Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “scalable performance”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,531 records · Page 85
All sourcesNASA NTRSDOE OSTI
NASA NTRS2015

Overview and Accomplishments of Advanced Mirror Technology Development Phase 2 (AMTD-2) Project

The Advance Mirror Technology Development (AMTD) project is in Phase 2 of a multiyear effort, initiated in FY12, to mature by at least a half TRL step critical technologies required to enable 4 meter or larger UVOIR space telescope primary mirror assemblies for both general astrophysics and ultra-high contrast observations of exoplanets. AMTD Phase 1 completed all of its goals and accomplished all of its milestones. AMTD Phase 2 started in 2014. Key accomplishments include deriving primary mirror engineering specifications from science requirements; developing integrated modeling tools and using those tools to perform parametric design trades; and demonstrating new mirror technologies via sub-scale fabrication and test. AMTD-1 demonstrated the stacked core technique by making a 43-cm diameter 400 mm thick 'biscuit-cut' of a 4-m class mirror. AMTD-2 is demonstrating lateral scalability of the stacked core method by making a 1.5 meter 1/3rd scale model of a 4-m class mirror.

Space Telescope Mirrors↗
NASA NTRS2017

Development and Testing of a Novel Green Propellant Piston Tank

Analytical Mechanics Associates (AMA), in cooperation with NASA Marshall Space Flight Center's (MSFC's) Spacecraft Propulsion Systems Branch, developed and tested a novel propellant tank design that employs an internal piston pressurized with an inert gas to expel propellant to thrusters. During the course of this activity, AMA designed, oversaw fabrication, and delivered to MSFC for testing, a piston propellant tank sized for 3U or larger CubeSats. MSFC conducted liquid expulsion testing using ethylene glycol as a referee fluid to map the tank's performance at different pressures and piston positions. Following the expulsion test campaign, the tank is planned to be integrated into a propulsion system test bed for hot fire tests with a 100mN monopropellant thruster to evaluate the tank's influence on thruster performance when operated in a flight like manner. Described in this paper is a comprehensive summary of how the tanks were designed, built, and tested. The fundamental knowledge gained through the fabrication and testing of these tanks gives evidence that the piston tank design may be scalable to meet the requirements and constraints of other small satellites.

Diaz, C. E.↗
NASA NTRSDate not supplied

Robotic Manipulation Testbeds with HPSC

Interoperability and scalability of robotic manipulators will be key to develop and sustain a lunar surface and cislunar ecosystem. From in-space servicing, assembly, and manufacturing (ISAM) to logistics, maintenance, and science operations, robotic manipulation is a critical NASA capability need and the demand for high-performance spaceflight computing will only rise as robotic tasks become more autonomous. With increased complexity, testbeds for research, feasibility studies, and technology demonstrations will be essential. The Dexterous Robotics Team at NASA Johnson Space Center has established multiple robotic manipulation testbeds taking a supervised autonomous remote operations approach and plans to infuse High-Performance Spaceflight Computing (HPSC) to emulate the flight environment and close the gap between space technology development and flight operations.

Alex Sowell↗
DOE OSTI2025

A Machine Learning Approach for Hourly Traffic Prediction Used in EV-Charging Sites

Reliable forecasting of hourly traffic volumes on highways is critical for planning and operating electric-vehicle charging infrastructure without overloading the grid. In this work, we develop and evaluate a station-specific machine-learning approach based on NeuralProphet, enhanced with conditional seasonality to better distinguish weekday, weekend, and holiday patterns. For each station, the model automatically retrieves the same calendar day from the prior years as an AR-Net initialization, fits trend and Fourier-based seasonality components, and then applies short-term auto-regressive corrections. We train and test on 2021 and 2022 TMAS data, respectively, and validate performance over the whole year. We chose to demonstrate how the model performs on a typical weekday (3/15/2022), weekend (3/27/2022), and a special holiday (12/25/2022). Our results yield MAPE of 7.4%, 23.6%, and 32.0%, respectively. Over the entire year 2022, the overall MAPE was 17%. This demonstrates that station-specific models with conditional seasonality can achieve accurate, scalable hourly forecasts for EV-charging load planning.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Scalable Bayesian optimization with randomized prior networks

Several fundamental problems in science and engineering consist of global optimization tasks involving unknown high-dimensional (black-box) functions that map a set of controllable variables to the outcomes of an expensive experiment. Bayesian Optimization (BO) techniques are known to be effective in tackling global optimization problems using a relatively small number objective function evaluations, but their performance suffers when dealing with high-dimensional outputs. To overcome the major challenge of dimensionality, here we propose a deep learning framework for BO and sequential decision making based on bootstrapped ensembles of neural architectures with randomized priors. Using appropriate architecture choices, we show that the proposed framework can approximate functional relationships between design variables and quantities of interest, even in cases where the latter take values in high-dimensional vector spaces or even infinite-dimensional function spaces. In the context of BO, we augmented the proposed probabilistic surrogates with re-parameterized Monte Carlo approximations of multiple-point (parallel) acquisition functions, as well as methodological extensions for accommodating black-box constraints and multi-fidelity information sources. We test the proposed framework against state-of-the-art methods for BO and demonstrate superior performance across several challenging tasks with high-dimensional outputs, including a constrained multi-fidelity optimization task involving shape optimization of rotor blades in turbo-machinery.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Data-Driven Scalable Emulation of Hydropower Using Real-Time Hardware-in-the-Loop

This presentation covers Motivation: (1) With the increased grid integration of inverter-based resources, hydropower plays a crucial role in maintaining the bulk power system reliability and resilience; and (2) A more dynamic response and new control designs are required to meet the grid requirements. To evaluate any modification, control-prototyping, performance validation and de-risking grid integration of hydropower, a high-fidelity environment is required. Also covers Objectives: (1) To develop data-driven emulation of hydropower using hardware-in-the-loop for different size, types of hydro plants; and (2) To characterize hardware and obtain accurate dynamic response for shaft speed, torque, and power. Provide a mechanical power interface with emulated dynamics of a hydro-turbine shaft that can be coupled to electrical generators for mechanical and electrical PHIL.

electrical↗
DOE OSTI2024

How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits

In the span of four decades, quantum computation has evolved from an intellectual curiosity to a potentially realizable technology. Today, small-scale demonstrations have become possible for quantum algorithmic primitives on hundreds of physical qubits and proof-of-principle error-correction on a single logical qubit. Nevertheless, despite significant progress and excitement, the path toward a full-stack scalable technology is largely unknown. There are significant outstanding quantum hardware, fabrication, software architecture, and algorithmic challenges that are either unresolved or overlooked. These issues could seriously undermine the arrival of utility-scale quantum computers for the foreseeable future. Here, we provide a comprehensive review of these scaling challenges. We show how the road to scaling could be paved by adopting existing semiconductor technology to build much higher-quality qubits, employing system engineering approaches, and performing distributed quantum computation within heterogeneous high-performance computing infrastructures. These opportunities for research and development could unlock certain promising applications, in particular, efficient quantum simulation/learning of quantum data generated by natural or engineered quantum systems. To estimate the true cost of such promises, we provide a detailed resource and sensitivity analysis for classically hard quantum chemistry calculations on surface-code error-corrected quantum computers given current, target, and desired hardware specifications based on superconducting qubits, accounting for a realistic distribution of errors. Furthermore, we argue that, to tackle industry-scale classical optimization and machine learning problems in a cost-effective manner, heterogeneous quantum-probabilistic computing with custom-designed accelerators should be considered as a complementary path toward scalability.

Mohseni, Masoud↗
NASA NTRS2015

Ethernet for Aerospace Applications - Ethernet Heads for the Skies

One of the goals of aerospace applications is to reduce the cost and complexity of avionic systems. Ethernet is a highly scalable, flexible, and popular protocol. The aerospace market is large, with a forecasted production of over 50,000 turbine-powered aircraft valued at $1.7 trillion between 2012 and 2022. Boeing estimates demand for commercial aircraft by 2033 to total over 36,000 with a value of over $5 trillion. In 2014 US airlines served over 750 million passengers and this is growing over 2% yearly. Electronic fly-by-wire is now used for all airliners and high performance aircraft. Although Ethernet has been widely used for four decades, its use in aerospace applications is just beginning to become common. Ethernet is the universal solution in commercial networks because of its high bandwidths, lower cost, openness, reliability, maintainability, flexibility, and interoperability. However, when Ethernet was designed applications with time-critical, safety relevant and deterministic requirements were not given much consideration. Many aerospace applications use a variety of communication architectures that add cost and complexity. Some of them are SpaceWire, MIL-STD-1553, Avionics Full Duplex Switched Ethernet (AFDX), and Time-Triggered Ethernet (TTE). Aerospace network designers desire to decrease the number of networks to reduce cost and effort while improving scalability, flexibility, openness, maintainability, and reliability. AFDX and TTE are being considered more for critical aerospace systems because they provide redundancy, failover protection, guaranteed timing, and frame priority and are based on Ethernet IEEE 802.3. This paper explores the use of AFDX and TTE for aerospace applications.

Ethernet↗
DOE OSTI2022

Standardized excitable elements for scalable engineering of far-from-equilibrium chemical networks

Engineered far-from-equilibrium synthetic chemical networks that pulse or switch states in response to environmental signals could precisely regulate the kinetics of chemical synthesis or self-assembly. Currently, such networks must be extensively tuned to compensate for the different activities of and unintended reactions between a network’s various chemical components. Modular elements with standardized performance could be used to rapidly construct networks with designed functions. Here we develop standardized excitable chemical regulatory elements, termed genelets, and use them to construct complex in vitro transcriptional networks. We develop a protocol for identifying >15 interchangeable genelet elements with uniform performance and minimal crosstalk. Furthermore, these elements can be combined to engineer feedforward and feedback modules whose dynamics match those predicted by a simple kinetic model. Modules can then be rationally integrated and organized into networks that produce tunable temporal pulses and act as multistate switchable memories. Standardized genelet elements, and the workflow to identify more, should make engineering complex far-from-equilibrium chemical dynamics routine.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation?: A case study of four watersheds with different hydro-climatic regions across the CONUS

With recent developments in computational techniques, Data-driven Machine Learning Models (DMLs) have shown great potential in simulating streamflow and capturing the rainfall-runoff relationship in given watersheds, which are traditionally fulfilled by Process-based Hydrologic Models (PHMs). There are debates on whether the DMLs can outperform and possibly replace the classical PHMs for streamflow simulation and river forecasting, but no clear conclusions have been made. This study aims to investigate whether the newer DMLs have any potential in further improving the simulation accuracy of classical PHMs, and vice versa. To do this, we compared a few popular PHMs and DMLs over four watersheds across the Continental US (CONUS) that are associated with different input, climate, and regional conditions. A total of five hydrologic models were chosen, including (1) two classical lumped models, i.e., the Sacramento Soil Moisture Accounting (SAC-SMA) and Xinanjiang (XAJ); (2) one modern distributed model, termed Coupled Routing and Excess Storage (CREST); (3) and two DMLs including an Artificial Neural Networks (ANN) and a deep learning model, termed Long Short Term Memory (LSTM). Our results demonstrated that the DMLs still significantly biased when using the baseline input scenario with the PHMs. However, the DMLs fed with delayed input scenarios had great potential and can reach high simulation accuracy. The DMLs, especially the ANN, outperformed other employed models under the rainfall-runoff relationship in which rainfall dominantly drives. Furthermore, the DMLs also showed better performance in the high-flow regime, while the PHMs had a better performance for the low-flow regime, implying both PHMs and DMLs have their own merits and are worthy of joint development. In general, our study indicated a great potential of using DMLs to simulate streamflow, but further studies are still needed to verify the transferability and scalability of DMLs in large-scale experiments, such as the Distributed Model Intercomparison Projects 1&2 conducted by National Weather Services but to compare modern DMLs and PHMs.

58 GEOSCIENCES↗
DOE OSTI2023

Titanium porous-transport layers for PEM water electrolysis prepared by tape casting

While the porous-transport layer (PTL) is a key component in PEM electrolyzers, it is one of the most underexplored due to limited available structures. In this work, we present a novel PTL design for PEM water electrolyzers enabled by a cost-effective, scalable tape-casting technique. Here, a precise control of the PTL pore structure is achieved by incorporating poreformers of various sizes, and by varying the titanium and poreformer ratio. The structures are characterized with SEM and synchrotron X-ray computed tomography imaging techniques. Comprehensive electrochemical performance analysis demonstrates that higher titanium loading provides improved contact at the catalyst-layer/PTL interface but suffers from severe mass-transport losses due to gas bubbles. We solve this mass-transport problem by mixing in large poreformer beads that produce a highly porous structure with excellent gas removal properties yet still maintaining mechanical integrity. The PTL fabricated with 60:40 Ti:PMMA ratio and 60 μm PMMA bead size outperformed the standard commercial Ti powder-based PTL by 62 mV at 4 A/cm 2 .

25 ENERGY STORAGE↗
DOE OSTI2021

Ultralow Voltage GaN Vacuum Nanodiodes in Air

The III-nitride semiconductors have many attractive properties for field-emission vacuum electronics, including high thermal and chemical stability, low electron affinity, and high breakdown fields. In this work, we report top-down fabricated gallium nitride (GaN)-based nanoscale vacuum electron diodes operable in air, with record ultralow turn-on voltages down to ~0.24 V and stable high field-emission currents, tested up to several microamps for single-emitter devices. We leverage a scalable, top-down GaN nanofabrication method leading to damage-free and smooth surfaces. Gap-dependent and pressure-dependent studies provide new insights into the design of future, integrated nanogap vacuum electron devices. The results show promise for a new class of high-performance and robust, on-chip, III-nitride-based vacuum nanoelectronics operable in air or reduced vacuum.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2022

Single electrons on solid neon as a solid-state qubit platform

Progress towards the realization of quantum computers requires persistent advances in their constituent building blocks-qubits. Novel qubit platforms that simultaneously embody long coherence, fast operation and large scalability offer compelling advantages in the construction of quantum computers and many other quantum information systems 1-3 . Electrons, ubiquitous elementary particles of non-zero charge, spin and mass, have commonly been perceived as paradigmatic local quantum information carriers. Despite superior controllability and configurability, their practical performance as qubits through either motional or spin states depends critically on their material environment 3-5 . In this work, we report our experimental realization of a qubit platform based on isolated single electrons trapped on an ultraclean solid neon surface in vacuum 6-13 . By integrating an electron trap in a circuit quantum electrodynamics architecture 14-20 , we achieve strong coupling between the motional states of a single electron and a single microwave photon in an on-chip superconducting resonator. Qubit gate operations and dispersive readout are implemented to measure the energy relaxation time T 1 of 15 μs and phase coherence time T 2 over 200 ns. These results indicate that the electron-on-solid-neon qubit already performs near the state of the art for a charge qubit 21 .

36 MATERIALS SCIENCE↗
DOE OSTI2024

Radiatively cooled quantum microwave amplifiers

Superconducting microwave amplifiers are essential for sensitive signal readout in superconducting quantum processors. Typically based on Josephson junctions, these amplifiers require operation at milli-Kelvin temperatures to achieve quantum-limited performance. Here, we demonstrate a quantum microwave amplifier that employs radiative cooling to operate at elevated temperatures and maintain near quantum-limited added noise. This kinetic-inductance-based parametric amplifier, patterned from a single layer of relatively high-Tc NbN thin film, maintains a high gain and meanwhile enables low added noise of 1.3 quanta when operated at 1.5 K. Remarkably, this represents only a 0.2 quanta increase compared to the performance at a base temperature of 0.1 K. Based on our findings, we also discuss the practicality of such an operating scheme for various quantum applications. By uplifting the parametric amplifiers from the mixing chamber without compromising readout efficiency, this work represents an important step toward more scalable microwave quantum technologies.

Physics↗
DOE OSTI2026

Regression Analysis with the Directed Infusion of Data

Integrating artificial intelligence and machine learning tools into industry necessitates large-scale collaborative efforts that ensure the robust and accurate execution of downstream analytics such as time series prediction, uncertainty quantification, grid optimization, and condition monitoring. However, concerns related to data privacy pervade the nuclear industry due to the proprietary nature of its data and the possibility of data leakage. Legacy techniques such as encryption often require the explicit transmission of data to trustworthy parties, thereby inviting data leakage concerns. The ideal collaboration scenario avoids the explicit dissemination of data/code while maintaining experimental fidelity, which is currently accomplished using various techniques such as trusted execution environments, homomorphic encryption, differential privacy, and multimatrix masking. These techniques, however, often necessitate a trade-off between trust, efficiency, and utility. This article extends a previously proposed technique called the directed infusion of data (DIOD) that ensures data privacy, allows for scalable obfuscation, and combats the risk of data leakage without compromising utility. The experiments discussed in this article examine a regression-type scenario using DIOD with the goal of preserving the inferential link between two variables. Using the point-kinetics equations, regression experiments compare the performance of a model trained using the original data to that of a model trained using the obfuscated data, which produced identical results. Our claim is further strengthened by an information theoretic proof and experiment, which showed that the inferential content between variables remains the same after obfuscation, thereby avoiding the required communication of the proprietary data.

47 - OTHER INSTRUMENTATION↗
DOE OSTI2025

Implementation of Advanced Grid Support Functionalities by Smart Operation of Residential Loads with low Cost Converter Interface

This paper investigates a grid-supportive load concept for small-scale residential appliances, focusing on a residential refrigerator. Power consumption is adjusted based on grid conditions to achieve IEEE-1547 grid support functions. Two key aspects are presented: a low-cost refrigerator converter with Lyapunov energy function-based local controllers for speed control, and the impact on a standard microgrid system, demonstrating advanced grid support from the load side. This method enhances grid resilience and reliability and can be extended to other residential loads. The study contributes to efficient and robust grid-supportive load management systems, showing promising performance. This approach has the potential to improve overall grid stability and can be adapted for various types of residential appliances. The modeling and simulations in MATLAB/Simulink and PLECS confirm the feasibility and effectiveness of the proposed solution. Future work will explore real-world implementation and scalability of this concept for broader applications.

grid supportive loads (GSL)↗
DOE OSTI2025

An Efficient Storage-Driven Machine Learning Model for Performance in the Era of Multimodal Scientific Data

Scientific workflows are increasingly relying on machine learning (ML), simulation, and hybrid techniques to predict, understand, and optimize the behavior of complex experiments. High-performance computing has greatly improved researchers’ ability to acquire diverse data modalities in these workflows. Recent studies suggest that the performance of machine learning models can be improved by integrating data from various sources. Unfortunately, these workloads pose unprecedent pressure on the network storage to meet the demands associated with accessing these multimodal data. To mitigate the impact of intensive IO, we propose a solution that utilizes a multi-tier High-Performance Computing (HPC) distributed storage and data processing framework, placing computation where the data resides for better performance. By adopting this project, the scientific community will gain new opportunities to explore multimodal storage-driven possibilities, integrating multiple scientific data sources with advanced streaming frameworks. Additionally, our framework effectively utilizes computing resources and bridges the gaps identified by HPC experts. Our proposed approach tackles scalability and persistence challenges by leveraging native persistency, which has posed difficulties in traditional approaches. Furthermore, we seek to enhance fault-tolerance and load-balance of computations by leveraging real-time streaming in diverse scientific computing environments, thereby propelling advanced scientific computing research into the next generation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Layer-Parallel Training of Deep Residual Neural Networks

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.

97 MATHEMATICS AND COMPUTING↗