Chatter Prediction in End Milling by FNN Model with Pruning

This paper is concerned with a study of chatter prediction in high-speed end milling operations. Chatter vibration occurring in mechanical machining gives rise to poor surface finish and dimensional inaccuracy in machined parts, reduction of tool life, and even damages machine tools. Various studies of its prediction and avoidance have been carried out over the last several decades. The purpose of this study is to develop an expert system for predicting chatter vibrations in high-speed end milling using wavelet transform and fuzzy neural network models with pruning. The FNN model employed here uses a pruning process which reduces a neural network to its most effective size. The amount of learning for convergence of a pruned network is reduced in comparison with an initial network. The proposed method is applied to a jig grinding machine, and the results demonstrate the effectiveness of the chatter prediction procedure.