Structural Damage Detection with Automatic Feature‐Extraction through Deep Learning

265

138

Visual inspection has traditionally been used for structural health monitoring. However, assessments conducted by trained inspectors or using contact sensors on structures for monitoring are costly and inefficient because of the number of inspectors and sensors required. To date, data acquisition using unmanned aerial vehicles (UAVs) equipped with cameras has become popular, but UAVs require skilled pilots or a global positioning system (GPS) for autonomous flight. Unfortunately, GPS cannot be used by a UAV for autonomous flight near some parts of certain structures (e.g., beneath a bridge), but these are the critical locations that should be inspected to monitor and maintain structural health. To address this difficulty, this article proposes an autonomous UAV method using ultrasonic beacons to replace the role of GPS, a deep convolutional neural network (CNN) for damage detection, and a geo‐tagging method for the localization of damage. Concrete cracks, as an example of structural damage, were successfully detected with 97.7% specificity and 91.9% sensitivity, by processing video data collected from an autonomous UAV.

Section: Introductionmentioning

confidence: 99%

Autonomous UAVs for Structural Health Monitoring Using Deep Learning and an Ultrasonic Beacon System with Geo‐Tagging

Kang

Cha

2018

265

138

“…Makantasis, Protopapadakis, Doulamis, Doulamis, and Loupos (2015) used a CNN with only two layers and a fully connected (FC) layer to detect tunnel cracks. Lin, Nie, and Ma (2017) proposed a novel structural damage detection approach based on deep CNN to automatically extract damage features and identify damage locations. Cha, Choi, Suh, Mahmoudkhani, and Büyüköztürk (2018) originally used the Faster R-CNN method to realize category 5 damage detection in real time in the field of structural damage detection.…”

Section: Introductionmentioning

confidence: 99%

Autonomous damage segmentation and measurement of glazed tiles in historic buildings via deep learning

Wang

Zhao

Zou

et al. 2019

Detecting and measuring the damage on historic glazed tiles plays an important role in the maintenance and protection of historic buildings. However, the current visual inspection method for identifying and assessing superficial damage on historic buildings is time and labor intensive. In this article, a novel two‐level object detection, segmentation, and measurement strategy for large‐scale structures based on a deep‐learning technique is proposed. The data in this study are from the roof images of the Palace Museum in China. The first level of the model, which is based on the Faster region‐based convolutional neural network (Faster R‐CNN), automatically detects and crops two types of glazed tile photographs from 100 roof images (2,488 × 3,264 pixels). The average precision values (AP) for roll roofing and pan tiles are 0.910 and 0.890, respectively. The cropped images are used to form a dataset for training a Mask R‐CNN model. The second level of the model, which is based on Mask R‐CNN, automatically segments and measures the damage based on the cropped historic tile images; the AP for the damage segmentation is 0.975. Based on Mask R‐CNN, the predicted pixel‐level damage segmentation result is used to quantitatively measure the morphological features of the damage, such as the damage topology, area, and ratio. To verify the performance of the proposed method, a comparative study was conducted with Mask R‐CNN and a fully convolutional network. This is the first attempt at employing a two‐level strategy to automatically detect, segment, and measure large‐scale superficial damage on historic buildings based on deep learning, and it achieved good results.

“…Some state‐of‐the‐art reviews were also provided to summarize and compare the works in vibration‐based SHM (Qarib and Adeli, ; Amezquita‐Sanchez and Adeli, ; Qarib and Adeli, ), feature extraction (Amezquita‐Sanchez and Adeli, ), and time‐frequency analysis for modal identification (Perez‐Ramirez et al., ). Several novel approaches such as multiple signal classification (Qarib and Adeli, ; Amezquita‐Sanchez and Adeli, ), synchrosqueezed WT (Amezquita‐Sanchez and Adeli, ; Perez‐Ramirez et al., ), fractality (Amezquita‐Sanchez and Adeli, ), the stretching method (Tsogka et al., ), filtered response vector (Kim et al., ), and deep convolutional neural network (Cha et al., ; Lin et al., ) were most recently developed in the above‐mentioned fields. Applications are even extended to the SHM of composite aircraft structures (Zhong and Xiang, ) and on‐line vehicle routing (Liao, ).…”

Section: Introductionmentioning

confidence: 99%

A Rapidly Convergent Empirical Mode Decomposition Method for Analyzing the Environmental Temperature Effects on Stay Cable Force

Chen

Jhou

et al. 2018

The variation histories of cable force and effective temperature were recently processed by empirical mode decomposition (EMD) to discover that they can both be categorized into two main components including the daily and long‐term variations. A rapidly convergent EMD method aimed to more efficiently decompose these two types of signals is established in this study. To deal with the typically encountered problems of slow convergence, scale mixing, and end effect in EMD, an objective stoppage criterion is first proposed and efforts are also made to clarify the origin of scale mixing and slow divergence. Based on the above explorations, an extremum neglecting algorithm and a boundary modification technique with appropriate control points are further developed to complete the whole methodology. The superiority of this new method is verified by more concisely decomposing the previously processed data into fewer intrinsic mode functions with a significant reduction in computation time.