Research on the Stability Prediction and Optimization of CNC Milling Based on Bagging–NSGAⅡ Under the Influence of Multiple Factors

The occurrence of chatter in the milling process is a key factor limiting the efficiency and quality of machining. The stability of milling depends mainly on the process parameters and the dynamic characteristics of the tool–workpiece system; however, the system dynamics vary with the machining position and tool properties. Considering these multiple influencing factors, herein, a method is proposed to predict the milling stability and determine optimal machining parameters based on a bootstrap aggregating (bagging) procedure and the non-dominated sorting genetic algorithm–Ⅱ (NSGA–Ⅱ). First, an orthogonal experimental design is used to divide the working space of the machine tool into different machining positions. Under each position, impact testing is then carried out at the tool tip for different tool-overhang lengths to obtain the corresponding frequency response functions (FRFs). Then, limiting axial cutting depth aplim values are theoretically predicted using the tool-tip FRFs and machining parameters. Using sample information, the bagging algorithm is applied to establish a model for predicting aplim, in which the inputs are the displacements of the moving parts (x, y, z), tool diameter (d), tool-overhang length (h), spindle speed (n), cutting width (ae), and feed rate per tooth (fz). Taking these process parameters (x, y, z, d, h, n, ap, ae, fz) as design variables, a multi-objective optimization model is constructed to balance machining efficiency and tool life. Additionally, the pre-established aplim prediction model is used to express the milling-stability constraint. The multi-objective optimization model is then solved using NSGA–Ⅱ, and the Pareto-optimal set is obtained. Finally, the entropy weight method and the technique for order preference by similarity to an ideal solution (TOPSIS) are combined to select a unique optimal solution from the Pareto-optimal set. A three-axis vertical machining center was used to carry out a case study. The prediction accuracy of the established bagging model for aplim was 2.99%, and no chatter was observed when performing a milling test with the determined optimal process parameters. These experimental results validate the feasibility of the proposed method for predicting milling stability and selecting optimal process parameters under multiple influencing factors. © 2024 Sichuan University. All rights reserved.