Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Neural Networks (Computer)”

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

Fast neural Poincaré maps for toroidal magnetic fields

Poincaré maps for toroidal magnetic fields are routinely employed to study gross confinement properties in devices built to contain hot plasmas. In most practical applications, evaluating a Poincaré map requires numerical integration of a magnetic field line, a process that can be slow and that cannot be easily accelerated using parallel computations. We propose a novel neural network architecture, the HénonNet, and show that it is capable of accurately learning realistic Poincaré maps from observations of a conventional field-line-following algorithm. After training, such learned Poincaré maps evaluate much faster than the field-line integration method. Moreover, the HénonNet architecture exactly reproduces the primary physics constraint imposed on field-line Poincaré maps: flux preservation. Furthermore, this structure-preserving property is the consequence of each layer in a HénonNet being a symplectic map. We demonstrate empirically that a HénonNet can learn to mock the confinement properties of a large magnetic island by using coiled hyperbolic invariant manifolds to produce a sticky chaotic region at the desired island location. This suggests a novel approach to designing magnetic fields with good confinement properties that may be more flexible than ensuring confinement using KAM tori.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Leveraging dendritic complexity for neuromorphic computing

Abstract Beyond-von Neumann computing approaches are necessary to sustain the growth of microelectronics and the increasing appetite for artificial intelligence/machine learning algorithms. Neuromorphic computing is an emerging paradigm that takes inspiration from the brain to provide a path forward to improve the computational efficiency and computational density of next-generation computing architectures. In nature, we observe brains performing complex computations with a much smaller energy footprint than conventional computing approaches. Current neuromorphic systems are focused primarily on scalability, namely, increasing the number of computational units (neurons) and connections between units (synapses). However, for brain-like cognition and efficiency in next-generation computing hardware, we need increased complexity in function, as well as improved connection density for scalability. Here, we present our work that aims to incorporate dendrites for ‘compute-on-wire’ in neuromorphic architectures to increase the computational complexity (e.g. number of programmable parameters, nonlinear dynamics) as well as computational efficiency (energy/compute) of artificial neural networks (ANNs). We do this by showcasing neuromorphic dendrite elements that can be leveraged for various applications. We will present examples of neuroscience-inspired direction-selective circuits and an ANN with active dendrites leveraging shunting inhibition. We also demonstrate the benefits of using dendrites in deep neural networks. To conclude, we discuss how we can utilize emerging hardware devices in these systems and design next-generation neuromorphic architectures with dendrites.

Cardwell, Suma G. (ORCID:0000000226575545)↗

Inference of response functions with the help of machine-learning algorithms

Response functions are a key quantity to describe the near-equilibrium dynamics of strongly interacting many-body systems. Recent techniques that attempt to overcome the challenges of calculating these ab initio have employed expansions in terms of orthogonal polynomials. We employ a neural network prediction algorithm to reconstruct a response function 𝑆⁡(𝜔) defined over a range in frequencies 𝜔. Here, we represent the calculated response function as a truncated Chebyshev series whose coefficients can be optimized to reduce the representation error. We compare the quality of response functions obtained using coefficients calculated using a neural network (NN) algorithm with those computed using the Gaussian integral transform (GIT) method. In the regime where only a small number of terms in the Chebyshev series are retained, we find that the NN scheme outperforms the GIT method.

Kurkcuoglu, Doga Murat [Fermi National Accelerator↗

Real-Time Evolution and Deployment of Neuromorphic Computing at The Edge

Extremely low power neuromorphic systems are well-suited for deployment to the edge for many applications. In many use cases of neuromorphic computing for control, a spiking neural network is trained off-line using a simulation and then deployed to a neuromorphic system at the edge, where it will operate without ongoing training or learning. However, it may be desirable to continue training or learning at the edge to refine or adapt to the real-world system. In this work, we propose an approach for performing real-time evolutionary optimization for spiking neural networks for neuromorphic deployment at the edge. In particular, we propose a combination of simulation and real-world evaluations, along with feedback from the real-world environment, to train spiking neural networks for continuous deployment to the edge. We show that the real-time evolution at the edge approach achieves comparable performance to an evolution approach that requires constant evaluation in the realworld environment.

Schuman, Catherine↗

DFSynthesizer: Dataflow-based Synthesis of Spiking Neural Networks to Neuromorphic Hardware

Spiking Neural Networks (SNNs) are an emerging computation model that uses event-driven activation and bio-inspired learning algorithms. SNN-based machine learning programs are typically executed on tile-based neuromorphic hardware platforms, where each tile consists of a computation unit called a crossbar, which maps neurons and synapses of the program. However, synthesizing such programs on an off-the-shelf neuromorphic hardware is challenging. This is because of the inherent resource and latency limitations of the hardware, which impact both model performance, e.g., accuracy, and hardware performance, e.g., throughput. We propose DFSynthesizer, an end-to-end framework for synthesizing SNN-based machine learning programs to neuromorphic hardware. The proposed framework works in four steps. First, it analyzes a machine learning program and generates SNN workload using representative data. Second, it partitions the SNN workload and generates clusters that fit on crossbars of the target neuromorphic hardware. Third, it exploits the rich semantics of the Synchronous Dataflow Graph (SDFG) to represent a clustered SNN program, allowing for performance analysis in terms of key hardware constraints such as number of crossbars, dimension of each crossbar, buffer space on tiles, and tile communication bandwidth. Finally, it uses a novel scheduling algorithm to execute clusters on crossbars of the hardware, guaranteeing hardware performance. We evaluate DFSynthesizer with 10 commonly used machine learning programs. Our results demonstrate that DFSynthesizer provides a much tighter performance guarantee compared to current mapping approaches.

Computer Science↗

G-Band Vapor Radiometer Precipitable Water Vapor (GVRPWV) Value-Added Product

The G-Band Vapor Radiometer Precipitable Water Vapor (GVRPWV) value-added product (VAP) computes precipitable water vapor using neural network techniques from data measured by the GVR. The GVR reports time-series measurements of brightness temperatures for four channels located at 183.3 ± 1, 3, 7, and 14 GHz.

54 ENVIRONMENTAL SCIENCES↗

How is statistical thinking useful for evaluating foundation models?

Good’s statement appears to be rather prescient – while humanity has marched on through to the 21st century, modern artificial intelligence (AI), driven by a menagerie of immense deep-neural-network architectures aided with parallel computation, seems positioned to change life as we know it. It would be an understatement to say that the world has been captivated by AI. Recent engineering feats, such as autonomous vehicles and generative AI, have gripped the public sphere, and AI is poised to disrupt a host of industries – including software, pharmaceuticals, healthcare, manufacturing, entertainment, and a slew of others; indeed, one is hard pressed to find any industry that does not claim to bear an impact from the so-called AI revolution.

97 MATHEMATICS AND COMPUTING↗

Demonstrate new plasticity models for doped UO 2 that capture dislocation mechanisms

In light water reactors, fuel vendors are investigating the use of dopants to modify the properties of UO 2 pellets, with the goal of improving pellet-cladding mechanical interactions during operation. Dopants are expected to ‘soften’ the pellets; that is, the doped pellets have higher plastic deformation than conventional UO 2 . This leads to a reduction in the severity of mechanical pellet-cladding interactions, helping to reduce the hoop strain on the cladding. By minimizing the strain exerted by the pellet on the cladding, it is anticipated that cladding performance under accident conditions can be enhanced (i.e., lowering the risk of burst during a LOCA). Dopants such as chromium (Cr) promote grain growth during pellet fabrication, leading to larger grains; therefore, understanding the link between chemistry, microstructure and mechanical deformation (enhanced creep rates) behavior of UO 2 is critical to helping operators further substantiate the benefits of doping UO 2 . Historically, the nuclear energy industry has relied on empirical models to make assessments of performance. Compared to empirical models, mechanistic physics-based models provide benefits, such as, fewer data points for validation and better extrapolation where experimental data is scarce or non-existent. In this report, Bayesian inference techniques have been applied to a previously developed lower length-scale-informed diffusional creep model. The objective is to i) infer lower-length-scale parameter distributions from available experiment and then ii) determine the uncertainties in the measurable quantity (in this case creep rates) after propagating the inferred lower length scale parameter uncertainties. The approach requires many evaluations of the model, which becomes computationally insurmountable; therefore, a neural-network model is trained to data obtained by sampling the full model over the most important parameters. This neural-network is then used in the Bayesian inference approach to determine probability distributions in the parameter values that represent the uncertainty in the model given what is known from the experiments (posterior). A significant reduction compared to conservative initial (prior) uncertainties is achieved through inference against the experimental data, demonstrating the efficacy of this approach. Furthermore, by accounting for uncertainties in the experimental conditions and sample non-stoichiometry, it is possible to resolve apparent discrepancies in experimental measurements within a self-consistent grain boundary (Coble) creep model that is sensitive to chemistry. This work has been written up and submitted to Nuclear Technology for a special issue on accelerated fuel qualification (AFQ). This uncertainty quantification (UQ) work not only improves the diffusional model, while accounting for uncertainty, but also establishes a framework which can readily be applied to the mechanistic models of dislocation deformation developed in this study. The most likely values from the Bayesian analysis are incorporated into our UO 2 diffusional creep model and a lower length scale-informed irradiation UO 2 creep mechanistic model to generate a dataset. This dataset has been provided to our INL collaborators for training an artificial neural network surrogate model, which will be implemented in the BISON fuel performance code to assess how the results differ from those currently obtained using a fully empirical model and that of using the nominal (uncalibrated) atomic scale parameters in our mechanistic model. Plastic deformation (creep and glide) in UO 2 is a complex phenomenon, governed by multiple underlying processes such as local defect concentrations, applied stresses, and microstructural characteristics. Consequently, there is a need for a meso-scale model with polycrystalline resolution capable of extrapolating to large grain sizes applicable to doped UO 2 , where data is limited and the model can help bridge the knowledge gap. By integrating atomistic data into the polycrystal LApx code, it becomes possible to predict dislocation climb and glide plasticity that simple analytical models cannot accurately represent. The application of atomic-scale data within LApx demonstrated the importance of climb and glide mechanisms in reproducing high-stress UO 2 behavior. Behaviors such as this are crucial to capture and implement in BISON, as parts of the fuel pellet can reach temperatures where glide can occur before pellet cracking. This model which captures dislocation based mechanisms for UO 2 is then used to stand up the doped model accounting for larger grain sizes. It was found that larger grain sizes can lead to enhanced deformation rates in the glide regime, and therefore can help with the pellet cladding mechanical interaction. Therefore if the fuel pellet reaches conditions (stress/temperature) where glide is active, the enhanced creep rates for larger grains in the glide regime (doped UO 2 ) can help with pellet cladding mechanical interactions. Plastic deformation in UO 2 involves multiple mechanisms, including diffusional creep, dislocation climb, and glide. This milestone contains two parts: (1) UQ of a pre-existing lower length scale informed mechanistic diffusional creep model, and (2) development of a new LApx based model for dislocation-mediated creep mechanisms in UO 2 , with application to large-grain doped UO 2 .

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Explosion Detection using Transfer Learning via YAMNet [Poster]

The acoustic data of explosions and noise collected on smartphones were fed to the YAMNet model to obtain the scores of each class. The data was split 60/20/20 for training, validation, and testing. A single-layered neural network was trained using the computed scores to predict if the data was an explosion or noise. The trained model was then combined with the YAMNet model. The combined model was tested with the ESC-50 dataset to investigate overall accuracy and class based false positive rates.

98 - NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL↗

Application and Evaluation of Surrogate Models for Radiation Source Search

Surrogate models are increasingly required for applications in which first-principles simulation models are prohibitively expensive to employ for uncertainty analysis, design, or control. They can also be used to approximate models whose discontinuous derivatives preclude the use of gradient-based optimization or data assimilation algorithms. We consider the problem of inferring the 2D location and intensity of a radiation source in an urban environment using a ray-tracing model based on Boltzmann transport theory. Whereas the code implementing this model is relatively efficient, extension to 3D Monte Carlo transport simulations precludes subsequent Bayesian inference to infer source locations, which typically requires thousands to millions of simulations. Additionally, the resulting likelihood exhibits discontinuous derivatives due to the presence of buildings. To address these issues, we discuss the construction of surrogate models for optimization, Bayesian inference, and uncertainty propagation. Specifically, we consider surrogate models based on Legendre polynomials, multivariate adaptive regression splines, radial basis functions, Gaussian processes, and neural networks. We detail strategies for computing training points and discuss the merits and deficits of each method.

Cook, Jared A.↗

A Hybrid Approach for Model Order Reduction of Barotropic Quasi-Geostrophic Turbulence

We put forth a robust reduced-order modeling approach for near real-time prediction of mesoscale flows. In our hybrid-modeling framework, we combine physics-based projection methods with neural network closures to account for truncated modes. We introduce a weighting parameter between the Galerkin projection and extreme learning machine models and explore its effectiveness, accuracy and generalizability. To illustrate the success of the proposed modeling paradigm, we predict both the mean flow pattern and the time series response of a single-layer quasi-geostrophic ocean model, which is a simplified prototype for wind-driven general circulation models. We demonstrate that our approach yields significant improvements over both the standard Galerkin projection and fully non-intrusive neural network methods with a negligible computational overhead.

42 ENGINEERING↗

How Captain Amerika uses neural networks to fight crime

Artificial neural network models can make amazing computations. These models are explained along with their application in problems associated with fighting crime. Specific problems addressed are identification of people using face recognition, speaker identification, and fingerprint and handwriting analysis (biometric authentication).

Rogers, Steven K.↗

Automatic Inspection of Aircraft Using Open-Architecture Robotic Platforms

Aging aircraft structures and composite materials are requiring rapid inspection of large areas. Removal from the aircraft for NDE at an inspection facility is not economical as compared to field inspection. Detection and characterization of defects are labor intensive, time consuming and when the process is manual the results are subjected to human error. These limitations of NDE created a need for portable, user friendly inspection systems that can rapidly scan large areas of complex structures and locate all the detrimental material conditions. Addressing this need has been an evolutionary process that followed the technology trend, and unique devices were developed to allow rapid field inspection. This development involves multi-disciplinary approaches to integrate NDE, telerobotics, neural networks, advanced materials science, imbedded computing and automated control. These efforts have led to the development of various portable inspection systems and the current trend is towards fully automatic systems that will operate autonomously.

Bar-Cohen, Yoseph↗

Intelligent, Robust Control of Deteriorated Turbofan Engines via Linear Parameter Varying Quadratic Lyapunov Function Design

A method for accommodating engine deterioration via a scheduled Linear Parameter Varying Quadratic Lyapunov Function (LPVQLF)-Based controller is presented. The LPVQLF design methodology provides a means for developing unconditionally stable, robust control of Linear Parameter Varying (LPV) systems. The controller is scheduled on the Engine Deterioration Index, a function of estimated parameters that relate to engine health, and is computed using a multilayer feedforward neural network. Acceptable thrust response and tight control of exhaust gas temperature (EGT) is accomplished by adjusting the performance weights on these parameters for different levels of engine degradation. Nonlinear simulations demonstrate that the controller achieves specified performance objectives while being robust to engine deterioration as well as engine-to-engine variations.

Turso, James A.↗

Telerobotic Surgery: An Intelligent Systems Approach to Mitigate the Adverse Effects of Communication Delay

An extremely innovative approach has been presented, which is to have the surgeon operate through a simulator running in real-time enhanced with an intelligent controller component to enhance the safety and efficiency of a remotely conducted operation. The use of a simulator enables the surgeon to operate in a virtual environment free from the impediments of telecommunication delay. The simulator functions as a predictor and periodically the simulator state is corrected with truth data. Three major research areas must be explored in order to ensure achieving the objectives. They are: simulator as predictor, image processing, and intelligent control. Each is equally necessary for success of the project and each of these involves a significant intelligent component in it. These are diverse, interdisciplinary areas of investigation, thereby requiring a highly coordinated effort by all the members of our team, to ensure an integrated system. The following is a brief discussion of those areas. Simulator as a predictor: The delays encountered in remote robotic surgery will be greater than any encountered in human-machine systems analysis, with the possible exception of remote operations in space. Therefore, novel compensation techniques will be developed. Included will be the development of the real-time simulator, which is at the heart of our approach. The simulator will present real-time, stereoscopic images and artificial haptic stimuli to the surgeon. Image processing: Because of the delay and the possibility of insufficient bandwidth a high level of novel image processing is necessary. This image processing will include several innovative aspects, including image interpretation, video to graphical conversion, texture extraction, geometric processing, image compression and image generation at the surgeon station. Intelligent control: Since the approach we propose is in a sense predictor based, albeit a very sophisticated predictor, a controller, which not only optimizes end effector trajectory but also avoids error, is essential. We propose to investigate two different approaches to the controller design. One approach employs an optimal controller based on modern control theory; the other one involves soft computing techniques, i.e. fuzzy logic, neural networks, genetic algorithms and hybrids of these.

Cardullo, Frank M.↗

Development of a Filtered CFD-DEM Drag Model with Multiscale Markers Using an Artificial Neural Network and Nonlinear Regression

Here, the accuracy of coarse-grained Euler-Lagrangian simulations of fluidized beds heavily depends on the mesoscale drag models to account for the influences of the unresolved sub-grid structures. Traditional filtered drag models are regressed with mesoscale markers such as voidage and slip velocities. In this research, a filtered drag was regressed with both mesoscale and macro-scale markers using fine grid Computational Fluid Dynamics - Discrete Element Method (CFD-DEM) simulations. The traditional non-linear regression method was compared with machine learning regression using an Artificial Neural Network (ANN) implemented in PyTorch and coupled with MFiX. The new drag showed higher accuracy than the Wen-Yu drag and another filtered drag derived from the two-fluid model. The nonlinear regression shows slightly better results than ANN regression in cases with similar R 2 values. The utilization of the gas inlet velocity as an additional macro-scale marker reduced the errors by up to 55.3% in the tested cases.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

On the Convergence of Physics Informed Neural Networks for Linear Second-Order Elliptic and Parabolic Type PDEs

Physics informed neural networks (PINNs) are deep learning based techniques for solving partial differential equations (PDEs) encountered in computational science and engineering. Guided by data and physical laws, PINNs find a neural network that approximates the solution to a system of PDEs. Such a neural network is obtained by minimizing a loss function in which any prior knowledge of PDEs and data are encoded. Despite its remarkable empirical success in one, two or three dimensional problems, there is little theoretical justification for PINNs. As the number of data grows, PINNs generate a sequence of minimizers which correspond to a sequence of neural networks. We want to answer the question: Does the sequence of minimizers converge to the solution to the PDE? We consider two classes of PDEs: linear second-order elliptic and parabolic. By adapting the Schauder approach and the maximum principle, we show that the sequence of minimizers strongly converges to the PDE solution in C 0 . Furthermore, we show that if each minimizer satisfies the initial/boundary conditions, the convergence mode becomes H 1 . Computational examples are provided to illustrate our theoretical findings. To the best of our knowledge, this is the first theoretical work that shows the consistency of PINNs.

97 MATHEMATICS AND COMPUTING↗

Vector-Matrix Multiplication Engine for Neuromorphic Computation with a CBRAM Crossbar Array [Slides]

The core function of many neural network algorithms is the dot product, or vector matrix multiply (VMM) operation. Crossbar arrays utilizing resistive memory elements can reduce computational energy in neural algorithms by up to five orders of magnitude compared to conventional CPUs. Moving data between a processor, SRAM, and DRAM dominates energy consumption. By utilizing analog operations to reduce data movement, resistive memory crossbars can enable processing of large amounts of data at lower energy than conventional memory architectures.

97 MATHEMATICS AND COMPUTING↗