Structural Damage Detection with Automatic Feature‐Extraction through Deep Learning

By Yi-Zhou Lin, Zhen-Hua Nie, Hongwei Ma. Comput. Aided Civ. Infrastructure Eng., 2017

578 citations recorded by the source corpus.

Subfields: Civil and Structural Engineering, Mechanics of Materials

View Paper: https://www.semanticscholar.org/paper/44dee0457d955a640c68a0e1a4ab94132b57d8c8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

In Mechanics of Materials

Citations in the corpus

Automatic Pixel‐Level Crack Detection and Measurement Using Fully Convolutional Network (2018, methodology): “…11-layer DNN integrated with Na¨ıve Bayes to detect multiple damages for the inspection of nuclear power plants; Zhang et al. (2017) devised a ﬁve-layer CNN with predeﬁned line ﬁlters to detect cracks on 3D asphalt surfaces; Lin et al. (2017) constructed an automatic damage feature-extraction DNN.”
FEMa: a finite element machine for fast learning (2019, background): “…neural networks [23], recurrent networks [22, 25], adaptive conjugate gradient neural network [1, 2], and deep neural network learning [8, 24, 45] are now being implemented in general-purpose computing on graphics processing units (GPGPU) to cope with streams of data that need to be…”
A Fast Detection Method via Region‐Based Fully Convolutional Neural Networks for Shield Tunnel Lining Defects (2018, unknown): “(Lin et al., 2017).”
Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection (2020, unknown): “In damage detection of a numerical beam model, Lin et al. (2017) employed t-SNE to visualize 256 acceleration time frames with 11 dimensions for cluster demonstration, and found time frames of the same damage case can be presented in the same cluster in a 2D map.”
Recent progress and future trends on damage identification methods for bridge structures (2019, methodology): “Ren et al.162 and Lin et al.163 established a damage‐sensitive but environment‐insensitive damage index through the covariance‐driven identification based on the stochastic subspace together with the statistical pattern recognition technology; the damage index is insensitive to the temperature varia”
Image‐based post‐disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization (2018, background): “…Gabbouj, & Inman, 2017), pavement crack detection (Vetrivel, Gerke, Kerle, Nex, & Vossel-man, 2018; Zhang et al., 2017), structural damage recognition through transfer learning (Gao & Mosalam, 2018), and structural damage detection with feature extracted from deep learning (Lin, Nie, & Ma, 2017).”
Efficient training of physics‐informed neural networks via importance sampling (2021, background): “Examples include, but are not limited to, structural damage detection and image recognition (e.g., Azimi & Pekcan, 2019; Cha et al., 2017; Koziarski & Cyganek, 2017; Liang, 2019; Lin et al., 2017; Rafiei & Adeli, 2018, 2017; Zeinali & Story, 2017; X. Zhang et al., 2019), estimation of concrete compr”
Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review (2020, methodology): “[54] Vibration-based feature extraction for damage detection 459 set of vertical acceleration signals collected from nine nodes in 1024 × 9 matrices”
Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network (2019, methodology): “A deep learning-based method was developed to detect railway defects (Soukup & Huber-Mörk, 2014), road cracks (Zhang et al., 2017; Zhang, Yang, Zhang, & Zhu, 2016b), concrete cracks (Cha, Choi, & Büyüköztürk, 2017a; Zhao & Li, 2017), and other damages (Lin, Nie, & Ma, 2017).”