Structural sensing with deep learning: Strain estimation from acceleration data for fatigue assessment

Abstract

Many of the civil structures experience significant vibrations and repeated stress cycles during their life span. These conditions are the bases for fatigue analysis to accurately establish the remaining fatigue life of the structures that ideally requires a full-field strain assessment of the structures over years of data collection. Traditional inspection methods collect strain measurements by using strain gauges for a short time span and extrapolate the measurements in time; nevertheless, large-scale deployment of strain gauges is expensive and laborious as more spatial information is desired. This paper introduces a deep learning-based approach to replace this high cost by employing inexpensive data coming from acceleration sensors. The proposed approach utilizes collected acceleration responses as inputs to a multistage deep neural network based on long short-term memory and fully connected layers to estimate the strain responses. The memory requirement of training long acceleration sequences is reduced by proposing a novel training strategy. In the evaluation of the method, a laboratory-scale horizontally curved girder subjected to various loading scenarios is tested.

Deep Learning-Based Applications for Safety Management in the AEC Industry: A Review

“…The developed CNN achieved good results on both the in-lab structure and the in-service bridge. Gulgec et al [87] used a DL-based method for steel fatigue assessment. Compared to the traditional method, which is costly and laborious, their proposed method could achieve a high detection accuracy with a low cost.…”

A hybrid deep learning model for predictive flood warning and situation awareness using channel network sensors data

“…For example, advanced learning approaches such as deep convolutional neural network‐long short‐term memory (CNN‐LSTM) have been applied to optimize the use of autonomous vehicles (S. Chen, Leng, & Labi, 2020; Y. Wang, Hou, & Wang, 2020). ML has also been used in the field of structural health monitoring to analyze vibration response of structures and detection of anomalies extracted from sensors (Azimi & Pekcan, 2020; Gulgec, Takáč, & Pakzad, 2020; Ni, Zhang, & Noori, 2019). DL has also been used to help analyze traffic crash data (X. Zhang, Waller, & Jiang, 2020), analyze crack patterns in concrete structures (Cha, Choi, & Büyüköztürk, 2017; Okazaki, Okazaki, Asamoto, & Chun, 2020), and conduct reliability analysis on infrastructure networks (Nabian & Meidani, 2018).…”

Fatigue modeling using neural networks: A comprehensive review

“…An RNN works with sequential data. The difference between RNN and FNN is that connections are pointing backward in an RNN 21 . RNNs capture the dynamics of sequences with directed loops in them.…”

“…LSTM networks are designed to control the information in a memory cell to mitigate this problem. The input gate, forget gate, and output gate in the memory cell are used for the information control 21 …”