A Monte Carlo Simulation Approach in Non-linear Structural Dynamics Using Convolutional Neural Networks
Open Access
- 3 May 2021
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Built Environment
Abstract
The evaluation of the structural response statistics constitutes one of the principal tasks in engineering. However, in the tail region near structural failure, engineering structures behave highly non-linear, making an analytic or closed form of the response statistics difficult or even impossible. Evaluating a series of computer experiments, the Monte Carlo method has been proven a useful tool to provide an unbiased estimate of the response statistics. Naturally, we want structural failure to happen very rarely. Unfortunately, this leads to a disproportionately high number of Monte Carlo samples to be evaluated to ensure an estimation with high confidence for small probabilities. Thus, in this paper, we present a new Monte Carlo simulation method enhanced by a convolutional neural network. The sample-set used for this Monte Carlo approach is provided by artificially generating site-dependent ground motion time histories using a non-linear Kanai-Tajimi filter. Compared to several state-of-the-art studies, the convolutional neural network learns to extract the relevant input features and the structural response behavior autonomously from the entire time histories instead of learning from a set of hand-chosen intensity inputs. Training the neural network based on a chosen input sample set develops a meta-model that is then used as a meta-model to predict the response of the total Monte Carlo sample set. This paper presents two convolutional neural network-enhanced strategies that allow for a practical design approach of ground motion excited structures. The first strategy enables for an accurate response prediction around the mean of the distribution. It is, therefore, useful regarding structural serviceability. The second strategy enables for an accurate prediction around the tail end of the distribution. It is, therefore, beneficial for the prediction of the probability of failure.This publication has 24 references indexed in Scilit:
- Approaches to the rapid seismic damage prediction of r/c buildings using artificial neural networksEngineering Structures, 2018
- Efficient solution of the multiple seismic pounding problem using hierarchical substructure techniquesComputational Mechanics, 2017
- An efficient response identification strategy for nonlinear structures subject to nonstationary generated seismic excitationsMechanics Based Design of Structures and Machines, 2016
- A new model order reduction strategy adapted to nonlinear problems in earthquake engineeringEarthquake Engineering & Structural Dynamics, 2016
- Computational IntelligencePublished by Springer Science and Business Media LLC ,2015
- Application of the proper orthogonal decomposition for linear and nonlinear structures under transient excitationsActa Mechanica, 2012
- Computational Analysis of Randomness in Structural MechanicsPublished by Taylor & Francis Ltd ,2009
- Tail-equivalent linearization method for nonlinear random vibrationProbabilistic Engineering Mechanics, 2007
- Monte Carlo techniques in computational stochastic mechanicsArchives of Computational Methods in Engineering, 1998
- Structural reliability methods for seismic safety assessment: a reviewEngineering Structures, 1996