Vibration-based structural damage detection via phase-based motion estimation using convolutional neural networks. (1st October 2022)

• Record Type: Journal Article
• Authors: Zhang, Tianlong; Shi, Dapeng; Wang, Zhuo; Zhang, Peng; Wang, Shiming; Ding, Xiaoyu
• Is Part Of: Mechanical systems and signal processing. Volume 178(2022)
• Publication Date: 2022-10-01
• Subjects: Vibration -- Structural damage detection -- Phase-based motion estimation -- Convolutional neural networks -- Continuous wavelet transform; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2022.109320
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: Phase-based motion estimation and CNNs are combined to detect structural damage. Massive vibration signals could be obtained from a single video. The proposed method provides a solution of data shortage problem in CNN training. One video under each condition is possible to accurately detect bolt looseness. Abstract: Detection of structural damage is a major concern for engineers. In recent years, convolutional neural networks (CNNs) have been used for feature extraction and classification of vibration signals that reveal structural damage. Damage detection by CNNs greatly depends on high-quality learning data which are usually difficult to be obtained in actual engineering scenarios. To solve this problem, we combine phase-based motion estimation (PME) with the use of CNNs. By PME method, each pixel in a video can be regarded as a separate displacement sensor. Thus, it is possible to obtain millions of vibration signals from a single video, greatly facilitating CNN applications. We used a two-story steel structure for experimental validation. It was demonstrated that only one measured video sample obtained under each structural condition is possible to train a CNN model accurately detecting the location and severity of bolt looseness damage. This verified the outstanding performance of the proposed method.