Deep Learning in Computational Mechanics
An Introductory Course
Article
Ductile damage models and cohesive laws incorporate the material plasticity entailing the growth of irrecoverable deformations even after complete failure. This unrealistic growth remains concealed until the u...
Article
The rapid growth of deep learning research, including within the field of computational mechanics, has resulted in an extensive and diverse body of literature. To help researchers identify key concepts and pro...
Article
The direct numerical simulation of metal additive manufacturing processes such as laser powder bed fusion is challenging due to the vast differences in spatial and temporal scales. Classical approaches based o...
Chapter
Additive manufacturing processes are driven by moving laser-induced thermal sources which induce strong heat fluxes and fronts of phase change coupled to mechanical fields. Their numerical simulation poses sev...
Article
In this contribution we provide benchmark problems in the field of computational solid mechanics. In detail, we address classical fields as elasticity, incompressibility, material interfaces, thin structures a...
Chapter
Machine Learning is already being frequently used in computer vision, recommendation systems, medical diagnosis, or financial forecasting. Recently, physics and engineering have also taken advantage of machine...
Chapter
The deep energy method is an alternative to the physics-informed neural networks (PINNs). Both approaches leverage the underlying physics to reduce the amount of data required. Instead of directly using the go...
Chapter
Significant advancements have been made in the field of artificial intelligence in recent years. Thus, artificial intelligence has also become of greater interest in areas other than computer science, such as ...
Chapter
Machine Learning algorithms are different from conventional algorithms as they automatically improve through experience. They traditionally accomplish this using data. This chapter gives an overview of the fun...
Book
Chapter
Artificial neural networks (ANNs) are state-of-the-art machine learning architectures modeling neurons and their connections through weights and biases. ANNs serve as universal function approximators, meaning ...
Chapter
Physics-informed neural networks (PINNs) are used for problems where data are scarce. The underlying physics is enforced via the governing differential equation, including the residual in the cost function. PI...
Article
This paper proposes an extension of the finite cell method (FCM) to V-rep models, a novel geometric framework for volumetric representations. This combination of an embedded domain approach (FCM) and a new mod...
Article
Process-dependent residual stresses are one of the main burdens to a widespread adoption of laser powder bed fusion technology in industry. Residual stresses are directly influenced by process parameters, such...
Article
This work focuses on the study of several computational challenges arising when trimmed surfaces are directly employed for the isogeometric analysis of Kirchhoff–Love shells. To cope with these issues and to r...
Article
In this contribution, we validate a physical model based on a transient temperature equation (including latent heat), w.r.t. the experimental set AMB2018-02 provided within the additive manufacturing benchmark...
Chapter and Conference Paper
This contribution presents a method for numerical analysis of solids whose boundaries are represented by oriented point clouds. In contrast to standard finite elements that require a boundary-conforming discre...
Article
In order to reduce the transfer of sound and vibrations in structures such as timber buildings, thin elastomer layers can be embedded between their components. The influence of these elastomers on the response...
Article
This paper presents an image-based method aimed at generating a mesh of high-order finite elements on a tubular structure. The method assumes that the object is immersed in a liquid with known refractive coeff...
Article
The finite cell method (FCM) is a fictitious domain approach that greatly simplifies simulations involving complex structures. Recently, the FCM has been applied to contact problems. The current study continue...