An Automated Image-Based Multivariant Concrete Defect Recognition Using a Convolutional Neural Network with an Integrated Pooling Module.

Buildings and infrastructure in congested metropolitan areas are continuously deteriorating. Various structural flaws such as surface cracks, spalling, delamination, and other defects are found, and keep on progressing. Traditionally, the assessment and inspection is conducted by humans; however, due to human physiology, the assessment limits the accuracy of image evaluation, making it more subjective rather than objective. Thus, in this study, a multivariant defect recognition technique was developed to efficiently assess the various structural health issues of concrete. The image dataset used was comprised of 3650 different types of concrete defects, including surface cracks, delamination, spalling, and non-crack concretes. The proposed scheme of this paper is the development of an automated image-based concrete condition recognition technique to categorize, not only non-defective concrete into defective concrete, but also multivariant defects such as surface cracks, delamination, and spalling. The developed convolution-based model multivariant defect recognition neural network can recognize different types of defects on concretes. The trained model observed a 98.8% defect detection accuracy. In addition, the proposed system can promote the development of various defect detection and recognition methods, which can accelerate the evaluation of the conditions of existing structures.

Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning.

The adoption of artificial intelligence in post-earthquake inspections and reconnaissance has received considerable attention in recent years, owing to its exponential increase in computation capabilities and inherent potential in addressing disadvantages associated with manual inspections. Herein, we present the effectiveness of automated deep learning in enhancing the assessment of damage caused by the 2017 Pohang earthquake. Six classical pre-trained convolutional neural network (CNN) models are implemented through transfer learning (TL) on a small dataset, comprising 1780 manually labeled images of structural damage. Feature extraction and fine-tuning TL methods are trained on the image datasets. The performances of various CNN models are compared on a testing image dataset. Results confirm that the MobileNet fine-tuned model offers the best performance. Therefore, the model is further developed as a web-based application for classifying earthquake damage. The severity of damage is quantified by assigning damage assessment values, derived using the CNN model and gradient-weighted class activation mapping. The web-based application can effectively and automatically classify structural damage resulting from earthquakes, rendering it suitable for decision making, such as in resource allocation, policy development, and emergency response.

Multivariate Analysis of Concrete Image Using Thermography and Edge Detection.

With the growing demand for structural health monitoring system applications, data imaging is an ideal method for performing regular routine maintenance inspections. Image analysis can provide invaluable information about the health conditions of a structure's existing infrastructure by recording and analyzing exterior damages. Therefore, it is desirable to have an automated approach that reports defects on images reliably and robustly. This paper presents a multivariate analysis approach for images, specifically for assessing substantial damage (such as cracks). The image analysis provides graph representations that are related to the image, such as the histogram. In addition, image-processing techniques such as grayscale are also implemented, which enhance the object's information present in the image. In addition, this study uses image segmentation and a neural network, for transforming an image to analyze it more easily and as a classifier, respectively. Initially, each concrete structure image is preprocessed to highlight the crack. A neural network is used to calculate and categorize the visual characteristics of each region, and it shows an accuracy for classification of 98%. Experimental results show that thermal image extraction yields better histogram and cumulative distribution function features. The system can promote the development of various thermal image applications, such as nonphysical visual recognition and fault detection analysis.

Aerodynamic Characteristics and Lateral Displacements of a Set of Two Buildings in a Linked Tall Building System.

This study evaluates the aerodynamic characteristics and lateral displacements of two staggered buildings in a linked-building (LB) system. Particle image velocimetry and pressure measurements are employed, and the lateral displacement is evaluated using a 3-dimensional analytical model. When the gap distance between two non-linked buildings is small, the wind flows in a narrow jet, and a strong suction is generated on the inner surfaces of the two buildings, leading to a large cross-wind-induced response. However, the cross-wind-induced response is significantly reduced when a link is installed, because the suction forces generated from the buildings are in opposite directions and have a negative aerodynamic correlation. Conversely, with a large gap distance, the buildings at the front obstruct the wind blowing toward the rear buildings. Therefore, while the pressure distribution, wind-force coefficients, and wind-induced responses of the front and rear buildings show similar trends, the magnitude of impact on the front building is larger than that on the rear building. Installing a link is demonstrated to reduce the wind-induced response of the buildings in an LB system. However, the reduction in the along-wind-induced response is less than that in the cross-wind-induced response when the gap distance is small.

Wind-Induced Pressure Prediction on Tall Buildings Using Generative Adversarial Imputation Network.

Wind tunnel testing techniques are the main research tools for evaluating the wind loadings of buildings. They are significant in designing structurally safe and comfortable buildings. The wind tunnel pressure measurement technique using pressure sensors is significant for assessing the cladding pressures of buildings. However, some pressure sensors usually fail and cause loss of data, which are difficult to restore. In the literature, numerous techniques are implemented for imputing the single instance data values and data imputation for multiple instantaneous time intervals with accurate predictions needs to be addressed. Thus, the data imputation capacity of machine learning models is used to predict the missing wind pressure data for tall buildings in this study. A generative adversarial imputation network (GAIN) is proposed to predict the pressure coefficients at various instantaneous time intervals on tall buildings. The proposed model is validated by comparing the performance of GAIN with that of the K-nearest neighbor and multiple imputations by chained equation models. The experimental results show that the GAIN model provides the best fit, achieving more accurate predictions with the minimum average variance and minimum average standard deviation. The average mean-squared error for all four sides of the building was the minimum (0.016), and the average R-squared error was the maximum (0.961). The proposed model can ensure the health and prolonged existence of a structure based on wind environment.