Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “feedforward”

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 163 records · Page 9

Blackstart and Fault Ride-Through Capability of DFIG-Based Wind Turbines

Grid-forming wind turbines must be able to re-energize transmission branches, motor loads, unbalanced loads, and power electronics loads following a blackout. Further, they must ride through faults that can arise during restoration. To tackle these challenges, this paper sets forth a grid-forming control strategy for wind turbines using doubly-fed induction generators (DFIGs). In particular, a special set of feedforward control loops are engineered to mitigate the impacts of restoration transients as well as symmetrical and asymmetrical faults on the regulation of DFIG rotor currents and stator voltages. This paper also leverages two-axis anti-windup regulators to bound two-axis voltage and current commands within ratings. As a result, the controller performance is demonstrated via a high-fidelity simulation model of a notional wind-dominant grid.

17 WIND ENERGY↗

PagMYB128 regulates secondary cell wall formation by direct activation of cell wall biosynthetic genes during wood formation in poplar

The biosynthesis of cellulose, lignin, and hemicelluloses in plant secondary cell walls (SCWs) is regulated by a hierarchical transcriptional regulatory network. Here, this network features orthologous transcription factors shared between poplar and Arabidopsis, highlighting a foundational similarity in their genetic regulation. However, knowledge on the discrepant behavior of the transcriptional-level molecular regulatory mechanisms between poplar and Arabidopsis remains limited. In this study, we investigated the function of PagMYB128 during wood formation and found it had broader impacts on SCW formation compared to its Arabidopsis ortholog, AtMYB103. Transgenic poplar trees overexpressing PagMYB128 exhibited significantly enhanced xylem development, with fiber cells and vessels displaying thicker walls, and an increase in the levels of cellulose, lignin, and hemicelluloses in the wood. In contrast, plants with dominant repression of PagMYB128 demonstrated the opposite phenotypes. RNA sequencing and reverse transcription – quantitative polymerase chain reaction showed that PagMYB128 could activate SCW biosynthetic gene expression, and chromatin immunoprecipitation along with yeast one-hybrid, and effector–reporter assays showed this regulation was direct. Further analysis revealed that PagSND1 (SECONDARY WALL-ASSOCIATED NAC-DOMAIN PROTEIN1) directly regulates PagMYB128 but not cell wall metabolic genes, highlighting the pivotal role of PagMYB128 in the SND1-driven regulatory network for wood development, thereby creating a feedforward loop in SCW biosynthesis.

59 BASIC BIOLOGICAL SCIENCES↗

Selective area doping for Mott neuromorphic electronics

The cointegration of artificial neuronal and synaptic devices with homotypic materials and structures can greatly simplify the fabrication of neuromorphic hardware. We demonstrate experimental realization of vanadium dioxide (VO 2 ) artificial neurons and synapses on the same substrate through selective area carrier doping. By locally configuring pairs of catalytic and inert electrodes that enable nanoscale control over carrier density, volatility or nonvolatility can be appropriately assigned to each two-terminal Mott memory device per lithographic design, and both neuron- and synapse-like devices are successfully integrated on a single chip. Feedforward excitation and inhibition neural motifs are demonstrated at hardware level, followed by simulation of network-level handwritten digit and fashion product recognition tasks with experimental characteristics. Spatially selective electron doping opens up previously unidentified avenues for integration of emerging correlated semiconductors in electronic device technologies.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

fPINNs: Fractional Physics-Informed Neural Networks

Physics-informed neural networks (PINNs), introduced, are effective in solving integer-order partial differential equations (PDEs) based on scattered and noisy data. PINNs employ standard feedforward neural networks (NNs) with the PDEs explicitly encoded into the NN using automatic differentiation, while the sum of the mean-squared PDE residuals and the mean-squared error in initial-boundary conditions is minimized with respect to the NN parameters. Here we extend PINNs to fractional PINNs (fPINNs) to solve space-time fractional advection-diffusion equations (fractional ADEs), and we study systematically their convergence, hence explaining both fPINNs and PINNs for the first time. Specifically, we demonstrate their accuracy and effectiveness in solving multidimensional forward and inverse problems with forcing terms whose values are only known at randomly scattered spatio-temporal coordinates (black-box (BB) forcing terms). A novel element of the fPINNs is the hybrid approach that we introduce for constructing the residual in the loss function using both automatic differentiation for the integer-order operators and numerical discretization for the fractional operators. This approach bypasses the difficulties stemming from the fact that automatic differentiation is not applicable to fractional operators because the standard chain rule in integer calculus is not valid in fractional calculus. To discretize the fractional operators, we employ the Grünwald--Letnikov (GL) formula in one-dimensional fractional ADEs and the vector GL formula in conjunction with the directional fractional Laplacian in two- and three-dimensional fractional ADEs. We first consider the one-dimensional fractional Poisson equation and compare the convergence of the fPINNs against the finite difference method (FDM). We present the solution convergence using both the mean L 2 error as well as the standard deviation due to sensitivity to NN parameter initializations. Using different GL formulas we observe first-, second-, and third-order convergence rates for small size training sets but the error saturates for larger training sets. We explain these results by analyzing the four sources of numerical errors due to discretization, sampling, NN approximation, and optimization. The total error decays monotonically (below 10 –5 for a third-order GL formula) but it saturates beyond that point due to the optimization error. We also analyze the relative balance between discretization and sampling errors and observe that the sampling size and the number of discretization points (auxiliary points) should be comparable to achieve the highest accuracy. As we increase the depth of the NN up to certain value, the mean error decreases and the standard deviation increases, whereas the width has essentially no effect unless its value is either too small or too large. We next consider time-dependent fractional ADEs and compare white-box (WB) and BB forcing. We observe that for the WB forcing, our results are similar to the aforementioned cases; however, for the BB forcing fPINNs outperform FDM. Subsequently, we consider multidimensional time-, space-, and space-time-fractional ADEs using the directional fractional Laplacian and we observe relative errors of 10 –3 ~ 10 –4 . Lastly, we solve several inverse problems in one, two, and three dimensions to identify the fractional orders, diffusion coefficients, and transport velocities and obtain accurate results given proper initializations even in the presence of significant noise.

97 MATHEMATICS AND COMPUTING↗

Extended Galerkin Neural Network Approximation of Singular Variational Problems with Error Control

We present extended Galerkin neural networks, a variational framework for approximating general boundary value problems (BVPs) with error control. The main contributions of this work are (1) a rigorous theory guiding the construction of new weighted least squares variational formulations suitable for use in neural network approximation of general BVPs, and (2) an “extended” feedforward network architecture which incorporates and is even capable of learning singular solution structures, thus greatly improving approximability of singular solutions. Furthermore, numerical results are presented for several problems, including steady Stokes flow around reentrant corners and in convex corners with Moffatt eddies in order to demonstrate efficacy of the method.

a posteriori error estimate↗

Tencoder: tensor-product encoder-decoder architecture for predicting solutions of PDEs with variable boundary data

It is widely hoped that artificial intelligence will boost data-driven surrogate models in science and engineering. However, fundamental spatial aspects of AI surrogate models remain under-studied. We investigate the ability of neural-network surrogate models to predict solutions to PDEs under variable boundary values. We do not wish to retrain the model when the boundary values change but to make them inputs to the model and infer the solution of the PDE under those boundary conditions. Such a capability is essential to making AI-based surrogate models practically useful. While simple feedforward networks are used for one-dimensional (1D) Poisson equation, an encoder-decoder architecture with a tensor-product layer is developed for the two-dimensional Poisson equation posed on a rectangular domain. We show that it is indeed possible to infer solutions to PDEs from variable boundary data using neural networks in this relatively simple setting, and point to future directions.

Kashi, Aditya↗

scANN

SAND2025-00656O scANN, also known as sampling by coinflips artificial neural networks, is a software tool that estimates uncertainty in artificial intelligence by performing Monte Carlo analysis on the weight matrices of feedforward neural networks. This computationally intensive process aims to explore the potential value added by future probabilistic hardware. The program’s output helps researchers gain insights into how probabilistic neural networks work. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

SciDAC↗

Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to the lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons. The SNNs with self-recurrent connections can realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. The network dynamics is enriched by skip connections between nonadjacent layers. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neuron's intrinsic parameters according to neuronal activity, the proposed BIP method optimizes intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Here, based on challenging speech, neuromorphic speech, and neuromorphic image datasets, the proposed ScSr-SNNs can boost performance by up to 2.85% compared with other types of RSNNs trained by state-of-the-art BP methods.

97 MATHEMATICS AND COMPUTING↗

Generalizable, fast, and accurate DeepQSPR with fastprop

Abstract Quantitative Structure–Property Relationship studies (QSPR), often referred to interchangeably as QSAR, seek to establish a mapping between molecular structure and an arbitrary target property. Historically this was done on a target-by-target basis with new descriptors being devised to specifically map to a given target. Today software packages exist that calculate thousands of these descriptors, enabling general modeling typically with classical and machine learning methods. Also present today are learned representation methods in which deep learning models generate a target-specific representation during training. The former requires less training data and offers improved speed and interpretability while the latter offers excellent generality, while the intersection of the two remains under-explored. This paper introduces , a software package and general Deep-QSPR framework that combines a cogent set of molecular descriptors with deep learning to achieve state-of-the-art performance on datasets ranging from tens to tens of thousands of molecules. provides both a user-friendly Command Line Interface and highly interoperable set of Python modules for the training and deployment of feedforward neural networks for property prediction. This approach yields improvements in speed and interpretability over existing methods while statistically equaling or exceeding their performance across most of the tested benchmarks. is designed with Research Software Engineering best practices and is free and open source, hosted at github.com/jacksonburns/fastprop.

Burns, Jackson W. (ORCID:0000000206579426)↗

Deep Neural Network Algorithm for CMC Microstructure Characterization and Variability Quantification

Microstructure characterization and variability quantification are crucial for understanding ceramic matrix composites (CMCs) mechanical behavior and deformation mechanisms across length scales. Traditionally, analyses of the micrographs obtained from microscopy are labor-intensive. However, with the vast improvement in computer vision (CV) and deep learning (DL), an automated algorithm can be designed to extract essential microstructure variability from micrographs which can then be used to construct a statistically representative volume element (SRVE). The DL-based algorithm spans the taxonomy of microstructure analyses, including semantic segmentation of microstructure constituents, secondary phases, matrix/fiber interface, and defects, and quantifying the microstructure variability in terms of probability distributions. In this work, C/SiNC and SiC/SiNC CMCs microstructures are semantically segmented through a deep convolutional neural network, followed by variability quantification through the implementation of a fully connected regression layer, hence forming a deep regression network. The deep regression network operates in a feedforward regime, in which the neuron output signal traverses through the network in a unidirectional manner. The weight tensor associated with each layer is updated through a backpropagation stochastic gradient descent approach. The input gray-scale image obtained through in-house scanning electron microscope and confocal microscope micrographs is augmented through affine transformations to increase the training set size, which is then processed through four strided convolutional layers. This compresses the image resolution by half at each layer while increasing the image depth by applying different filters (image encoding). The class activation maps (CAMs) corresponding to the applied filters highlight the key architectural features and assist with the semantic segmentation of the microstructure.

Hamza, Mohamed H.↗

Integrated reference cavity with dual-mode optical thermometry for frequency correction

Photonic integrated resonators have advantages over traditional benchtop cavities in terms of size, weight, and cost with the potential to enable applications that require spectrally pure light. However, integrated resonators suffer from temperature-dependent frequency variations and are sensitive to external environmental perturbations, which hinders their usage in precision frequency applications. One solution is to use interrogation of the cavity temperature through dual-mode optical thermometry (DMOT) by measuring the shift of the resonance frequency difference between two polarization or optical frequency modes. Yet this approach has only been demonstrated in bulk-optic whispering gallery mode and fiber resonators. In this paper, we implement dual-mode optical thermometry in an ultra-high Q integrated silicon nitride resonator. A dual-mode resonance frequency difference temperature sensitivity of 188 ± <#comment/> 15 M H z / K is measured. We demonstrate feedforward DMOT frequency correction that, under an applied external temperature ramp, is able to reduce the optical frequency change to 0.31 kHz/s as compared to an uncorrected 10.03 kHz/s, a factor of 30 × <#comment/> reduction. These results show promise for on-chip frequency correction solutions for quantum, metrology, atomic, and coherent optical communications applications.

Zhao, Qiancheng (ORCID:0000000206968667)↗

Determining the Control Circuitry of Redox Metabolism at the Genome-Scale

Determining how facultative anaerobic organisms sense and direct cellular responses to electron acceptor availability has been a subject of intense study. However, even in the model organism Escherichia coli, established mechanisms only explain a small fraction of the hundreds of genes that are regulated during electron acceptor shifts. Here we propose a qualitative model that accounts for the full breadth of regulated genes by detailing how two global transcription factors (TFs), ArcA and Fnr of E. coli, sense key metabolic redox ratios and act on a genome-wide basis to regulate anabolic, catabolic, and energy generation pathways. We first fill gaps in our knowledge of this transcriptional regulatory network by carrying out ChIP-chip and gene expression experiments to identify 463 regulatory events. We then interfaced this reconstructed regulatory network with a highly curated genome-scale metabolic model to show that ArcA and Fnr regulate .80% of total metabolic flux and 96% of differential gene expression across fermentative and nitrate respiratory conditions. Based on the data, we propose a feedforward with feedback trim regulatory scheme, given the extensive repression of catabolic genes by ArcA and extensive activation of chemiosmotic genes by Fnr. We further corroborated this regulatory scheme by showing a 0.71 r 2 (p,1e-6) correlation between changes in metabolic flux and changes in regulatory activity across fermentative and nitrate respiratory conditions. Finally, we are able to relate the proposed model to a wealth of previously generated data by contextualizing the existing transcriptional regulatory network.

59 BASIC BIOLOGICAL SCIENCES↗

TRANSIENT BEAM LOADING EFFECTS IN RF SYSTEMS IN JLEIC

The pulsed electron bunch trains generated from the Continuous Electron Beam Accelerator Facility (CEBAF) linac to inject into the proposed Jefferson Lab Electron Ion Collider (JLEIC) e-ring will produce transient beam loading effects in the Superconducting Radio Frequency (SRF) systems that, if not mitigated, could cause unacceptably large beam energy deviation in the injection capture, or exceed the energy acceptance of CEBAF’s recirculating arcs. In the electron storage ring, the beam abort or ion clearing gaps or uneven bucket filling can cause large beam phase transients in the (S)RF cavity control systems and even beam loss due to Robinson instability. We have first analysed the beam stability criteria in steady state and estimated the transient effect in Feedforward and Feedback RF controls. Initial analytical models for these effects are shown for the design of the JLEIC e-ring from 3GeV to 12GeV.

Wang, Haipeng↗

Status Update of a Harmonic Kicker Development for JLEIC

The Jefferson Lab Electron-Ion Collider (JLEIC) is an asymmetric high luminosity ring-ring collider proposed as the next major R&D facility for the nuclear physics community. Both of JLEIC?s electron and ion collider rings have high beam current with gaps serving the pur-poses of beam abort, ion clearing, etc. Those gaps will cause time-varying beam loading in the storage RF cavi-ties, and may result in modulation of cavity RF phase/voltage and cyclic shift of collision point, which could lead to significant luminosity loss. We studied a few approaches to mitigate the RF phase modulation and IP shift, such as correcting the RF phase/voltage modula-tion with traditional LLRF feedback, one-turn feedback (OTFB), or RF feedforward (FF); optimizing the bunch fill pattern to limit the RF phase/voltage modulation to a small fraction of the bunch trains in the collider ring; or matching the RF phase modulation in the two rings. The preliminary results are discussed in this paper.

Guo, Jiquan↗

BEAMLINE-CONTROLLED STEERING OF SOURCE-POINT ANGLE AT THE ADVANCED PHOTON SOURCE

An EPICS-based steering software system has been implemented for beamline personnel to directly steer the angle of the synchrotron radiation sources at the Advanced Photon Source. A script running on a workstation monitors "start steering" beamline EPICS records, and effects a steering given by the value of the "angle request" EPICS record. The new system makes the steering process much faster than before, although the older steering protocols can still be used. The robustness features of the original steering remain. Feedback messages are provided to the beamlines and the accelerator operators. Underpinning this new steering protocol is the recent refinement of the global orbit feedback process whereby feedforward of dipole corrector set points and orbit set points are used to create a local steering bump in a rapid and seamless way.

APS↗

LIDAR Wind Speed Measurements of Evolving Wind Fields

Light Detection and Ranging (LIDAR) systems are able to measure the speed of incoming wind before it interacts with a wind turbine rotor. These preview wind measurements can be used in feedforward control systems that are designed to reduce turbine loads. However, the degree to which such preview-based control techniques can reduce loads by reacting to turbulence depends on how accurately the incoming wind field can be measured. Past studies have assumed the validity of physicist G.I. Taylor’s 1938 frozen turbulence hypothesis, which implies that turbulence remains unchanged as it advects downwind at the mean wind speed. With Taylor’s hypothesis applied, the only source of wind speed measurement error is distortion caused by the LIDAR. This study introduces wind evolution, characterized by the longitudinal coherence of the wind, to LIDAR measurement simulations using the National Renewable Energy Laboratory’s (NREL’s) 5-megawatt turbine model to create a more realistic measurement model. A simple model of wind evolution was applied to a frozen wind field that was used in previous studies to investigate the effects of varying the intensity of wind evolution. LIDAR measurements were also evaluated using a large eddy simulation (LES) of a stable boundary layer that was provided by the National Center for Atmospheric Research.

17 WIND ENERGY↗

A comparative study on wave prediction for WECs

The idea of acausality for control of a wave energy converter (WEC) is a concept that has been popular since the birth of modern wave energy research in the 1970s. This concept has led to considerable research into wave prediction and feedforward WEC control algorithms. However, the findings in this report mostly negate the need for wave prediction to improve WEC energy absorption, and favor instead feedback driven control strategies. Feedback control is shown to provide performance that rivals a prediction-based controller, which has been unrealistically assumed to have perfect prediction. It is well known in classical control engineering that perfect knowledge of past and future events will always lead to higher performing systems. However, it is also well known that the underlying system must be well-designed; control cannot fix a bad design. Additionally, one must consider the practical application of a control design, which relies on measurements and actuation systems. There are major implications to cost and reliability when relying on remote sensors requiring real-time data-streaming (e.g., remote wave buoys). This report shows that for a well-designed WEC, in which closed loop dynamics is considered since early stages of design, a suboptimal controller using no prediction can achieve more than 90% of the theoretical maximum. A predictionless feedback resonating (FBR) controller performs within 0.1% percent of a controller with perfect future knowledge (something which is not practically attainable). Given the major challenges with accurate and robust wave prediction, this result provides a major argument and incentive for utilizing feedback for WEC control. Implementation of these feedback strategies is readily attainable, while the strategy requiring perfect wave prediction will demand an unknown number of additional years to research and develop, all in the service of a marginal 1% benefit.

16 TIDAL AND WAVE POWER↗