Back to Search Start Over

Using Graph Neural Networks and Frequency Domain Data for Automated Operational Modal Analysis of Populations of Structures

Authors :
Jian, Xudong
Xia, Yutong
Duthé, Gregory
Bacsa, Kiran
Liu, Wei
Chatzi, Eleni
Publication Year :
2024

Abstract

The Population-Based Structural Health Monitoring (PBSHM) paradigm has recently emerged as a promising approach to enhance data-driven assessment of engineering structures by facilitating transfer learning between structures with some degree of similarity. In this work, we apply this concept to the automated modal identification of structural systems. We introduce a Graph Neural Network (GNN)-based deep learning scheme to identify modal properties, including natural frequencies, damping ratios, and mode shapes of engineering structures based on the Power Spectral Density (PSD) of spatially-sparse vibration measurements. Systematic numerical experiments are conducted to evaluate the proposed model, employing two distinct truss populations that possess similar topological characteristics but varying geometric (size, shape) and material (stiffness) properties. The results demonstrate that, once trained, the proposed GNN-based model can identify modal properties of unseen structures within the same structural population with good efficiency and acceptable accuracy, even in the presence of measurement noise and sparse measurement locations. The GNN-based model exhibits advantages over the classic Frequency Domain Decomposition (FDD) method in terms of identification speed, as well as against an alternate Multi-Layer Perceptron (MLP) architecture in terms of identification accuracy, rendering this a promising tool for PBSHM purposes.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2407.06492
Document Type :
Working Paper