An ensemble neural network for optimising a CNC milling process
Computer numerical control (CNC) milling is a common method for the efficient mass production of products. Process efficiency and product quality have a strong dependency on the cutting process conditions. Furthermore, optimising a process for material removal rate (MRR) and surface roughness (SR), which are measures of process efficiency and product quality, respectively, is a complex optimisation task due to their contrasting relationships with process parameters. In this work, CNC end milling is performed on aluminium 6061 to investigate the influence of key process input variables (feed per tooth, cutting speed, and depth of cut) on the machined part’s SR. Firstly, a full factorial parametric study is conducted and analysed using Analysis of Variance (ANOVA) before an Ensemble Neural Network (ENN) is trained on the experimental data. To capture the complex nonlinear relationships accurately, each base model of the ENN is a combined genetic algorithm-artificial neural network, whose hyperparameters are optimised using a Bayesian optimisation framework.