This paper comprehensively analyzes the artificial intelligence (AI) models that predict low-cycle fatigue life for an aluminum alloy, considering tension–compression and torsion–torsion experiments. The study highlights the crucial need for precise fatigue life predictions to ensure the reliability and safety of structures subjected to different cyclic loading conditions. By incorporating diverse loading scenarios, the aim is to develop AI models that surpass traditional approaches’ limitations, offering enhanced predictive capabilities. This work explores the potential of AI models for fatigue life prediction, focusing on bridging the gap between traditional learning and ensemble learning predictive techniques. Its analysis improves the understanding of fatigue and contributes to developing accurate and versatile predictive tools. The ensemble learning techniques that combine the strengths of different algorithms are targeted to assess their performance. Based on the methodology, the results provide a thorough explanation of the proposed AI models for normal and shear strain-controlled cyclic loading conditions. The impact of ensemble learning methods, LightGBM, XGBoost, CatBoost, extra trees, and nearest neighbors are investigated on the accuracy of fatigue life prediction. A comparative evaluation of these AI models in terms of their predictive capabilities in different strain scenarios is presented. This approach enhances the overall efficacy of the learning system by considering a host of perspectives and drawing on the strengths of diverse models.
Abdul-LatifA (2021) Continuum damage model for low-cycle fatigue of metals: An overview. International Journal of Damage Mechanics16: 133–158.
2.
Abdul-LatifAChadliM (2007) Modeling of the heterogeneous damage evolution at the granular scale in polycrystals under complex cyclic loadings. International Journal of Damage Mechanics16: 133–158.
3.
Abdul-LatifAMounoungaTBS (2009) Damage deactivation modeling under multiaxial cyclic loadings for polycrystals. International Journal of Damage Mechanics18: 177–198.
4.
Abdul-LatifASaanouniK (1994) Damaged anelastic behavior of FCC polycrystalline metals with micromechanical approach. International Journal of Damage Mechanics3: 237–259.
5.
Abi MannanSEl-AlfyEChangY, et al. (2023) Ensemble multifeatured deep learning models and applications: A survey. IEEE Access (99): 1–1. DOI: 10.1109/ACCESS.2023.3320042.
6.
AgrawalADeshpandePCecenA, et al. (2014) Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters. Integrating Materials and Manufacturing Innovation3(1): 90–108.
7.
AgrawalAHoudharyA (2018) An online tool for predicting fatigue strength of steel alloys based on ensemble data mining. International Journal of Fatigue113: 389–400.
8.
AhmadAFarooqFNiewadomskiP, et al. (2021) Prediction of compressive strength of fly ash based concrete using individual and ensemble algorithm. Materials14(4): 94.
9.
Al-DahidiSAyadiOAlrbaiM, et al. (2019) Ensemble approach of optimized artificial neural networks for solar photovoltaic power prediction. IEEE Access7(99): 81741–81758.
10.
Al-DahidiSHammadBAlrbaiM, et al. (2024) A novel dynamic/adaptive K-nearest neighbor model for the prediction of solar photovoltaic systems’ performance. Results in Engineering22(Part 3): 102141.
11.
AlkunteSFidanI (2023) Machine learning-based fatigue life prediction of functionally graded materials using material extrusion technology. Journal of Composites Science7(10): 20.
12.
AlotaibiOPardedeETomyS (2023) Cleaning big data streams: A systematic literature review. Technologies11(4): 01.
13.
AmatoALecceV (2023) Data preprocessing impact on machine learning algorithm performance. Open Computer Science13(1). DOI: 10.1515/comp-2022-2078.
14.
BilaliAAbdeslamTNafiiA, et al. (2023) An interpretable machine learning approach based on DNN, SVR, extra tree, and XGBoost models for predicting daily pan evaporation. Journal of Environmental Management327: 116890.
15.
ChadliM, 2005. Modélisation de l’endommagement mésoscopique des polycristaux via de nouveaux critères d’amorçage local et global. PhD thésis, Université de Technologie de Troyes.
16.
ChadliMAbdul-LatifA (2005) Meso-damage evolution in polycrystals. Journal of Engineering Materials and Technology127: 214–221.
17.
ChenCTanakaKKoteraM, et al. (2020) Comparison and improvement of the predictability and interpretability with ensemble learning models in QSPR applications. Journal of Cheminformatics12(1). DOI: 10.1186/s13321-020-0417-9.
18.
ChoiD (2019) Data-driven materials modeling with XGBoost algorithm and statistical inference analysis for prediction of fatigue strength of steels. International Journal of Precision Engineering and Manufacturing20(7): 129–138.
19.
Da SilvaDLockwoodJLiangW, et al. (2020a) Mean stress effect in stress-life for hard steels. International Journal of Fatigue146(3): 106101.
20.
Da SilvaRRibeiroMMoreniS, et al. (2020b) A novel decomposition-ensemble learning framework for multi-step ahead wind energy forecasting. Energy216(1): 119174.
21.
DeoTSanjuA (2022) Data imputation and comparison of custom ensemble models with existing libraries like XGBoost, CATBoost, AdaBoost and Scikit learn for predictive equipment failure. Materials Today Proceedings72: 1596–1604.
22.
FengSZHanXLiZ, et al. (2021) Ensemble learning for remaining fatigue life prediction of structures with stochastic parameters: A data-driven approach. Applied Mathematical Modelling101(9): 420–431.
23.
GanLWuHZhongZ (2022) Fatigue life prediction in the presence of mean stresses using domain knowledge-integrated ensemble of extreme learning machines. AUTHOREA. DOI: 10.22541/au.165237521.14489105/v1.
24.
GaoSXuJMaZ, et al. (2024) Research on modeling of industrial soft sensor based on ensemble learning. IEEE Sensors Journal24(99): 14380–14391.
25.
GarnerWWinklerDAlexanderD, et al. (2024) Effect of data preprocessing and machine learning hyperparameters on mass spectrometry imaging m models. Journal of Vacuum Science & Technology A41(6). DOI:10.1116/6.0002788.
26.
GholozadehSLemanZBaharudinB (2023) State-of-the-art ensemble learning and unsupervised learning in fatigue crack recognition of glass fiber reinforced polyester composite (GFRP) using acoustic emission. Ultrasonics132(3): 106998.
27.
GüneyH (2023) Preprocessing impact analysis for machine learning-based network intrusion detection. Sakarya University Journal of Computer and Information Sciences6: 67–79.
28.
GuoRFuDSollazzoG (2021) An ensemble learning model for asphalt pavement performance prediction based on gradient boosting decision tree. International Journal of Pavement Engineering23(1): 3633–3646.
29.
GuptaRYadavAJhaS, et al. (2023) A robust regressor model for estimating solar radiation using an ensemble stacking approach based on machine learning. International Journal of Green Energy21(1): 1853–1873.
30.
HancockJKhoshgooftaarT (2020) CatBoost for big data: an interdisciplinary review. Journal of Big Data7(1). DOI: 10.1186/s40537-020-00369-8.
31.
HeGYZhaoYXYanCL (2022) Application of tabular data synthesis using generative adversarial networks on machine learning-based multiaxial fatigue life prediction. International Journal of Pressure Vessels and Piping199: 104779.
32.
HeinermannJKramerO (2016) Machine learning ensembles for wind power prediction. Renewable Energy89: 671–679.
33.
HouJWangXGuoH, et al. (2023) Combined high and low cycle fatigue life prediction model based on damage curve method considering loading interaction effect. International Journal of Damage Mechanics32: 185–203.
34.
IliouTAnagnostopoulosCNerantzakiM, et al. (2015). A novel machine learning data preprocessing method for enhancing classification algorithms performance. In: Conference: Proceedings of the 16th international conference on engineering applications of neural networks (INNS), Greece.
35.
JiaoZWangHXingJ, et al. (2023) A LightGBM based framework for lithium-ion battery remaining useful life prediction under driving conditions. IEEE Transactions on Industrial Informatics19(99): 11353–11362.
36.
KhanAChaudhariOChandraR (2024) A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation. Expert Systems with Applications244(2): 122778.
37.
KhanPYeunCByunY (2023) Fault detection of wind turbines using SCADA data and genetic algorithm-based ensemble learning. Engineering Failure Analysis148(2): 107209.
38.
KumarBJyothiBSinghA, et al. (2024) Enhancing EV charging predictions: A comprehensive analysis using K-nearest neighbors and ensemble stack generalization. Multiscale and Multidisciplinary Modeling, Experiments and Design7: 4011–4037.
39.
KumarRChanniAKaurR, et al. (2023) Exploring the intricacies of machine learning-based optimization of electric discharge machining on squeeze cast TiB2/AA6061 composites: Insights from morphological, and microstructural aspects in the surface structure analysis of recast layer formation and worn-out analysis. Journal of Materials Research and Technology26(29 September 2023): 8569–8603.
40.
KumariPToshniwalD (2020) Extreme gradient boosting and deep neural network based ensemble learning approach to forecast hourly solar irradiance. Journal of Cleaner Production279(8): 123285.
41.
KunchevaLWhitakerC (2003) Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Machine Learning51(2): 181–207.
42.
LiXSongLChoyY, et al (2023) Fatigue reliability analysis of aero-engine blade-disc systems using physics-informed ensemble learning. Philosophical Transactions A381: 5–17. DOI: 10.1098/rsta.2022.0384.
43.
LiXYangHYangJ (2024) Fretting fatigue life prediction for aluminum alloy based on particle-swarm-optimized back propagation neural network. Metals14(4): 381.
44.
LiuHXiaoQJinY, et al. (2022a) Improved LightGBM-based framework for electric vehicle lithium-ion battery remaining useful life prediction using multi-health indicators. Symmetry14(8): 1584.
45.
LiuWChenZHuY (2022b) XGBoost algorithm-based prediction of safety assessment for pipelines. International Journal of Pressure Vessels and Piping197(3): 104655.
46.
LuHMaX (2020) Hybrid decision tree-based machine learning models for short-term water quality prediction. Chemosphere249: 126169.
47.
MahmoudiAJirandehiAPAmooieMA, et al. (2024) Entropy-based damage model for assessing the remaining useful fatigue life. International Journal of Damage Mechanics33(3): 223–244.
48.
MoonJKimYSonM, et al. (2018) Hybrid short-term load forecasting scheme using random forest and multilayer perceptron. Energies11(12): 3283.
49.
MounoungaTBSAbdul-LatifARazafindramaryD (2011) Damage induced-oriented anisotropy behavior of polycrystals under complex cyclic loadings. International Journal of Mechanical Sciences53(4): 271–280.
50.
NagashimaNHayakawaMMasudaH, et al. (2024) Estimating the S–N curve by machine learning random forest method. Materials Transactions65(4): 428–433.
51.
NarteniSOraniVCambiasoE, et al. (2022) On the intersection of explainable and reliable AI for physical fatigue prediction. IEEE Access10(1): 76243–76260.
52.
NasiriHDadashiAAzadiM (2024) Machine learning for fatigue lifetime predictions in 3D-printed polylactic acid biomaterials based on interpretable extreme gradient boosting model. Materials Today Communications39(No. 4): 109054.
53.
NasiriSKhosravaniM (2022) Applications of data-driven approaches in prediction of fatigue and fracture. Materials Today Communications33: 104437.
54.
OluwasakinETorkuTTingtingS, et al. (2023) Minimization of high computational cost in data preprocessing and modeling using MPI4Py. Machine Learning with Applications13: 100483.
55.
OpitzDMaclinR (1999) Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research11: 169–198.
56.
PapadopoulosSAzarEWoonW, et al. (2017) Evaluation of tree-based ensemble learning algorithms for building energy performance estimation. Journal of Building Performance Simulation11: 322–332.
57.
PerovićZBŠumaracDMĆorićSB, et al. (2025) Energy based damage model for low-cycle fatigue of ductile materials. International Journal of Damage Mechanics34: 352–373.
58.
PolikarR (2006) Ensemble-based systems in decision making. IEEE Circuits and Systems Magazine6(3): 21–45.
59.
RashidMMustafaMSulaimanN, et al. (2021) Random subspace K-NN based ensemble classifier for driver fatigue detection utilizing selected EEG channels. Treatment du Signal38(5): 1259–1270.
60.
RibeiroGMarianiVCoelhoL (2019) Enhanced ensemble structures using wavelet neural networks applied to short-term load forecasting. Engineering Applications of Artificial Intelligence82: 272–281.
61.
RidzuanFZainonW (2019) A review on data cleansing methods for big data. Procedia Computer Science161(3): 731–738.
RondinellaFDaneluzFHofkoB, et al. (2023) Improved predictions of asphalt concrete dynamic modulus and phase angle using decision-tree based categorical boosting model. Construction and Building Materials400(10): 132709.
64.
SaiWChaiGNarasimaluS (2020) Fatigue life prediction of GLARE composites using regression tree ensemble-based machine learning model. Advanced Theory and Simulations3: 6.
65.
SaiduMShagariSKabirM, et al. (2023) Improving university students’ data analysis outputs through effective data collection, cleaning, screening, and normalisation. Applied Quantitative Analysis (AQA)3(2): 2023.
66.
SalmanRAlzaatrehASuliemanH, et al. (2021) A bootstrap framework for aggregating within and between feature selection methods. Entropy23(2): 200.
67.
SantosKMianiRSilvaF (2024) Evaluating the impact of data preprocessing techniques on the performance of intrusion detection systems. Journal of Network and Systems Management32: 36. DOI: 10.1007/s10922-024-09813-z.
68.
SauABhaktaI (2019) Screening of anxiety and depression among seafarers using machine learning technology. Informatics in Medicine Unlocked16: 100228.
69.
ShuaiMTianKSunY, et al. (2024) Fatigue life prediction of composite bolted joints based on finite element model and machine learning. Fatigue & Fracture of Engineering Materials & Structures47: 2029–2043.
70.
SilvaGFernandesPSchnelleM, et al. (2023) Data-driven, physics-based, or both: Fatigue prediction of structural adhesive joints by artificial intelligence. Applied Mechanics4(1): 334–355.
71.
SollichPKroghA (1996) Learning with ensembles: How over-fitting can be useful. In: TouretzkyDSMozerMCHasselmoME (eds) Advances in Neural Information Processing Systems 8, Denver, CO. Cambridge, MA: MIT Press, pp.190–196.
72.
SonJYangS (2022) A new approach to machine learning model development for prediction of concrete fatigue life under uniaxial compression. Applied Sciences12(19): 9766.
73.
SongLLiXZhuS, et al. (2024) Cascade ensemble learning for multi-level reliability evaluation. Aerospace Science and Technology: 148: 109101.
74.
UllahILiuKYamamotoT, et al. (2021) Electric vehicle energy consumption prediction using stacked generalization: An ensemble learning approach. International Journal of Green Energy18(9): 896–909.
75.
WangKHeBSamuiP, et al. (2024) Predicting rock burst in underground engineering leveraging a novel metaheuristic-based LightGBM model. Computer Modeling in Engineering & Sciences140(1): 229–253.
76.
WangLLeeEYuenR (2018a) Novel dynamic forecasting model for building cooling loads combining an artificial neural network and an ensemble approach. Applied Energy228: 1740–1753.
77.
WangYFengL (2024) New ensemble learning algorithm based on classification certainty and semantic correlation. Journal of Intelligent & Fuzzy Systems46(4): 10985–11001.
78.
WangZSrinivasanR (2016) A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models. Renewable and Sustainable Energy Reviews75: 796–808.
79.
WangZWangYSrinivasanR (2018b) A novel ensemble learning approach to support building energy use prediction. Energy and Buildings159: 109–122.
80.
WeiYJiRLiQ, et al. (2023) Mechanical performance prediction model of steel bridge deck pavement system based on XGBoost. Applied Sciences13(21): 12048.
81.
WuNSunJ (2022) Fatigue detection of air traffic controllers based on radiotelephony communications and self-adaption quantum genetic algorithm optimization ensemble learning. Applied Sciences12(20): 10252.
82.
XiaoJLiCLiuB, et al. (2022) Prediction of wind turbine blade icing fault based on selective deep ensemble model. Knowledge-Based Systems242(5): 108290.
83.
YanFSongKLiuY, et al. (2020) Predictions and mechanism analyses of the fatigue strength of steel based on machine learning. Journal of Materials Science55(31): 15334–15349.
84.
YangY (2017) Chapter 4: Ensemble learning. In: Temporal Data Mining via Unsupervised Ensemble Learning. Amsterdam, Netherlands: Elsevier, Computers, 172.
85.
YangtaoLBaoTJianG, et al. (2020) The prediction of dam displacement time series using STL, extra-trees, and stacked LSTM neural network. IEEE Access8(99): 94440–94452.
86.
ZhangZZhangYYintangW, et al. (2023a) An improved stacking ensemble learning model for predicting the effect of lattice structure defects on yield stress. Computers in Industry151(4): 103986.
87.
ZhangZZhangYYintangW, et al. (2023b) Data-driven XGBoost model for maximum stress prediction of additive manufactured lattice structures. Complex & Intelligent Systems9(36): 5881–5892.
