In EDS ansehen

Wavelet-Statistic-Frame with LSTM-Attention Network for Continuous Damage Identification and Localization in Bridge Vibration Signals.

Gespeichert in:
Bibliographische Detailangaben
Titel: Wavelet-Statistic-Frame with LSTM-Attention Network for Continuous Damage Identification and Localization in Bridge Vibration Signals.
Autoren: Hu, Jianxin1 (AUTHOR), Yan, Senguang2 (AUTHOR), Ai, Shangpu2 (AUTHOR), Wang, Yucheng2 (AUTHOR), Fan, Wenlong2 (AUTHOR), Chang, Shilong2 (AUTHOR), Che, Gongjian2 (AUTHOR) chegongjian@163.com, Xue, Linyan2 (AUTHOR) chegongjian@163.com
Quelle: Traitement du Signal. Aug2025, Vol. 42 Issue 4, p1945-1954. 10p.
Schlagwörter: BRIDGE vibration, STRUCTURAL health monitoring, FEATURE extraction, WAVELETS (Mathematics), TIME-domain analysis, MACHINE learning, DEEP learning, DAMAGE models
Abstract: To address the challenges of non-stationarity and multi-scale feature extraction in bridge vibration signals for structural health monitoring, this paper proposes a deep learning framework, termed Wavelet-Statistic-Frame with LSTM-Attention Network (WSF-LANet), that integrates multi-source feature extraction with temporal modeling to extract damage-sensitive features from bridge vibration signals for identification and localization of different damage states. The model architecture is designed with three parallel feature extraction pathways: Discrete Wavelet Transform (DWT) based time-frequency analysis, extract statistical descriptors for quantifying latent damage indicators, and frame-wise segmentation and extraction of spatiotemporal features. After merging the features extracted from these three paths, a multi-attention block dynamically allocates weights across feature dimensions. The Long Short-Term Memory (LSTM) network is then used to further effectively capture the temporal dependencies of the sequence. The output is the final predicted damage matrix, which contains damage identification for each channel. In order to achieve both damage identification and localization functions, we additionally use unique heat encoding to represent multi-location and multi-category labels in a unified format. Experimental results show that on a bridge dataset from Japan, the proposed method achieves an accuracy of up to 97.5% for damage classification and a macro precision of 96.82% for localization. Ablation studies further validate the effectiveness of each feature extraction path. Cross-dataset evaluations also demonstrate strong generalization capability. In summary, the proposed WSF-LANet offers an efficient, accurate, and generalizable solution for intelligent damage identification and localization in bridge structural health monitoring. [ABSTRACT FROM AUTHOR]
Copyright of Traitement du Signal is the property of International Information & Engineering Technology Association (IIETA) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Datenbank: Business Source Index
Beschreibung
Abstract:To address the challenges of non-stationarity and multi-scale feature extraction in bridge vibration signals for structural health monitoring, this paper proposes a deep learning framework, termed Wavelet-Statistic-Frame with LSTM-Attention Network (WSF-LANet), that integrates multi-source feature extraction with temporal modeling to extract damage-sensitive features from bridge vibration signals for identification and localization of different damage states. The model architecture is designed with three parallel feature extraction pathways: Discrete Wavelet Transform (DWT) based time-frequency analysis, extract statistical descriptors for quantifying latent damage indicators, and frame-wise segmentation and extraction of spatiotemporal features. After merging the features extracted from these three paths, a multi-attention block dynamically allocates weights across feature dimensions. The Long Short-Term Memory (LSTM) network is then used to further effectively capture the temporal dependencies of the sequence. The output is the final predicted damage matrix, which contains damage identification for each channel. In order to achieve both damage identification and localization functions, we additionally use unique heat encoding to represent multi-location and multi-category labels in a unified format. Experimental results show that on a bridge dataset from Japan, the proposed method achieves an accuracy of up to 97.5% for damage classification and a macro precision of 96.82% for localization. Ablation studies further validate the effectiveness of each feature extraction path. Cross-dataset evaluations also demonstrate strong generalization capability. In summary, the proposed WSF-LANet offers an efficient, accurate, and generalizable solution for intelligent damage identification and localization in bridge structural health monitoring. [ABSTRACT FROM AUTHOR]
ISSN:07650019
DOI:10.18280/ts.420409