Coupling life prediction of bending very high cycle fatigue of completion strings made of different materials using deep wise separable convolution

• Published in: Fatigue & fracture of engineering materials & structures 2024-07, Vol.47 (7), p.2381-2395
• Main Authors: Zhu, Zhenyu, Chen, Maolin, He, Mingge, Zhang, Junliang, Huang, Yanyan, Chen, Siqi, Du, Xuanyu, Chai, Guocai, Wang, Qingyuan
• Format: Article
• Language: English
• Subjects: Bending fatigue; bending very high cycle fatigue; completion strings; Convolution; convolutional neural networks; Coupling; Crack initiation; Deep learning; Fatigue cracks; Fatigue failure; Fatigue life; fatigue life prediction; Fatigue strength; Fatigue tests; High cycle fatigue; Life prediction; Metal fatigue; Nickel base alloys; Prediction models; Strings
• ISSN: 8756-758X; 1460-2695; 1460-2695
• DOI: 10.1111/ffe.14299

This article predicts bending very high cycle fatigue (VHCF) life of three typical nickel‐based alloys SM2550, BG2532, and G3 used for completion strings. Fatigue tests were conducted on the three alloys using an ultrasonic fatigue system at a frequency of 20 kHz. The results showed that the fatigue strength ranges of the three alloys were markedly different, reflecting their different sensitivities to fatigue loading. Scanning electron microscope observations revealed numerous fatigue crack origins with internal decohesion in the fatigue source region. To achieve unified prediction of the fatigue life for the three alloys, a prediction model based on deep learning was built with inputs including fatigue initiation quantity, cleavage facet size, and other fatigue fracture characteristics. It was found that single source feature was insufficient to obtain satisfactory prediction accuracy for all alloys, while multifeature coupling integration could significantly improve the prediction precision, enabling reliable prediction of alloy fatigue life. This study provides new insights into bending VHCF life prediction. Highlights This article predicts bending VHCF life for three completion strings. Bending VHCF life model utilizing deep wise separable convolution was established. Deep learning can effectively integrate with bending VHCF analyses.