Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “inverse prediction methods”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
NASA NTRS1988

Canopy reflectance modeling in a tropical wooded grassland

The Li-Strahler canopy reflectance model, driven by LANDSAT Thematic Mapper (TM) data, provided regional estimates of tree size and density in two bioclimatic zones in Africa. This model exploits tree geometry in an inversion technique to predict average tree size and density from reflectance data using a few simple patameters measured in the field and in the imagery. Reflectance properties of the trees were measured in the study sites using a pole-mounted radiometer. The measurements showed that the assumptions of the simple Li-Strahler model are reasonable for these woodlands. The field radiometer measurements were used to calculate the normalized difference vegetation index (NDVI), and the integrated NDVI over the canopy was related to crown volume. Predictions of tree size and density from the canopy model were used with allometric equations from the literature to estimate woody biomass and potential foliar biomass for the sites and for the regions. Estimates were compared with independent measurements made in the Sahelian sites, and to typical values from the literature for these regions and for similar woodlands. In order to apply the inversion procedure regionally, an area must first be stratified into woodland cover classes, and dry-season TM data were used to generate a stratum map of the study areas with reasonable accuracy. The method used was unsupervised classification of multi-data principal components images.

Simonett, David↗
NASA NTRS1994

Advanced studies of electromagnetic scattering

In radar signature applications it is often desirable to generate the range profiles and inverse synthetic aperture radar (ISAR) images of a target. They can be used either as identification tools to distinguish and classify the target from a collection of possible targets, or as diagnostic/design tools to pinpoint the key scattering centers on the target. The simulation of synthetic range profiles and ISAR images is usually a time intensive task and computation time is of prime importance. Our research has been focused on the development of fast simulation algorithms for range profiles and ISAR images using the shooting and bouncing ray (SBR) method, a high frequency electromagnetic simulation technique for predicting the radar returns from realistic aerospace vehicles and the scattering by complex media.

Ling, Hao↗
DOE OSTI2024

A deep learning-based workflow for fast prediction of 3D state variables in geological carbon storage: A dimension reduction approach

Deep learning (DL) models are extensively used as surrogate models for high-fidelity simulations of multiphase fluid flow in porous media at large scales, enabling fast forecasts of the spatial–temporal evolution of three-dimensional (3D) state variables in geological carbon storage (GCS). However, training these models in high-dimensional space remains computationally demanding and prone to overfitting because of limited training data. This paper presents a novel workflow to address these challenges by integrating dimension reduction (DR) methods. Here, the proposed workflow employed pre-trained DR models to extract the latent variables of geological models and state variables and utilized the multi-layer perceptron (MLP) for constructing mapping functions between the input and output variables in latent spaces. Subsequently, the pre-trained reconstruction models converted the MLP-predicted latent state variables to their original high-dimensional form. Furthermore, we proposed a novel strategy for the DR and reconstruction of 3D saturation fields to account for the unique data characteristics of sparsity, nonuniformity, and discontinuity. The proposed strategy applied PCA and inverse PCA for 2D average saturation fields and developed a DL-based 3D reconstruction model, leveraging three 2D average saturation fields as input to produce a 3D saturation field as output. The pre-training of DR and reconstruction models and training of MLP models were conducted on 84 Gulf of Mexico (GoM) simulations and evaluated on 12 testing simulations. Each simulation contained 720 monthly time steps, with the first 360 months as the injection period and the rest as the post-injection period. The proposed workflow, incorporating DR and DL models, accurately predicts the normalized 3D pressure fields, achieving mean square error (MSE) of 2.92 × 10 -7 compared to the ground truth obtained from a full-physics simulator. Furthermore, the proposed strategy outperformed PCA and convolutional autoencoder (CAE) models on 3D saturation fields, resulting in minor workflow prediction errors with an MSE of 2.93 × 10 -5 . The results suggest the proposed workflow provides sufficient predictive fidelity across temporal and spatial scales, and enables a speedup of 160 times compared to the full-physics simulator, facilitating improved decision-making and risk assessment for large-scale GCS management in real-time scenarios.

3D reconstruction model↗
NASA NTRS1980

A comprehensive comparison between experiment and prediction for a transonic turbulent separated flow

Attempts to predict surface pressure distributions on lifting surfaces have been relatively unsuccessful in the transonic regime when the shock wave is of sufficient strength to produce an extensive region of turbulent separated flow. For these conditions, the viscous flow behavior must be accurately described even to obtain reasonable predictions of surface pressure. The present paper addresses this problem. Detailed comparisons between prediction and experiment are made for a transonic, turbulent boundary-layer separation (freestream Mach number = 0.875) for which the turbulent flow properties (including the turbulent Reynolds stress) had been measured by the laser velocimeter technique from upstream of the separated region through reattachment. The flow was generated on an axisymmetric 'bump' model designed to simulate the flow on an airfoil at transonic conditions. The numerical methods used in the comparisons include the solution of the time-dependent, mass-averaged Navier-Stokes equations, and the solution of the compressible boundary-layer equations by the inverse method. Solutions were obtained for the well established Cebeci-Smith algebraic turbulence model and the more recently developed Wilcox-Rubesin two-equation turbulence model.

Johnson, D. A.↗
DOE OSTI2022

Variational encoder geostatistical analysis (VEGAS) with an application to large scale riverine bathymetry

Estimation of riverbed profiles, also known as bathymetry, plays a vital role in many applications, such as safe and efficient inland navigation, prediction of bank erosion, land subsidence, and flood risk management. The high cost and complex logistics of direct bathymetry surveys, i.e, depth imaging, have encouraged the use of indirect measurements such as surface flow velocities. However, estimating high-resolution bathymetry from indirect measurements is an inverse problem that can be computationally challenging. Here, we propose a reduced-order model (ROM) based approach that utilizes a variational autoencoder (VAE), a type of deep neural network with a narrow layer in the middle, to compress bathymetry and flow velocity information and accelerate bathymetry inverse problems from flow velocity measurements. In our application, the shallow-water equations (SWE) with appropriate boundary conditions (BCs), e.g., the discharge and/or the free surface elevation, constitute the forward problem, to predict flow velocity. Then, ROMs of the SWEs are constructed on a nonlinear manifold of low dimensionality through a variational encoder and the bathymetry inversion problem is derived on the low-dimensional latent space in a Hierarchical Bayesian setting. Further, the reformulation allows variational inference with a small number (e.g., $\mathscr{O}$ (100) of ROM runs and efficient uncertainty quantification. We have tested our inversion approach on a one-mile reach of the Savannah River, GA, USA. Once the neural network is trained (offline stage), the proposed technique can perform the inversion operation orders of magnitude faster than traditional inversion methods that are commonly based on linear projections, such as principal component analysis (PCA), or the principal component geostatistical approach (PCGA). Furthermore, tests show that the algorithm can estimate the bathymetry with good accuracy even with sparse flow velocity measurements.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1992

LAI inversion from optical reflectance using a neural network trained with a multiple scattering model

The inversion of the leaf area index (LAI) canopy parameter from optical spectral reflectance measurements is obtained using a backpropagation artificial neural network trained using input-output pairs generated by a multiple scattering reflectance model. The problem of LAI estimation over sparse canopies (LAI < 1.0) with varying soil reflectance backgrounds is particularly difficult. Standard multiple regression methods applied to canopies within a single homogeneous soil type yield good results but perform unacceptably when applied across soil boundaries, resulting in absolute percentage errors of >1000 percent for low LAI. Minimization methods applied to merit functions constructed from differences between measured reflectances and predicted reflectances using multiple-scattering models are unacceptably sensitive to a good initial guess for the desired parameter. In contrast, the neural network reported generally yields absolute percentage errors of <30 percent when weighting coefficients trained on one soil type were applied to predicted canopy reflectance at a different soil background.

Smith, James A.↗
DOE OSTI2020

Polymer informatics: Current status and critical next steps

Artificial intelligence (AI) based approaches are beginning to impact several domains of human life, science and technology. Polymer informatics is one such domain where AI and machine learning (ML) tools are being used in the efficient development, design and discovery of polymers. Surrogate models are trained on available polymer data for instant property prediction, allowing screening of promising polymer candidates with specific target property requirements. Questions regarding synthesizability, and potential (retro)synthesis steps to create a target polymer, are being explored using statistical means. Data-driven strategies to tackle unique challenges resulting from the extraordinary chemical and physical diversity of polymers at small and large scales are being explored. Other major hurdles for polymer informatics are the lack of widespread availability of curated and organized data, and approaches to create machine-readable representations that capture not just the structure of complex polymeric situations but also synthesis and processing conditions. Methods to solve inverse problems, wherein polymer recommendations are made using advanced AI algorithms that meet application targets, are being investigated. As various parts of the burgeoning polymer informatics ecosystem mature and become integrated, efficiency improvements, accelerated discoveries and increased productivity can result. Here in this paper, we review emergent components of this polymer informatics ecosystem and discuss imminent challenges and opportunities.

36 MATERIALS SCIENCE↗
NASA NTRS1972

Probability of stress-corrosion fracture under random loading.

A method is developed for predicting the probability of stress-corrosion fracture of structures under random loadings. The formulation is based on the cumulative damage hypothesis and the experimentally determined stress-corrosion characteristics. Under both stationary and nonstationary random loadings, the mean value and the variance of the cumulative damage are obtained. The probability of stress-corrosion fracture is then evaluated using the principle of maximum entropy. It is shown that, under stationary random loadings, the standard deviation of the cumulative damage increases in proportion to the square root of time, while the coefficient of variation (dispersion) decreases in inversed proportion to the square root of time. Numerical examples are worked out to illustrate the general results.

Yang, J.-N.↗
DOE OSTI2024

Comparison of machine learning and electrical resistivity arrays to inverse modeling for locating and characterizing subsurface targets

Here, this study evaluates the performance of multiple machine learning (ML) algorithms and electrical resistivity (ER) arrays for inversion with comparison to a conventional Gauss-Newton numerical inversion method. Four different ML models and four arrays were used for the estimation of only six variables for locating and characterizing hypothetical subsurface targets. The combination of dipole-dipole with Multilayer Perceptron Neural Network (MLP-NN) had the highest accuracy. Evaluation showed that both MLP-NN and Gauss-Newton methods performed well for estimating the matrix resistivity while target resistivity accuracy was lower, and MLP-NN produced sharper contrast at target boundaries for the field and hypothetical data. Both methods exhibited comparable target characterization performance, whereas MLP-NN had increased accuracy compared to Gauss-Newton in prediction of target width and height, which was attributed to numerical smoothing present in the Gauss-Newton approach. MLP-NN was also applied to a field dataset acquired at U.S. DOE Hanford site.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2010

Inversion Method for Early Detection of ARES-1 Case Breach Failure

A document describes research into the problem of detecting a case breach formation at an early stage of a rocket flight. An inversion algorithm for case breach allocation is proposed and analyzed. It is shown how the case breach can be allocated at an early stage of its development by using the rocket sensor data and the output data from the control block of the rocket navigation system. The results are simulated with MATLAB/Simulink software. The efficiency of an inversion algorithm for a case breach location is discussed. The research was devoted to the analysis of the ARES-l flight during the first 120 seconds after the launch and early prediction of case breach failure. During this time, the rocket is propelled by its first-stage Solid Rocket Booster (SRB). If a breach appears in SRB case, the gases escaping through it will produce the (side) thrust directed perpendicular to the rocket axis. The side thrust creates torque influencing the rocket attitude. The ARES-l control system will compensate for the side thrust until it reaches some critical value, after which the flight will be uncontrollable. The objective of this work was to obtain the start time of case breach development and its location using the rocket inertial navigation sensors and GNC data. The algorithm was effective for the detection and location of a breach in an SRB field joint at an early stage of its development.

Mackey, Ryan M.↗
NASA NTRS2024

Harnessing Collaborative Learning Automata to Guide Multi-objective Optimization based Inverse Analysis for Structural Damage Identification

Structural damage identification based on physical models is often transformed into an optimization problem that minimizes the difference between measurement information of structure being monitored and the model prediction in the parametric space. However, the objective function in this context often exhibits multimodality, involving high-dimensional variables due to the reliance on finite element models for damage identification. These features pose challenges to optimization algorithms, where entrapment in local solutions can lead to false positives and false negatives in damage identification. In this research, we propose a reinforcement learning based multi-swarm optimizer to tackle such challenges in pursuit of a small yet diverse solution set that can capture the true damage scenario as one of the solutions. The proposed method leverages the flexibility of the particle swarm optimizer and incorporates novel strategies of metaheuristics to realize targeted improvement. To enable the particle swarm to adaptively select the appropriate search strategy based on the current environment, we adopt the learning automata technique, which sidesteps the need for reward strategy selection that is usually ad hoc at each step of the search. The integration harnesses the automatic learning and self-adaptation capabilities of learning automata, enabling the particles to navigate based on environmental signals. This leads to accumulated probabilities tied to advantageous movements, fostering an adaptive exploration of particles in the search space. The proposed approach is first validated through implementing into benchmark test cases with comparisons. It is then applied to structural damage identification with piezoelectric admittance experimental signals. `The results highlight the capability of the algorithm to identify a small solution set with high accuracy to match the actual damage scenario.

Yang Zhang↗
DOE OSTI2025

Hamiltonian parameter inference from resonant inelastic x-ray scattering with active learning

Identifying model Hamiltonians is a vital step toward creating predictive models of materials. Here, in this study, we combine Bayesian optimization with the EDRIXS numerical package to infer Hamiltonian parameters from resonant inelastic x-ray scattering (RIXS) spectra within the single atom approximation. To evaluate the efficacy of our method, we test it on experimental RIXS spectra of NiPS 3 , NiCl 2 , Ca 3 ⁢LiOsO 6 , and Fe 2⁢ O 3 , and demonstrate that it can reproduce results obtained from hand-fitted parameters to a precision similar to expert human analysis while providing a more systematic mapping of parameter space. Our work provides a key first step toward solving the inverse scattering problem to extract effective multi-orbital models from information-dense RIXS measurements, which can be applied to a host of quantum materials. We also propose atomic model parameter sets for two materials, Ca 3⁢ LiOsO 6 and Fe 2⁢ O 3 , that were previously missing from the literature.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2020

sMF-BO-2CoGP: A sequential multi-fidelity constrained Bayesian optimization framework for design applications

Bayesian optimization (BO) is an effective surrogate-based method that has been widely used to optimize simulation-based applications. While the traditional Bayesian optimization approach only applies to single-fidelity models, many realistic applications provide multiple levels of fidelity with various levels of computational complexity and predictive capability. In this work, we propose a multi-fidelity Bayesian optimization method for design applications with both known and unknown constraints. The proposed framework, called sMF-BO-2CoGP, is built on a multi-level CoKriging method to predict the objective function. An external binary classifier, which we approximate using a separate CoKriging model, is used to distinguish between feasible and infeasible regions. Finally, the sMF-BO-2CoGP method is demonstrated using a series of analytical examples and a flip-chip application for design optimization to minimize the deformation due to warping under thermal loading conditions.

42 ENGINEERING↗
NASA NTRS1981

Visual tracking in stereo

A method is described for visual object tracking by a computer vision system using TV cameras and special low-level image processing hardware. The tracker maintains an internal model of the location, orientation, and velocity of the object in three-dimensional space. This model is used to predict where features of the object will lie on the two-dimensional images produced by stereo TV cameras. The differences in the locations of features in the two-dimensional images as predicted by the internal model and as actually seen create an error signal in the two-dimensional representation. This is multiplied by a generalized inverse Jacobian matrix to deduce the error in the internal model. The procedure repeats to update the internal model of the object's location, orientation and velocity continuously.

Saund, E.↗
NASA NTRS1991

Numerical identification of boundary conditions on nonlinearly radiating inverse heat conduction problems

An explicit and unconditionally stable finite difference method for the solution of the transient inverse heat conduction problem in a semi-infinite or finite slab mediums subject to nonlinear radiation boundary conditions is presented. After measuring two interior temperature histories, the mollification method is used to determine the surface transient heat source if the energy radiation law is known. Alternatively, if the active surface is heated by a source at a rate proportional to a given function, the nonlinear surface radiation law is then recovered as a function of the interface temperature when the problem is feasible. Two typical examples corresponding to Newton cooling law and Stefan-Boltzmann radiation law respectively are illustrated. In all cases, the method predicts the surface conditions with an accuracy suitable for many practical purposes.

Murio, Diego A.↗
NASA NTRS1993

Computation of nonequilibrium radiating shock layers

A computational technique of coupling radiative transfer to fluid motion is developed for axisymmetric blunt body shock layer flows in a thermochemical nonequilibrium environment. The coupled formulation of radiation and flowfield leads to a governing set of integro-differential equations. This equation set is solved using a modified Gauss-Seidel line relaxation techniques which incorporates the inversion of full block matrix associated with radiative transfer using a block iteration method. The thermodynamic state of the gas is described by three temperatures: translational, rotational, and vibrational-electronic. Radiation phenomenon is assumed to be governed by the vibrational-electronic temperature. The radiative properties are described by a spectrally detailed model. The computations are presented for two cases, including the Fire II flight experiment. It is shown that the method converges and the calculated spectra qualitatively agree with the experimental data for the two test cases. The calculated total radiative flux underestimates the measured values owing to the low vibrational-electronic temperature predicted in the flowfield calculation.

Gokcen, Tahir↗
NASA NTRS1998

Transfer function analysis of dynamic cerebral autoregulation in humans

To test the hypothesis that spontaneous changes in cerebral blood flow are primarily induced by changes in arterial pressure and that cerebral autoregulation is a frequency-dependent phenomenon, we measured mean arterial pressure in the finger and mean blood flow velocity in the middle cerebral artery (VMCA) during supine rest and acute hypotension induced by thigh cuff deflation in 10 healthy subjects. Transfer function gain, phase, and coherence function between changes in arterial pressure and VMCA were estimated using the Welch method. The impulse response function, calculated as the inverse Fourier transform of this transfer function, enabled the calculation of transient changes in VMCA during acute hypotension, which was compared with the directly measured change in VMCA during thigh cuff deflation. Beat-to-beat changes in VMCA occurred simultaneously with changes in arterial pressure, and the autospectrum of VMCA showed characteristics similar to arterial pressure. Transfer gain increased substantially with increasing frequency from 0.07 to 0.20 Hz in association with a gradual decrease in phase. The coherence function was > 0.5 in the frequency range of 0.07-0.30 Hz and < 0.5 at < 0.07 Hz. Furthermore, the predicted change in VMCA was similar to the measured VMCA during thigh cuff deflation. These data suggest that spontaneous changes in VMCA that occur at the frequency range of 0.07-0.30 Hz are related strongly to changes in arterial pressure and, furthermore, that short-term regulation of cerebral blood flow in response to changes in arterial pressure can be modeled by a transfer function with the quality of a high-pass filter in the frequency range of 0.07-0.30 Hz.

NASA Discipline Cardiopulmonary↗
DOE OSTI2021

Model fusion with physics-guided machine learning: Projection-based reduced-order modeling

The unprecedented amount of data generated from experiments, field observations, and large-scale numerical simulations at a wide range of spatiotemporal scales has enabled the rapid advancement of data-driven and especially deep learning models in the field of fluid mechanics. Although these methods are proven successful for many applications, there is a grand challenge of improving their generalizability. This is particularly essential when data-driven models are employed within outer-loop applications like optimization. In this work, we put forth a physics-guided machine learning (PGML) framework that leverages the interpretable physics-based model with a deep learning model. Leveraging a concatenated neural network design from multi-modal data sources, the PGML framework is capable of enhancing the generalizability of data-driven models and effectively protects against or inform about the inaccurate predictions resulting from extrapolation. We apply the PGML framework as a novel model fusion approach combining the physics-based Galerkin projection model and long- to short-term memory (LSTM) network for parametric model order reduction of fluid flows. We demonstrate the improved generalizability of the PGML framework against a purely data-driven approach through the injection of physics features into intermediate LSTM layers. Our quantitative analysis shows that the overall model uncertainty can be reduced through the PGML approach, especially for test data coming from a distribution different than the training data. Moreover, we demonstrate that our approach can be used as an inverse diagnostic tool providing a confidence score associated with models and observations. The proposed framework also allows for multi-fidelity computing by making use of low-fidelity models in the online deployment of quantified data-driven models.

42 ENGINEERING↗