Enhancing polynomial chaos expansion based surrogates through probabilistic transfer learning
Abstract not provided.
Publications
Search results
Jump to search filtersTransfer Learning of Closure Terms and in Reduced Order Models of Chemically Reactive Flows
Abstract not provided.
Robust initializations of variational inference using global optimization and Laplace approximations
Abstract not provided.
Transfer Learning of Gaussian Processes to Capture Unmodeled Physics
Abstract not provided.
Transfer learning of Gaussian processes to capture unmodeled physics: application to control of nonlinear dynamical systems
Abstract not provided.
A heteroencoder architecture for prediction of failure locations in porous metals using variational inference
Computer Methods in Applied Mechanics and Engineering
In this work we employ an encoder–decoder convolutional neural network to predict the failure locations of porous metal tension specimens based only on their initial porosities. The process we model is complex, with a progression from initial void nucleation, to saturation, and ultimately failure. The objective of predicting failure locations presents an extreme case of class imbalance since most of the material in the specimens does not fail. In response to this challenge, we develop and demonstrate the effectiveness of data- and loss-based regularization methods. Since there is considerable sensitivity of the failure location to the particular configuration of voids, we also use variational inference to provide uncertainties for the neural network predictions. We connect the deterministic and Bayesian convolutional neural network formulations to explain how variational inference regularizes the training and predictions. We demonstrate that the resulting predicted variances are effective in ranking the locations that are most likely to fail in any given specimen.
Probabilistic Approaches to Transfer Learning
Abstract not provided.
Coupling of NovelProbabilistic Transfer Learning Strategies and Autoencoders to Expedite Turbulent Combustion Modeling
Abstract not provided.
Probabilistic Approaches to Transfer Learning for Sparse and Noisy Data Environments
Abstract not provided.
Combined selection of the dynamic model and modeling error in nonlinear aeroelastic systems using Bayesian Inference
Journal of Sound and Vibration
We report a Bayesian framework for concurrent selection of physics-based models and (modeling) error models. We investigate the use of colored noise to capture the mismatch between the predictions of calibrated models and observational data that cannot be explained by measurement error alone within the context of Bayesian estimation for stochastic ordinary differential equations. Proposed models are characterized by the average data-fit, a measure of how well a model fits the measurements, and the model complexity measured using the Kullback–Leibler divergence. The use of a more complex error models increases the average data-fit but also increases the complexity of the combined model, possibly over-fitting the data. Bayesian model selection is used to find the optimal physical model as well as the optimal error model. The optimal model is defined using the evidence, where the average data-fit is balanced by the complexity of the model. The effect of colored noise process is illustrated using a nonlinear aeroelastic oscillator representing a rigid NACA0012 airfoil undergoing limit cycle oscillations due to complex fluid–structure interactions. Several quasi-steady and unsteady aerodynamic models are proposed with colored noise or white noise for the model error. The use of colored noise improves the predictive capabilities of simpler models.
Robust initialization of variational inference through global optimization and Laplace approximations
Abstract not provided.
Coupling of Novel Probabilistic Transfer Learning Strategies and Autoencoders to Expedite Turbulent Combustion Modeling
Abstract not provided.
Sensitivity of void mediated failure to geometric design features of porous metals
International Journal of Solids and Structures
Material produced by current metal additive manufacturing processes is susceptible to variable performance due to imprecise control of internal porosity, surface roughness, and conformity to designed geometry. Using a double U-notched specimen, we investigate the interplay of nominal geometry and porosity in determining ductile failure characteristics during monotonic tensile loading. We simulate the effects of distributed porosity on plasticity and damage using a statistical model based on populations of pores visible in computed tomography scans and additional sub-threshold voids required to match experimental observations of deformation and failure. We interpret the simulation results from a physical viewpoint and provide a statistical model of the probability of failure near stress concentrations. We provide guidance for designs where material defects could cause unexpected failures depending on the relative importance of these defects with respect to features of the nominal geometry.
UQTk Version 3.1.2 User Manual
The UQ Toolkit (UQTk) is a collection of libraries and tools for the quantification of uncertainty in numerical model predictions. Version 3.1.2 offers intrusive and non-intrusive methods for propagating input uncertainties through computational models, tools for sensitivity analysis, methods for sparse surrogate construction, and Bayesian inference tools for inferring parameters from experimental data. This manual discusses the download and installation process for UQTk, provides pointers to the UQ methods used in the toolkit, and describes some of the examples provided with the toolkit.
Extending relevance vector machine to resolve overtting during Bayesian calibration in nonlinear stochastic dynamics
Abstract not provided.
Modeling and predicting power from a WEC array
Abstract not provided.
Probabilistic Approaches to Transfer Learning
Abstract not provided.
A parallel update step of a sampling-free EnKF-type %0Clter
Abstract not provided.
Nonlinear sparse Bayesian learning using EnKF based state estimator
Abstract not provided.
Wave Energy Production Optimization and Forecasting Tool
Abstract not provided.
Probabilistic Approaches to Transfer Learning
Abstract not provided.
UQTk Version 3.1.1 User Manual
The UQ Toolkit (UQTk) is a collection of libraries and tools for the quantification of uncertainty in numerical model predictions. Version 3.1.1 offers intrusive and non-intrusive methods for propagating input uncertainties through computational models, tools for sensitivity analysis, methods for sparse surrogate construction, and Bayesian inference tools for inferring parameters from experimental data. This manual discusses the download and installation process for UQTk, provides pointers to the UQ methods used in the toolkit, and describes some of the examples provided with the toolkit.
Sparse learning of a nonlinear aeroelastic model using Bayesian inference
Abstract not provided.
Sparse Learning of Over-Parametrized Nonlinear Engineering Models
Abstract not provided.
Calibrating optimal modeling error in nonlinear dynamics
Abstract not provided.
Results 1–25 of 112