The current study aims to evaluate the performance of the ultrasonic vibration-assisted milling (USVAM) process when machining two different materials with high deviations in mechanical properties, specifically 7075 aluminium alloy and Ti-6Al-4V titanium alloy. Additionally, this study seeks to develop an AI-based model to predict the process performance based on experimental data for the different workpiece characteristics. In this regard, an ultrasonic vibratory setup was designed to provide vibration oscillations at 28 kHz frequency and 8 µm amplitude in the cutting feed direction for the two characterised materials of 7075 aluminium alloy (150 BHN) and Ti-6Al-4V titanium alloy (350 BHN) workpieces. A series of slotting experiments were conducted using both conventional milling (CM) and USVAM techniques. The axial cutting force and machined slot surface roughness were evaluated for each method. Subsequently, Support Vector Regression (SVR) and artificial neural network (ANN) models were built, tested and compared. AI-based models were developed to analyse the experimental results and predict the process performance for both workpieces. The experiments demonstrated a significant reduction in cutting force by up to 30% and an improvement in surface roughness by approximately four times when using USVAM compared to CM for both materials. Validated by the experimental findings, the ANN model accurately and better predicted the performance metrics with RMSE = 0.11 µm and 0.12 N for Al surface roughness and cutting force. Regarding Ti, surface roughness and cutting force were predicted with RMSE of 0.12 µm and 0.14 N, respectively. The results indicate that USVAM significantly enhances milling performance in terms of a reduced cutting force and improved surface roughness for both 7075 aluminium alloy and Ti-6Al-4V titanium alloy. The ANN model proved to be an effective tool for predicting the outcomes of the USVAM process, offering valuable insights for optimising milling operations across different materials.

Welded joints are sensitive to fatigue failure due to cyclic loading, as well as fatigue crack propagation influenced by the distribution of welding residual stress. In this study, the fatigue crack propagation rates in butt-welded joints for 304 stainless steel sheets were evaluated in the presence of welding residual stresses. The analysis consisted of two separate models: first, a 3D-finite element (FE) model was used to predict the residual stresses due to welding; second, a numerical study was undertaken to predict fatigue crack propagation in the presence and absence of residual stress using the extended finite element method (XFEM). The crack growth model (NASGRO) and available experimental data were applied to verify the simulation results. The XFEM without residual stress effects shows good agreement with the experimental data and the NASGRO model. However, in the presence of residual stress, the simulation results show less agreement with the NASGRO model. The level and the nature of residual stress have significant effects on crack growth. A faster crack propagation rate is recognized due to the effect of tensile residual stress at the crack tip, while a higher resistance to crack growth is developed due to a compressive residual stress field.

Assessing the structural integrity of a cracked weldment is crucial. Cracks detected during welding inspections must be examined in the context of the structure's mechanical resistance. Generally, fracture mechanics supplies essential tools to determine a fracture criterion for loading conditions. This study explores the effect of residual stress (RS) and crack orientation on determining the stress intensity factor (𝐾 ) for a welded joint using the extended finite element method. This study comprises a 3D thermo-mechanical finite element (FE) analysis to study the temperature history and the residual stress distribution of a welded joint, and a 3D FE crack model that considers two cases of cracks—longitudinal (case I) and transverse (case II)—to calculate the 𝐾 value at the middle surface of a thin butt joint. 𝐾 is calculated for cracks under applied external and residual stresses. The results demonstrate that the welding residual stress can beneficially or detrimentally affect 𝐾 depending on stress distribution and sign, and indicate the significance of RS and crack orientation on 𝐾 . Simulation results demonstrate that the longitudinal crack in case I has higher 𝐾 values than those in case II for the transverse crack and show good agreement with the analytical results.

This work investigates how ultrasonic vibration can enhance friction stir welding (FSW) of an AA6082-T6 aluminium alloy and develops a data-driven tool to predict joint performance from process settings. A custom ultrasonic transducer and horn were designed and tuned using finite element modal and harmonic analyses, confirming a strong longitudinal resonance near 27.9 kHz with a tip amplitude of about 46 µm. A 27-run factorial experiment varied tool rotation (600–900 rpm), welding speed (45–55 mm/min), and plunge depth (0.10–0.25 mm). Welded joints were assessed using tensile strength and Vickers hardness. Four predictive models, support vector regression (SVR), Gaussian process regression (GPR), artificial neural networks (ANNs), and multiple linear regression (MLR) were trained and compared under five-fold cross-validation. The best joint quality was obtained at 900 rpm, 55 mm/min, and a 0.25 mm plunge depth, yielding a tensile strength of 188.7 MPa and a hardness of 102 HV. Overall, MLR provided the strongest predictive performance while remaining interpretable (UTS R² = 0.81, RMSE = 11.84 MPa; hardness R² = 0.67, RMSE = 2.36 HV), matching the ANN for UTS prediction and outperforming the ANN, GPR, and SVR for hardness. A coupling physics-based ultrasonic design with an interpretable predictive model offers a practical route to reduce trial and error, improve parameter selection, and accelerate the process development for ultrasonic vibration-assisted FSW of aluminium alloys; however, modest models can outperform complex ones when the dataset is limited.