Search NASA⌕ Search

SEARCH · Search NASA

Results for “data driven operations”

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 1,153 records · Page 64

Exploring the Use of Novel Spatial Accelerators in Scientific Applications

Driven by the need to find alternative accelerators which can viably replace GPUs in next-generation Supercomputing systems, this paper proposes a methodology to enable agile application/hardware co-design. The application-first methodology provides the ability to come up with design of accelerators while working with real-world workloads, available accelerators, and system software. The iterative design process targets a set of kernels in a workload for performance estimates that can prune the design space for later phases of detailed architectural evaluations. To this effect, in this paper, a novel data-parallel device model is introduced that simulates the latency of performance-sensitive operations in an accelerator including data transfers and kernel computation using multi-core CPUs. The use of off-the-shelf simulators, such as pre-RTL simulator Aladdin or multiple tools available for exploring the design of deep neural network accelerators (e.g., Timeloop) is demonstrated for evaluation of various accelerator designs using applications with realistic inputs. Examples of multiple device configurations that are instantiable in a system are explored to evaluate the performance benefit of deploying novel accelerators. The proposed device is integrated with a programming model and system software to potentially explore the impacts of high-level programming languages/compilers and low-level effects such as task scheduling on multiple accelerators. We analyze our methodology for a set of applications that represent high-performance computing (HPC) and graph analytics. The applications include a computational chemistry kernel realized using tensor contractions, triangle counting, GraphSAGE and Breadth-first Search. These applications include kernels such as dense matrix-dense matrix multiplication, sparse matrix-spare matrix multiplication, and sparse matrix-dense vector multiplication. Our results indicate potential performance benefits and insights for system design by including accelerators that realize these kernels along-side general purpose accelerators.

AI, codesign, Accelerated Computing, Modeling and ↗

Enabling off-highway diesel engine downsizing and performance improvement using electrically assisted turbocharging

Internal combustion engine (ICE) downsizing through various turbocharging configurations is generally known by the powertrain design community as an effective means to reduce frictional losses, increase waste heat recovery, and improve fuel efficiency while increasing engine power density. However, often is the case that turbocharging strategies, including variable geometry turbochargers, and regulated two-stage turbochargers, incur the performance tradeoff between transient response and fuel economy (pumping losses) at high engine speeds. For off-highway vehicles having particularly transient and high-powered duty cycles, efforts to improve this tradeoff and increase operational flexibility have turned to evaluating various electrified air system architectures. In this study, a 4.5 L diesel-ICE configured with an electrically driven compressor (eBooster ® ) is placed in series with a conventional turbocharger and integrated into a 48 V mild-hybrid powertrain architecture. The objective of this powertrain configuration is to enable engine downsizing by 34%, replacing the current 6.8 L ICE platform with the hybridized 4.5 L ICE concept. The commercial 1-D simulation software GT-SUITE is used for powertrain system development and system optimization. Development and validation of the GT-SUITE model and air system controls is concurrently supported through experimental data collection. The simulation model development includes using machine learning methods for optimizing exhaust gas dilution, injection timing, and eBooster ® power to improve steady-state and transient brake-specific fuel consumption while minimizing criteria pollutant emissions. It was found that total specific fluid consumption over the standardized non-road transient engine duty cycle could be reduced by 18% over the current 6.8 L engine by using an optimized eBoosted 4.5 L engine. The hybridized 4.5 L engine concept concurrently showed sufficient transient response capability and nearly an order of magnitude reduction in duty cycle total soot production.

25 ENERGY STORAGE↗

Next Generation H- Ion Sources for the SNS

The U.S. Spallation Neutron Source (SNS) is the leading accelerator-based, pulsed neutron-scattering facility, currently in the process of ramping up neutron production. In order to insure meeting operational requirements as well as providing for future facility beam power upgrades, a multifaceted H{sup -} ion source development program is ongoing. This work discusses several aspects of this program, specifically the design and first beam measurements of an RF-driven, external antenna H{sup -} ion source based on an AlN ceramic plasma chamber, elemental and chromate Cs-systems, and plasma ignition gun. Unanalyzed beam currents of up to {approx}100 mA (60Hz, 1ms) have been observed and sustained currents >60 mA (60Hz, 1ms) have been demonstrated on the test stand. Accelerated beam currents of {approx}40 mA have also been demonstrated into the SNS front end. Data are also presented describing the first H{sup -} beam extraction experiments from a helicon plasma generator based on the Variable Specific Impulse Magnetoplasma Rocket (VASIMR) engine design.

33 ADVANCED PROPULSION SYSTEMS↗

Verification of RESRAD-RDD. (Version 2.01)

In this report, the results generated by RESRAD-RDD version 2.01 are compared with those produced by RESRAD-RDD version 1.7 for different scenarios with different sets of input parameters. RESRAD-RDD version 1.7 is spreadsheet-driven, performing calculations with Microsoft Excel spreadsheets. RESRAD-RDD version 2.01 revamped version 1.7 by using command-driven programs designed with Visual Basic.NET to direct calculations with data saved in Microsoft Access database, and re-facing the graphical user interface (GUI) to provide more flexibility and choices in guideline derivation. Because version 1.7 and version 2.01 perform the same calculations, the comparison of their results serves as verification of both versions. The verification covered calculation results for 11 radionuclides included in both versions: Am-241, Cf-252, Cm-244, Co-60, Cs-137, Ir-192, Po-210, Pu-238, Pu-239, Ra-226, and Sr-90. At first, all nuclide-specific data used in both versions were compared to ensure that they are identical. Then generic operational guidelines and measurement-based radiation doses or stay times associated with a specific operational guideline group were calculated with both versions using different sets of input parameters, and the results obtained with the same set of input parameters were compared. A total of 12 sets of input parameters were used for the verification, and the comparison was performed for each operational guideline group, from A to G, sequentially. The verification shows that RESRAD-RDD version 1.7 and RESRAD-RDD version 2.01 generate almost identical results; the slight differences could be attributed to differences in numerical precision with Microsoft Excel and Visual Basic.NET. RESRAD-RDD version 2.01 allows the selection of different units for use in reporting calculation results. The results of SI units were obtained and compared with the base results (in traditional units) used for comparison with version 1.7. The comparison shows that RESRAD-RDD version 2.01 correctly reports calculation results in the unit specified in the GUI.

54 ENVIRONMENTAL SCIENCES↗

2022 Summer Resource Adequacy in the ERCOT Region

This report is a 2022 update to the National Energy Technology Laboratory (NETL) report that examined the potential system performance of the Electric Reliability Council of Texas (ERCOT) system during the summer of 2021. Anticipated summer reserve margins in ERCOT have risen year-over-year from the 15.7 percent reported in ERCOT’s Final Seasonal Assessment of Resource Adequacy (SARA) for Summer 2021 to 22.8 percent in the Final SARA for Summer 2022, driven mostly by increases in wind and solar generation. Using data from ERCOT’s 2022 Summer SARA, Capacity, Demand and Reserves (CDR) reports, and historical performance data obtained from ERCOT and Hitachi Energy Velocity Suite, six economic dispatch scenarios using PROMOD were developed to assess the risk to ERCOT of a load shedding event for Summer 2022. The results suggests that ERCOT may be facing a very tight resource adequacy situation, with the potential for a serious shortfall during the summer peak, usually the end of July through mid-August, if demand and generator outage rates significantly exceed peak levels. Under these conditions, ERCOT will need to call on its operating tools, including Energy Emergency Alerts (EEA) and calls to conserve electricity, to maintain reliability and continue serving load. Those measures alone may not be sufficient to avert a shedding of load.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Off-Angle Iris Correction Methods

In many real world iris recognition systems obtaining consistent frontal images is problematic do to inexperienced or uncooperative users, untrained operators, or distracting environments. As a result many collected images are unusable by modern iris matchers. In this chapter we present four methods for correcting off-angle iris images to appear frontal which makes them compatible with existing iris matchers. The methods include an affine correction, a retraced model of the human eye, measured displacements, and a genetic algorithm optimized correction. The affine correction represents a simple way to create an iris image that appears frontal but it does not account for refractive distortions of the cornea. The other method account for refraction. The retraced model simulates the optical properties of the cornea. The other two methods are data driven. The first uses optical flow to measure the displacements of the iris texture when compared to frontal images of the same subject. The second uses a genetic algorithm to learn a mapping that optimizes the Hamming Distance scores between off-angle and frontal images. In this paper we hypothesize that the biological model presented in our earlier work does not adequately account for all variations in eye anatomy and therefore the two data-driven approaches should yield better performance. Results are presented using the commercial VeriEye matcher that show that the genetic algorithm method clearly improves over prior work and makes iris recognition possible up to 50 degrees off-angle.

iris recognition↗

Process prediction and detection of faults using probabilistic bidirectional recurrent neural networks on real plant data

Attaining Industry 4.0 for manufacturing operations requires advanced monitoring systems and real-time data analytics of plant data, among other topics. We propose a Probabilistic Bidirectional Recurrent Network (PBRN) for industrial process monitoring for the early detection of faults. The model is based on a Gated Recurrent Unit (GRU) neural network that allows the model to retain long-term dependencies between sensor data along a time horizon, hence learning the dynamic behavior of the process. To reduce the false-positive detection rate of the model, we compel the model to learn from a highly noisy sensor reading while outputting noise-free sensor outputs. The performance of the proposed model is compared to other data-driven statistical process monitoring schemes using real plant data from an industrial Air Separations Unit (ASU) containing noisy sensor readings. We show that the model can learn from noisy data without reducing its performance. Using two different fault cases, we demonstrate the model’s ability to carry out early fault detection with average false-positive rates of 2.9% and 4.9% for both fault cases. The missed detection rates are 0.1% and 0.2%, respectively.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Experimental results of a magnetically coupled piezoelectric actuator to relieve microchannel heat exchanger maldistribution

Refrigerant maldistribution is a common issue in microchannel heat exchangers. Refrigerant maldistribution can have significant negative effects on the heat transfer performance and increase the pressure drop, leading to increased superheat temperature at the outlet and increased compressor work, lowering system efficiency. In this work, a novel piezoelectric-driven magnetic actuator (PEDMA) was fabricated and inserted into the inlet header of the microchannel evaporator, with the goal of improving the non-uniformity of the flow distribution by regulating the flow in the header to the microchannels. Two prototype PEDMA designs were tested and showed significant impact on the refrigerant flow in the region of actuation. In the first design, the experimental data showed superheat reductions up to 9 °C when the individual channel temperatures were measured. The second design redistributed the refrigerant such that a 1% increase in capacity was calculated for the whole heat exchanger without significantly impacting the heating efficiency. The experimental results demonstrate the successful operation of the PEDMA devices and represent a new method of active flow distribution control which is based on a simple design with minimal additional energy consumption, and which can be inserted into microchannel heat exchanger headers to potentially relieve the refrigerant maldistribution.

42 ENGINEERING↗

Next Generation H{sup -} Ion Sources for the SNS

The U.S. Spallation Neutron Source (SNS) is the leading accelerator-based, pulsed neutron-scattering facility, currently in the process of ramping up neutron production. In order to insure meeting operational requirements as well as providing for future facility beam power upgrades, a multifaceted H- ion source development program is ongoing. This work discusses several aspects of this program, specifically the design and first beam measurements of an RF-driven, external antenna H- ion source based on an A1N ceramic plasma chamber, elemental and chromate Cs-systems, and plasma ignition gun. Unanalyzed beam currents of up to {approx}100 mA(60 Hz, 1 ms) have been observed and sustained currents >60 mA(60 Hz, 1 ms) have been demonstrated on the test stand. Accelerated beam currents of {approx}40 mA have also been demonstrated into the SNS front end. Data are also presented describing the first H- beam extraction experiments from a helicon plasma generator based on the Variable Specific Impulse Magnetoplasma Rocket (VASIMR) engine design.

43 PARTICLE ACCELERATORS↗

Toward fusion plasma scenario planning for NSTX-U using machine-learning-accelerated models

One of the most promising devices for realizing power production through nuclear fusion is the tokamak. To maximize performance, it is preferable that tokamak reactors achieve advanced operating scenarios characterized by good plasma confinement, improved magnetohydrodynamic (MHD) stability, and a largely non-inductively driven plasma current. Such scenarios could enable steady-state reactor operation with high \emph{fusion gain} --- the ratio of produced fusion power to the external power provided through the plasma boundary. Precise and robust control of the evolution of the plasma boundary shape as well as the spatial distribution of the plasma current, density, temperature, and rotation will be essential to achieving and maintaining such scenarios. The complexity of the evolution of tokamak plasmas, arising due to nonlinearities and coupling between various parameters, motivates the use of model-based control algorithms that can account for the system dynamics. In this work, a learning-based accelerated model trained on data from the National Spherical Torus Experiment Upgrade (NSTX-U) is employed to develop planning and control strategies for regulating the density and temperature profile evolution around desired trajectories. The proposed model combines empirical scaling laws developed across multiple devices with neural networks trained on empirical data from NSTX-U and a database of first-principles-based computationally intensive simulations. The reduced execution time of the accelerated model will enable practical application of optimization algorithms and reinforcement learning approaches for scenario planning and control development. An initial demonstration of applying optimization approaches to the learning-based model is presented, including a strategy for mitigating the effect of leaving the finite validity range of the accelerated model. The approach shows promise for actuator planning between experiments and in real-time.

machine learning↗

A Study on Co-existing Heterogeneous Wireless Networks for Data Transmission within a Nuclear Facility

Deployment of wireless technologies is a salient need for modernization, automation and improved operation of nuclear power plants (NPPs). As a single technology cannot support the ever-changing needs, it is required to have a heterogeneous wireless network architecture to address the different technical and economic challenges. However, the coexistence of these multiband heterogeneous wireless networks brings numerous challenges due to the factors including dissimilarity in their channel access mechanism, distance between nodes, transmit power level and many more. This paper develops real-world experiments and simulations of wireless coexistence for Wi-Fi, Fifth generation cellular (5G) and Zigbee in the unlicensed band to understand the challenges and opportunities. The experiments were conducted over the Platform for Open Wireless Data-driven Experimental Research (POWDER) testbed at the university of Utah. In addition, this paper is the first to propose a novel packet rate control technique at the network layer to create temporary opportunities for 5G or Zigbee signal transmissions focusing its application in a nuclear facility while using the shared band. The performance of the proposed coexistence solution is validated with experimental results and simulation.

5G↗

Neural chaos: A spectral stochastic neural operator

Building surrogate models for operators with uncertainty quantification capabilities is essential for many engineering applications where randomness–such as variability in material properties, boundary conditions, and initial conditions–is unavoidable. Polynomial Chaos Expansion (PCE) is widely recognized as a go-to method for constructing stochastic surrogates in both intrusive and non-intrusive ways, and it has recently been used in the context of operator learning. However, its application becomes challenging for complex or high-dimensional processes, as achieving accuracy requires higher-order polynomials, which can increase computational demand and/or the risk of overfitting. Furthermore, PCE requires specialized treatments to manage random variables that are not independent, and these treatments may be problem-dependent or may fail with increasing complexity. Here, in this work, we adopt the same formalism as the spectral expansion used in PCE; however, we replace the classical polynomial basis functions with neural network (NN) basis functions to leverage their expressivity. To achieve this, we propose an algorithm that identifies NN-parameterized basis functions in a purely data-driven manner, without any prior assumptions about the joint distribution of the random variables involved, whether independent or dependent, or about their marginal distributions. The proposed algorithm identifies each NN-parameterized basis function sequentially, ensuring they are orthogonal with respect to the data distribution. The basis functions are constructed directly on the joint stochastic variables without requiring a tensor product structure or assuming independence of the random variables. This approach may offer greater flexibility for complex stochastic models, while simplifying implementation compared to the tensor product structures typically used in PCE to handle random vectors. This is particularly advantageous given the current state of open-source packages, where building and training neural networks can be done with just a few lines of code and extensive community support. We demonstrate the effectiveness of the proposed scheme through several numerical examples of varying complexity and provide comparisons with classical PCE.

Polynomial chaos expansion↗

Development of Solenoid-Driven and Pneumatic Punches for Launching High- Z Cryogenic Pellets for Tokamak Disruption Mitigation Experiments

Mitigation of disruption events in future high energy density tokamaks is essential for machine longevity. The creation of runaway electrons, large electromagnetic forces, and high localized heat loads during a disruption can be devastating to machine components. Shattered pellet injection is currently the most effective method of disruption mitigation. Injection of cryogenically solidified deuterium, neon, or argon (or mixtures thereof) have been shown to efficiently radiate thermal energy of the plasma so that the heat load is distributed on the walls of the machine. Pellets are formed by desublimating gas in the barrel of a pipe gun and fired using a pulse of high-pressure light gas. Current gas gun designs cannot reach sufficient pressure to dislodge pure neon and argon pellets at low temperatures because the material strength is too high. Pellet temperatures must be kept low (to well below the triple-point temperature of the material) to ensure minimal gas flow into the machine due to vapor pressure of the pellet. A gas-driven punch device has been designed and tested to dislodge pure neon or argon pellets. The breakaway strength of a pellet is proportional to the surface area of the pellet in contact with the inner diameter of the barrel. As pellets get larger in diameter, the amount of force needed to dislodge them increases. To better understand the mechanics behind how a punch dislodges a pellet, a solenoid-operated punch was designed so that kinetic energy of the punch, when striking a pellet, can be varied by changing input current to the solenoid. This solenoid punch will be used to determine kinetic energy versus pellet surface area threshold for breakaway. These data will be used to design mechanical punches for use in a high-field tokamak environment. Furthermore, this paper outlines the modeling, design, experimental testing, and results of the punch development activities.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

The NO v A simulation chain

The NO v A experiment is a two-detector, long-baseline neutrino experiment operating in the recently upgraded NuMI muon neutrino beam. Simulating neutrino interactions and backgrounds requires many steps including: the simulation of the neutrino beam flux using FLUKA and the FLUGG interface, cosmic ray generation using CRY, neutrino interaction modeling using GENIE, and a simulation of the energy deposited in the detector using GEANT4. To shorten generation time, the modeling of detector-specific aspects, such as photon transport, detector and electronics noise, and readout electronics, employs custom, parameterized simulation applications. We will describe the NO v A simulation chain, and present details on the techniques used in modeling photon transport near the ends of cells, and in developing a novel data-driven noise simulation. Due to the high intensity of the NuMI beam, the Near Detector samples a high rate of muons originating in the surrounding rock. In addition, due to its location on the surface at Ash River, MN, the Far Detector collects a large rate ((˜) 140 kHz) of cosmic muons. Furthermore, we will discuss the methods used in NO v A for overlaying rock muons and cosmic ray muons with simulated neutrino interactions and show how realistically the final simulation reproduces the preliminary NO v A data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Online Model-Free DER Dispatch Via Adaptive Voltage Sensitivity Estimation and Chance Constrained Programming

This paper proposes an online data-driven distributed energy resource management system (DERMS) for distribution system optimal DER dispatch as well as voltage regulation. Here, the key innovation is to leverage the Local Sensitivity Factor (LSF) for transforming the DER control into a computationally efficient linear programming (LP) problem. By taking real-time measurements, the estimation of LSF eliminates the need for an accurate distribution system model as well as full nodal load information, which is difficult to achieve in practice. A robust recursive least squares method is also developed to ensure the robust estimation of LSF, which is initialized using reasonable values from model-derived LSFs. This allows the system to adapt to changing operational conditions effectively. A scenario-based, chance-constrained framework is further employed to ensure voltage remains within acceptable limits in the presence of measurement and estimation uncertainties. Test results on a real-world, 759-node distribution network located in western Colorado, U.S., validate the effectiveness and robustness of the proposed control approach and demonstrate its superior performance as compared to alternative methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Dominant Controls of Downdip Afterslip and Viscous Relaxation on the Postseismic Displacements Following the M w 7.9 Gorkha, Nepal, Earthquake

Here, we analyze three-dimensional GPS coordinate time series from continuously operating stations in Nepal and South Tibet and calculate the initial 1 year postseismic displacements. We first investigate models of poroelastic rebound, afterslip, and viscoelastic relaxation individually and then attempt to resolve the trade-offs between their contributions by evaluating the misfit between observed and simulated displacements. We compare kinematic inversions for distributed afterslip with stress-driven afterslip models. The modeling results show that no single mechanism satisfactorily explains near- and far-field postseismic deformation following the Gorkha earthquake. When considering contributions from all three mechanisms, we favor a combination of viscoelastic relaxation and afterslip alone, as poroelastic rebound always worsens the misfit. The combined model does not improve the data misfit significantly, but the inverted afterslip distribution is more physically plausible. The inverted afterslip favors slip within the brittle-ductile transition zone downdip of the coseismic rupture and fills the small gap between the mainshock and largest aftershock slip zone, releasing only 7% of the coseismic moment. Our preferred model also illuminates the laterally heterogeneous rheological structure between India and the South Tibet. The transient and steady state viscosities of the upper mantle beneath Tibet are constrained to be greater than 10 18 Pa s and 10 19 Pa s, whereas the Indian upper mantle has a high viscosity ≥10 20 Pa s. The viscosity in the lower crust of southern Tibet shows a clear trade-off with its southward extent and thickness, suggesting an upper bound value of ~8 × 10 19 Pa s for its steady state viscosity.

58 GEOSCIENCES↗

Ultrafast Molecular Frame Quantum Tomography

Here, we develop and experimentally demonstrate a methodology for a full molecular frame quantum tomography (MFQT) of dynamical polyatomic systems. We exemplify this approach through the complete characterization of an electronically nonadiabatic wave packet in ammonia (NH 3 ). The method exploits both energy and time-domain spectroscopic data, and yields the lab frame density matrix (LFDM) for the system, the elements of which are populations and coherences. The LFDM fully characterizes electronic and nuclear dynamics in the molecular frame, yielding the time- and orientation-angle dependent expectation values of any relevant operator. For example, the time-dependent molecular frame electronic probability density may be constructed, yielding information on electronic dynamics in the molecular frame. In NH 3 , we observe that electronic coherences are induced by nuclear dynamics which nonadiabatically drive electronic motions (charge migration) in the molecular frame. Here, the nuclear dynamics are rotational and it is nonadiabatic Coriolis coupling which drives the coherences. Interestingly, the nuclear-driven electronic coherence is preserved over longer timescales. In general, MFQT can help quantify entanglement between electronic and nuclear degrees of freedom, and provide new routes to the study of ultrafast molecular dynamics, charge migration, quantum information processing, and optimal control schemes.

74 ATOMIC AND MOLECULAR PHYSICS↗

ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads

The Message Passing Interface (MPI) standard plays a crucial role in enabling scientific applications for parallel computing and is an essential component in high-performance computing (HPC). However, implementing MPI code manually—especially applying a proper domain decomposition and communication pattern—is a challenging and error-prone task. We present ChatMPI, an AI assistant for MPI parallelization of sequential C codes. In our analysis, we focus on testing six essential HPC workloads, which are based on Basic Linear Algebra Subprograms levels 1, 2, and 3 as well as sparse, stencil, and iterative operations. We analyze the process of creating ChatMPI by using the ChatHPC library. This lightweight large language model (LLM)–based infrastructure enables HPC experts to efficiently create and supervise trustworthy AI capabilities for critical HPC software tasks. We study the data required for training (fine-tuning) ChatMPI to generate parallel codes that not only use MPI syntax correctly but also apply HPC techniques to reduce memory communication and maximize performance by using proper work decomposition. With a relatively small training dataset composed of a few dozen prompts and fewer than 15 minutes of fine-tuning on one node equipped with two NVIDIA H100 GPUs, ChatMPI elevates trustworthiness for MPI code generation of current LLMs (e.g., Code Llama, ChatGPT-4o and ChatGPT 5). Additionally, we evaluate the performance of the MPI codes generated by ChatMPI in comparison with the ones generated by ChatGPT-4o and ChatGPT-5. The codes generated by ChatMPI provide up to a 4 × boost in performance by using better problem decomposition, communication patterns, and HPC techniques (e.g., communication avoiding).

Valero Lara, Pedro [ORNL] (ORCID:0000000214794310)↗