Machine learning assisted probabilistic creep-fatigue damage assessment

Gu, Hang-Hang; Wang, Run-Zi; Zhu, Shun‐Peng; Wang, Xiaowei; Wang, Dongming; Zhang, Guodong; Fan, Zhichao; Zhang, Xiancheng; Tu, Shan‐Tung

doi:10.1016/j.ijfatigue.2021.106677

Cited by 47 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, 2021). In conclusion, the multiaxial random/VA fatigue life prediction based on the critical plane needs to be further studied and demonstrated (ŁAgoda and Macha, 2000; Carpinteri et al ., 2017), and a variety of random/VA loading tests and practical engineering problems for different materials also need to be applied (Zhu et al ., 2017; Gu et al. , 2022).…”

Section: Discussion and Challengesmentioning

confidence: 99%

“…Alternatively, after the cycle period determined by the stress/strain component, the energy method is used to compute the damage (ŁAgoda and Macha, 2000;Zhu et al, 2018;Ahmadzadeh and Varvani-Farahani, 2019;Xue et al, 2020;Wu et al, 2021). In conclusion, the multiaxial random/VA fatigue life prediction based on the critical plane needs to be further studied and demonstrated (ŁAgoda and Macha, 2000;Carpinteri et al, 2017), and a variety of random/VA loading tests and practical engineering problems for different materials also need to be applied (Zhu et al, 2017;Gu et al, 2022).…”

Section: Discussion and Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Multiaxial fatigue under variable amplitude loadings: review and solutions

Deng

Zhu

et al. 2022

IJSI

Self Cite

View full text Add to dashboard Cite

PurposeEngineering components/structures with geometric discontinuities normally bear complex and variable loads, which lead to a multiaxial and random/variable amplitude stress/strain state. Hence, this study aims how to effectively evaluate the multiaxial random/variable amplitude fatigue life.Design/methodology/approachRecent studies on critical plane method under multiaxial random/variable amplitude loading are reviewed, and the computational framework is clearly presented in this paper.FindingsSome basic concepts and latest achievements in multiaxial random/variable amplitude fatigue analysis are introduced. This review summarizes the research status of four main aspects of multiaxial fatigue under random/variable amplitude loadings, namely multiaxial fatigue criterion, method for critical plane determination, cycle counting method and damage accumulation criterion. Particularly, the latest achievements of multiaxial random/variable amplitude fatigue using critical plane methods are classified and highlighted.Originality/valueThis review attempts to provide references for further research on multiaxial random/variable amplitude fatigue and to promote the development of multiaxial fatigue from experimental research to practical engineering application.

show abstract

Section: Discussion and Challengesmentioning

confidence: 99%

Section: Discussion and Challengesmentioning

confidence: 99%

Multiaxial fatigue under variable amplitude loadings: review and solutions

Deng

Zhu

et al. 2022

IJSI

Self Cite

View full text Add to dashboard Cite

show abstract

“…The machine learning approach can overcome the limitation of empirical solutions and preferably describe the nonlinear relationships between high dimensional data. As such, many investigators have taken advantage of advanced machine learning methods to solve complex problems such as the creep rupture life prediction, 23,43 life prediction of components at high temperatures under creep, fatigue, and creep-fatigue conditions, 49 creepfatigue damage assessment, 12 multiaxial fatigue life prediction, 42,45,46,51 FCGR prediction, 24 prediction of mechanical strength of concrete, 28 and so forth. For instance, Zhou et al 51 proposed a machine learning framework that combines the artificial neural network (ANN) and partial least squares (PLS) algorithm to predict fatigue life and identify genetic features of 316LN steel under uniaxial and multiaxial loading conditions.…”

Section: Introductionmentioning

confidence: 99%

Machine learning‐based approach for fatigue crack growth prediction using acoustic emission technique

Chai

Liu

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

In this study, a general machine learning‐based approach is proposed for fatigue crack growth rate (FCGR) prediction using multivariate acoustic emission (AE) online monitoring data. To improve the prediction accuracy, a backpropagation neural network optimized by genetic algorithm (GA‐BPNN) is developed to describe the intricate link between the FCGR and multivariate input data. Several conventional machine learning models and the traditional FCGR prediction method based on the linear relationship between AE energy rate and FCGR are also used to examine the effectiveness of the proposed GA‐BPNN model. The results indicate that the developed GA‐BPNN exhibits higher accuracy and superior adaptability in predicting FCGR from unseen data than other methods. The findings of this study will provide a strategy for developing and optimizing a machine learning solution for FCGR prediction based on AE monitoring data and also aid in determining the most suitable feature for AE monitoring studies.

show abstract

“…The maximum change rate is 50% of the rated power output. Although there has been a lot of researches on single-factor-driven fatigue or creep damage of many Ni-based alloys, [8][9][10][11] a clear and thorough understanding of the mechanism of fatigue and creep combined loading effect for Alloy 617 and Alloy 625 has not been clarified yet.…”

Section: Introductionmentioning

confidence: 99%

Acceleration mechanism of the degradation of the lifetime of Ni‐based superalloys under creep‐fatigue loading at elevated temperatures

Luo

Takahashi

Nakayama

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

In this study, intermittent creep-fatigue tests were applied on Ni-based Alloy 617 and Alloy 625. Scanning electron microscope (SEM) observation and electron back-scatter diffraction (EBSD) analysis were employed to the evaluation of the degradation of the crystallinity under the creep-fatigue loads. It was found that the initial damage under creep-fatigue load basically appeared as intergranular cracks. In addition, the lifetimes of Alloy 625 samples fluctuated significantly due to the growth of NbC precipitates. The initial damage of these two alloys was dominated by the growth and accumulation of dislocations and vacancies around the interface that consisted of large lattice mismatch. Local atomic diffusion was activated when the summation of the nominal stress and local stress caused by the large lattice mismatch exceeded a critical value. The stress-induced acceleration of the degradation of the crystallinity of the alloys was analyzed by applying the modified Arrhenius equation. Instead of the most popular inversion methods according to the final failure mode, the quantitative description in life prediction was developed based on the dynamic progress for acceleration mechanism of the degradation. It is of importance to perfecting the frontiers of damage mechanics approach.

show abstract

Machine learning assisted probabilistic creep-fatigue damage assessment

Cited by 47 publications

References 54 publications

Multiaxial fatigue under variable amplitude loadings: review and solutions

Multiaxial fatigue under variable amplitude loadings: review and solutions

Machine learning‐based approach for fatigue crack growth prediction using acoustic emission technique

Acceleration mechanism of the degradation of the lifetime of Ni‐based superalloys under creep‐fatigue loading at elevated temperatures

Contact Info

Product

Resources

About