{"title":"Neural network approaches for real-time fatigue life estimation by Surrogating the rainflow counting method","authors":"Yiwen Guo, Liangxing Li, Jiabin Gui, Shurui Hu","doi":"10.1016/j.ijfatigue.2025.108941","DOIUrl":"10.1016/j.ijfatigue.2025.108941","url":null,"abstract":"<div><div>Fatigue life estimation is critical for ensuring the safety and reliability of systems under cyclic loading. Traditional rainflow counting methods require exhaustive traversal of load histories, making them computationally expensive for real-time applications. To address this issue, this present study leverages the increasing demand for efficient high-cycle fatigue (HCF) life estimation methods, combining neural network surrogate modeling with physical principles to enhance both accuracy and computational speed. The Euler neural network (ENN) and the Runge-Kutta 4th-order neural network (RK4NN) for fatigue life estimation are proposed. These approaches are validated by comparing the results of rainflow counting with wind turbine damage ratios, demonstrating the accuracy achieves errors within 15 % for over 74 % of cases in the numerical stability range. Moreover, the RK4NN displayed superior generalization and fitting capacities across varied load conditions, effectively capturing early-stage damage growth while avoiding overfitting with the mean squared error 1.99 × 10<sup>−36</sup>. Additionally, the ENN and the RK4NN achieved the acceleration ratio of 19.53 × and 19.38 × respectively in comparison with the modified rainflow counting method (RCM). These findings underscore the practical value of the surrogate models in improving the real-time responsiveness and computational efficiency of fatigue life estimation frameworks, particularly in digital twin applications for industrial systems.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108941"},"PeriodicalIF":5.7,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Attilio Arcari , Evan P. Strickland , Nicole A. Apetre , John G. Michopoulos
{"title":"On the assessment of low cycle fatigue performance of octet-based structural metamaterial","authors":"Attilio Arcari , Evan P. Strickland , Nicole A. Apetre , John G. Michopoulos","doi":"10.1016/j.ijfatigue.2025.108936","DOIUrl":"10.1016/j.ijfatigue.2025.108936","url":null,"abstract":"<div><div>Although metamaterials have shown their superior multiphysics responses compared to their solid counterparts, designing and deploying them requires that their durability and damage tolerance properties be well understood and characterized. The current work investigates low cycle fatigue properties of octet-based metamaterials by conducting an experimental fatigue study and identifying the failure modes and sequence within the strut-based lattices. A geometry consisting of octet cells was manufactured by selective laser sintering (SLS) using a PA2200 − Polyamide 12 material. The fatigue life was experimentally measured and compared for samples made with octets of different strut thicknesses in terms of the normalized specimen effective stiffness as a function of cycles. The progression of strut failures showed that the breaking of a strut within the main center volume of the sample was the most significant event in the fatigue life of the sample. A novel visualization technique to better analyze the finite element modeling results of the tested samples was developed and additional tests for samples with an initial state of damage demonstrated the validity of the approach.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108936"},"PeriodicalIF":5.7,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A data-assisted physics-informed neural network for predicting fatigue life of electronic components under complex shock loads","authors":"Shuai Ma , Yongbin Dang , Yi Sun , Zhiqiang Yang","doi":"10.1016/j.ijfatigue.2025.108933","DOIUrl":"10.1016/j.ijfatigue.2025.108933","url":null,"abstract":"<div><div>Reusable spacecraft electronic components experience multiple, complex shock damage during their operational life, which is a primary contributor to mission failure. This study proposes a data-assisted physics-informed neural network (DA-PINN) model to assess fatigue damage in electronic components under complex shock loads. Unlike traditional PINN that solves partial differential equations, DA-PINN combines experimental with physics equations to enhance prediction accuracy. An autoregressive (AR) model was used to improve the shock fatigue life model, which was then integrated as a physical constraint into the loss function of DA-PINN. Subsequently, using ball grid array (BGA) solder joints as the research subject, complex shock fatigue experiments were conducted to train and validate the DA-PINN model. The results demonstrate the outstanding performance of the DA-PINN model, with all predicted shock fatigue life values falling within a scatter band of 1.5 times, surpassing the traditional shock fatigue life model and artificial neural networks. Notably, the physics-informed constraints embedded in DA-PINN enable it to maintain strong prediction accuracy and stability even when trained on small datasets. The proposed model can provide a reference for predicting the shock fatigue life of electronic components in reusable spacecraft.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108933"},"PeriodicalIF":5.7,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143637193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Grain size refinement of hard nitride coating to mitigate fatigue performance degradation in ductile metal substrate","authors":"Zhaolu Zhang","doi":"10.1016/j.ijfatigue.2025.108935","DOIUrl":"10.1016/j.ijfatigue.2025.108935","url":null,"abstract":"<div><div>This paper proposes an effective way to relieve the side effect of hard nitride coating on tough metal substrate by reducing coating grain size and revealing its inner mechanism. Utilizing the thickness-dependent effect of physical vapor deposited hard coating grain size, TiN coatings with grain sizes of 9.6 nm, 16.5 nm, and 23.4 nm were prepared on the surface of 2A70 aluminum alloy fatigue specimen by filtered cathodic vacuum arc deposition. Rotating bending fatigue tests revealed that the median fatigue limits of 2A70, 2A70 with TiN coating at grain sizes of 9.6 nm, 16.5 nm, and 23.4 nm are 165.83 MPa, 127.5 MPa, 113.75 MPa, and 112.5 MPa, respectively. Under high-cycle fatigue loading, the TiN coating with a grain size of 9.6 nm exhibits the least damage to the substrate’s fatigue performance. And the fatigue resistance of TiN determines its damage extent to metal substrate’s fatigue behavior. Molecular dynamics analysis shows that the maximum stress experienced by TiN coatings increases with grain size after undergoing various fatigue loading cycles. Under alternating loads, smaller grains with more grain boundaries lead to predominant intergranular sliding in the TiN coating.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108935"},"PeriodicalIF":5.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xusheng Yang , Wenya Xiao , Weijiu Huang , Xianghui Zhu , Mofang Liu , Yuanzhi Qian
{"title":"The influence of stress levels on crack initiation and propagation behaviors of an Al-Li alloy under high cycle fatigue","authors":"Xusheng Yang , Wenya Xiao , Weijiu Huang , Xianghui Zhu , Mofang Liu , Yuanzhi Qian","doi":"10.1016/j.ijfatigue.2025.108934","DOIUrl":"10.1016/j.ijfatigue.2025.108934","url":null,"abstract":"<div><div>This study investigates the crack initiation and propagation behavior in AA2099 Al-Li alloy under high cycle fatigue (HCF) conditions using SEM, TEM, and EDS. The research focuses on the formation mechanisms of slip bands (SBs) and fatigue striations of small cracks. Results show that crack initiation primarily originates from surface or near-surface regions, particularly near inclusions and Fe-rich particles. Crack initiation tends to be single-source at low stress levels and multi-source at higher stress levels. SBs formation is closely associated with stress levels; as stress increases, SBs formation becomes more pronounced, and band spacing decreases. At low stress levels, significant crack deflection occurs due to single slip mechanism activation, while at high stress levels, multiple slip system activation results in a flatter fatigue crack propagation (FCP) path. Early-stage FCP of Al-Li alloys under HCF exhibits small crack characteristics. The formation of fatigue striations in small cracks is influenced by the degree of work hardening at the crack tip, and the spacing of fatigue striations decreases with increasing stress levels. However, as the crack length increases, the spacing of fatigue striations gradually increases, which is attributed to the development of the crack closure effect during the later stages of FCP.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108934"},"PeriodicalIF":5.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pengjie Wang , Hanlin Song , Jie Li , Jinyi Ren , Zhenyu Liu
{"title":"The high cycle fatigue behavior of niobium micro-alloyed high-Mn austenitic steel with unusual precipitation at 77 K","authors":"Pengjie Wang , Hanlin Song , Jie Li , Jinyi Ren , Zhenyu Liu","doi":"10.1016/j.ijfatigue.2025.108914","DOIUrl":"10.1016/j.ijfatigue.2025.108914","url":null,"abstract":"<div><div>Five high-Mn austenitic steels with different niobium contents are adopted to investigate their fatigue performance at 77 K by a homemade cryogenic device. The results show that although the tensile strength increases with the increase in Nb content, the fatigue performance shows an increasing followed by decreasing trend. Because the density of deformation twins is almost unchanged, so the increase in fatigue performance can be attributed to solution strengthening, grain refinement strengthening and precipitation strengthening. While the decrease can be attributed to the reduced initial microstructure uniformity and precipitates along twin boundaries which reduces the fatigue cracking resistance.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108914"},"PeriodicalIF":5.7,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143629918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yang Meng , Chungen Zhou , Zihua Zhao , Yuliang Shen , Haonan Pei , Ming Zhao
{"title":"Effect of oxidation on the competition between internal and external fatigue crack initiation of Ni-based single crystal superalloy","authors":"Yang Meng , Chungen Zhou , Zihua Zhao , Yuliang Shen , Haonan Pei , Ming Zhao","doi":"10.1016/j.ijfatigue.2025.108930","DOIUrl":"10.1016/j.ijfatigue.2025.108930","url":null,"abstract":"<div><div>Whether surface oxidation damage can shift the crack initiation location of Ni-based single crystal superalloys from internal defects to the surface in the VHCF regime remains an open question. This study examined two experimental conditions with pre-oxidation or high oxidation rates: fatigue tests at 1000 °C after pre-oxidation at 1100 °C for 100 h, and at 1050 °C on unoxidized specimens. The results indicate that both severe pre-oxidation and elevated oxidation rates lead to surface crack initiation. In pre-oxidized specimens, surface recrystallization occurs early, triggering surface cracking and reducing fatigue strength at 10<sup>7</sup> cycles, though its effect at 10<sup>9</sup> cycles is minimal. At 1050 °C, the fatigue strength decreases markedly compared with 1000 °C, and cracks consistently initiate at the surface and propagation in Mode I. Thermal growth stress of oxides near the crack tip alters the local stress state, promoting γ’ rafting. Deformation accumulated at γ/γ’ interfaces, coupled with γ’ rafting and low-angle grain boundaries, accelerates aluminum diffusion, forming Al<sub>2</sub>O<sub>3</sub> as the dominant oxide. Additionally, oxidation lowers the effective stress intensity factor, affecting crack propagation. Overall, these findings confirm that enhancing oxidation resistance is still critical for improving VHCF performance in Ni-based single crystal superalloys.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108930"},"PeriodicalIF":5.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C.L. Zou , B.Z. Tan , Y.J. Zhang , J.C. Pang , F. Shi , A.L. Jiang , S.X. Li , Q.H. Wu , Z.F. Zhang
{"title":"Thermo-mechanical fatigue damage mechanism and life prediction of compacted graphite iron with high strength","authors":"C.L. Zou , B.Z. Tan , Y.J. Zhang , J.C. Pang , F. Shi , A.L. Jiang , S.X. Li , Q.H. Wu , Z.F. Zhang","doi":"10.1016/j.ijfatigue.2025.108931","DOIUrl":"10.1016/j.ijfatigue.2025.108931","url":null,"abstract":"<div><div>The thermo-mechanical fatigue (TMF) damage mechanism of typical compacted graphite iron with high strength (RuT450) was investigated in different temperature ranges. The results indicate that the TMF life decreases as the peak temperatures rise from 400 °C to 500 °C. As the cyclic number increases, the maximum tensile stress shows slight cyclic hardening in the temperature range of 100 to 400 °C. Additionally, in the temperature range of 100 to 500 °C, the maximum compressive stress exhibits slight cyclic softening. The fatigue damage and crack propagation processes demonstrate that the tearing of vermicular graphite at the edge of the sample is the primary cause for fatigue crack initiation in the lower temperature range. The weakening region comprised of multiple vermicular graphite particles facilitates the gradual extension of cracks. At higher peak temperature, oxidation rapidly erodes the interface between the vermicular graphite and the matrix, which leads to the debonding of graphite and initiation of the fatigue cracks. The rapid oxidation effect accelerates the corrosion of the metal matrix, promoting crack propagation, which is the primary factor contributing to the reduction of fatigue life. Given the complexity and high cost associated with the TMF test, a method for predicting the TMF life by building the correlation between low-cycle fatigue and the TMF lives in terms of the hysteresis energy is proposed. This method enables rapid and accurate prediction of the TMF life through a relatively small amount of samples and simpler experiments, demonstrating significant industrial application potential.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108931"},"PeriodicalIF":5.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143644062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The physics of fatigue crack propagation","authors":"Michael D. Sangid","doi":"10.1016/j.ijfatigue.2025.108928","DOIUrl":"10.1016/j.ijfatigue.2025.108928","url":null,"abstract":"<div><div>The fatigue life can be expressed as the sum of the number of loading cycles to initiate a crack and propagate the crack to catastrophic fracture. A previous review provided perspectives on the mechanisms of fatigue crack initiation (Sangid, IJF 2013). In this review, the primary emphasis is describing the mechanisms of fatigue crack propagation, with emphasis on microstructurally small fatigue crack (MSFC) growth. The behavior of long cracks is well documented in the fatigue literature and informs damage tolerant life assessment strategies that have been employed for the last 50+ years. For MSFCs, the local microstructure dictates the crack behavior, which is the focus of this review paper. In engineering components, most of the fatigue lifetime is spent in the MSFC growth regime, hence necessitating the importance to describe the mechanisms governing MSFC growth. For the microstructure immediately surrounding a small crack, the irreversible dislocation processes, stress state, strain localization, micromechanical fatigue predictive metrics, and environmental considerations are discussed. Moreover, this review is timely due to recent advancements in experimental characterization approaches that can quantify the grain and sub-grain level total strains and lattice strains (and associated stresses) near the crack tip and micromechanical modeling to predict fatigue propagation.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108928"},"PeriodicalIF":5.7,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A TCN-based feature fusion framework for multiaxial fatigue life prediction: Bridging loading dynamics and material characteristics","authors":"Peng Zhang , Keke Tang","doi":"10.1016/j.ijfatigue.2025.108915","DOIUrl":"10.1016/j.ijfatigue.2025.108915","url":null,"abstract":"<div><div>Multiaxial fatigue represents one of the most prevalent and critical fatigue issues in engineering applications, yet its life prediction remains challenging due to the combined effects of material characteristics and dynamic loading paths. This study proposes a cross-material adaptive framework that innovatively fuses dynamic loading sequence features with material properties through an attention-based mechanism. The framework employs lightweight Temporal Convolutional Networks (TCN) for temporal feature extraction while considering frequency-domain features, and incorporates both static and cyclic material properties as structured inputs. The attention-based fusion mechanism enables adaptive integration of temporal and material features, enhancing the model’s ability to capture complex interactions between loading conditions and material characteristics. To validate this approach, a multiaxial fatigue dataset comprising 499 data points was established across six major categories of metallic materials. The model’s performance underwent rigorous evaluation using hierarchical nested cross-validation, while key features were identified through SHAP analysis and recursive feature elimination. Results demonstrate that the proposed unified model exhibits robust predictive performance, with TCN showing superior stability and efficiency compared to other temporal feature extraction methods. Furthermore, the study explores cross-material prediction, revealing that fine-tuning with a small proportion of new material data can significantly enhance prediction accuracy. This research provides a novel approach to multiaxial fatigue life prediction while laying the groundwork for future cross-material prediction capabilities.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"197 ","pages":"Article 108915"},"PeriodicalIF":5.7,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}