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

TL;DR

This paper proposes a population-informed machine learning approach for structural dynamics that leverages meta-learning algorithms to improve transferability, explainability, and trustworthiness over traditional models, especially in data-scarce scenarios.

Contribution

It introduces a population-based scheme using meta-learning algorithms, MAML and CNP, to develop data-driven models that learn from similar phenomena and outperform traditional methods.

Findings

Meta-learning algorithms outperform traditional machine learning in approximating quantities of interest.

Models exhibit transferability and behavior similar to classical models as training data varies.

Proposed approach enhances trustworthiness and applicability in industry settings.

Abstract

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.