As one essential indicator of surface integrity, residual stress has an important influence on the fatigue performance of aero engines’ thin-walled parts. Larger compressive or smaller tensile residual stress is more prone to causing fatigue cracks. To optimize the state of residual stress, the relationship between the surface residual stress and the machining conditions is studied in this work. A radial basis function (RBF) neural network model based on simulated and experimental data is developed to predict the surface residual stress for multi-axis milling of Ti-6Al-4V titanium alloy. Firstly, a 3D numerical model is established and verified through a cutting experiment. These results are found to be in good agreement with average absolute errors of 11.6% and 15.2% in the σ_x and σ_y directions, respectively. Then, the RBF neural network is introduced to relate the machining parameters with the surface residual stress using simulated and experimental samples. A good correlation is observed between the experimental and the predicted results. The verification shows that the average prediction error rate is 14.4% in the σ_x direction and 17.2% in the σ_y direction. The effects of the inclination angle, cutting speed, and feed rate on the surface residual stress are investigated. The results show that the influence of machining parameters on surface residual stress is nonlinear. The proposed model provides guidance for the control of residual stress in the precision machining of complex thin-walled structures.

The original Johnson–Cook equation fails to describe the significant thermal softening phenomenon of flow stress in cutting process of titanium alloy Ti6Al4V. Recently, some researchers developed some modified Johnson–Cook models of Ti6Al4V by introducing some additional parameters. But effective parameter identification method is unavailable in those research works. In this work, an inverse approach is developed to determine the additional parameters. A modified Johnson–Cook model with the hyperbolic tangent function is adopted, in which four unknown parameters need to be determined. The parameter assessment is taken as an optimization process based on the unequal division parallel-sided shear zone model. Along with the measured cutting force and chip thickness, the firefly algorithm is introduced to search for the parametric optimal solution. Those four parameters are determined when the difference between the predicted and experimental effective stress at shear plane reaches its minimum. The identified constitutive model is subsequently verified by finite element simulation of orthogonal cutting process, and compared with previous different material models. With the identified modified Johnson–Cook model, the serrated chip is observed in all the simulations. A good agreement between verification experiments and simulations is achieved. An acceptable prediction accuracy with an error of 10.28% on cutting force and an error of 18.12% on chip size is achieved.