Ensemble Deep Learning Model for Damage Identification via Output-Only Signal Analysis

Matthew Sands, Jongyeop Kim, Jinki Kim, Seongsoo Kim

Research output: Contribution to book or proceedingConference articlepeer-review

1 Scopus citations

Abstract

Vibration-based methods have received considerable attention in structural condition monitoring applications. We have proposed a model to detect damaged points of a target structure using the GRU model and classify the 0.84 overall accuracy. To increase the model's accuracy in this research, we propose an ensemble deep learning model using LSTM and bi-directional LSTM incorporated with GRU. Each model predicted its RMSE trend and combined the damage estimation results from both models, which are mostly close to the true damage locations. As a result of synthesizing the three algorithms, the damage point of the cantilever beam was found with an accuracy of 0.88 and a misclassification rate of 0.12. The results indicate that the proposed combined approach provides enhanced reliability than a single algorithm.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE/ACIS 24th International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022
EditorsShu-Ching Chen, Her-Terng Yau, Roland Stenzel, Hsiung-Cheng Lin
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages83-90
Number of pages8
ISBN (Electronic)9798350310412
DOIs
StatePublished - 2022
Event24th IEEE/ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022 - Taichung, Taiwan, Province of China
Duration: Dec 7 2022Dec 9 2022

Publication series

NameProceedings - 2022 IEEE/ACIS 24th International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022

Conference

Conference24th IEEE/ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2022
Country/TerritoryTaiwan, Province of China
CityTaichung
Period12/7/2212/9/22

Keywords

  • Bidirectional LSTM
  • deep learning
  • GRU
  • LSTM
  • Signal processing
  • Structural health monitoring
  • Vibration analysis

Fingerprint

Dive into the research topics of 'Ensemble Deep Learning Model for Damage Identification via Output-Only Signal Analysis'. Together they form a unique fingerprint.

Cite this