A study of on-line identification of grinding burn and wheel wear based on self-clustering neural network

The identification of workpiece surface integrity is of interest to the people in the field of machine manufacturing. The approach of online identification of grinding burn and wheel wear based on self-clustering neural networks is proposed in this paper. The approach can identify burned workpiece for every machine part being ground, and wheel wear in the grinding process. Especially, since this method belongs to unsupervisory self-learning, people need not know types of training samples. This is available to the productive situations. The theoretical and experiment results show that the self-clustering network is one of the suitable methods with high identification accuracy.