Model-Embedding based Damage Detection Method for Recurrent Neural Network

被引：0

作者：

Weng, Shun ^{[1
]}

Lei, Aoqi ^{[1
]}

Chen, Zhidan ^{[1
]}

Yu, Hong ^{[2
]}

Yan, Yongyi ^{[2
]}

Yu, Xingsheng ^{[2
]}

机构：

[1] School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan

[2] China Railway Siyuan Survey and Design Group Co. ，Ltd., Wuhan

来源：

Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences | 2024年 / 51卷 / 07期

关键词：

damage detection; recurrent neural network; Runge-Kutta method;

D O I：

10.16339/j.cnki.hdxbzkb.2024064

中图分类号：

学科分类号：

摘要：

Currently，the majority of structure damage identification methods based on deep learning rely on deep neural networks to automatically extract damage-sensitive features of structures and achieve pattern classification recognition through the differences in features between damage states. However，these methods face challenges in the accurate quantification of damage and require a large amount of data for model training. This article proposes a damage detection method based on a model-embedding recurrent neural network（MERNN）. Firstly，a data-driven convolutional neural network was used to establish the mapping relationship between load and response. Then，the traditional recurrent neural network was improved using the Runge-Kutta method to create a numerical computing unit based on the recurrent neural network architecture. Finally，based on the loss function composed of the residual errors between measured responses and computed responses，the structural stiffness parameters were updated with the automatic differentiation mechanism of the neural network to achieve structural damage identification. Damage identification results of a numerical three-layer frame and a laboratory-scale shear-type frame indicate that the proposed method can accurately quantify structural damage based on the limited amount of response datas. © 2024 Hunan University. All rights reserved.

引用

页码：21 / 29

页数：8

共 13 条

[1] LIN Y Z, MA H W., Structural damage detection with automatic feature-extraction through deep learning［J］, Computer-Aided Civil and Infrastructure Engineering, 32, 12, pp. 1025-1046, (2017)
[2] Convolutional neural networks for automated damage recognition and damage type identification［J］, Structural Control and Health Monitoring, 25, 10, (2018)
[3] SHU J P，, ZHANG C G，, CHEN X Y，, Et al., Model-informed deep learning strategy with vision measurement for damage identification of truss structures［J］, Mechanical Systems and Signal Processing, 196, (2023)
[4] TENG S，, CHEN X D，, CHEN G F，, Et al., Structural damage detection based on transfer learning strategy using digital twins of bridges［J］, Mechanical Systems and Signal Processing, 191, (2023)
[5] LI Z Q, WENG S，, ZHU H P, Cross-domain damage identification based on domain adaption-support vector machine, Progress in Steel Building Structures, 25, 9, pp. 91-100, (2023)
[6] ZHU H P, MAO L, WENG S．, A sensitivity-based structural damage identification method with unknown input excitation using transmissibility concept［J］, Journal of Sound and Vibration, 333, 26, pp. 7135-7150, (2014)
[7] CHEN Z D，, WENG S, Bayesian-based method for the simultaneous identification of structural damage and moving force［J］, Mechanical Systems and Signal Processing, 185, (2023)
[8] GUO X Y, FANG S E．, Structural parameter identification using physics-informed neural networks［J］．Measurement, 220, (2023)
[9] SUN L M, A convolutional neural network-based full-field response reconstruction framework with multitype inputs and outputs［J］, Structural Control and Health Monitoring, 29, 7, pp. 1-23, (2022)
[10] XIA Y．, Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks［J］, Structural Health Monitoring, 20, 4, pp. 2069-2087, (2021)

← 1 2 →