Gaussian process regression based remaining fatigue life prediction for metallic materials under two-step loading. (May 2022)

• Record Type: Journal Article
• Authors: Gao, Jingjing; Wang, Cunjun; Xu, Zili; Wang, Jun; Yan, Song; Wang, Zhen
• Is Part Of: International journal of fatigue. Volume 158(2022)
• Publication Date: 2022-05
• Subjects: Gaussian Process Regression -- Fatigue life prediction -- Machine learning -- Two-step loading -- Remaining fatigue life; Materials -- Fatigue -- Periodicals; Materials -- Fatigue; Periodicals; 620.1122
• DOI: 10.1016/j.ijfatigue.2022.106730
• Languages: English
• ISSNs: 0142-1123

Abstract

Highlights: The proposed method is proposed for remaining life prediction and uncertainty quantification under two-step loading. The proposed method is verified by a database containing 12 metallic materials, 328 two-step loading experimental results. The proposed method can achieve greater accuracy and reliability in prediction of remaining life under two-step loading. The proposed method shows effective application in the estimation of the untrained Al-2024-T42 material. Abstract: Remaining fatigue life prediction is vital for engineering structures to ensure safety and reliability. It can be more challenging when the structures suffer variable amplitude loadings because of the complex, non-uniform of the fatigue damage accumulation and inherent noise, uncertainty in the data. To further tackle the problem, the Gaussian process regression (GPR) is introduced, which can simultaneously estimate the output value and quantify the associated uncertainty. Therefore, a GPR-based remaining fatigue life prediction method is proposed to predict the remaining fatigue life for metallic materials under two-step loading in this paper. The proposed method is comprehensively evaluated on the dataset containing 12 materials, 328 samples in total. The proposed method achieves the lowest mean square error (MSE), mean absolute percentage error (MAPE), residual standard deviation (RSD) values and the highest correlation coefficient (CC) values among the six machine learning methods and the two model-driven methods. Those results indicate that the proposed method can achieve greater accuracy and reliability in remaining life prediction under two-step loading, which illustrate the effectiveness of the proposed method as a data-driven method in the field of remaining life prediction.