GaussianProcess

DeepONet: a deep-learning-based framework for approximating linear and nonlinear operators

by

Delighted to convene the inaugural meeting of the research team for the coordinated POTENTIAL project in Cartagena. Our discussions on electromechanics, optimal control, and deep-learning algorithms were exceptionally fruitful, fostering an atmosphere of collaboration and innovation. Excited to witness the promising developments that will emerge as we continue to work together towards our shared objectives.Grant … Read more

New paper: “Gradient enhanced gaussian process regression for constitutive modelling in finite strain hyperelasticity”

by

New paper published in CMAME under the project “Multiphysics-Informed Design of Tunable Smart Materials”. This paper introduces a metamodelling technique that leverages gradient-enhanced Gaussian process regression (also known as gradient-enhanced Kriging), effectively emulating the response of diverse hyperelastic strain energy densities. The approach adopted incorporates principal invariants as inputs for the surrogate of the strain energy density. This integration enables … Read more

New paper: “Learning nonlinear constitutive models in finite strain electromechanics with Gaussian process predictors” 

by

The first paper authored by our PhD student, Alberto Pérez Escolar, under the project “Multiphysics-Informed Design of Tunable Smart Materials” has been published in CM. This paper introduces a gradient-enhanced Gaussian process metamodel designed to emulate homogenized nonlinear electromechanical constitutive models. The methodology, implemented entirely using Julia, incorporates principal invariants as inputs for the surrogate … Read more