Hidden semi-Markov model-based method for tool wear estimation in milling process

This paper presents a new method for tool wear estimation in milling process by utilizing the hidden semi-Markov model (HSMM). HSMM differs greatly from the standard hidden Markov model (HMM) in state duration distribution. The model structure and corresponding parameters of HSMM can be easily determined without optimization. Two groups of experiments are carried out to prove the effectiveness of the HSMM-based method by recurring to the Gamma distribution. Five types of time-domain features that characterize tool wear states are extracted from the cutting force signals during milling process. The extracted signal features are utilized to realize tool wear estimation by means of HSMM and some other published methods, respectively. The experimental and analytical results show that the HSMM-based method can reach higher accuracy for tool wear estimation. Besides, the consuming time of HSMM for the identification of tool wear state is less than 0.05 s, which makes tool wear monitoring in industrial environment become more realistic and operable.