Multi-scale hybrid HMM for tool wear condition monitoring

Liao, Zhirong; Gao, Dong; Lu, Yong; Lv, Zekun

Abstract

In a machining system, accurate tool wear condition monitoring is paramount for guaranteeing the quality of the workpiece and tool life. Cutting force signal is the most commonly used signal to depict the tool wear variation during the machining process. In this paper, a novel approach for tool wear condition monitoring is proposed, which is based on the multi-scale hybrid hidden Markov model (HHMM) analysis of cutting force signal. The proposed approach captures the deeply mined information of tool wear states and holds an accurate tool wear value monitoring performance from both local and global analyses point of view. The local model deals with the wavelet coefficients of cutting force in different frequencies as a cross-twist Markov depended structure within instant time resolution, which reflects the tool wear state feature from frequency dimension. The global model depicts the long time dynamical degradation of tool wear condition combined with the local model as a composite structure. Experimental studies on CNC turning of nickel alloy, Inconel 718, show that the proposed HHMM approach is efficient in tool wear monitoring and outperforms the single hidden Markov model (HMM).

Citation

Liao, Z., Gao, D., Lu, Y., & Lv, Z. (2016). Multi-scale hybrid HMM for tool wear condition monitoring. International Journal of Advanced Manufacturing Technology, 84(9-12), 2437-2448. doi:10.1007/s00170-015-7895-3

• Journal Article Type: Article
• Acceptance Date: Sep 24, 2015
• Online Publication Date: Oct 3, 2015
• Publication Date: 2016-06
• Deposit Date: Nov 27, 2018
• Journal: The International Journal of Advanced Manufacturing Technology
• Print ISSN: 0268-3768
• Electronic ISSN: 1433-3015
• Publisher: BMC
• Peer Reviewed: Peer Reviewed
• Volume: 84
• Issue: 9-12
• Pages: 2437-2448
• DOI: https://doi.org/10.1007/s00170-015-7895-3
• Public URL: https://nottingham-repository.worktribe.com/output/1313039
• Publisher URL: https://link.springer.com/article/10.1007%2Fs00170-015-7895-3