... by constructing a multifidelity random process based on latent map Gaussian processes (LMGPs). In particular, we use LMGPs to calibrate the damage parameters of an ROM as a function of microstructure and clustering (i.e., fidelity) level such that the ROM faithfully surrogates DNS. We demonstrate the application...

... while also estimating calibration parameters. To address this gap, we introduce a novel approach that, using latent-map Gaussian processes (LMGPs), converts data fusion into a latent space learning problem where the relations among different data sources are automatically learned. This conversion endows...

....2020.103024 [44] Deisenroth , M. P. , 2010 , Efficient Reinforcement Learning Using Gaussian Processes , Vol. 9 , KIT Scientific Publishing , Karlsruhe, Germany . [45] Arulkumaran , K. , Deisenroth , M. P. , Brundage , M. , and Bharath , A. A. , 2017 , “ A Brief Survey...

...Robert Planas; Nick Oune; Ramin Bostanabad Emulation plays an important role in engineering design. However, most emulators such as Gaussian processes (GPs) are exclusively developed for interpolation/regression and their performance significantly deteriorates in extrapolation. To address...

...Piyush Pandita; Panagiotis Tsilifis; Sayan Ghosh; Liping Wang Gaussian process (GP) regression or kriging has been extensively applied in the engineering literature for the purposes of building a cheap-to-evaluate surrogate, within the contexts of multi-fidelity modeling, model calibration...

...Ramin Bostanabad; Yu-Chin Chan; Liwei Wang; Ping Zhu; Wei Chen We introduce a novel method for Gaussian process (GP) modeling of massive datasets called globally approximate Gaussian process (GAGP). Unlike most large-scale supervised learners such as neural networks and trees, GAGP is easy to fit...

... of this paper is to develop a BODE methodology for estimating the statistical expectation of the physical response. The technical details of our approach are as follows. Much like the majority of the work in BODE, we use Gaussian process (GP) surrogates to emulate the physical response [ 56 ]. The expected...

... on the validation data is generalized using Gaussian process regression (GPR) [ 35 ]. This allows for the estimation of the model prediction error at a prediction point based on the model prediction errors over the validation data. At each prediction point, the estimated prediction errors of the competing models...

.... Methods Appl. Mech. Eng. , 197 ( 29–32 ), pp. 2457 – 2466 . 10.1016/j.cma.2007.05.032 26 Rasmussen , C. E. , and Williams , C. K. I. , 2006 , Gaussian Processes for Machine Learning , MIT, Cambridge , MA . 27 Jin , R. , Chen , W. , and Simpson , T. W. , 2001...

... for random dimension variables with small variances, the motion error becomes a nonstationary Gaussian process. We at first derive analytical equations for upcrossing and downcrossing rates and then develop a numerical procedure that integrates the two rates to obtain the kinematic reliability. A four-bar...

... random field produced during a casting process on the product damage is studied and a reliability-based design of the control arm is performed. 22 04 2008 04 10 2008 07 01 2009 automotive components CAD/CAM casting concurrent engineering failure analysis Gaussian processes...

... fusion technique based on the Bayesian–Gaussian process modeling is employed to construct cheap surrogate models to integrate information from both low-fidelity and high-fidelity models, while the interpolation uncertainty of the surrogate model due to the lack of sufficient high-fidelity simulations...

... to build a model based on a Gaussian process. The fitted model is then “adjusted” by incorporating a small amount of data from detailed simulations to obtain a more accurate prediction model. The effectiveness of this approach is demonstrated with a design example involving cellular materials...