A new cyclical generative adversarial network based data augmentation method for multiaxial fatigue life prediction. (September 2022)

• Record Type: Journal Article
• Authors: Sun, Xingyue; Zhou, Kun; Shi, Shouwen; Song, Kai; Chen, Xu
• Is Part Of: International journal of fatigue. Volume 162(2022)
• Publication Date: 2022-09
• Subjects: Multiaxial Fatigue -- Generative adversarial networks -- Data augmentation -- Fourier transformation -- Machine learning; Materials -- Fatigue -- Periodicals; Materials -- Fatigue; Periodicals; 620.1122
• DOI: 10.1016/j.ijfatigue.2022.106996
• Languages: English
• ISSNs: 0142-1123

Abstract

Graphical abstract: Highlights: A cGAN model is proposed to make multiaxial fatigue cyclic data augmentation. Fourier transformation is integrated into the cGAN to preprocess fatigue data. With data augmentation, the performance of machine learning models is improved by 35%-91%. Partial Least Square is adopted to extract the features in prediction processing. Abstract: To meet the requirement of large experimental data for machine learning (ML) methods on multiaxial life prediction, a cyclical Generative Adversarial Network (named cGAN) integrating Fourier transformation and other semi-empirical equations, was proposed to augment data following physical knowledge. Two samples of each loading path can be augmented into hundreds of good quality samples. Consequently, the accuracy of ML methods for multiaxial fatigue life of 316L stainless steel can been improved by 35%-91%. The new method can definitely balance time cost of bigger sample size and prediction accuracy well.