Deep learning enhanced principal component analysis for structural health monitoring

• Type: Article in International Scientific Journal
• Date: 2022

Authors

Fernandez Navamuel, A (Author) Other; Magalhães, F. (Author) FEUP; Zamora Sanchez, D (Author) Other; Omella, AJ (Author) Other; Garcia Sanchez, D (Author) Other; Pardo, D (Author) Other

Journal

Title: Structural Health Monitoring

Vol. 21 No. 2

Pages: 1710-1722

ISSN: 1475-9217

Publisher: SAGE

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Other information

Authenticus ID: P-00W-0BK

DOI: 10.1177/14759217211041684

Abstract (EN): This paper proposes a Deep Learning Enhanced Principal Component Analysis (PCA) approach for outlier detection to assess the structural condition of bridges. We employ 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.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 13