Training Data Selection for Machine Learning-Enhanced Monte Carlo Simulations in Structural Dynamics
Training Data Selection for Machine Learning-Enhanced Monte Carlo Simulations in Structural Dynamics
复制标题
结构动力学中机器学习增强型蒙特卡罗模拟的训练数据选择
作者：
Denny Thaler;Leonard Elezaj;F. Bamer;B. Markert
结构响应的评估是地震动结构设计中的一项基本任务。在这种情况下，蒙特卡罗模拟是一个强大的工具来估计非线性系统的响应统计，这不能解析表示。不幸的是，估计所需的高置信度的样本的数量不断增加，以获得低概率事件的可靠估计。因此，从计算的角度来看，蒙特卡罗模拟成为一个不可实现的任务。我们表明，机器学习算法的应用显着降低了蒙特卡罗方法的计算负担。我们使用人工神经网络来预测结构响应行为，使用监督学习。然而，监督学习的一个缺点是，当外推到神经网络尚未看到的数据时，无法进行足够准确的预测。在本文中，神经网络预测结构的反应受到非平稳地面激励。在此过程中，我们提出了一种新的训练数据选择过程，以提供可靠预测罕见事件所需的样本。我们，最后，证明了新的策略的结果在一个显着改善的预测的响应统计分布的尾端。
The evaluation of structural response constitutes a fundamental task in the design of ground-excited structures. In this context, the Monte Carlo simulation is a powerful tool to estimate the response statistics of nonlinear systems, which cannot be represented analytically. Unfortunately, the number of samples which is required for estimations with high confidence increases disproportionally to obtain a reliable estimation of low-probability events. As a consequence, the Monte Carlo simulation becomes a non-realizable task from a computational perspective. We show that the application of machine learning algorithms significantly lowers the computational burden of the Monte Carlo method. We use artificial neural networks to predict structural response behavior using supervised learning. However, one shortcoming of supervised learning is the inability of a sufficiently accurate prediction when extrapolating to data the neural network has not seen yet. In this paper, neural networks predict the response of structures subjected to non-stationary ground excitations. In doing so, we propose a novel selection process for the training data to provide the required samples to reliably predict rare events. We, finally, prove that the new strategy results in a significant improvement of the prediction of the response statistics in the tail end of the distribution.
结构力学中的纽马克时空方法
DOI：
10.1002/pamm.202000304
发表时间：
2020
期刊：
PAMM
影响因子：
--
作者：
F Bamer;N Shirafkan;A Oueslati;M Stoffel;G de Saxcé;B Markert
通讯作者：
B Markert
轴横向联合荷载作用下空心结构截面柱的倒塌行为
影响因子：
4.1
作者：
Sediek, Omar A.;Wu, T.-Y.;McCormick, Jason;El-Tawil, Sherif
通讯作者：
El-Tawil, Sherif