Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Regularization”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Nonconvex regularization for sparse neural networks

Convex ℓ 1 regularization using an infinite dictionary of neurons has been suggested for constructing neural networks with desired approximation guarantees, but can be affected by an arbitrary amount of over-parametrization. This can lead to a loss of sparsity and result in networks with too many active neurons for the given data, in particular if the number of data samples is large. As a remedy, in this paper, a nonconvex regularization method is investigated in the context of shallow ReLU networks: We prove that in contrast to the convex approach, any resulting (locally optimal) network is finite even in the presence of infinite data (i.e., if the data distribution is known and the limiting case of infinite samples is considered). Moreover, here we show that approximation guarantees and existing bounds on the network size for finite data are maintained.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Magnetically charged regular black hole in a model of nonlinear electrodynamics

We obtain a magnetically charged regular black hole in general relativity. The source to the Einstein field equations is nonlinear electrodynamic field in a physically reasonable model of nonlinear electrodynamics (NED). “Physically” here means the NED model is constructed on the basis of three conditions: the Maxwell asymptotic in the weak electromagnetic field limit; the presence of vacuum birefringence phenomenon; and satisfying the weak energy condition (WEC). In addition, we analyze the thermodynamic properties of the regular black hole in two ways. According to the usual black hole thermodynamics, we calculate the heat capacity at constant charge, from which we know the smaller black hole is more stable. We also employ the horizon thermodynamics to discuss the thermodynamic quantities, especially the heat capacity at constant pressure.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2018

Generalized uncertainty principles, effective Newton constant and the regular black hole

In this paper, the quantum spacetime with a running gravitational coupling is explored. Analyzing the gravity-induced quantum interference pattern and the Gedanken for weighting a photon, we find that the running Newton constant can be inspired by the generalized uncertainty principles. A characteristic momentum associated with the tidal effect is suggested, which incorporates the quantum effect with the geometric nature of gravity. When the simplest generalized uncertainty principle is considered, the minimal model of the regular black holes is reproduced by the effective Newton constant. The black hole’s tunneling probability, accurate to the second order correction, is carefully analyzed. We find that the tunneling probability is regularized by the size of the black hole remnant. Moreover, for a given initial black hole, the remnant is the final state of a transition process that the probability is minimal. We also suggest a theory of modified gravity, by substituting the effective Newton constant into the Hilbert–Einstein action.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

From Anderson localization on random regular graphs to many-body localization

Highlights: • Anderson transition from ergodicity to localization on random regular graphs (RRG). • Analytical, pool method, and exact-diagonalization study of correlations on RRG. • Many-body localization (MBL) to ergodicity transition: quantum dots and spin chains. • Dynamical eigenstate correlation functions in RRG and MBL problems. • Anderson localization on RRG as a toy model for MBL. The article reviews the physics of Anderson localization on random regular graphs (RRG) and its connections to many-body localization (MBL) in disordered interacting systems. Properties of eigenstate and energy level correlations in delocalized and localized phases, as well at criticality, are discussed. In the many-body part, models with short-range and power-law interactions are considered, as well as the quantum-dot model representing the limit of the “most long-range” interaction. Central themes – which are common to the RRG and MBL problems – include ergodicity of the delocalized phase, localized character of the critical point, strong finite-size effects, and fractal scaling of eigenstate correlations in the localized phase.

36 MATERIALS SCIENCE↗
DOE OSTI2023

GRIDS-Net: Inverse shape design and identification of scatterers via geometric regularization and physics-embedded deep learning

This study presents a deep learning based methodology for both remote sensing and design of acoustic scatterers. The ability to determine the shape of a scatterer, either in the context of material design or sensing, plays a critical role in many practical engineering problems. This class of inverse problems is extremely challenging due to their high-dimensional, nonlinear, and ill-posed nature. To overcome these technical hurdles, we introduce a geometric regularization approach for deep neural networks (DNN) based on non-uniform rational B-splines (NURBS) and capable of predicting complex 2D scatterer geometries in a parsimonious dimensional representation. Then, this geometric regularization is combined with physics-embedded learning and integrated within a robust convolutional autoencoder (CAE) architecture to accurately predict the shape of 2D scatterers in the context of identification and inverse design problems. Further, an extensive numerical study is presented in order to showcase the remarkable ability of this approach to handle complex scatterer geometries while generating physically-consistent acoustic fields. The study also assesses and contrasts the role played by the (weakly) embedded physics in the convergence of the DNN predictions to a physically consistent inverse design.

42 ENGINEERING↗
DOE OSTI2013

Simulation of Canopy CO2/H2O Fluxes for a Rubber (Hevea Brasiliensis) Plantation in Central Cambodia: The Effect of the Regular Spacing of Planted Trees

We developed a soil-vegetation-atmosphere transfer (SVAT) model applicable to simulating CO2 and H2O fluxes from the canopies of rubber plantations, which are characterized by distinct canopy clumping produced by regular spacing of plantation trees. Rubber (Hevea brasiliensis Müll. Arg.) plantations, which are rapidly expanding into both climatically optimal and sub-optimal environments throughout mainland Southeast Asia, potentially change the partitioning of water, energy, and carbon at multiple scales, compared with traditional land covers it is replacing. Describing the biosphere-atmosphere exchange in rubber plantations via SVAT modeling is therefore essential to understanding the impacts on environmental processes. The regular spacing of plantation trees creates a peculiar canopy structure that is not well represented in most SVAT models, which generally assumes a non-uniform spacing of vegetation. Herein we develop a SVAT model applicable to rubber plantation and an evaluation method for its canopy structure, and examine how the peculiar canopy structure of rubber plantations affects canopy CO2 and H2O exchanges. Model results are compared with measurements collected at a field site in central Cambodia. Our findings suggest that it is crucial to account for intensive canopy clumping in order to reproduce observed rubber plantation fluxes. These results suggest a potentially optimal spacing of rubber trees to produce high productivity and water use efficiency.

eddy covariance↗
DOE OSTI2013

Optical tomography reconstruction algorithm with the finite element method: An optimal approach with regularization tools

Highlights: •New strategies to improve the accuracy of the reconstruction through mesh and finite element parameterization. •Use of gradient filtering through an alternative inner product within the adjoint method. •An integral form of the cost function is used to make the reconstruction compatible with all finite element formulations, continuous and discontinuous. •Gradient-based algorithm with the adjoint method is used for the reconstruction. -- Abstract: Optical tomography is mathematically treated as a non-linear inverse problem where the optical properties of the probed medium are recovered through the minimization of the errors between the experimental measurements and their predictions with a numerical model at the locations of the detectors. According to the ill-posed behavior of the inverse problem, some regularization tools must be performed and the Tikhonov penalization type is the most commonly used in optical tomography applications. This paper introduces an optimized approach for optical tomography reconstruction with the finite element method. An integral form of the cost function is used to take into account the surfaces of the detectors and make the reconstruction compatible with all finite element formulations, continuous and discontinuous. Through a gradient-based algorithm where the adjoint method is used to compute the gradient of the cost function, an alternative inner product is employed for preconditioning the reconstruction algorithm. Moreover, appropriate re-parameterization of the optical properties is performed. These regularization strategies are compared with the classical Tikhonov penalization one. It is shown that both the re-parameterization and the use of the Sobolev cost function gradient are efficient for solving such an ill-posed inverse problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

A physics-informed and hierarchically regularized data-driven model for predicting fluid flow through porous media

This paper presents a new deep learning data-driven model for predicting structure dependent pore-fluid velocity fields in rock. The model is based on a Convolutional Auto-Encoder (CAE) artificial neural network capable of learning from image data generated by direct numerical simulations of fluid flow through pore-structures, such as by Lattice Boltzmann or molecular dynamics methods. The main novelty of the model in comparison to previous CAE-based data-driven approaches consists of three parts. The first is a methodology for decomposing the full-domain of the porous media into sub-regions, or “sub-domains”, in order to reduce the overall size of the CAE, batch process the sub-domains in parallel, and enable the CAE to learn local and generalizable nonlinear mappings of pore-fluid velocities. The second consists of embedding the finite difference solutions of the incompressible Navier-Stokes and continuity equations into convolutional layers prior to the CAE in order to provide the CAE with knowledge of fluid dynamics physics (PhyFlow). The third main novelty is that the training of the CAE is regularized with a hierarchical loss function that encourages the learning of fluid flow patterns (in a way similar to ranked modes in principal component analysis), ranking from most to least important. This is shown to increase the stability in learning, reduce over-fitting, and promote interpretability of the CAE neural network layers (HierCAE). The comprehensive new data-driven model, which we call the PhyFlow-HierCAE model, is shown to exhibit improved accuracy and generalizability of flow field predictions over conventional CAE models, attributable to the embedded physical knowledge and the hierarchical regularization, as well as realize orders of magnitude speed-ups in computation times as a surrogate for the direct numerical simulations. Examples of training and forward predictions on unseen pore-structures are provided and evaluated for data from Lattice Boltzmann and molecular dynamics simulations of pore-fluid flow. The model is shown to be a fast and accurate emulator (or “surrogate”) for predicting effective permeability of unseen pore-structures based on learning from relatively small direct numerical simulation datasets.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processes

The ability of recurrent neural networks (RNN) to model nonlinear dynamics of high dimensional process data has enabled data-driven RNN-based fault detection algorithms. Previous studies have focused on detecting faults by identifying the discrepancies in data distribution between the faulty and normal data, as reflected in prediction errors generated by RNN models. However, in industrial processes, variations in data distribution can also result from changes in normal control setpoints and compensatory control adjustments in response to disturbances, making it hard to differentiate between normal and faulty conditions. This paper proposes a fault detection method utilizing a long short-term memory (LSTM) encoder–decoder structure with regularized hidden dynamics and reversible instance normalization (RevIN) to compactly represent high-dimensional measurements for effective monitoring. During training, the hidden states of the model are regularized to form a low-dimensional latent space representation of the original multivariate time series data. As a result, the prediction errors of the latent states can be used to monitor the abnormal dynamic variations, while the reconstruction errors of the measured variables are used to monitor the abnormal static variations. Furthermore, the proposed indices can reflect operating conditions, even when the distribution of test data changes, which helps distinguish faults from normal adjustments and disturbances that controllers can settle. Here, data from numerical simulation and the Tennessee Eastman process are used to illustrate the effectiveness of the proposed fault detection method.

42 ENGINEERING↗
DOE OSTI2020

A practical way to regularize unfolding of sharply varying spectra with low data statistics

Unfolding is a well-established tool in particle physics. However, a naive application of the standard regularization techniques to unfold the momentum spectrum of protons ejected in the process of negative muon nuclear capture led to a result exhibiting unphysical artifacts. A finite data sample limited the range in which unfolding can be performed, thus introducing a cutoff. A sharply falling “true” distribution led to low data statistics near the cutoff, which exacerbated the regularization bias and produced an unphysical spike in the resulting spectrum. An improved approach has been developed to address these issues and is illustrated using a toy model. The approach uses full Poisson likelihood of data, and produces a continuous, physically plausible, unfolded distribution. Here, the new technique has a broad applicability since sharply falling spectra are common.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions

Abstract Despite recent advances in high-throughput combinatorial mutagenesis assays, the number of labeled sequences available to predict molecular functions has remained small for the vastness of the sequence space combined with the ruggedness of many fitness functions. While deep neural networks (DNNs) can capture high-order epistatic interactions among the mutational sites, they tend to overfit to the small number of labeled sequences available for training. Here, we developed Epistatic Net (EN), a method for spectral regularization of DNNs that exploits evidence that epistatic interactions in many fitness functions are sparse. We built a scalable extension of EN, usable for larger sequences, which enables spectral regularization using fast sparse recovery algorithms informed by coding theory. Results on several biological landscapes show that EN consistently improves the prediction accuracy of DNNs and enables them to outperform competing models which assume other priors. EN estimates the higher-order epistatic interactions of DNNs trained on massive sequence spaces-a computational problem that otherwise takes years to solve.

Aghazadeh, Amirali (ORCID:0000000302230873)↗
DOE OSTI2026

Regularization by denoising diffusion models for solving inverse PDE problems with application to full waveform inversion

Partial differential equation (PDE)-governed inverse problems are fundamental across various scientific and engineering applications; yet they face significant challenges due to nonlinearity, ill-posedness, and sensitivity to noise. Here, we introduce a computational framework, regularization by denoising using diffusion models for partial differential equations (RED-DiffEq), by integrating physics-driven inversion and data-driven learning. RED-DiffEq leverages pretrained diffusion models as a regularization mechanism for PDE-governed inverse problems. We apply RED-DiffEq to solve the full waveform inversion problem in geophysics, a challenging seismic imaging technique that seeks to reconstruct high-resolution subsurface velocity models from seismic measurement data. Our method shows enhanced accuracy and robustness compared to benchmark methods. Additionally, it exhibits strong generalization and domain decomposition capacity, enabling the inversion of more complex velocity models with larger domains than those used in training the diffusion model. Our framework can also be directly applied to diverse PDE-governed inverse problems.

Shan, Siming [Yale University, New Haven, CT (Unit↗
DOE OSTI2022

Sequentially regular polymer acceptors featuring flexible spacers for high-performance and mechanically robust all-polymer solar cells

Developing high-performance and mechanically robust polymer solar cells (PSCs) is crucial for realizing wearable power sources. While efficient all-polymer solar cells (all-PSCs) can be fabricated from polymerized small-molecule acceptors (PSMAs) with high optical absorption and electron mobilities, they still show limited mechanical robustness. Here, we achieve highly efficient and mechanically robust all-PSCs by designing a PSMA (PYFS-Reg) containing sequence-regular flexible spacers (FSs). The regular incorporation of the FS units into PSMAs is essential in simultaneously improving the electrical and mechanical properties of blend films. As a result, all-PSCs featuring PYFS-Reg achieve a high power conversion efficiency (PCE = 16.1%) and stretchability (crack onset strain (COS) = 22.4%), outperforming PSMAs without FSs (i.e., PYBDT, PCE = 12.6% and COS = 11.7%) or with randomly distributed FSs (i.e., PYFS-Ran, PCE = 12.2% and COS = 18.1%). Importantly, these all-PSCs are fabricated by an environmentally benign, non-halogenated solvent process. To further demonstrate their feasible applications in wearable devices, we construct intrinsically stretchable (IS) all-PSCs by using PYFS-Reg-based active layers, which exhibit a high PCE (10.6%) and excellent device stretchability (strain at PCE 80% = 36.7%).

14 SOLAR ENERGY↗
DOE OSTI2013

Minimum Fisher regularization of image reconstruction for infrared imaging bolometer on HL-2A

An infrared imaging bolometer diagnostic has been developed recently for the HL-2A tokamak to measure the temporal and spatial distribution of plasma radiation. The three-dimensional tomography, reduced to a two-dimensional problem by the assumption of plasma radiation toroidal symmetry, has been performed. A three-dimensional geometry matrix is calculated with the one-dimensional pencil beam approximation. The solid angles viewed by the detector elements are taken into account in defining the chord brightness. And the local plasma emission is obtained by inverting the measured brightness with the minimum Fisher regularization method. A typical HL-2A plasma radiation model was chosen to optimize a regularization parameter on the criterion of generalized cross validation. Finally, this method was applied to HL-2A experiments, demonstrating the plasma radiated power density distribution in limiter and divertor discharges.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2014

Regularization approach for tomosynthesis X-ray inspection

X-ray inspection is intended to be used as an escalation technique for inspection of carbon fiber reinforced plastics (CFRP) in aerospace applications, especially in case of unclear indications from ultrasonic or other NDT modalities. Due to their large dimensions, most aerospace components cannot be scanned by conventional computed tomography. In such cases, X-ray Laminography may be applied, allowing a pseudo 3D slice-by-slice reconstruction of the sample with Tomosynthesis. However, due to the limited angle acquisition geometry, reconstruction artifacts arise, especially at surfaces parallel to the imaging plane. To regularize the Tomosynthesis approach, we propose an additional prescan of the object to detect outer sample surfaces. We recommend the use of contrasted markers which are temporarily attached to the sample surfaces. The depth position of the markers is then derived from that prescan. As long as the sample surface remains simple, few markers are required to fit the respective object surfaces. The knowledge about this surface may then be used to regularize the final Tomosynthesis reconstruction, performed with markerless projections. Eventually, it can also serve as prior information for an ART reconstruction or to register a CAD model of the sample. The presented work is carried out within the European FP7 project QUICOM. We demonstrate the proposed approach within a simulation study applying an acquisition geometry suited for CFRP part inspection. A practical verification of the approach is planned later in the project.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2015

The geometric β-function in curved space-time under operator regularization

In this paper, I compare the generators of the renormalization group flow, or the geometric β-functions, for dimensional regularization and operator regularization. I then extend the analysis to show that the geometric β-function for a scalar field theory on a closed compact Riemannian manifold is defined on the entire manifold. I then extend the analysis to find the generator of the renormalization group flow to conformally coupled scalar-field theories on the same manifolds. The geometric β-function in this case is not defined.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2016

Mutual interaction between high and low stereo-regularity components for crystallization and melting behaviors of polypropylene blend fibers

Crystallization and melting behaviors of blend fibers of two types of polypropylene (PP), i.e. high stereo-regularity/high molecular weight PP (HPP) and low stereo-regularity/low molecular weight PP (LPP), was investigated. Blend fibers consisting of various HPP/LPP compositions were prepared through the melt spinning process. Differential scanning calorimetry (DSC), temperature modulated DSC (TMDSC) and wide-angle X-ray diffraction (WAXD) analysis were applied for clarifying the crystallization and melting behaviors of individual components. In the DSC measurement of blend fibers with high LPP composition, continuous endothermic heat was detected between the melting peaks of LPP at around 40 °C and that of HPP at around 160 °C. Such endothermic heat was more distinct for the blend fibers with higher LPP composition indicating that the melting of LPP in the heating process was hindered because of the presence of HPP crystals. On the other hand, heat of crystallization was detected at around 90 °C in the case of blend fibers with LPP content of 30 to 70 wt%, indicating that the crystallization of HPP component was taking place during the heating of as-spun blend fibers in the DSC measurement. Through the TMDSC analysis, re-organization of the crystalline structure through the simultaneous melting and re-crystallization was detected in the cases of HPP and blend fibers, whereas re-crystallization was not detected during the melting of LPP fibers. In the WAXD analysis during the heating of fibers, amount of a-form crystal was almost constant up to the melting in the case of single component HPP fibers, whereas there was a distinct increase of the intensity of crystalline reflections from around 100 °C, right after the melting of LPP in the case of blend fibers. These results suggested that the crystallization of HPP in the spinning process as well as during the conditioning process after spinning was hindered by the presence of LPP.

36 MATERIALS SCIENCE↗
DOE OSTI2020

A light weight regularization for wave function parameter gradients in quantum Monte Carlo

The parameter derivative of the expectation value of the energy, ∂E/∂p, is a key ingredient in variational Monte Carlo (VMC) wave function optimization methods. In some cases, a naïve estimate of this derivative suffers from an infinite variance, which inhibits the efficiency of optimization methods that rely on a stable estimate of the derivative. In this work, we derive a simple regularization of the naïve estimator, which is trivial to implement in existing VMC codes, has finite variance, and a negligible bias, which can be extrapolated to zero bias with no extra cost. We use this estimator to construct an unbiased, finite variance estimation of ∂E/∂p for a multi-Slater–Jastrow trial wave function on the LiH molecule and in the optimization of a multi-Slater–Jastrow trial wave function on the CuO molecule. This regularized estimator is a simple and efficient estimator of ∂E/∂p for VMC optimization techniques.

36 MATERIALS SCIENCE↗