Friction stir welding (FSW) has been adopted in the aerospace industry for fabricating structural alloys due to the low melting point and high thermal conductivity of aviation aluminum alloys. However, welding residual stresses can lead to secondary deformation in friction stir welded (FSWed) structures. Additionally, microstructural characteristics impact the crack growth rates and directions in these structures. Therefore, it is necessary to investigate the effects of residual stress and microstructure on the fatigue responses of FSWed joints. In this paper, we studied the fatigue crack growth behavior of two homogeneous and dissimilar FSWed joints with varying welding parameters, namely 2024-T3 and 7075-T6. The residual stresses were measured with the X-ray diffraction method. The dislocations and precipitates in different zones of the FSWed joints were analyzed via transmission electron microscopy (TEM). The results demonstrated that the residual stress significantly affected the fatigue crack growth rate and direction; the tensile residual stress promoted fatigue crack growth and offset the decrease in the fatigue crack growth rate that occurred due to grain refinement. The results of the microstructural analysis indicated that dislocation density and sliding resistance increased with the decrease in rotational speed and led to a decreased rate of fatigue crack propagation.

Fatigue crack propagation in friction stir welded joints significantly affects aircraft structural integrity. This study investigates the influence of welding speed, rotational speed, specimen thickness, loading frequency, and stress ratio on the fatigue crack growth rate. Four classical machine learning models with different structures—Deep Back-Propagation Network, Random Forest, Support Vector Regression, and K-Nearest Neighbors—were employed to predict fatigue crack growth behavior. The results show that all models achieve strong predictive performance. For FSWed joints, Deep BP and KNN exhibit comparable performance (R² > 0.98) on the training data, indicating similar learning capabilities with sufficient data coverage. Notably, KNN achieves the fastest training time (<0.3 s), while all models require less than 5 s of computation time. These results demonstrate that machine learning-based models provide an efficient and reliable alternative for rapid fatigue crack growth evaluation, supporting damage-tolerant design and structural integrity assessment in aircraft engineering.

The integral welded panel represents a highly promising aircraft structural component, owing to its lightweight design and reduced connector requirements. However, the complexity of its welded structure results in the formation of cross-welded joints. This study systematically investigated the mechanical properties of the cross-welded joints through tensile tests across different welded regions, which were complemented by fracture morphology examination via scanning electron microscopy (SEM). The residual stress distribution was characterized using X-ray diffraction, while electron backscatter diffraction (EBSD) analysis was used to elucidate the relationship between residual stress and microstructure. Key findings revealed that the cross-welded zone exhibited lower yield strength and ductility than the single-welded zone, and the advancing heat-affected zone demonstrated superior tensile properties relative to the retreating side. Residual stress analysis showed that the cross-welded joint lacked the “double peak” profile characteristic and displayed lower maximum residual stress than the single-welded joint. EBSD analysis indicated significant grain elongation in the cross-welded zone due to mechanical forces during the welding process, resulting in higher dislocation density and deformation, corresponding with elevated residual stress levels.

In this work, the effect of residual stress on mixed-mode crack propagation behavior in friction stir welded (FSW) 7075-T6 panel under biaxial loading was investigated. The cruciform sample was designed and manufactured by FSW. Residual stress profiles across the welded sample were measured by the X-ray diffraction technique. Crack propagation behaviors were simulated with five different biaxial loading ratios. Stress intensity factors ( K _Ι and K _ΙΙ ) were evaluated by finite element method (FEM) and used to study the effects of residual stress on crack behaviors. It was observed that residual stress has a considerable effect on the mixed-mode crack growth. In most of the cases, the crack deflection is mainly affected by residual stress at the beginning of crack propagation. The variation of crack propagation path is strongly linked with the residual stress as well as the biaxial loading ratio. In addition, K _Ι and K _ΙΙ are susceptible to residual stress under biaxial loading conditions. Residual stresses contribute to a higher proportion of K _ΙΙ compared to that of K _Ι . K _Ι and K _ΙΙ in the retreating side are more affected by the residual stress.

The bi-axial 7075-T6 Al alloy samples were designed and manufactured by Friction Stir Welding (FSW). The residual stress profiles were measured. Crack propagation behavior were simulated with five different biaxial loading ratios. ABAQUS software was used to calculate the stress intensity factors (SIFs) and to study the effects of residual stress on crack behaviors. It is found that residual stress can affect the effect of biaxial loading ratio on crack growing. Mode I and mode II SIFs are susceptible to residual stress when λ= 0.5~2. Cracks at the retreating side are much more affected by the residual stress. At given biaxial loading ratio, the distribution characteristics of SIF components have similarity on the advancing side and the retreating side.