Search

• Fatigue life prediction method of 25CrMo4 steel is investigated using fracture mechanics and machine learning methods. • Residual stress relaxation process is incorporated into fatigue crack growth in combination with NASGRO equation and equivalent initial flaw size (EIFS) methodology. • Different machine learning methods areemployed to investigate theireffectiveness in fatigue life prediction. In this work, fracture mechanics and machine learning methods are separately employed to predict the high cycle fatigue (HCF) life of micro-shot peened 25CrMo4 alloy steel containing artificial notches. The influences of notch size, stress level, and surface condition on fatigue life are incorporated into the prediction model. The results shows that the fatigue life of shot-peened specimens is enhanced by the compressive residual stress (CRS) compared with that of the un-peened specimens. The prediction result using fracture mechanics method is within the error band of ±2, while that using machine learning method almost lies in the error band of ±1.5. The stress level and notch size are the most critical factors affecting the HCF fatigue life. The applicability and limitation of the two methods are finally discussed. [ABSTRACT FROM AUTHOR]

• Effects of the corrosive environment on the fatigue strength of EA4T axle steel are explored. • The evolution of corrosion process during fatigue loading is fully investigated. • Crack aspect ratio in the corrosive environment is obtained by using synchrotron radiation X-ray computed microtomography (SR-μCT). • Fatigue life prediction model is developed based on the pit growth, short crack growth, and long crack growth stages. High-speed railway axle is the critical safety component of modern ground vehicles, which experiences extremely complex environments. In this paper, the effect of corrosion on the fatigue behavior of EA4T axle steel was investigated in an artificial rainwater environment. Combining scanning electron microscopy (SEM) and synchrotron radiation X-ray micro computed microtomography (SR-μCT) with theoretical analysis, damage measurement enabled a full evolution characterization of the corrosion process for exploring the corrosion mechanism and its influence on the fatigue life. It is found that the corrosive environment significantly reduced fatigue strength and facilitated multiple crack initiation, while showed relatively little effect on the long fatigue crack growth. The fitness of the 3-P Weibull distribution was slightly higher than that of the Gumbel distribution in terms of crack population. The life prediction model incorporating the pit growth, short crack, and long crack stages showed a good agreement within the 95% and 5% probabilistic S-N curve. [ABSTRACT FROM AUTHOR]