Establishing compromise between model accuracy and hardware use for distributed structural health monitoring

  • Carolina O. Contente Departamento de Engenharia Mecânica, Pontifícia Universidade Católica do Rio de Janeiro, RJ
  • Helon V. H. Ayala Departamento de Engenharia Mecânica, Pontifícia Universidade Católica do Rio de Janeiro, RJ
Keywords: structural health monitoring, autoregressive model, dimensionality reduction, principal component analysis, supervised machine learning, support vector machine, logistic regression, decision trees, random forest, k-nearest neighborhood, Convolutional Neural Networks, Recurrent Neural Networks


Structural health monitoring has been the focus of recent developments in the field of vibration-based assessment and, more recently, in the scope of internet of things as measurement and computation becomes distributed. Data has become abundant even though the transmission is not always feasible at higher frequencies needed for proper assessment, especially in remote applications such as pipelines, subsea, and smart fleets. It is thus important to devise data-driven model workflows that ensure the best compromise between model accuracy for condition assessment and also the computational resources needed for embedded solutions, a topic that has not been widely used in the context of vibration-based measurements. In this context, the present paper proposes a modeling workflow able to reduce the dimension of autoregressive models built on the basis of many acceleration sensors. The three-story building example was used to demonstrate the effectiveness of the method, together with ways assess the best compromise between accuracy and model size. We hope to point future research directions of embedded computing, predictive analytics, and vibration based structural health monitoring, in order to ensure that the models created can be conveniently deployed while optimizing costs for computing infrastructure.