Feed-Forward Neural Networks for Failure Mechanics Problems

Abstract

This work addresses an efficient neural network (NN) representation for the phase-field modeling of isotropic brittle fracture. In recent years, data-driven approaches, such as neural networks, have become an active research field in mechanics. In this contribution, deep neural networks—in particular, the feed-forward neural network (FFNN)—are utilized directly for the development of the failure model. The verification and generalization of the trained models for elasticity as well as fracture behavior are investigated by several representative numerical examples under different loading conditions. As an outcome, promising results close to the exact solutions are produced.

A first-principles and machine-learning investigation on the electronic, photocatalytic, mechanical and heat conduction properties of nanoporous C5N monolayers

“…Similar to other 2D materials, the C 5 N monolayer shows three acoustic modes initiating from the Γ point. [30][31][32] As clearly shown in the inset of Fig. 2a, none of the acoustic modes in this monolayer exhibit imaginary frequencies, confirming its desirable dynamic stability.…”

Research on the Purchase Intention of Children's Educational Products Based on Feedforward Neural Network and Factor Analysis

“…Hidden layers can be either one layer or multiple layers. There is no feedback in the whole network, and the signal propagates unidirectionally from the input layer to the output layer [11]. Figure 1 shows the basic structure and mechanism of the feedforward neural network.…”

Machine learning for rock mechanics problems; an insight

“…The more common ones include fracture toughness measurements, problems of crack propagation, crack identification, etc. Commonly used machine learning methods include support vector machine (Deng et al, 2013), neural network (Aldakheel et al, 2021), Bayesian optimization and reinforcement learning (Alipour et al, 2021;Fuchs et al, 2021), etc.…”