{"title":"A physics-informed neural network for predicting structural fatigue damage of orthotropic bridge deck through updating model uncertainties","authors":"Cheng Xie , Yongtao Bai","doi":"10.1016/j.ijfatigue.2025.109253","DOIUrl":"10.1016/j.ijfatigue.2025.109253","url":null,"abstract":"<div><div>Orthotropic bridge deck (OBD) is commonly used in long-span bridges and is the critical structure prone to high-cycle fatigue (HCF) damage. To solve the difficulties in fatigue assessment on full-scale engineering structures, this paper proposed a modern physical-informed neural network (PINN) for conducting the structural fatigue modeling on the OBD structures through updating model uncertainties. Firstly, the three-stage fatigue crack growth (FCG) model for structural components was presented, especially with the multiple uncertainties introduced. Then, the PINN that consists of input layers, output layers, and interpretable hidden layers never involved in the previous model was built and named as StructFatigueNet. Subsequently, following the workflow of the StructFatigueNet, the structural fatigue models on three ODB structures were carried out for the prediction of the local crack and structural displacement change during the life, which showed not only the exceeding 90% accuracy, but also the uses of the structural fatigue behavior prediction, missing crack data acquisition and real-time health monitoring. Compared with a normal LSTM, the StructFatigueNet improved accuracy by 33% owing to the three-stage FCG physics information. Furthermore, it was also extended for other shapes of critical fatigue detail in the long-span bridge, illustrating the relative accuracy.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109253"},"PeriodicalIF":6.8,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144931605","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}
Zhanguang Zheng , Cheng Lin , Jun Yang , Dongyang Chen , Liping Jiang
{"title":"The hybrid model of domain knowledge, symbolic regression and neural networks for multiaxial fatigue life prediction","authors":"Zhanguang Zheng , Cheng Lin , Jun Yang , Dongyang Chen , Liping Jiang","doi":"10.1016/j.ijfatigue.2025.109246","DOIUrl":"10.1016/j.ijfatigue.2025.109246","url":null,"abstract":"<div><div>To further enhance the prediction performance of multiaxial fatigue life based on Physics Informed Neural Network (PINN), Domain Knowledge guided Symbolic Regression-Neural Network (DKSR-NN) framework is proposed. At first, domain knowledge is employed to guide symbolic regression in generating expressions that possess both physical interpretability and high predictive accuracy. These expressions are then incorporated as physics-informed loss functions within the PINN architecture. This integration significantly improves the model’s accuracy and stability, especially under conditions of limited fatigue data. At last, the proposed method is validated by comparisons with different machine learning on AZ61A magnesium alloy, TC4 titanium alloy, and sintered porous iron. The results demonstrate that the DKSR-NN framework is better than PINN using critical plane models as physical loss constraints, DKSR and pure data-driven machine learning methods. This will provide a prospect for multiaxial fatigue life prediction.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109246"},"PeriodicalIF":6.8,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895501","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}
Yuan-Ze Tang , Run-Zi Wang , Hang-Hang Gu , Kai-Shang Li , Yu-Chen Zhao , Zhi-Shen Wang , Yi-Quan Guo , Xian-Cheng Zhang , Shan-Tung Tu
{"title":"Sequential physics-data coupling framework for multi-model life prediction of fatigue, creep, and creep-fatigue","authors":"Yuan-Ze Tang , Run-Zi Wang , Hang-Hang Gu , Kai-Shang Li , Yu-Chen Zhao , Zhi-Shen Wang , Yi-Quan Guo , Xian-Cheng Zhang , Shan-Tung Tu","doi":"10.1016/j.ijfatigue.2025.109248","DOIUrl":"10.1016/j.ijfatigue.2025.109248","url":null,"abstract":"<div><div>Accurate life prediction for high-temperature components subjected to fatigue, creep, and their interactions presents considerable complexity, driven not only by coupled degradation mechanisms but also by the inherent intricacy of high-precision models requiring rigorous parameter fitting. In practice, model selection is often guided by application-specific requirements through resource-intensive trial-and-error processes, potentially overlooking synergistic insights from complementary approaches. This study introduces a sequential physics-data coupling framework designed to reconcile these challenges. Classical physical models are harmonized through multi-objective optimization to generate robust baseline predictions. A data-driven correction module further refines predictions by adaptively correcting model biases via confidence-guided multi-task learning. Validated on five alloys including GH4169, TC4, MAR-M247, 9Cr1Mo, and 304HCu, the framework demonstrates enhanced generalization across creep-fatigue, high-cycle fatigue, and creep rupture scenarios. By synergizing physics-based interpretability with adaptive corrections, it reduces over-reliance on single-model selection while maintaining computational efficiency, offering a practical tool for engineering reliability assessments.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109248"},"PeriodicalIF":6.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895503","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":"High cycle fatigue behavior and magnetic domain structure of non-oriented and grain-oriented electrical steels at Rσ = 0.1 and Rσ = −1","authors":"C. Backes, M. Smaga, T. Beck","doi":"10.1016/j.ijfatigue.2025.109251","DOIUrl":"10.1016/j.ijfatigue.2025.109251","url":null,"abstract":"<div><div>The high cycle fatigue behavior of a non-oriented electrical steel (NOES) and a grain-oriented electrical steel (GOES) was investigated under two loading conditions with respect to the rolling direction and the transverse direction. The deformation behavior under non-symmetric cyclic loading, i.e. R<sub>σ</sub> = 0.1 is characterized by strongly pronounced ratcheting. While ratcheting starts within the first cycle after overcoming the cyclic Lüders band propagation for NOES, the onset of ratcheting for GOES is delayed and starts after an incubation period. For symmetric cyclic loading, i.e. R<sub>σ</sub> = -1, an anti-buckling device was applied to the specimen. The cyclic deformation behavior was characterized by mostly elastic behavior in a saturated state with cyclic microplasticity leading to material failure. The investigation of the magnetic domain structure after cyclic loading revealed for NOES a refined domain structure of the specimens after non-symmetric cyclic loading due to higher amounts of plastic deformation. After symmetric cyclic loading, the magnetic domain structure was less altered due to the lower amount of plastic deformation from mostly elastic behavior during cyclic loading. The magnetic domain structures of GOES aligned with the loading direction after non-symmetric cyclic loading, whereas after symmetric cyclic loading there was no clear tendency.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109251"},"PeriodicalIF":6.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144899914","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":"Post-fire low-cycle fatigue behavior of stainless-clad bimetallic steels","authors":"Peng Dai, Xiaofeng Yang, Huiyong Ban","doi":"10.1016/j.ijfatigue.2025.109250","DOIUrl":"10.1016/j.ijfatigue.2025.109250","url":null,"abstract":"<div><div>Stainless-clad bimetallic steel has attracted increasing attention in structural applications due to its superior corrosion resistance and cost-effectiveness. However, its post-fire low-cycle fatigue behavior remains largely unexplored. This paper presents an experimental investigation into the post-fire low-cycle fatigue behavior of 316L + Q355 stainless-clad bimetallic steel, considered three key variables: nine target exposure temperatures (room temperature and 300 to 1000 °C in 100 °C increments), two cooling methods (air cooling and water cooling), and three strain amplitudes (1.0, 1.5, and 2.0 %). Fatigue failure modes, cyclic stress–strain responses, peak stress evolution, and fatigue life variations were systematically examined. The results indicate that air-cooled specimens exhibited fatigue life comparable to room-temperature conditions up to 500 °C, a moderate increase between 500 and 700 °C, and a reduction beyond 800 °C. For water-cooled specimens, fatigue life was similar to air-cooled counterparts below 700 °C but progressively decreased at higher temperatures. Based on the experimental results, temperature-dependent parameter expressions were developed for air-cooled and water-cooled specimens in both the adapted Basquin-Coffin-Manson and strain energy-based models, and validation demonstrated that the adapted Basquin-Coffin-Manson model achieved higher predictive accuracy over the entire temperature range.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109250"},"PeriodicalIF":6.8,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144924078","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}
Xichang Xiong , Yanan Hu , Jiahua Zhao , Ziyi Wang , Chao Yu , Qianhua Kan , Guozheng Kang
{"title":"Anisotropic cyclic deformation of additively manufactured 316L stainless steel at 400 °C: Experiment and constitutive model","authors":"Xichang Xiong , Yanan Hu , Jiahua Zhao , Ziyi Wang , Chao Yu , Qianhua Kan , Guozheng Kang","doi":"10.1016/j.ijfatigue.2025.109243","DOIUrl":"10.1016/j.ijfatigue.2025.109243","url":null,"abstract":"<div><div>Anisotropic microstructures and defect distributions impart a strong build-orientation dependence to the cyclic deformation behaviour of additively manufactured metallic materials. Accurately capturing this anisotropy through tailored cyclic elasto-plastic constitutive models is critical for ensuring structural integrity. This study investigates the high-temperature anisotropic cyclic plasticity of 316L stainless steel fabricated by laser powder bed fusion (L-PBF) through a combination of experimental investigation and constitutive modelling. Experimental results reveal that horizontally built specimens exhibit higher yield stress, leading to increased stress amplitude and reduced ratchetting strain compared to their vertically built counterparts. The L-PBF 316L stainless steel exhibits cyclic hardening, followed by a cyclic softening stage, with the pronounced cyclic hardening observed in the horizontally built specimens. Both the cyclic softening/hardening behavior and ratchetting exhibit strong dependence on applied strain and stress amplitudes. To model the anisotropic cyclic plasticity of L-PBF 316L stainless steel, a novel cyclic elasto-plastic constitutive model is developed. The model integrates Hill's anisotropic yield criterion, superimposed isotropic hardening, a modified Ohno-Karim kinematic hardening law, and a novel memory surface to capture the amplitude- and orientation-dependent cyclic plasticity. Moreover, the evolution of anisotropy under cyclic loading is modelled by introducing the accumulated plastic strain-dependent coefficient matrix into the Hill’s parameters. Simulations agree well with experimental results, offering a theoretical basis for evaluating the service performance of additively manufactured metallic components.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109243"},"PeriodicalIF":6.8,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144901814","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}
Michael Kuhn , Martin A. Eder , Alexander Krimmer , Claudio Balzani
{"title":"Predicting multiaxial stiffness degradation using uniaxial data — A model based on non-proportional experiments on a structural adhesive","authors":"Michael Kuhn , Martin A. Eder , Alexander Krimmer , Claudio Balzani","doi":"10.1016/j.ijfatigue.2025.109240","DOIUrl":"10.1016/j.ijfatigue.2025.109240","url":null,"abstract":"<div><div>In this work, multiaxial experiments on a structural adhesive with varying levels of non-proportionality are analyzed with a focus on the stiffness degradation process. A load level-dependent stiffness degradation model is employed that captures both, Young’s and shear modulus degradation. It was found that a multiaxial stiffness degradation can be modeled with good approximation as a superposition of the uniaxial stiffness degradations. Furthermore, the results indicate an insignificant influence of the level of non-proportionality on both Young’s and shear modulus degradation for the analyzed short fiber-reinforced adhesive.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109240"},"PeriodicalIF":6.8,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144900280","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}
Shawkat I. Shakil , Wiktor Bednarczyk , Marta Gajewska , Zaynab Mahbooba , Ankit Saharan , Andrea Tridello , Alessandro Benelli , Meysam Haghshenas
{"title":"Microstructure, mechanical properties, and fatigue performance of a PBF-LB Al2139ZrTi alloy","authors":"Shawkat I. Shakil , Wiktor Bednarczyk , Marta Gajewska , Zaynab Mahbooba , Ankit Saharan , Andrea Tridello , Alessandro Benelli , Meysam Haghshenas","doi":"10.1016/j.ijfatigue.2025.109245","DOIUrl":"10.1016/j.ijfatigue.2025.109245","url":null,"abstract":"<div><div>This study investigates the microstructure, tensile, and fatigue behavior of post-aged powder bed fused-laser beam (PBF-LB) Al2139ZrTi alloy, developed by EOS North America. The microstructure exhibits an equiaxed grain structure with an average grain size of approximately 1.5 µm and lacks any strong crystallographic texture. It also contains a dense dispersion of fine, uniformly distributed precipitates including: (i) Al<sub>3</sub>(Zr,Ti) dispersoids with L1<sub>2</sub>-type structure, acting as semi-coherent nucleation sites that contribute to grain refinement; (ii) a unique Al<sub>3</sub>(Zr,Ti) plate-like phase, further confirming Zr–Ti-driven modification of precipitation pathways; (iii) Al(CuFeMn) and Al(MnCu) intermetallics, notably Al<sub>7</sub>Cu<sub>2</sub> (Fe,Mn) and Al<sub>20</sub>Cu<sub>2</sub>Mn<sub>3</sub>(T-phase), and (iv) Mg oxides, pointing to minor oxidation during processing. Notably, Al<sub>2</sub>Cu-based θ′ and Ω phases are sparse, with only coarse θ-phase particles (∼0.5–1 µm) at grain boundaries and fine plate-like Ω-phase (∼tens of nm thick) along the [100] zone axis. Mechanical properties were evaluated via tensile testing, yielding ∼ 470 MPa yield stress (YS), ∼570 MPa ultimate tensile strength (UTS), and ∼ 6.5 % elongation. Conventional (servo-hydraulic) and ultrasonic fatigue tests were performed to cover high cycle and very high cycle fatigue responses spanning up to 10<sup>9</sup> cycles. Fractographic analyses, including optical and electron microscopy techniques, were carried out to quantify the crack initiation mechanisms in the mentioned regimes.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109245"},"PeriodicalIF":6.8,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895502","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}
E.D.A. John , J.B. Boxall , R.P. Collins , E.T. Bowman , L. Susmel
{"title":"Multiaxial notch fatigue of corroded cast iron pipes","authors":"E.D.A. John , J.B. Boxall , R.P. Collins , E.T. Bowman , L. Susmel","doi":"10.1016/j.ijfatigue.2025.109247","DOIUrl":"10.1016/j.ijfatigue.2025.109247","url":null,"abstract":"<div><div>Grey Cast Iron (GCI) water pipes often develop localised corrosion pits that act as notches and can also experience biaxial fatigue stresses, resulting in a multiaxial notch fatigue problem. This paper experimentally investigates for the first time, the high-cycle fatigue sensitivity of GCI to localised notches, under bending and biaxal loading, and validates a multiaxial notch fatigue model for GCI. The work uses a recently developed, novel biaxial fatigue experiment to generate the first fatigue data for GCI featuring pit-like notches. Approximately 40 new fatigue tests were completed to calibrate and test four multiaxial notch fatigue models, and to investigate the effects of notch root radius, localised notches, bending loading, and biaxial loading. The data shows that pit-like notches can have a statistically significant influence on the fatigue strength of GCI when <span><math><mrow><msub><mi>K</mi><mrow><mi>t</mi><mo>,</mo><mi>n</mi></mrow></msub><mo>></mo><mn>4</mn></mrow></math></span>. Additionally, 180° out-of-phase biaxial loading was found to reduce the fatigue strength of un-notched specimens by 28 %. The Effective Volume notch fatigue model, coupled with the linear-elastic Smith-Watson-Topper criterion, was found to give good predictions for notched GCI pipes subject to uniaxial and bending loading. This work highlights the ability of the Effective Volume approach to make good fatigue life estimates for thin, notched components featuring inclusions, where critical distance-based approaches performed less well. Future work on similar problems may wish to consider this approach.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109247"},"PeriodicalIF":6.8,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889190","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":"Experimental investigation on anelasticity-controlled cyclic creep behavior in multiscale hybrid-reinforced TiAl alloys","authors":"Zhenquan Liang , Shulong Xiao , Qingchao Li , Lijuan Xu , Xiang Xue , Jing Tian , Yuyong Chen , Hao Wang","doi":"10.1016/j.ijfatigue.2025.109244","DOIUrl":"10.1016/j.ijfatigue.2025.109244","url":null,"abstract":"<div><div>As hot-end components in aero-engines, TiAl alloys are expected to experience cyclic creep in service. In this work, hybrid-reinforced TiAl alloys with superior creep resistance were developed through synergistic micro-alloying of C and Y<sub>2</sub>O<sub>3</sub> combined with long-term annealing. Monotonic and cyclic creep tests under various loading conditions were conducted to specifically investigate the cyclic creep behavior of the hybrid-reinforced TiAl alloys. The results indicate that, compared with monotonic creep, cyclic creep exhibits a longer rupture life and a lower strain rate due to anelastic recovery. However, the introduction of cyclic loading enhances the intrinsic creep deformation capacity of TiAl alloys due to primary creep regeneration effect, and accelerates the intrinsic creep damage, resulting in a shorter creep endurance life. Two dominant anelastic recovery mechanisms associated with dislocation cells and dislocation pile-ups were revealed. Moreover, the presence of hybrid reinforcements enhances the anelastic recovery extent. The effects of various loading parameters, including the peak stress dwell time, stress ratio, and temperature, on the macroscopic cyclic creep response were clarified. The microscopic cyclic creep deformation and failure mechanisms, as well as the dynamic precipitation behavior of Ti<sub>2</sub>AlC within the B2 phase were elucidated. A comprehensive understanding of cyclic creep behavior from both macroscopic and microscopic perspectives will help advance the structural integrity assessment of TiAl alloys.</div></div>","PeriodicalId":14112,"journal":{"name":"International Journal of Fatigue","volume":"202 ","pages":"Article 109244"},"PeriodicalIF":6.8,"publicationDate":"2025-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889191","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}