Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network robustness”

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 577 records · Page 32

NASA's Next Generation Space Geodesy Program

Requirements for the ITRF have increased dramatically since the 1980s. The most stringent requirement comes from critical sea level monitoring programs: a global accuracy of 1.0 mm, and 0.1mm/yr stability, a factor of 10 to 20 beyond current capability. Other requirements for the ITRF coming from ice mass change, ground motion, and mass transport studies are similar. Current and future satellite missions will have ever-increasing measurement capability and will lead to increasingly sophisticated models of these and other changes in the Earth system. Ground space geodesy networks with enhanced measurement capability will be essential to meeting the ITRF requirements and properly interpreting the satellite data. These networks must be globally distributed and built for longevity, to provide the robust data necessary to generate improved models for proper interpretation of the observed geophysical signals. NASA has embarked on a Space Geodesy Program with a long-range goal to build, deploy and operate a next generation NASA Space Geodetic Network (SGN). The plan is to build integrated, multi-technique next-generation space geodetic observing systems as the core contribution to a global network designed to produce the higher quality data required to maintain the Terrestrial Reference Frame and provide information essential for fully realizing the measurement potential of the current and coming generation of Earth Observing spacecraft. Phase 1 of this project has been funded to (1) Establish and demonstrate a next-generation prototype integrated Space Geodetic Station at Goddard's Geophysical and Astronomical Observatory (GGAO), including next-generation SLR and VLBI systems along with modern GNSS and DORIS; (2) Complete ongoing Network Design Studies that describe the appropriate number and distribution of next-generation Space Geodetic Stations for an improved global network; (3) Upgrade analysis capability to handle the next-generation data; (4) Implement a modern survey system to measure inter-technique vectors for co-location; and (5) Develop an Implementation Plan to build, deploy and operate a next-generation integrated NASA SGN that will serve as NASA's contribution to the international global geodetic network. An envisioned Phase 2 (which is not currently funded) would include the replication of up to ten such stations to be deployed either as integrated units or as a complement to already in-place components provided by other organizations. This talk will give an update on the activities underway and the plans for completion.

Merkowitz, S. M.↗

NASA's Next Generation Space Geodesy Program

Requirements for the ITRF have increased dramatically since the 1980s. The most stringent requirement comes from critical sea level monitoring programs: a global accuracy of 1.0 mm, and 0.1mm/yr stability, a factor of 10 to 20 beyond current capability. Other requirements for the ITRF coming from ice mass change, ground motion, and mass transport studies are similar. Current and future satellite missions will have ever-increasing measurement capability and will lead to increasingly sophisticated models of these and other changes in the Earth system. Ground space geodesy networks with enhanced measurement capability will be essential to meeting the ITRF requirements and properly interpreting the satellite data. These networks must be globally distributed and built for longevity, to provide the robust data necessary to generate improved models for proper interpretation of the observed geophysical signals. NASA has embarked on a Space Geodesy Program with a long-range goal to build, deploy and operate a next generation NASA Space Geodetic Network (SGN). The plan is to build integrated, multi-technique next-generation space geodetic observing systems as the core contribution to a global network designed to produce the higher quality data required to maintain the Terrestrial Reference Frame and provide information essential for fully realizing the measurement potential of the current and coming generation of Earth Observing spacecraft. Phase 1 of this project has been funded to (1) Establish and demonstrate a next-generation prototype integrated Space Geodetic Station at Goddard s Geophysical and Astronomical Observatory (GGAO), including next-generation SLR and VLBI systems along with modern GNSS and DORIS; (2) Complete ongoing Network Design Studies that describe the appropriate number and distribution of next-generation Space Geodetic Stations for an improved global network; (3) Upgrade analysis capability to handle the next-generation data; (4) Implement a modern survey system to measure inter-technique vectors for co-location; and (5) Develop an Implementation Plan to build, deploy and operate a next-generation integrated NASA SGN that will serve as NASA s contribution to the international global geodetic network. An envisioned Phase 2 (which is not currently funded) would include the replication of up to ten such stations to be deployed either as integrated units or as a complement to already in-place components provided by other organizations. This talk will give an update on the activities underway and the plans for completion.

Pearlman, M. R.↗

Neural network controller development for a magnetically suspended flywheel energy storage system

A neural network controller has been developed to accommodate disturbances and nonlinearities and improve the robustness of a magnetically suspended flywheel energy storage system. The controller is trained using the back propagation-through-time technique incorporated with a time-averaging scheme. The resulting nonlinear neural network controller improves system performance by adapting flywheel stiffness and damping based on operating speed. In addition, a hybrid multi-layered neural network controller is developed off-line which is capable of improving system performance even further. All of the research presented in this paper was implemented via a magnetic bearing computer simulation. However, careful attention was paid to developing a practical methodology which will make future application to the actual bearing system fairly straightforward.

Fittro, Roger L.↗

Robust Online Sequential RVFLNs for Data Modeling of Dynamic Time-Varying Systems with Application of an Ironmaking Blast Furnace

In a world where the increasing complexity of modern industrial processes brings difficulties for accurate mathematical modeling, taking advantage of data has become an efficient solution to complex dynamic process modeling issue. In this paper, we develop a novel robust online sequential version of random vector functional-link networks (RVFLNs) for data-driven modeling of dynamic time-varying system and applied it in a blast furnace (BF) ironmaking process. First, to overcome the time-varying dynamics of process and to enable the RVFLNs to learn online with avoiding data saturation, an improved online sequential version of RVFLNs (OS-RFVLNs) is first presented by online sequential learning with forgetting factor. This improved OS-RVFLNs algorithm is not only suitable for the real-time and large data transfer situation, but also can adjust the sensitivity of the algorithm to different samples with the help of the introduced forgetting factor. Second, since the output weights of the improved OS-RVFLNs as well as other RVFLNs algorithms are obtained by the least squares approach, a robustness problem may occur when the training dataset is contaminated with various outliers. To solve this problem, a Cauchy distribution weighted M-estimator is introduced to improve the robustness of the improved OS- RVFLNs. For this proposed robust OS-RVFLNs (R-OS- RVFLNs), since the weights of different outlier data are properly determined by the Cauchy distribution function, their corresponding contribution on modeling can be properly distinguished. Thus robust and better modeling results can be achieved. Experiments using actual industrial data of BF ironmaking process and comparative studies have demonstrated that the proposed method produces a better estimation accuracy and stronger robustness than other methods.

Blast furnace (BF), Modelling, Dynamic systems↗

Deep Learning for Intelligent Bubble Size Detection in the Spallation Neutron Source Visual Target

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory (ORNL) will undergo proton power upgrade (PPU), increasing the proton beam power from 1.4 MW to 2.8 MW. From 2.8 MW, 2.0 MW will go to the current First Target Station and the rest will go to the future Second Target Station (STS). The First Target Station uses a liquid mercury target that is contained in a 316L stainless steel vessel. The proton beam is pulsed at 60 Hz, with a pulse of about 0.7μs. When the proton beam hits the target, the intense energy deposition leads to a rapid rise in temperature in the mercury. This temperature rise creates pressure waves that propagate through the mercury and cause cavitation erosion. The power upgrade will cause stronger pressure waves that will further increase damage because of cavitation. Injecting small helium bubbles in the mercury has been an efficient method of mitigating the pressure wave at 1.4 MW. However, at higher power, additional mitigation is necessary. Therefore, the 2 MW target vessel will be equipped with swirl bubblers and an additional gas injection port near the nose to inject more gas in the target. To develop a gas injection strategy and design, flow visualization in water with a transparent prototypical target (“visual target”) was performed. Bubble sizes and their spatial distribution in the flow loop are crucial to understanding the effectiveness of the bubbles in mitigating pressure waves. Bubbles were generated in the visual target under varied conditions of input pressures with helium and air. Images were captured using a high-speed camera at varied frame rates at different positions away from the swirl bubbler and different depths in the flow loop under varying lighting conditions. Initially, methods such as circular Hough transforms were applied after a series of images processing to obtain a general distribution of bubble sizes. Bubbles smaller than 500 μm are preferred to effectively mitigate the effect of pressure waves, which demands an accurate bubble detection and sizing system. Intelligent detection and identification of bubble sizes alleviate misdetection and improves accuracies. Employing neural networks, intelligent detection of bubble sizes and their distribution was developed and provides a robust alternative to traditional techniques. Human intervention was employed to label in-focus and out-of-focus bubbles in the set of training images. An object detection network using a pretrained convolutional neural network was created that extracted the features from the training images. Data augmentation was used to improve network accuracy through a random transformation of the original data.

Rasheed, Fayaz↗

Advanced control techniques for modern inertia based inverters

In this research three artificial intelligent (AI)-based techniques are proposed to regulate the voltage and frequency of a grid-connected inverter. The increase in the penetration of renewable energy sources (RESs) into the power grid has led to the increase in the penetration of fast-responding inertia-less power converters. The increase in the penetration of these power electronics converters changes the nature of the conventional grid, in which the existing kinetic inertia in the rotating parts of the enormous generators plays a vital role. The concept of virtual inertia control scheme is proposed to make the behavior of grid connected inverters more similar to the synchronous generators, by mimicking the mechanical behavior of a synchronous generator. Conventional control techniques lack to perform optimally in nonlinear, uncertain, inaccurate power grids. Besides, the decoupled control assumption in conventional VSGs makes them nonoptimal in resistive grids. The neural network predictive controller, the heuristic dynamic programming, and the dual heuristic dynamic programming techniques are presented in this research to overcome the draw backs of conventional VSGs. The nonlinear characteristics of neural networks, and the online training enable the proposed methods to perform as robust and optimal controllers. The simulation and the experimental laboratory prototype results are provided to demonstrate the effectiveness of the proposed techniques.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Prognostic Validation of a Neural Network Unified Physics Parameterization

Weather and climate models approximate diabatic and sub-grid-scale processes in terms of grid-scale variables using parameterizations. Current parameterizations are designed by humans based on physical understanding, observations, and process modeling. As a result, they are numerically efficient and interpretable, but potentially oversimplified. However, the advent of global high-resolution simulations and observations enables a more robust approach based on machine learning. In this letter, a neural network-based parameterization is trained using a near-global aqua-planet simulation with a 4-km resolution (NG-Aqua). The neural network predicts the apparent sources of heat and moisture averaged onto (160 km)2 grid boxes. A numerically stable scheme is obtained by minimizing the prediction error over multiple time steps rather than single one. In prognostic single-column model tests, this scheme matches both the fluctuations and equilibrium of NG-Aqua simulation better than the Community Atmosphere Model does.

54 ENVIRONMENTAL SCIENCES↗

Imputation of urban environmental sensor data using gated attention bidirectional long short-term memory (GA-BiLSTM): methods, performance, and implications

Urban environmental monitoring networks frequently encounter significant data gaps due to sensor malfunctions, environmental disturbances, and communication failures. Reliable approaches to address these gaps are essential for ensuring the continuity and quality of environmental data streams. In this study, we developed a gated attention bidirectional long short-term memory (GA-BiLSTM) model to impute missing data in a dense urban monitoring network. Using observations from the CROCUS network in Chicago, we evaluated GA-BiLSTM against widely used approaches (XGBoost and K-nearest neighbors) under scenarios of both short-term intermittent gaps and prolonged outages. GA-BiLSTM consistently outperformed comparative methods, particularly during extended outages of up to ten days, demonstrating its ability to capture spatiotemporal dependencies across sensor nodes. Beyond performance metrics, feature importance and spatial network analyses highlighted the unexpected but critical predictive role of peripheral rural nodes, underlining their strategic value for maintaining robust urban monitoring systems. These results emphasize that advanced imputation methods can substantially improve the reliability of environmental monitoring networks and support more resilient data infrastructures for urban sustainability.

Data imputation↗

Next Generation NASA Initiative for Space Geodesy

Space geodesy measurement requirements have become more and more stringent as our understanding of the physical processes and our modeling techniques have improved. In addition, current and future spacecraft will have ever-increasing measurement capability and will lead to increasingly sophisticated models of changes in the Earth system. Ground-based space geodesy networks with enhanced measurement capability will be essential to meeting these oncoming requirements and properly interpreting the sate1!ite data. These networks must be globally distributed and built for longevity, to provide the robust data necessary to generate improved models for proper interpretation ofthe observed geophysical signals. These requirements have been articulated by the Global Geodetic Observing System (GGOS). The NASA Space Geodesy Project (SGP) is developing a prototype core site as the basis for a next generation Space Geodetic Network (SGN) that would be NASA's contribution to a global network designed to produce the higher quality data required to maintain the Terrestrial Reference Frame and provide information essential for fully realizing the measurement potential of the current and coming generation of Earth Observing spacecraft. Each of the sites in the SGN would include co-located, state of-the-art systems from all four space geodetic observing techniques (GNSS, SLR, VLBI, and DORIS). The prototype core site is being developed at NASA's Geophysical and Astronomical Observatory at Goddard Space Flight Center. The project commenced in 2011 and is scheduled for completion in late 2013. In January 2012, two multiconstellation GNSS receivers, GODS and GODN, were established at the prototype site as part of the local geodetic network. Development and testing are also underway on the next generation SLR and VLBI systems along with a modern DORIS station. An automated survey system is being developed to measure inter-technique vector ties, and network design studies are being performed to define the appropriate number and distribution of these next generation space geodetic core sites that are required to achieve the driving ITRF requirements. We present the status of this prototype next generation space geodetic core site, results from the analysis of data from the established geodetic stations, and results from the ongoing network design studies.

Merkowitz, S. M.↗

Neural Network for Positioning Space Station Solar Arrays

As a shuttle approaches the Space Station Freedom for a rendezvous, the shuttle's reaction control jet firings pose a risk of excessive plume impingement loads on Freedom solar arrays. The current solution to this problem, in which the arrays are locked in a feathered position prior to the approach, may be neither accurate nor robust, and is also expensive. An alternative solution is proposed here: the active control of Freedom's beta gimbals during the approach, positioning the arrays dynamically in such a way that they remain feathered relative to the shuttle jet most likely to cause an impingement load. An artificial neural network is proposed as a means of determining the gimbal angles that would drive plume angle of attack to zero. Such a network would be both accurate and robust, and could be less expensive to implement than the current solution. A network was trained via backpropagation, and results, which compare favorably to the current solution as well as to some other alternatives, are presented. Other training options are currently being evaluated.

Graham, Ronald E.↗

Modeling Multi-View Impedance-Based Cross-Geometry SOH Estimator for Li-ion Batteries

Abstract: Accurately estimating battery’s State of Health (SOH) remains challenging when models must generalize across cell designs and operating conditions. Most Electrochemical Impedance Spectroscopy (EIS)-based approaches either (i) hand-engineer a few Nyquist-plot features for shallow models—fast but does not generalize across geometries—or (ii) learn directly from Nyquist plots with deep networks, which removes manual feature extraction, yet still limited to a single plot type. As a result, cross-geometry robustness and deployability on constrained Internet of Things (IoT) devices remain open problems. We propose a compact Convolutional Neural Network (CNN) (∼ 10k parameters) that takes multi-representation EIS inputs—Nyquist (real/imaginary) and phase–magnitude (|Z|/ϕ) stacked as four channels, so the model can learn complementary degradation signatures while remaining small enough for fast inference. We build a dataset from cyclic aging of two geometries (LG INR18650MJ1 cylindrical cells and LIR2032 coin cells), acquire EIS every ten cycles from 10 kHz to 10 mHz (10 points/decade), and evaluate with leave-one-cell-out testing strategy. We further study fusion vs. single-representation inputs and assess feasibility for on-device deployment (e.g., NVIDIA Jetson device). The results show that training on multiple EIS representations improves SOH estimation accuracy and cross-geometry generalization compared to single-representation models, which uses only Nyquist or phase–magnitude plots. This design targets accurate, generalizable SOH prediction without manual feature engineering while enabling practical real-time use.

Bakr, Ahmed [The University of Alabama (UA)]↗

DeepMerge – II. Building robust deep learning algorithms for merging galaxy identification across domains

In astronomy, neural networks are often trained on simulation data with the prospect of being used on telescope observations. Unfortunately, training a model on simulation data and then applying it to instrument data leads to a substantial and potentially even detrimental decrease in model accuracy on the new target dataset. Simulated and instrument data represent different data domains, and for an algorithm to work in both, domain-invariant learning is necessary. Here we employ domain adaptation techniques— Maximum Mean Discrepancy (MMD) as an additional transfer loss and Domain Adversarial Neural Networks (DANNs)— and demonstrate their viability to extract domain-invariant features within the astronomical context of classifying merging and non-merging galaxies. Additionally, we explore the use of Fisher loss and entropy minimization to enforce better in-domain class discriminability. We show that the addition of each domain adaptation technique improves the performance of a classifier when compared to conventional deep learning algorithms. We demonstrate this on two examples: between two Illustris-1 simulated datasets of distant merging galaxies, and between Illustris-1 simulated data of nearby merging galaxies and observed data from the Sloan Digital Sky Survey. The use of domain adaptation techniques in our experiments leads to an increase of target domain classification accuracy of up to ~20%. With further development, these techniques will allow astronomers to successfully implement neural network models trained on simulation data to efficiently detect and study astrophysical objects in current and future large-scale astronomical surveys.

galaxies: interactions↗

Effective cosmic density field reconstruction with convolutional neural network

ABSTRACT We present a cosmic density field reconstruction method that augments the traditional reconstruction algorithms with a convolutional neural network (CNN). Following previous work, the key component of our method is to use the reconstructed density field as the input to the neural network. We extend this previous work by exploring how the performance of these reconstruction ideas depends on the input reconstruction algorithm, the reconstruction parameters, and the shot noise of the density field, as well as the robustness of the method. We build an eight-layer CNN and train the network with reconstructed density fields computed from the Quijote suite of simulations. The reconstructed density fields are generated by both the standard algorithm and a new iterative algorithm. In real space at z = 0, we find that the reconstructed field is 90 per cent correlated with the true initial density out to $k\sim 0.5 \, \mathrm{ h}\, \rm {Mpc}^{-1}$, a significant improvement over $k\sim 0.2 \, \mathrm{ h}\, \rm {Mpc}^{-1}$ achieved by the input reconstruction algorithms. We find similar improvements in redshift space, including an improved removal of redshift space distortions at small scales. We also find that the method is robust across changes in cosmology. Additionally, the CNN removes much of the variance from the choice of different reconstruction algorithms and reconstruction parameters. However, the effectiveness decreases with increasing shot noise, suggesting that such an approach is best suited to high density samples. This work highlights the additional information in the density field beyond linear scales as well as the power of complementing traditional analysis approaches with machine learning techniques.

Astronomy & Astrophysics↗

Scaling Subspace-Driven Approaches Using Information Fusion

In this work, we seek to exploit the deep structure of multi-modal data to robustly exploit the group subspace distribution of the information using the Convolutional Neural Networks (CNNs) formalism. Upon unfolding the set of subspaces constituting each data modality, and learning their corresponding encoders, an optimized integration of the generated inherent information is carried out to yield a characterization of various classes. Referred to as deep Multimodal Robust Group Subspace Clustering (DRoGSuRe), this approach is compared against the independently developed state-of-the-art approach named Deep Multimodal Subspace Clustering (DMSC). Experiments on different multimodal datasets show that our approach is competitive and more robust in the presence of noise.

Ghanem, Sally↗

Intelligent failure-tolerant control

An overview of failure-tolerant control is presented, beginning with robust control, progressing through parallel and analytical redundancy, and ending with rule-based systems and artificial neural networks. By design or implementation, failure-tolerant control systems are 'intelligent' systems. All failure-tolerant systems require some degrees of robustness to protect against catastrophic failure; failure tolerance often can be improved by adaptivity in decision-making and control, as well as by redundancy in measurement and actuation. Reliability, maintainability, and survivability can be enhanced by failure tolerance, although each objective poses different goals for control system design. Artificial intelligence concepts are helpful for integrating and codifying failure-tolerant control systems, not as alternatives but as adjuncts to conventional design methods.

Stengel, Robert F.↗

Finding Your Niche: An Evolutionary Approach to HPC Topologies

Traditional interconnection network design approaches focus on building general network topologies by optimizing the bisection bandwidth or minimizing the network’s diameter to reduce the maximum distance between any two nodes, thus amortizing the overall execution time of the HPC workloads. While such network topologies may accommodate a wide variety of applications in general, this may result in sub-optimal performance for many frequently-executed or dynamic workloads. In this paper, instead of focusing on designing an all-encompassing, general-purpose network topology, we develop a methodology to design customized network interconnects, evolved by “finding” the optimal topologies for a particular target workload given by its communication and contention profiles. To this end, we implement a Genetic Algorithm (GA)-based approach for network topology design tailored to improve the overall execution time of a particular workload of interest. We conducted extensive experiments with well-known motifs in physics-based workloads (Sweep3D and FFT), as well as with a representative graph application (MiniVite), using the well-known Structural Simulation Toolkit (SST) Macroscale Element Library (SST/macro) simulator for network interconnect evaluation. We demonstrate that our genetic algorithm-based approach is robust enough to find the underlying optimal topology of a particular workload.

network interconnects, graph search, meta-heuristi↗

Robustness, efficiency, and optimality in the Fenna-Matthews-Olson photosynthetic pigment-protein complex

Pigment-protein complexes (PPCs) play a central role in facilitating excitation energy transfer (EET) from light-harvesting antenna complexes to reaction centres in photosynthetic systems; understanding molecular organisation in these biological networks is key to developing better artificial light-harvesting systems. In this article, we combine quantum-mechanical simulations and a network-based picture of transport to investigate how chromophore organization and protein environment in PPCs impacts on EET efficiency and robustness. In a prototypical PPC model, the Fenna-Matthews-Olson (FMO) complex, we consider the impact on EET efficiency of both disrupting the chromophore network and changing the influence of (local and global) environmental dephasing. Surprisingly, we find a large degree of resilience to changes in both chromophore network and protein environmental dephasing, the extent of which is greater than previously observed; for example, FMO maintains EET when 50% of the constituent chromophores are removed, or when environmental dephasing fluctuations vary over two orders-of-magnitude relative to the in vivo system. We also highlight the fact that the influence of local dephasing can be strongly dependent on the characteristics of the EET network and the initial excitation; for example, initial excitations resulting in rapid coherent decay are generally insensitive to the environment, whereas the incoherent population decay observed following excitation at weakly coupled chromophores demonstrates a more pronounced dependence on dephasing rate as a result of the greater possibility of local exciton trapping. Finally, we show that the FMO electronic Hamiltonian is not particularly optimised for EET; instead, it is just one of many possible chromophore organisations which demonstrate a good level of EET transport efficiency following excitation at different chromophores. Overall, these robustness and efficiency characteristics are attributed to the highly connected nature of the chromophore network and the presence of multiple EET pathways, features which might easily be built into artificial photosynthetic systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗