Convolutional neural networks (CNNs)-based multi-category damage detection and recognition of high-speed rail (HSR) reinforced concrete (RC) bridges using test images. (1st February 2023)

• Record Type: Journal Article
• Authors: Chen, Lingkun; Chen, Wenxin; Wang, Lu; Zhai, Chencheng; Hu, Xiaolun; Sun, Linlin; Tian, Yuan; Huang, Xiaoming; Jiang, Lizhong
• Is Part Of: Engineering structures. Volume 276(2023)
• Publication Date: 2023-02-01
• Subjects: high-speed rail (HSR) bridges -- reinforced concrete (RC) multi-category damage -- Non-destructive testing -- Damage detection -- convolutional neural networks (CNNs) -- Deep learning (DL); Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2022.115306
• Languages: English
• ISSNs: 0141-0296

Abstract

Highlights: Based on HSR bridge damage pictures, bridge damage diseases are categorized into three major categories. Train AlexNet convolutional neural network by migration learning technique. Constructed an automatic bridge structure damage recognition model. Abstract: The fast networking of high-speed rail (HSR) may cause in-service fatigue and ultimate load damage to bridges. This paper investigates the application of deep convolutional neural networks (CNNs) for multi-category damage image classification recognition of HSR-reinforced concrete (RC) bridges. The present study establishes a deep learning (DL) system based on a large amount of HSR bridge test data. When to begin, the damage done to HSR bridge piers may be broken down into three primary categories: concrete cracks, concrete spalling, and reinforcement exposure. These categories are determined by the statistics of HSR bridge pier testing. Secondly, in order to develop an automated recognition model for the damage of HSR piers, AlexNet CNNs were taught a transfer learning approach and then used to train themselves. The correct recognition rate of the three damaged pictures in the actual application of the model is 86% for cracks, 82% for reinforcement exposure, and 70% for concrete spalling, all of which have good recognition rates. The study's accuracy and precision enhance detection efficiency and may be utilized to identify HSR pier deterioration quickly. The research comprises a random selection from the training and validation sets. It also assesses the training model's generalization to out-of-sample pictures for engineering applications. This aspect of the work sets it apart from previous research in the same study area.