Residual Strength Evaluation of Corroded Textile-Reinforced Concrete by the Deep Learning-Based Method

Abstract

Residual strength of corroded textile-reinforced concrete (TRC) is evaluated using the deep learning-based method, whose feasibility is demonstrated by experiment. Compared to the traditional method, the proposed method does not need to know the climatic conditions in which the TRC exists. Firstly, the information about the faster region-based convolutional neural networks (Faster R-CNN) is described briefly, and then procedures to prepare datasets are introduced. Twenty TRC specimens were fabricated and divided into five groups that were treated to five different corrosion degrees corresponding to five different residual strengths. Five groups of images of microstructure features of these TRC specimens with five different residual strengths were obtained with portable digital microscopes in various circumstances. With the obtained images, datasets required to train, validate, and test the Faster R-CNN were prepared. To enhance the precision of residual strength evaluation, parameter analysis was conducted for the adopted model. Under the best combination of considered parameters, the mean average precision for the residual strength evaluation of the five groups of the TRC is 98.98%. The feasibility of the trained model was finally verified with new images and the procedures to apply the presented method were summarized. The paper provides new insight into evaluating the residual strength of structural materials, which would be helpful for safety evaluation of engineering structures.

A Systematic Review of the Research Development on the Application of Machine Learning for Concrete

“…[4][5][6][7][8][9][10]. These subdisciplines provide a deeper grasp of learning and fundamental relationships, and allow for dealing with valuable datasets, diverse data sources, computer systems for data-concentrated functions, data privacy, and other related topics [11][12][13][14][15]. Nevertheless, ML is one of the most powerful and in-demand technologies globally [16][17][18][19][20].…”

Analysis of the Region of Interest According to CNN Structure in Hierarchical Pattern Surface Inspection Using CAM

“…Recently, with the development of industrial artificial intelligence along with computer technology, many studies have been reported using artificial intelligence to detect surface defects. The convolutional neural network (CNN) is an image-based deep learning algorithm and is a representative model used to surface inspection [ 4 , 5 , 6 , 7 , 8 , 9 ]. By repetitive training, features that define surface defects are automatically extracted without expert assistance.…”

Experimental Study on the Permeation and Migration Rules of Pressurized Water in Textile-Reinforced Concrete (TRC)

“…TRC is a new type of cement-based composite material consisting of multidimensional fiber bundles and concrete matrix [ 5 , 6 ]. Compared to reinforcement steel, textile fiber has the advantages of high corrosion resistance [ 7 , 8 , 9 ] and light weight [ 10 ]. Moreover, TRC can effectively resist the effects of chloride ions and carbon dioxide in the environment due to the presence of high corrosion resistance of the fiber materials [ 11 ] (such as carbon fiber, alkali-resistant glass fiber, basalt fiber).…”