Neural Networks and Friction: Slide, Hold, Learn

arXiv:2402.14148v1 Announce Type: cross
Abstract: In this study, it is demonstrated that Recurrent Neural Networks (RNNs), specifically those utilizing Gated Recurrent Unit (GRU) architecture, possess the capability to learn the complex dynamics of rate-and-state friction laws from synthetic data. The data employed for training the network is generated through the application of traditional rate-and-state friction equations coupled with the aging law for state evolution. A novel aspect of our approach is the formulation of a loss function that explicitly accounts …

abstract application architecture arxiv capability cs.lg data dynamics generated gru laws learn network networks neural networks physics.geo-ph rate recurrent neural networks state study synthetic synthetic data through training type