tested TrueBeam’s ability to deliver accurate trajectory based treatments involving simultaneous gantry and couch rotation with MLC and dose rate modulation along the trajectory.

60 APPLIED LIFE SCIENCES↗

A Comparison of Neuromorphic Classification Tasks

A variety of neural network models and machine learning techniques have arisen over the past decade, and their successes with image classification have been stunning. With other classification tasks, selecting and configuring a neural network solution is not straightforward. In this paper, we evaluate and compare a variety of neural network models, trained by a variety of machine learning techniques, on a variety of classification tasks. While Deep Learning typically exhibits the best classification accuracy, we note the promise of Reservoir Computing, and evolutionary optimization on spiking neural networks. In many cases, these technologies perform as well as, or better than Deep Learning, and the resulting networks are much smaller than their Deep Learning counterparts.

Reynolds, John↗

GDB-9-Ex_EOM-CCSD: Dataset containing Equation of Motion Coupled Cluster (EOM-CCSD) calculations for organic molecules of the GDB-9-Ex dataset.

This dataset contains data-intensive quantum chemical electronic structure calculations for 80,593 organic molecules of the GDB-9-Ex dataset. Calculations were performed using the Equation of Motion Coupled Cluster (EOM-CCSD) first principles method using the ORCA software. It provides UV-vis spectra calculations of molecules with a high level of accuracy. The optical spectra behavior was collected based on the optimized molecular geometries in the DFTB method with 3ob parameters. All calculations utilized the def2-TZVP basis sets with the auxiliary def2/J and def2-TZVP/C basis sets. The similarity-transformed EOM-CCSD method that used domain-based local pair natural orbitals (DLPNO) approximation which constitutes the STEOM-DLPNO-CCSD method was used. This method is based on the STEOM approach and was found to make accurate predictions of transition energies for organic molecules. For the excitation energy calculations, the lowest 50 excitation states were calculated.

AI dataset↗

GDB-9-Ex_TD-DFT-PBE0: Dataset containing Time Dependent Density Functional Theory (TDDFT) calculations for organic molecules of the GDB-9-Ex dataset.

This dataset contains data-intensive quantum chemical electronic structure calculations for 96,766 organic molecules of the GDB-9-Ex dataset. Calculations were performed using the Time Dependent Density Functional Theory (TDDFT) first principles method using the ORCA software. It provides UV-vis spectra calculations of molecules with a high level of accuracy. The optical spectra behavior was collected based on the optimized molecular geometries in the DFTB method with 3ob parameters. All calculations utilized the def2-TZVP basis sets with the auxiliary def2/J and def2-TZVP/C basis sets. The time-dependent density-functional theory (TDDFT) approach with the PBE0 exchange-correlation functional and ORCAs default integration grid was employed. For the excitation energy calculations, the lowest 50 excitation states were calculated.

AI dataset↗

Applying Linear Optics from Closed Orbits Modulation for finding beam-based alignment of harmonic sextupoles

A fast and accurate beam-based alignment (BBA) method for harmonic sextupoles has been devel oped at NSLS-II using Linear Optics from Closed Orbit Modulation (LOCOM). The approach excites the beam with simultaneous sine-wave signals at two fast correctors, chosen with an appropriate phase advance to span the full betatron phase space. This strategy suppresses systematic errors from hysteresis, while additional errors from orbit drift and power-supply calibration are minimized by the short measurement time (a few minutes) and reliance solely on beam-based current-to-field conver sion of the sextupoles, with hysteresis explicitly included. Simulations indicate that Linear Optics from Closed Orbits (LOCO) combined with 0.5 mm local orbit bumps can resolve relative sextupole field offsets (∆k₂) with precision better than 10% of k₂, reflecting to beam-based alignment (BBA) accuracy finer than 50 µm. Moreover, employing machine-learning-optimized local orbit bumps en hances sextupole-induced quadrupole signals in a deterministic manner and maintains orbit stability under large sextupole strength variations (±40%). The proposed method is experimentally validated through proof-of-principle measurements at NSLS-II, demonstrating its potential as a fast, precise, and robust tool for harmonic sextupole alignment.

43 PARTICLE ACCELERATORS↗

Digital Twin Framework for PIP-II Linac: AI-Driven Multi-Scale Modeling from Ion Source to 800 MeV

The PIP-II linac will enable >1.2 MW beam power for DUNE, requiring unprecedented operational reliability across its warm front-end (RFQ, MEBT) and five distinct SRF sections operating at 162.5/325/650 MHz. We present a comprehensive digital twin framework uniquely combining a fully differentiable fast beam transport code with neural network surrogates trained on high-fidelity PIC simulations, capturing space charge and nonlinear dynamics beyond traditional envelope codes while achieving 10⁴ speedup at <1% accuracy. End-to-end differentiability enables gradient-based optimization across 500+ parameters simultaneously previously impossible with conventional tools while the model incorporates static/dynamic errors and serves as a virtual commissioning platform for diverse hardware integration. The framework facilitates reinforcement learning for pulsed/CW mode transitions, predictive maintenance through anomaly detection, and autonomous tuning algorithm development with real-time execution capability. Validation against physics simulations shows excellent agreement for the front-end, with initial results demonstrating potential for 30% commissioning time reduction and proactive fault mitigation, providing a scalable blueprint for operating next-generation high-intensity accelerators.

Pathak, Abhishek [Fermilab] (ORCID:000000021704208↗