Inference of Self-Excited Vibration in High-Speed End-Milling Based on Fuzzy Neural Networks

This chapter introduces a new method for predicting chatter in milling process by a fuzzy neural network. Firstly, a milling experimental setup is built. And a set of the valuable experimental data is obtained under different tool wear states and cutting conditions. Secondly, since it is extremely difficult to construct an exact mathematical model for the setup, a fuzzy neural network model is proposed as a simplified one trained by using the experimental data. Thirdly, some simulation results are obtained based on the model. Finally, the further experiments are done to confirm the validity of predicting chatter in the model. The results show that chatter vibration in high-speed end milling could be exactly predicted via the model. Thus, the method described here is very effective to predict chatter in milling process.