Deep learning enhanced principal component analysis for structural health monitoring

This paper proposes a Deep Learning enhanced Principal Component Analysis (PCA) approach for outlier detection to assess the structural condition of bridges. We employ a partially explainable autoencoder architecture to replicate and enhance the data compression and reconstruction ability of PCA. Th...

Descripción completa

Detalles Bibliográficos
Autores: Fernandez-Navamuel, A., Magalhães, F., Zamora-Sánchez, D., Omella, A. J., Garcia-Sanchez, D., Pardo, D.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución:Basque Center for Applied Mathematics (BCAM)
Repositorio:BIRD. BCAM's Institutional Repository Data
OAI Identifier:oai:bird.bcamath.org:20.500.11824/1824
Acceso en línea:http://hdl.handle.net/20.500.11824/1824
https://doi.org/10.1177/14759217211041684
Access Level:acceso embargado
Palabra clave:Structural Health Monitoring
Deep Learning
Principal Component Analysis
Autoencoder
Reconstruction error
Descripción
Sumario:This paper proposes a Deep Learning enhanced Principal Component Analysis (PCA) approach for outlier detection to assess the structural condition of bridges. We employ a partially explainable autoencoder architecture to replicate and enhance the data compression and reconstruction ability of PCA. The particularity of the method lies in the addition of residual connections to account for nonlinearities. We apply the proposed method to monitoring data obtained from two bridges under real operation conditions and compare the results before and after adding the residual connections. Results show that the addition of residual connections enhances the outlier detection ability of the network, allowing to detect lighter damages.