Neural Network based Adaptive Control and Optimisation in the Milling Process

In this paper, an adaptive controller with optimisation for the milling process is designed based on two kinds of neural network. A modified BP neural network is proposed adjusting its learning rate and adding a dynamic factor in the learning process, and is used for the on-line modelling of the milling system. A modified ALM neural network is proposed adjusting its iteration step, and is used for the real-time optimal control of the milling process. The simulation and experimental results show that not only does the milling system with the designed controller have high robustness and global stability, but also the machining efficiency of the milling system with the adaptive controller is much higher than for the traditional CNC milling system.