Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network

2019 ◽  
Vol 26 (3) ◽  
pp. e2313 ◽  
Author(s):  
Yang Xu ◽  
Shiyin Wei ◽  
Yuequan Bao ◽  
Hui Li
Keyword(s):  
Neural Network ◽  
Reinforced Concrete ◽  
Convolutional Neural Network ◽  
Damage Identification ◽  
Concrete Columns ◽  
Seismic Damage ◽  
Deep Convolutional Neural Network ◽  
Reinforced Concrete Columns

scholarly journals Instant bridge visual inspection using an unmanned aerial vehicle by image capturing and geo-tagging system and deep convolutional neural network

2020 ◽  
pp. 147592172093238
Author(s):  
Muhammad Rakeh Saleem ◽  
Jong-Woong Park ◽  
Jin-Hwan Lee ◽  
Hyung-Jo Jung ◽  
Muhammad Zohaib Sarwar
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Visual Inspection ◽  
Crack Detection ◽  
Damage Identification ◽  
Deep Convolutional Neural Network ◽  
Crack Identification ◽  
Image Capturing ◽  
Damage Map ◽  
Tagging System

The structural condition of bridges is generally assessed using manual visual inspection. However, this approach consumes labor, time, and capital, and produces subjective results. Therefore, industries today are using automated visual inspection approaches, which quantify and localize damages such as cracks using robots and computer vision. This paper proposes an instant damage identification and localization approach that uses an image capturing and geo-tagging system and deep convolutional neural network for crack detection. The image capturing and geo-tagging allows the geo-tagging of three-dimensional coordinates and camera pose data with bridge inspection images; the deep convolutional neural network is trained for automated crack identification. The damages extracted by the convolutional neural network are instantly transformed into a global bridge damage map, with georeferencing data acquired using the image capturing and geo-tagging. This method is experimentally validated through a lab-scale test on a wall and a field test on a bridge to demonstrate the performance of the instant damage map.

scholarly journals Multiple-Input Convolutional Neural Network Model for Large-Scale Seismic Damage Assessment of Reinforced Concrete Frame Buildings

2021 ◽  
Vol 11 (17) ◽  
pp. 8258
Author(s):  
Chen Xiong ◽  
Jie Zheng ◽  
Liangjin Xu ◽  
Chengyu Cen ◽  
Ruihao Zheng ◽  
...  
Keyword(s):  
Neural Network ◽  
Reinforced Concrete ◽  
Convolutional Neural Network ◽  
Damage Assessment ◽  
Prediction Accuracy ◽  
Seismic Damage ◽  
Computation Efficiency ◽  
Frame Buildings ◽  
Multiple Input ◽  
Seismic Damage Assessment

This study introduces a multiple-input convolutional neural network (MI-CNN) model for the seismic damage assessment of regional buildings. First, ground motion sequences together with building attribute data are adopted as inputs of the proposed MI-CNN model. Second, the prediction accuracy of MI-CNN model is discussed comprehensively for different scenarios. The overall prediction accuracy is 79.7%, and the prediction accuracies for all scenarios are above 77%, indicating a good prediction performance of the proposed method. The computation efficiency of the proposed method is 340 times faster than that of the nonlinear multi-degree-of-freedom shear model using time history analysis. Third, a case study is conducted for reinforced concrete (RC) frame buildings in Shenzhen city, and two seismic scenarios (i.e., M6.5 and M7.5) are studied for the area. The simulation results of the area indicate a good agreement between the MI-CNN model and the benchmark model. The outcomes of this study are expected to provide a useful reference for timely emergency response and disaster relief after earthquakes.

Cumulative Seismic Damage of Reinforced Concrete Columns: Variable Amplitude Tests

2011 ◽  
Vol 52-54 ◽  
pp. 740-744
Author(s):  
Guo Hua Xing ◽  
Yuan Pan ◽  
Guo Fu ◽  
Jian Ling Hou
Keyword(s):  
Reinforced Concrete ◽  
Phase I ◽  
Low Cycle Fatigue ◽  
Damage Model ◽  
Concrete Columns ◽  
Seismic Damage ◽  
Cycle Fatigue ◽  
Constant Amplitude ◽  
Reinforced Concrete Columns ◽  
Variable Amplitude

The findings from an experimental study to investigate cumulative seismic damage in reinforced concrete columns are presented. Fourteen identical half-scale concrete columns were fabricated and tested to failure. Results from Phase I testing, which included constant amplitude tests to determine the low-cycle fatigue characteristics of the rectangular concrete column, were presented in a companion paper. This paper summarizes results of variable amplitude tests. The imposed displacement histories were obtained from analytical simulations of the model column subjected to a series of earthquakes. Test observations indicate that failure is generally initiated by confinement inadequacy and the rupture of the transverse hoop reinforcement. The tests also demonstrated the potential for low-cycle fatigue fracture of the main longitudinal steel when the specimen was subjected to relatively larger displacement amplitudes. A fatigue-based damage model, derived from the constant-amplitude tests completed in Phase I testing, was applied to the observed response of the three specimens tested in this phase. Findings from the study indicate that the energy capacity of members is ductility-dependent and that fatigue-based damage models offer a reliable means of assessing seismic structural performance.

IDENTIFICATION OF DAMAGE IN REINFORCED CONCRETE COLUMNS UNDER PROGRESSIVE SEISMIC EXCITATION STAGES

2011 ◽  
Vol 05 (02) ◽  
pp. 151-165 ◽  
Author(s):  
ZHISHEN WU ◽  
ADEKUNLE PHILIPS ADEWUYI ◽  
SONGTAO XUE
Keyword(s):  
Reinforced Concrete ◽  
Damage Identification ◽  
Concrete Columns ◽  
Shaking Table ◽  
Dynamic Loads ◽  
Strain Gauges ◽  
Experimental Investigations ◽  
Seismic Excitations ◽  
Reinforced Concrete Columns ◽  
Fbg Sensors

Prompt and accurate detection of realistic damage in constructed facilities is critical for effective condition assessment and structural health monitoring. This paper reports the experimental investigations of eccentric reinforced concrete columns mounted onto a shaking table and subject to progressively increasing seismic excitations. The investigation was aimed at studying the changes in the dynamic parameters in order to assess the structural conditions of the concrete columns after each post-seismic stage. The dynamic response of the structure was measured using accelerometers, traditional foil-strain gauges, and long-gauge fiber Bragg grating (FBG) sensors. The post-seismic conditions of the columns were evaluated via vibration-based damage identification methods. Results from this study demonstrate the applicability of specially packaged surface-mounted long-gauge FBG sensors for detecting the initiation and the progression of cracks due to reverse dynamic loads. The concept of modal macrostrain analysis was also introduced to identify and localize mild damage due to the applied seismic excitations of increasing intensities. The performance of the sensors for structural identification is also discussed.

Sign in / Sign up

Export Citation Format

Share Document