Search NASA⌕ Search

SEARCH · Search NASA

Results for “network embeddings”

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 91 records · Page 5

Embedding hard physical constraints in neural network coarse-graining of three-dimensional turbulence

In recent years, deep learning approaches have shown much promise in modeling complex systems in the physical sciences. A major challenge in deep learning of partial differential equations is enforcing physical constraints and boundary conditions. In this work, we propose a general framework to directly embed the notion of an incompressible fluid into convolutional neural networks, and apply this to coarse-graining of turbulent flow. These physics-embedded neural networks leverage interpretable strategies from numerical methods and computational fluid dynamics to enforce physical laws and boundary conditions by taking advantage the mathematical properties of the underlying equations. Here, we demonstrate results on three-dimensional fully developed turbulence, showing that this technique drastically improves local conservation of mass, without sacrificing performance according to several other metrics characterizing the fluid flow.

97 MATHEMATICS AND COMPUTING↗

Discontinuities in effective permeability due to fracture percolation

Motivated by a triaxial coreflood experiment with a sample of Utica shale where an abrupt jump in permeability was observed, possibly due to the creation of a percolating fracture network through the sample, we perform numerical simulations based on the experiment to characterize how the effective permeability of otherwise low-permeability porous media depends on fracture formation, connectivity, and the contrast between the fracture and matrix permeabilities. While a change in effective permeability due to fracture formation is expected, the dependence of its magnitude upon the contrast between the matrix permeability and fracture permeability and the fracture network structure is poorly characterized. We use two different high-fidelity fracture network models to characterize how effective permeability changes as percolation occurs. The first is a dynamic two-dimensional fracture propagation model designed to mimic the laboratory settings of the experiment. The second is a static three-dimensional discrete fracture network (DFN) model, whose fracture and network statistics are based on the fractured sample of Utica shale. Once the network connects the inflow and outflow boundaries, the effective permeability increases non-linearly with network density. In most networks considered, a jump in the effective permeability was observed when the embedded fracture network percolated. We characterize how the magnitude of the jump, should it occur, depends on the contrast between the fracture and matrix permeabilities. For small contrasts between the matrix and fracture permeabilities the change is insignificant. However, for larger contrasts, there is a substantial jump whose magnitude depends non-linearly on the difference between matrix and fracture permeabilities. A power-law relationship between the size of the jump and the difference between the matrix and fracture permeabilities is observed. In conclusion, the presented results underscore the importance of fracture network topology on the upscaled properties of the porous medium in which it is embedded.

36 MATERIALS SCIENCE↗

Embedded training of neural-network subgrid-scale turbulence models

We report that the weights of a deep neural-network model are optimized in conjunction with the governing flow equations to provide a model for subgrid-scale stresses in a temporally developing plane turbulent jet at Reynolds number Re 0 = 6000 . The objective function for training is first based on the instantaneous filtered velocity fields from a corresponding direct numerical simulation, and the training is by a stochastic gradient descent method, which uses the adjoint Navier-Stokes equations to provide the end-to-end sensitivities of the model weights to the velocity fields. In-sample and out-of-sample testing on multiple dual-jet configurations show that its required mesh density in each coordinate direction for prediction of mean flow, Reynolds stresses, and spectra is half that needed by the dynamic Smagorinsky model for comparable accuracy. The same neural-network model trained directly to match filtered subgrid-scale stresses, without the constraint of being embedded within the flow equations during the training, fails to provide a qualitatively correct prediction. The coupled formulation is generalized to train based only on mean-flow and Reynolds stresses, which are more readily available in experiments. The mean-flow training provides a robust model, which is important, though a somewhat less accurate prediction for the same coarse meshes, as might be anticipated due to the reduced information available for training in this case. The anticipated advantage of the formulation is that the inclusion of resolved physics in the training increases its capacity to extrapolate. This is assessed for the case of passive scalar transport, for which it outperforms established models due to improved mixing predictions.

42 ENGINEERING↗

Data-Augmented Modeling of Transition to Turbulence in Rayleigh-Taylor Mixing Layers

Existing turbulence models based on the Reynolds-averaged Navier–Stokes (RANS) equations are ill-equipped to represent transitional phenomena that are characteristic of problems such as those involved in Rayleigh-Taylor mixing layers. In this work, large eddy simulation(LES) data is used to augment and improve the predictive capability of RANS models. In-verse models are used to extract temporally varying embedded discrepancy functions from a number of LES datasets. These discrepancies are generalized into functional forms using neural networks and embedded inside the RANS solver to augment predictions. Specifically, the data-augmented models are demonstrated to provide improved predictions in Rayleigh-Taylor mixing problems at low Atwood numbers.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

A Graph Neural Network Surrogate Model for hls4ml

Recent advancements in use of machine learning (ML) techniques on field-programmable gate arrays (FPGAs) have allowed for the implementation of embedded neural networks with extremely low latency. This is invaluable for particle detectors at the Large Hadron Collider, where latency and used area are strictly bounded. The hls4ml framework is a procedure that converts trained ML model software to a synthesis result to can be used on an FPGA. However, running the pipeline is a time-consuming procedure, and there is a strong risk of failure. In particular, it may not be possible to successfully convert a model into a synthesis result, or the resource consumption of the model may exceed the resources of the target FPGA. To aid with this development, we introduce wa-hls4ml, a surrogate model using a graph neural network to emulate the structure of the source models. The goal is to estimate the chance of success and resource consumption of a given model when passed through the hls4ml pipeline, without needing to run the pipeline.

Plotnikov, Dennis↗

Toward an embedded training tool for Deep Space Network operations

There are three issues to consider when building an embedded training system for a task domain involving the operation of complex equipment: (1) how skill is acquired in the task domain; (2) how the training system should be designed to assist in the acquisition of the skill, and more specifically, how an intelligent tutor could aid in learning; and (3) whether it is feasible to incorporate the resulting training system into the operational environment. This paper describes how these issues have been addressed in a prototype training system that was developed for operations in NASA's Deep Space Network (DSN). The first two issues were addressed by building an executable cognitive model of problem solving and skill acquisition of the task domain and then using the model to design an intelligent tutor. The cognitive model was developed in Soar for the DSN's Link Monitor and Control (LMC) system; it led to several insights about learning in the task domain that were used to design an intelligent tutor called REACT that implements a method called 'impasse-driven tutoring'. REACT is one component of the LMC training system, which also includes a communications link simulator and a graphical user interface. A pilot study of the LMC training system indicates that REACT shows promise as an effective way for helping operators to quickly acquire expert skills.

Hill, Randall W., Jr.↗

Toward an Embedded Training Tool for Deep Space Network Operations

There are three issues to consider when building an embedded training system for a task domain involving the operation of complex equipment: (1) how skill is acquired in the task domain; (2) how the training system should be designed to assist in the acquisition of the skill, and more specifically, how an intelligent tutor could aid in learning; and (3) whether it is feasible to incorporate the resulting training system into the operational environment. This paper describes how these issues have been addressed in a prototype training system that was developed for operations in NASA's Deep Space Network (DSN). The first two issues were addressed by building an executable cognitive model of problem solving and skill acquisition of the task domain and then using the model to design an intelligent tutor.

Johnson, W. Lewis↗

Performance Characteristics of the BlueField-2 SmartNIC

High-performance computing (HPC) researchers have long envisioned scenarios where application workflows could be improved through the use of programmable processing elements embedded in the network fabric. Recently, vendors have introduced programmable Smart Network Interface Cards (SmartNICs) that enable computations to be offloaded to the edge of the network. There is great interest in both the HPC and high-performance data analytics (HPDA) communities in understanding the roles these devices may play in the data paths of upcoming systems. This paper focuses on characterizing both the networking and computing aspects of NVIDIA’s new BlueField-2 SmartNIC when used in a 100Gb/s Ethernet environment. For the networking evaluation we conducted multiple transfer experiments between processors located at the host, the SmartNIC, and a remote host. These tests illuminate how much effort is required to saturate the network and help estimate the processing headroom available on the SmartNIC during transfers. For the computing evaluation we used the stress-ng benchmark to compare the BlueField-2 to other servers and place realistic bounds on the types of offload operations that are appropriate for the hardware. Our findings from this work indicate that while the BlueField-2 provides a flexible means of processing data at the network’s edge, great care must be taken to not overwhelm the hardware. While the host can easily saturate the network link, the SmartNIC’s embedded processors may not have enough computing resources to sustain more than half the expected bandwidth when using kernel-space packet processing. From a computational perspective, encryption operations, memory operations under contention, and on-card IPC operations on the SmartNIC perform significantly better than the general-purpose servers used for comparisons in our experiments. Therefore, applications that mainly focus on these operations may be good candidates for offloading to the SmartNIC.

97 MATHEMATICS AND COMPUTING↗

Gemini Scout Control Software

The Gemini Scout Control Software consists of two Windows applications that allow the Gemini Scout vehicle to be controlled by an operator. The Embedded application runs on the vehicle's Gemini Scout Control Software onboard computer and controls the vehicle's various motors and sensors. This application reports the vehicle's status and receives vehicle commands overthe local-area-network. The Embedded applicationalso allows the user to control the vehicle using a USB game-pad connected directly to the vehicle. The Operator Control Unit (OCU) application runs on an external PC and communicates with the vehicle via an Ethernet connection. The OCU application sends commands to and receives data from the Embedded application running on the vehicle. The OCU application also communicates directly with the digital video encoders and radios in order to display video from the vehicle's cameras and the status of the radio link. The OCU application has a graphical user interface (GUI) that displays the vehicle's status and allows the user to change various vehicle settings. Finally, the OCU application receives input from a USB game-pad connected to the PC in order to control the vehicle's functions.

Clinton Hobart, Justin Garretson↗

Enhancing Fault Isolation for Health Monitoring of Electric Aircraft Propulsion by Embedding Failure Mode and Effect Analysis into Bayesian Networks

This paper describes a fault isolation approach for electric powertrains of unmanned aerial vehicles. The approach leverages the combination of failure mode and effect analysis (FMEA) and Bayesian networks, thus introducing depend-ability structures into a diagnostic framework. Faults and failure events from the FMEA are mapped within a Bayesian network, where network edges replicate the links embedded within FMEAs. This framework helps the fault isolation process by identifying the probability of occurrence of specific faults or root causes given evidence observed through sensor signals. The framework is applied to an electric power-train system of a small, rotary-wing unmanned aerial vehicle, demonstrating how a Bayesian network enhanced by FMEA helps disambiguate between root causes of incipient failures, which would otherwise be considered as equally probable.

Fault Isolation↗

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗

Probabilistic Physics-Informed Graph Convolutional Network for Active Distribution System Voltage Prediction

Here this letter proposes a novel data-driven probabilistic physics-informed graph convolutional network (GCN) for active distribution system voltage prediction with PVs and EVs. It leverages both measurements and network topology to accurately and efficiently predict node voltages without the need for an accurate distribution system power flow model. The dropout-enabled Bayesian inference is developed to achieve uncertainty quantification of the voltage prediction. Thanks to the network model embedding, it also has robustness against topology changes, a key difference with existing machine learning-based approaches. Comparison results with other state-of-the-art machine learning methods on a realistic 759-node distribution system demonstrate that the proposed method can achieve better accuracy and robustness under different scenarios.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Deep Analysis Net with Causal Embedding for Coal-fired Power Plant Fault Detection and Diagnosis (DANCE4CFDD)

Fault detection and diagnosis is critical to power plant operation to ensure attaining high reliability while reducing operation cost. As more renewable power is introduced to the power grid, traditional fossil power plants take on the extra burden of excessive load cycling to compensate the generation variability from renewable power. Such load cycling will pose more reliability challenges to power plant operation. There are a number of challenges faced by today’s asset health management system in coal- fired (or gas) power plants: 1) high-dimensional nonlinear interaction among multiple time series measurements; 2) high measurement variance induced by operational conditions/modes; 3) variation among asset types and plant configurations; and 4) a small number of faulty events to learn from. To cope with these challenges, today’s fielded asset health management systems rely heavily on manual efforts from domain experts and hand-crafted features or rules based on domain knowledge. Despite its role in plant reliability, such a practice is costly and hinders its scalability and sustainability, particularly when a plant undergoes modifications. The objective of this project is to develop a novel end-to-end AI learning system that is trainable (i.e., the AI representation of a complex system behavior can be directly learned from properly labeled data) for accurate fault detection and root cause analysis. The ability to create a fault detection model directly from time series could alleviate the efforts associated with today’s asset management solution development. In the course of this project, we have achieved the following: Created an AI model development environment incorporating state-of-the-art neural network architectures for rapid model development and evaluation; Developed novel learning strategies for training of fault detection model; Developed special-purpose neural network architecture embedded with variable association graph aiming for better interpretability; Developed a learning strategy to leverage a small number of faulty events for enhanced fault detection capability; Conducted detailed experimental study based on public benchmark datasets and demonstrated the effectiveness of the proposed solution; and Validated the developed system with data from both a coal-fired plant boiler dynamic simulation model and real-world coal-fired power plant covering multiple asset and fault types. Overall, the project attained a technology readiness level of TRL 5 from TRL 2 at the beginning of the project.

20 FOSSIL-FUELED POWER PLANTS↗

Garnet-rich composite solid electrolytes for dendrite-free, high-rate, solid-state lithium-metal batteries

Composite solid electrolytes (CSEs), which are composed of inorganic fillers and organic polymers, show improved safety and suppressed lithium dendrite growth in Li-metal batteries, as compared to flammable liquid electrolytes. However, the performance of current CSEs is limited by the agglomeration effect, with low content of inorganic Li + -conducting fillers and ineffective Li + transport between the inorganic fillers and the polymer matrix. To address these challenges, a new type of CSE composed of silane-modified Li 6.28 La 3 Al 0.24 Zr 2 O 12 (s@LLAZO) nanofibers and poly(ethylene glycol) diacrylate (PEGDA) is developed. Employment of the silane coupling agent, 3-(trimethoxysilyl)propyl methacrylate, enables the incorporation of a high content of LLAZO nanofibers (up to 70 wt%) with the polymer matrix and results in a well-percolated, three-dimensional LLAZO network fully embedded in the PEGDA matrix. Consequently, the silane coupling agent successfully eliminates the agglomeration effect, which ensures higher ionic conductivity, larger lithium transference number, wider electrochemical stability window, and better cycling stability for s@LLZAO-PEGDA CSEs. Excellent cycling stability and extraordinarily high rate capability (up to 10C) are demonstrated in the all-solid-state Li-metal batteries with LiFePO 4 and high-voltage Li[Ni 1/3 Mn 1/3 Co 1/3 ]O 2 cathodes at ambient temperature. This novel design of CSEs with s@LLAZO nanofibers paves the way for a new generation of improved functioning all-solid-state Li-metal batteries.

25 ENERGY STORAGE↗

PRODeepSyn: predicting anticancer synergistic drug combinations by embedding cell lines with protein–protein interaction network

Abstract Although drug combinations in cancer treatment appear to be a promising therapeutic strategy with respect to monotherapy, it is arduous to discover new synergistic drug combinations due to the combinatorial explosion. Deep learning technology holds immense promise for better prediction of in vitro synergistic drug combinations for certain cell lines. In methods applying such technology, omics data are widely adopted to construct cell line features. However, biological network data are rarely considered yet, which is worthy of in-depth study. In this study, we propose a novel deep learning method, termed PRODeepSyn, for predicting anticancer synergistic drug combinations. By leveraging the Graph Convolutional Network, PRODeepSyn integrates the protein–protein interaction (PPI) network with omics data to construct low-dimensional dense embeddings for cell lines. PRODeepSyn then builds a deep neural network with the Batch Normalization mechanism to predict synergy scores using the cell line embeddings and drug features. PRODeepSyn achieves the lowest root mean square error of 15.08 and the highest Pearson correlation coefficient of 0.75, outperforming two deep learning methods and four machine learning methods. On the classification task, PRODeepSyn achieves an area under the receiver operator characteristics curve of 0.90, an area under the precision–recall curve of 0.63 and a Cohen’s Kappa of 0.53. In the ablation study, we find that using the multi-omics data and the integrated PPI network’s information both can improve the prediction results. Additionally, the case study demonstrates the consistency between PRODeepSyn and previous studies.

Wang, Xiaowen↗

A new ATLAS muon CSC readout system with system on chip technology on ATCA platform

The ATLAS muon Cathode Strip Chamber (CSC) back-end readout system has been upgraded during the LHC 2013-2015 shutdown to be able to handle the higher Level-1 trigger rate of 100 kHz and the higher occupancy at Run 2 luminosity. The readout design is based on the Reconfiguration Cluster Element (RCE) concept for high bandwidth generic DAQ implemented on the ATCA platform. The RCE design is based on the new System on Chip Xilinx Zynq series with a processor-centric architecture with ARM processor embedded in FPGA fabric and high speed I/O resources together with auxiliary memories to form a versatile DAQ building block that can host applications tapping into both software and firmware resources. The Cluster on Board (COB) ATCA carrier hosts RCE mezzanines and an embedded Fulcrum network switch to form an online DAQ processing cluster. More compact firmware solutions on the Zynq for G-link, S-link and TTC allowed the full system of 320 G-links from the 32 chambers to be processed by 6 COBs in one ATCA shelf through software waveform feature extraction to output 32 S-links. Furthermore, the full system was installed in Sept. 2014. We will present the RCE/COB design concept, the firmware and software processing architecture, and the experience from the intense commissioning towards LHC Run 2.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Differentiable, Learnable, Regionalized Process-Based Models With Multiphysical Outputs can Approach State-Of-The-Art Hydrologic Prediction Accuracy

Predictions of hydrologic variables across the entire water cycle have significant value for water resources management as well as downstream applications such as ecosystem and water quality modeling. Recently, purely data-driven deep learning models like long short-term memory (LSTM) showed seemingly insurmountable performance in modeling rainfall runoff and other geoscientific variables, yet they cannot predict untrained physical variables and remain challenging to interpret. Here, we show that differentiable, learnable, process-based models (called δ models here) can approach the performance level of LSTM for the intensively observed variable (streamflow) with regionalized parameterization. We use a simple hydrologic model HBV as the backbone and use embedded neural networks, which can only be trained in a differentiable programming framework, to parameterize, enhance, or replace the process-based model's modules. Without using an ensemble or post-processor, δ models can obtain a median Nash-Sutcliffe efficiency of 0.732 for 671 basins across the USA for the Daymet forcing data set, compared to 0.748 from a state-of-the-art LSTM model with the same setup. For another forcing data set, the difference is even smaller: 0.715 versus 0.722. Meanwhile, the resulting learnable process-based models can output a full set of untrained variables, for example, soil and groundwater storage, snowpack, evapotranspiration, and baseflow, and can later be constrained by their observations. Both simulated evapotranspiration and fraction of discharge from baseflow agreed decently with alternative estimates. The general framework can work with models with various process complexity and opens up the path for learning physics from big data.

54 ENVIRONMENTAL SCIENCES↗