Detecting failed tethers in submerged floating tunnels using an LSTM autoencoder and DNN algorithms

This study proposes a two-step approach for detecting damaged tethers in submerged floating tunnels. The proposed method employs two different artificial neural network algorithms. First, the long short-term memory (LSTM) autoencoder model trained using response datasets under intact conditions was...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Ocean engineering Ročník 312; s. 119105
Hlavní autoři:	Min, Seongi, Jeong, Kiwon, Kim, Seungjun
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 15.11.2024
Témata:	Damage detection and localization Deep neural networks LSTM autoencoder Measured motion response data Submerged floating tunnel Tether Submerged floating tunnel Deep neural networks Measured motion response data Damage detection and localization Tether LSTM autoencoder
ISSN:	0029-8018
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	This study proposes a two-step approach for detecting damaged tethers in submerged floating tunnels. The proposed method employs two different artificial neural network algorithms. First, the long short-term memory (LSTM) autoencoder model trained using response datasets under intact conditions was used to reconstruct the measured acceleration data of the target structure. Further, the data reconstruction error was used as the input for the deep neural network algorithm trained in advance using the reconstruction error pattern in various tether damage cases. The proposed method was verified by conducting a well-validated simulation based on hydrodynamics. The damage-detection accuracy of the proposed method was directly compared with that of a conventional supervised learning algorithm-based approach. In addition, the case study results confirmed that the proposed approach was applicable to other submerged floating tunnel (SFT) structures by retraining the LSTM autoencoder and deep neural network algorithms with intact datasets only. Thus, this approach does not require a large amount of training data or simulation model updates for other SFT structures. •A two-step approach for detecting damaged tethers in SFTs is proposed, combining unsupervised and supervised ANN algorithms.•The LSTM autoencoder is used to recognize changes in structural conditions from the tunnel's acceleration data.•The DNN is employed to localize failed tethers through the analysis of response data reconstruction error patterns.•Case studies validate the effectiveness and applicability of the proposed method compared to a conventional approach.
ISSN:	0029-8018
DOI:	10.1016/j.oceaneng.2024.119105