arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.09862cs.LGcs.AIeess.SP
收藏

面向结构动力学数据驱动模型定义的群体信息方法研究

Towards a population-informed approach to the definition of data-driven models for structural dynamics

University of Sheffield(谢菲尔德大学)

G. Tsialiamanis, N. Dervilis, D. J. Wagg, K. Worden

AI总结:

针对数据稀缺下机器学习建模的局限,提出从相似物理现象群体中学习的元学习方法(MAML和CNP),在结构动力学近似中优于传统算法。

摘要:

机器学习影响了各个领域许多现象的建模方式,结构动力学就是其中之一。然而,由于机器学习算法是针对特定问题的,在数据稀缺的情况下往往无法高效运行。为了解决此类问题,人们开发了基于物理的方法与机器学习算法的组合。尽管这些方法很有效,但它们也要求分析者理解问题的底层物理原理。当前的工作旨在推动使用从具有相似底层物理原理的现象群体中学习此类关系的模型。此类模型的开发受到基于物理的模型,更具体地说是有限元模型工作方式的启发。这些模型被认为是可转移的、可解释的和值得信赖的,这些属性对于机器学习模型而言并非轻易就能强加或实现的。因此,机器学习方法在工业界较少受到信任,通常被认为更难形成经过验证的模型。为了实现此类数据驱动模型,本文遵循基于群体的方案,并使用了来自元学习领域的两种不同的机器学习算法。这两种算法分别是模型不可知元学习(MAML)算法和条件神经过程(CNP)模型。这些算法似乎按预期执行,并且在近似目标量方面优于传统的机器学习算法。此外,关于性能作为训练群体中可用结构数量的函数,它们表现出与传统机器学习算法(例如神经网络或高斯过程)相似的行为。

英文摘要:

Machine learning has affected the way in which many phenomena for various domains are modelled, one of these domains being that of structural dynamics. However, because machine-learning algorithms are problem-specific, they often fail to perform efficiently in cases of data scarcity. To deal with such issues, combination of physics-based approaches and machine learning algorithms have been developed. Although such methods are effective, they also require the analyser's understanding of the underlying physics of the problem. The current work is aimed at motivating the use of models which learn such relationships from a population of phenomena, whose underlying physics are similar. The development of such models is motivated by the way that physics-based models, and more specifically finite element models, work. Such models are considered transferrable, explainable and trustworthy, attributes which are not trivially imposed or achieved for machine-learning models. For this reason, machine-learning approaches are less trusted by industry and often considered more difficult to form validated models. To achieve such data-driven models, a population-based scheme is followed here and two different machine-learning algorithms from the meta-learning domain are used. The two algorithms are the model-agnostic meta-learning (MAML) algorithm and the conditional neural processes (CNP) model. The algorithms seem to perform as intended and outperform a traditional machine-learning algorithm at approximating the quantities of interest. Moreover, they exhibit behaviour similar to traditional machine learning algorithms (e.g. neural networks or Gaussian processes), concerning their performance as a function of the available structures in the training population.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑