A deep learning-based fatigue crack growth rate measurement method using mobile phones. (February 2023)

• Record Type: Journal Article
• Authors: Long, Xiangyun; Yu, Mengchen; Liao, Wangwang; Jiang, Chao
• Is Part Of: International journal of fatigue. Volume 167:Part B(2023)
• Publication Date: 2023-02
• Subjects: Deep learning -- Fatigue crack growth rate measurement method -- Mobile phone -- Dual-scale Faster R-CNN -- Non-standard specimen; Materials -- Fatigue -- Periodicals; Materials -- Fatigue; Periodicals; 620.1122
• DOI: 10.1016/j.ijfatigue.2022.107327
• Languages: English
• ISSNs: 0142-1123

Abstract

Highlights: Deep learning-based fatigue crack growth rate measurement method is proposed. A novel dual-scale deep CNN is designed for crack length quantification. The proposed method can be integrated into mobile phones for automation. The proposed method is applicable to non-standard cracked specimens. The prediction accuracy of measuring crack length reaches up to 98.79% Abstract: This paper proposes a fatigue crack growth rate (FCGR) measure method based on deep learning. Crack data sets of different scales are first collected by a camera, and are then used to train the faster region-based convolutional neural network (Faster R-CNN), respectively. A novel global and local dual-scale Faster R-CNN is further constructed and integrated into the mobile phone to predict the crack length during the entire loading cycle. The fatigue crack growth rate constants are finally obtained by integrating fracture mechanics. The proposed method can effectively measure the propagating small cracks during cyclic loading and extend to non-standard specimens.