{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:03:12Z","timestamp":1785402192594,"version":"3.56.0"},"reference-count":50,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52475148"],"award-info":[{"award-number":["52475148"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"award":["52475148"],"award-info":[{"award-number":["52475148"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Materials"],"abstract":"<jats:p>The fatigue failure of railway axles is directly associated with the operational safety of trains. As 25CrMo4 steel is commonly employed for high-speed train axles, precise evaluation of its fatigue life is essential for transportation reliability. This study compared six machine learning models following hyperparameter optimization via a differential evolution algorithm. The DE-optimized Gaussian process regression (DE-GPR) model exhibited superior predictive performance, achieving a coefficient of determination (R2) of 0.8020 and a root mean square error (RMSE) of 0.1250 on the most significant outer test fold. Furthermore, an interpretable analysis of the model utilized a combination of SHapley Additive exPlanations (SHAP) and partial dependence plots (PDP) to elucidate feature importance. The results indicate that the applied stress level is the predominant feature affecting fatigue life predictions and that it slightly interacts with surface residual stress and full width at half maximum to influence the predicted fatigue life. This study can provide valuable insights into the fatigue life assessment and process optimization of 25CrMo4 steel components.<\/jats:p>","DOI":"10.3390\/ma19122544","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T09:49:51Z","timestamp":1781257791000},"page":"2544","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fatigue Life Prediction of 25CrMo4 Alloy Steel Based on Interpretable Methods"],"prefix":"10.3390","volume":"19","author":[{"given":"Ze-Cheng","family":"Li","sequence":"first","affiliation":[{"name":"International Institute of Engineering, Changsha University of Science and Technology, Changsha 410114, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Min","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Mechanical and Vehicle Engineering, Changsha University of Science and Technology, Changsha 410114, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109269","DOI":"10.1016\/j.engfracmech.2023.109269","article-title":"Fatigue Behaviour of EA4T Notched Specimens: Experiments and Predictions Using the Theory of Critical Distance","volume":"286","author":"Liao","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2847","DOI":"10.1007\/s42243-024-01393-1","article-title":"Hot Deformation Behavior and Microstructure Evolution Mechanisms of EA4T Axle Steel for High-Speed Train Application","volume":"32","author":"Zhang","year":"2025","journal-title":"J. Iron Steel Res. Int."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106656","DOI":"10.1016\/j.engfailanal.2022.106656","article-title":"Failure Causes and Hardening Techniques of Railway Axles\u2014A Review from the Perspective of Structural Integrity","volume":"141","author":"Gao","year":"2022","journal-title":"Eng. Fail. Anal."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"109835","DOI":"10.1016\/j.engfracmech.2023.109835","article-title":"Corrosion Fatigue Behavior and Life Prediction of Railway Axle EA4T Alloy Steel with Artificial Indentation","volume":"296","author":"Luo","year":"2024","journal-title":"Eng. Fract. Mech."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.aej.2025.05.011","article-title":"Fatigue Performance Evaluation of High-Strength Railway Axles Subjected to Different Surface Defects","volume":"127","author":"Zhao","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"108831","DOI":"10.1016\/j.engfracmech.2022.108831","article-title":"Determination of Optimal Ultrasonic Surface Rolling Parameters to Enhance the Fatigue Strength of Railway Axle EA4T Steel","volume":"275","author":"Qin","year":"2022","journal-title":"Eng. Fract. Mech."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108664","DOI":"10.1016\/j.ijfatigue.2024.108664","article-title":"Fatigue Properties of Non-Press-Fitted Part of Full-Scale Induction-Hardened Axles of Medium-Carbon Steel for High-Speed Railway Vehicles","volume":"190","author":"Makino","year":"2025","journal-title":"Int. J. Fatigue"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.prostr.2024.03.027","article-title":"Residual Life Assessment of Deep Rolled Railway Axles Considering the Effect of Process Parameters","volume":"57","author":"Pertoll","year":"2024","journal-title":"Procedia Struct. Integr."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"106613","DOI":"10.1016\/j.ijfatigue.2021.106613","article-title":"Effects of Conventional Shot Peening, Severe Shot Peening, Re-Shot Peening and Precised Grinding Operations on Fatigue Performance of AISI 1050 Railway Axle Steel","volume":"155","author":"Unal","year":"2022","journal-title":"Int. J. Fatigue"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"116320","DOI":"10.1016\/j.jmatprotec.2019.116320","article-title":"Effect of Micro-Shot Peening, Conventional Shot Peening and Their Combination on Fatigue Property of EA4T Axle Steel","volume":"275","author":"Li","year":"2020","journal-title":"J. Mater. Process. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"108131","DOI":"10.1016\/j.ijfatigue.2023.108131","article-title":"Fatigue Life Prediction for LPBF-Fabricated Ti-6Al-4V up to Very-High-Cycle Regime Based on Continuum Damage Mechanics Incorporating Effect of Defects","volume":"181","author":"Ling","year":"2024","journal-title":"Int. J. Fatigue"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"105793","DOI":"10.1016\/j.ijfatigue.2020.105793","article-title":"Fatigue Life Prediction of TC17 Titanium Alloy Based on Micro Scratch","volume":"139","author":"Ding","year":"2020","journal-title":"Int. J. Fatigue"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"109290","DOI":"10.1016\/j.engfracmech.2023.109290","article-title":"Fretting Fatigue Crack Growth Simulation and Residual Life Assessment of Railway Press-Fitted Axle","volume":"286","author":"Xu","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"109242","DOI":"10.1016\/j.engfracmech.2023.109242","article-title":"Machine Learning-Based Fatigue Life Prediction of Metal Materials: Perspectives of Physics-Informed and Data-Driven Hybrid Methods","volume":"284","author":"Wang","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"111525","DOI":"10.1016\/j.mtcomm.2025.111525","article-title":"Advancing Fatigue Life Prediction with Machine Learning: A Review","volume":"43","author":"Hamada","year":"2025","journal-title":"Mater. Today Commun."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105941","DOI":"10.1016\/j.ijfatigue.2020.105941","article-title":"Machine Learning Based Fatigue Life Prediction with Effects of Additive Manufacturing Process Parameters for Printed SS 316L","volume":"142","author":"Zhan","year":"2021","journal-title":"Int. J. Fatigue"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"107508","DOI":"10.1016\/j.engfracmech.2020.107508","article-title":"A Machine-Learning Fatigue Life Prediction Approach of Additively Manufactured Metals","volume":"242","author":"Bao","year":"2021","journal-title":"Eng. Fract. Mech."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"109709","DOI":"10.1016\/j.engfracmech.2023.109709","article-title":"A Machine Learning Based Approach with an Augmented Dataset for Fatigue Life Prediction of Additively Manufactured Ti-6Al-4V Samples","volume":"293","author":"Homola","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"106761","DOI":"10.1016\/j.ijfatigue.2022.106761","article-title":"Fatigue Life Prediction Considering Mean Stress Effect Based on Random Forests and Kernel Extreme Learning Machine","volume":"158","author":"Gan","year":"2022","journal-title":"Int. J. Fatigue"},{"key":"ref_20","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017, January 4\u20139). A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"110756","DOI":"10.1016\/j.engfracmech.2024.110756","article-title":"Multivariate Interpolation and Machine Learning Models for Extreme Defects-Based Fatigue Life Prediction of Ti6Al4V Specimens Fabricated by SLM","volume":"314","author":"Materna","year":"2025","journal-title":"Eng. Fract. Mech."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"111555","DOI":"10.1016\/j.engfracmech.2025.111555","article-title":"Brittle Fracture Strength Prediction via XML with Reliability Considerations","volume":"328","author":"Jafari","year":"2025","journal-title":"Eng. Fract. Mech."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.istruc.2023.03.060","article-title":"Fatigue Life Analysis of High-Strength Bolts Based on Machine Learning Method and SHapley Additive exPlanations (SHAP) Approach","volume":"51","author":"Zhang","year":"2023","journal-title":"Structures"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"108995","DOI":"10.1016\/j.ijfatigue.2025.108995","article-title":"Hybrid Clustering-Enhanced Interpretable Machine Learning for Fatigue Life Prediction across Various Cyclic Stages in Laser Powder Bed Fused Ti-6Al-4V Alloy","volume":"198","author":"Yu","year":"2025","journal-title":"Int. J. Fatigue"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"109498","DOI":"10.1016\/j.ijfatigue.2026.109498","article-title":"Data-Driven Fatigue Life Prediction of Corroded Steel Wires: A Transfer Learning on Stacking Interpretable Model and Feature Sensitivity Analysis","volume":"207","author":"Huang","year":"2026","journal-title":"Int. J. Fatigue"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2839","DOI":"10.1016\/j.patcog.2015.03.009","article-title":"Performance Evaluation of Classification Algorithms by K-Fold and Leave-One-out Cross Validation","volume":"48","author":"Wong","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"108992","DOI":"10.1016\/j.engfracmech.2022.108992","article-title":"Notch Fatigue Life Prediction of Micro-Shot Peened 25CrMo4 Alloy Steel: A Comparison between Fracture Mechanics and Machine Learning Methods","volume":"277","author":"Li","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"106951","DOI":"10.1016\/j.engfailanal.2022.106951","article-title":"The Research Progress and Prospect of Data Mining Methods on Corrosion Prediction of Oil and Gas Pipelines","volume":"144","author":"Xu","year":"2023","journal-title":"Eng. Fail. Anal."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4866","DOI":"10.1016\/j.jmrt.2025.10.179","article-title":"Shot Peening-Induced Surface Integrity Governing Fatigue Performance of Al Alloy in High to Very High Cycle Regime: Synergistic Effects of Residual Stress, Roughness and Microstructure","volume":"39","author":"Ma","year":"2025","journal-title":"J. Mater. Res. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1016\/0013-7944(74)90007-1","article-title":"Fatigue Crack Propagation from a Crack Inclined to the Cyclic Tensile Axis","volume":"6","author":"Tanaka","year":"1974","journal-title":"Eng. Fract. Mech."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"119795","DOI":"10.1016\/j.renene.2023.119795","article-title":"A Hybrid AHP-PROMETHEE II Onshore Wind Farms Multicriteria Suitability Analysis Using kNN and SVM Regression Models in Northeastern Greece","volume":"221","author":"Sotiropoulou","year":"2024","journal-title":"Renew. Energy"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"109714","DOI":"10.1016\/j.engfracmech.2023.109714","article-title":"A Random Forest Regression with Bayesian Optimization-Based Method for Fatigue Strength Prediction of Ferrous Alloys","volume":"293","author":"Guo","year":"2023","journal-title":"Eng. Fract. Mech."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"117000","DOI":"10.1016\/j.conbuildmat.2019.117000","article-title":"Machine Learning-Based Compressive Strength Prediction for Concrete: An Adaptive Boosting Approach","volume":"230","author":"Feng","year":"2020","journal-title":"Constr. Build. Mater."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Guo, Y., Rui, S.-S., Xu, W., and Sun, C. (2022). Machine Learning Method for Fatigue Strength Prediction of Nickel-Based Superalloy with Various Influencing Factors. Materials, 16.","DOI":"10.3390\/ma16010046"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"109020","DOI":"10.1016\/j.ijfatigue.2025.109020","article-title":"Fatigue Life Prediction of Aluminum-Steel Magnetic Pulse Crimped Joints Based on Point Cloud Measurement and Gradient Boosting Regression Trees","volume":"198","author":"Zhao","year":"2025","journal-title":"Int. J. Fatigue"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"108710","DOI":"10.1016\/j.engfailanal.2024.108710","article-title":"A Data-Driven Model for Predicting Fatigue Performance of High-Strength Steel Wires Based on Optimized XGBOOST","volume":"164","author":"Wang","year":"2024","journal-title":"Eng. Fail. Anal."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"106730","DOI":"10.1016\/j.ijfatigue.2022.106730","article-title":"Gaussian Process Regression Based Remaining Fatigue Life Prediction for Metallic Materials under Two-Step Loading","volume":"158","author":"Gao","year":"2022","journal-title":"Int. J. Fatigue"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"108159","DOI":"10.1016\/j.ijfatigue.2024.108159","article-title":"Data-Driven Fatigue Life Prediction of Small-Deep Holes in a Nickel-Based Superalloy after a Cold Expansion Process","volume":"181","author":"Tang","year":"2024","journal-title":"Int. J. Fatigue"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1023\/A:1008202821328","article-title":"Differential Evolution\u2014A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces","volume":"11","author":"Storn","year":"1997","journal-title":"J. Glob. Optim."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"119656","DOI":"10.1016\/j.ins.2023.119656","article-title":"Toward Explicit Control between Exploration and Exploitation in Evolutionary Algorithms: A Case Study of Differential Evolution","volume":"649","author":"Cai","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"110927","DOI":"10.1016\/j.engstruct.2020.110927","article-title":"Failure Mode and Effects Analysis of RC Members Based on Machine-Learning-Based SHapley Additive exPlanations (SHAP) Approach","volume":"219","author":"Mangalathu","year":"2020","journal-title":"Eng. Struct."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"109045","DOI":"10.1016\/j.ress.2022.109045","article-title":"Enhancing the Explainability of Regression-Based Polynomial Chaos Expansion by Shapley Additive Explanations","volume":"232","author":"Palar","year":"2023","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"101834","DOI":"10.1016\/j.rineng.2024.101834","article-title":"SHAP-Based Insights for Aerospace PHM: Temporal Feature Importance, Dependencies, Robustness, and Interaction Analysis","volume":"21","author":"Alomari","year":"2024","journal-title":"Results Eng."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy Function Approximation: A Gradient Boosting Machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"103135","DOI":"10.1016\/j.insmatheco.2025.103135","article-title":"Pitfalls in Machine Learning Interpretability: Manipulating Partial Dependence Plots to Hide Discrimination","volume":"125","author":"Xin","year":"2025","journal-title":"Insur. Math. Econ."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"106782","DOI":"10.1016\/j.engfailanal.2022.106782","article-title":"Fatigue Life Enhancement of Foreign Object Impacted Railway Axle EA4T Steel with Surface Shot Peening","volume":"142","author":"Luo","year":"2022","journal-title":"Eng. Fail. Anal."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"4847","DOI":"10.1016\/S1359-6454(03)00324-0","article-title":"The Evolution of Dislocation Density during Heat Treatment and Creep of Tempered Martensite Ferritic Steels","volume":"51","author":"Dronhofer","year":"2003","journal-title":"Acta Mater."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1016\/j.msea.2010.10.086","article-title":"Analysis on Fatigue Property of Microshot Peened Railway Axle Steel","volume":"528","author":"Zhang","year":"2011","journal-title":"Mater. Sci. Eng. A"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/j.ijfatigue.2014.07.002","article-title":"High- and Very High-Cycle Plain Fatigue Resistance of Shot Peened High-Strength Aluminum Alloys: The Role of Surface Morphology","volume":"70","author":"Benedetti","year":"2015","journal-title":"Int. J. Fatigue"}],"container-title":["Materials"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1996-1944\/19\/12\/2544\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T10:07:02Z","timestamp":1781258822000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1996-1944\/19\/12\/2544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":50,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["ma19122544"],"URL":"https:\/\/doi.org\/10.3390\/ma19122544","relation":{},"ISSN":["1996-1944"],"issn-type":[{"value":"1996-1944","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]}}}