Ensemble of Numerics-Informed Neural Networks with Embedded Hamiltonian Constraints for Modeling Nonlinear Structural Dynamics.
Abstract not provided.
Najera-Flores, David↗
SEARCH · Engineering Papers
Results for “Dynamic networks”
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.
Phosphorylation Dynamics in a flg22-Induced, G Protein–Dependent Network Reveals the AtRGS1 Phosphatase
Not provided.
Biochemistry & Molecular Biology↗
Ensemble of Numerics-Informed Neural Networks with Embedded Hamiltonian Constraints for Modeling Nonlinear Structural Dynamics.
Abstract not provided.
Najera-Flores, David↗
Dynamics of the solar chromosphere. I - Long-period network oscillations
We analyze differences in solar oscillations between the chromospheric network and internetwork regions from a 1 hr sequence of spectrograms of a quiet region near disk center. The spectrograms contain Ca II H, Ca I 422.7 nm, and various Fe I blends in the Ca II H wing. They permit vertical tracing of oscillations throughout the photosphere and into the low chromosphere. We find that the rms amplitude of Ca II H line center Doppler fluctuations is about 1.5 km/s for both network and internetwork, but that the character of the oscillations differs markedly in these two regions. Within internetwork areas the chromospheric velocity power spectrum is dominated by oscillations with frequencies at and above the acoustic cutoff frequency. They are well correlated with the oscillations in the underlying photosphere, but they are much reduced in the network. In contrast, the network Ca II H line center velocity and intensity power spectra are dominated by low-frequency oscillations with periods of 5-20 min. Their signature is much clearer in our Ca II H line center measurements than in previously used diagnostics which are contaminated by signals from deeper layers. We find that these long-period oscillations are not correlated with underlying photospheric disturbances, and we discuss their nature.
Lites, B. W.↗
Modeling Trust Dimensions and Dynamics in Human-Agent Conversation: A Trajectory Epistemic Network Analysis Approach
Explore the source record for details and available documents.
Mengyao Li↗
DCS-Neural-Network Program for Aircraft Control and Testing
A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.
Jorgensen, Charles C.↗
Improved Architectures and Training Algorithms for Deep Operator Networks
Operator learning techniques have recently emerged as a powerful tool for learning maps between infinite-dimensional Banach spaces. Trained under appropriate constraints, they can also be effective in learning the solution operator of partial differential equations (PDEs) in an entirely self-supervised manner. In this work we analyze the training dynamics of deep operator networks (DeepONets) through the lens of Neural Tangent Kernel theory, and reveal a bias that favors the approximation of functions with larger magnitudes. To correct this bias we propose to adaptively re-weight the importance of each training example, and demonstrate how this procedure can effectively balance the magnitude of back-propagated gradients during training via gradient descent. We also propose a novel network architecture that is more resilient to vanishing gradient pathologies. Taken together, our developments provide new insights into the training of DeepONets and consistently improve their predictive accuracy by a factor of 10-50x, demonstrated in the challenging setting of learning PDE solution operators in the absence of paired input-output observations.
97 MATHEMATICS AND COMPUTING↗
Robust Self-Healing Adhesives Based on Dynamic Urethane Exchange Reactions
Thermoset polyurethanes (PUs) have been successfully reprocessed as covalent adaptable networks (CANs) by catalyzing carbamate exchange. Here we extend bond exchange beyond the internal network cross-links to create a dynamic urethane adhesive. Interfacing PU CANs to substrates with nucleophilic functional groups creates adhesives capable of reversible transcarbamoylation with the substrate, which has not been demonstrated previously by CAN adhesives. Two types of thermoset PU films were synthesized, one containing the green carbamate exchange catalyst Zr(tmhd)4 and the other containing no catalyst. Although otherwise identical in chemical and network properties, as indicated by FT-IR spectroscopy and dynamic mechanical thermal analysis (DMTA), the film containing catalyst showed dynamic bond exchange behavior through stress relaxation analysis. When evaluated as an adhesive, the CAN film exhibited self-healing properties and retained its adhesive strength for five cycles, which is attributed to reversible covalent bonding to the glass substrate. Furthermore, this work expands industrially relevant CANs to structural adhesives and demonstrates their potential value in an application that presently employs PUs as single-use materials.
adhesive↗
Multi-Agent Control Planes for Quantum Networks: A Scalable Architecture for Autonomous Quantum Internet Management
Quantum networks are expected to enable distributed quantum computing, secure communication, and global entanglement distribution. However, operating such networks presents significant challenges, including stochastic quantum processes, fragile entanglement resources, dynamic topology, and cross-layer control requirements. Current quantum network control architectures largely rely on centralized or hierarchical controllers inspired by classical software-defined networking (SDN). While effective for small testbeds, these approaches face scalability, latency, and reliability limitations as quantum networks grow. This paper proposes a multi-agent control plane architecture for quantum networks. In this design, intelligent software agents operate at quantum nodes, repeaters, and orchestration layers, collectively managing entanglement generation, routing, purification, and scheduling. The distributed intelligence of the agent system allows the network to adapt dynamically to quantum hardware variability and environmental noise. We argue that multi-agent systems provide significant advantages over centralized control approaches, including scalability, resilience, local autonomy, and real-time adaptation. The paper discusses architectural design principles, agent coordination mechanisms, and research challenges in deploying multi-agent control planes for the emerging quantum Internet.
Alnajjar, Anees [ORNL] (ORCID:0000000237101601)↗
Flexspander: augmenting expander networks in high-performance systems with optical bandwidth steering
Communication efficiency is one of the deciding factors in determining many of today’s high-performance computing (HPC) applications. Traditionally, HPC systems have been on static network topologies, making them inflexible to the variety of skewed traffic demands that may arise due to the spatial locality inherent in many applications. To handle traffic locality, researchers have proposed integrating optical circuit switches (OCSs) into the network architecture, which reconfigures the network topology to alter and dynamically adapt to the predicted traffic. In this paper, we present a novel reconfigurable network topology called Flexspander. Beyond offering a flexible interconnect, Flexspander also offers full flexibility in terms of construction and can be built with any arbitrary combination of commercial electrical packet switches and OCSs. We evaluate Flexspander performance through extensive simulations with multiple network traces, and our results show improved performance for Flexspander over currently proposed static and reconfigurable topologies in terms of the flow completion time.
Teh, Min Yee↗
Dynamically Alterable Arrays of Polymorphic Data Types
An application library package was developed that represents data packets for Deep Space Network (DSN) message packets as dynamically alterable arrays composed of arbitrary polymorphic data types. The software was to address a limitation of the present state of the practice for having an array directly composed of a single monomorphic data type. This is a severe limitation when one is dealing with science data in that the types of objects one is dealing with are typically not known in advance and, therefore, are dynamic in nature. The unique feature of this approach is that it enables one to define at run-time the dynamic shape of the matrix with the ability to store polymorphic data types in each of its indices. Existing languages such as C and C++ have the restriction that the shape of the array must be known in advance and each of its elements be a monomorphic data type that is strictly defined at compile-time. This program can be executed on a variety of platforms. It can be distributed in either source code or binary code form. It must be run in conjunction with any one of a number of Lisp compilers that are available commercially or as shareware.
James, Mark↗
Development of novel dynamic machine learning-based optimization of a coal-fired power plant
The increasing fraction of intermittent renewable energy in the electrical grid is resulting in coal-fired boilers now routinely ramp up and down. The current state-of-the-art operation for such boilers is to apply steady-state, neural network-based optimization to make control decisions in real-time, and this report demonstrates the feasibility of extending this to dynamic, neural network-based optimization using a long short-term memory neural network. A simplified numerical simulation of a t-fired coal boiler and supporting equipment is used to represent a real plant subjected to both steady-state, neural network-based optimization and dynamic, neural network-based optimization. Using the same intervals and a particle swarm optimization algorithm, the dynamic optimization outperforms the steady-state optimization and realizes up to 4.58% improvement in thermal efficiency. Dynamic optimization with a long short-term memory neural network is shown to both be feasible and beneficial for operation of a coal-fired boiler under changing load.
42 ENGINEERING↗
Data assimilation empowered neural network parametrizations for subgrid processes in geophysical flows
In the past couple of years, there has been a proliferation in the use of machine learning approaches to represent subgrid-scale processes in geophysical flows with an aim to improve the forecasting capability and to accelerate numerical simulations of these flows. Despite its success for different types of flow, the online deployment of a data-driven closure model can cause instabilities and biases in modeling the overall effect of subgrid-scale processes, which in turn leads to inaccurate prediction. To tackle this issue, we exploit the data assimilation technique to correct the physics-based model coupled with the neural network as a surrogate for unresolved flow dynamics in multiscale systems. In particular, we use a set of neural network architectures to learn the correlation between resolved flow variables and the parametrizations of unresolved flow dynamics and formulate a data assimilation approach to correct the hybrid model during their online deployment. We illustrate our framework in a set of applications of the multiscale Lorenz 96 system for which the parametrization model for unresolved scales is exactly known, and the two-dimensional Kraichnan turbulence system for which the parametrization model for unresolved scales is not known a priori. Our analysis, therefore, comprises a predictive dynamical core empowered by (i) a data-driven closure model for subgrid-scale processes, (ii) a data assimilation approach for forecast error correction, and (iii) both data-driven closure and data assimilation procedures. We show significant improvement in the long-term prediction of the underlying chaotic dynamics with our framework compared to using only neural network parametrizations for future prediction. Moreover, we demonstrate that these data-driven parametrization models can handle the non-Gaussian statistics of subgrid-scale processes, and effectively improve the accuracy of outer data assimilation workflow loops in a modular nonintrusive way.
42 ENGINEERING↗
Learning a trajectory using adjoint functions and teacher forcing
A new methodology for faster supervised temporal learning in nonlinear neural networks is presented which builds upon the concept of adjoint operators to allow fast computation of the gradients of an error functional with respect to all parameters of the neural architecture, and exploits the concept of teacher forcing to incorporate information on the desired output into the activation dynamics. The importance of the initial or final time conditions for the adjoint equations is discussed. A new algorithm is presented in which the adjoint equations are solved simultaneously (i.e., forward in time) with the activation dynamics of the neural network. We also indicate how teacher forcing can be modulated in time as learning proceeds. The results obtained show that the learning time is reduced by one to two orders of magnitude with respect to previously published results, while trajectory tracking is significantly improved. The proposed methodology makes hardware implementation of temporal learning attractive for real-time applications.
Toomarian, Nikzad B.↗
Unusual dynamics of tetrahedral liquids caused by the competition between dynamic heterogeneity and structural heterogeneity
Tetrahedral liquids exhibit intriguing thermodynamic and transport properties because of the various ways tetrahedra can be packed and connected. Recently, an unusual temperature dependence of the stretching exponent β in a model tetrahedral liquid ZnCl 2 from T m + 85 K to T m + 35 K has been reported using neutron-spin echo spectroscopy. This discovery stands in sharp contrast to other glass-forming liquids. In this study, we conducted neural network force field driven molecular dynamic simulations of ZnCl 2 . We found a non-monotonic temperature dependence of β from liquid to supercooled liquid temperatures. Further structural decomposition and dynamic analysis suggest that this unusual dynamic behavior is a result of the competition between the decrease in the diversity of tetrahedra motifs (structural heterogeneity) and the increase in glassy dynamic heterogeneity. Furthermore, this result may contribute to new understandings of the structural relaxation of other network liquids.
36 MATERIALS SCIENCE↗
Sharing is caring: An extensive analysis of parameter-based transfer learning for the prediction of building thermal dynamics
In recent years deep neural networks have been proposed as a lightweight data-driven model to capture high-dimensional, nonlinear physical processes to predict building thermal responses. However, the need of a large amount of data for the training process of deep neural networks clashes with the potential limited data availability in most existing or new buildings. Transfer learning aims to enhance the performance of a target learner exploiting knowledge from related and similar environments. This study conducted a suite of experiments that leveraged 250 data-driven models based on a synthetic dataset of a building archetype to study the influence of data availability, energy efficiency level, occupancy and climate for the transfer process of thermal dynamics. The performance of the transfer learning process was compared against a classical machine learning approach. Here, the results suggest that building thermal dynamics can be effectively transferred under the same climatic conditions, increasing performance when dealing with different occupancy schedules, efficiency levels and low data availability. Furthermore, the paper compares the performance of both transfer learning and machine learning approaches in an online fashion, to support the implementation in real-world deployment.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
Adaptive Activation Functions Accelerate Convergence in Deep and Physics-informed Neural Networks
We employ adaptive activation functions for regression in deep and physics-informed neural networks (PINNs) to approximate smooth and discontinuous functions as well as solutions of linear and nonlinear partial differential equations. In particular, we solve the nonlinear Klein-Gordon equation, which has smooth solutions, the nonlinear Burgers equation, which can admit high gradient solutions, and the Helmholtz equation. We introduce a scalable hyper-parameter in the activation function, which can be optimized to achieve best performance of the network as it changes dynamically the topology of the loss function involved in the optimization process. The adaptive activation function has better learning capabilities than the traditional one (fixed activation) as it improves greatly the convergence rate, especially at early training, as well as the solution accuracy. To better understand the learning process, we plot the neural network solution in the frequency domain to examine how the network captures successively different frequency bands present in the solution. We consider both forward problems, where the approximate solutions are obtained, as well as inverse problems, where parameters involved in the governing equation are identified. Our simulation results show that the proposed method is a very simple and effective approach to increase the efficiency, robustness and accuracy of the neural network approximation of nonlinear functions as well as solutions of partial differential equations, especially for forward problems. We theoretically prove that in the proposed method, gradient descent algorithms are not attracted to suboptimal critical points or local minima.
machine leaning, Bad minima, Inverse problems, Phy↗
Engineering monitoring expert system's developer
This research project is designed to apply artificial intelligence technology including expert systems, dynamic interface of neural networks, and hypertext to construct an expert system developer. The developer environment is specifically suited to building expert systems which monitor the performance of ground support equipment for propulsion systems and testing facilities. The expert system developer, through the use of a graphics interface and a rule network, will be transparent to the user during rule constructing and data scanning of the knowledge base. The project will result in a software system that allows its user to build specific monitoring type expert systems which monitor various equipments used for propulsion systems or ground testing facilities and accrues system performance information in a dynamic knowledge base.
Lo, Ching F.↗