Hybrid prediction model for residual stress profile induced by multi-axis milling Ti-6Al-4 V titanium alloy combined finite element with experiment

Complex curved thin-walled structures, typically produced by multi-axis milling, are highly susceptible to deformation induced by residual stress. It is, therefore, that there is a considerable amount of research on developing predictive models for machining-induced residual stress. However, these developed models for residual stress prediction mainly focus on turning and three-axis milling. In the current study, a hybrid model combining experimental results and a finite element (FE) model is established to predict the residual stress profile of Ti-6Al-4 V titanium alloy for multi-axis milling. The residual stress profile is fitted by using the hyperbolic tangent function with the firefly algorithm (FA) based on the simulation and experiment. The R-2 values change from 85.3 to 99.1% in the sigma(x) direction and change from 80.7 to 98.1% in the sigma(y) direction, which indicates a high fitting accuracy. The radial basis function (RBF) neural network is employed to establish the association between the process parameters and the model coefficients. Thus, the residual stress profile can be expressed by the cutting speed, feed rate, and inclination angle. And the prediction accuracy is verified to achieve 92.7% and 91.4% in the sigma(x) and sigma(y) directions, respectively. The effects of the cutting speed, feed rate, and inclination angle on surface residual stress and response depth are investigated. The findings demonstrate a strong nonlinear connection between process parameters and surface residual stress. The proposed hybrid prediction model of residual stress can be used for further machining optimization of complex curved thin-walled structures.