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.

[1]  Chatchapol Chungchoo,et al.  On-line tool wear estimation in CNC turning operations , 2001 .

[2]  Søren Højsgaard,et al.  Hidden Semi Markov Models for Multiple Observation Sequences: The mhsmm Package for R , 2011 .

[3]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[4]  Ming Liang,et al.  Detection and diagnosis of bearing and cutting tool faults using hidden Markov models , 2011 .

[5]  P. S. Heyns,et al.  A comparative evaluation of neural networks and hidden Markov models for monitoring turning tool wear , 2005, Neural Computing & Applications.

[6]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[7]  Dongfeng Shi,et al.  Tool wear predictive model based on least squares support vector machines , 2007 .

[8]  Bülent Kaya,et al.  Force-torque based on-line tool wear estimation system for CNC milling of Inconel 718 using neural networks , 2011, Adv. Eng. Softw..

[9]  Dongdong Kong,et al.  Tool wear monitoring based on kernel principal component analysis and v-support vector regression , 2016, The International Journal of Advanced Manufacturing Technology.

[10]  Shunzheng Yu,et al.  Hidden semi-Markov models , 2010, Artif. Intell..

[11]  A. Galip Ulsoy,et al.  Reconfigurable manufacturing systems: Key to future manufacturing , 2000, J. Intell. Manuf..

[12]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[13]  Jan Bulla,et al.  hsmm - An R package for analyzing hidden semi-Markov models , 2010, Comput. Stat. Data Anal..

[14]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for automatic speech recognition , 1986 .

[15]  Guofeng Wang,et al.  Tool wear state recognition based on linear chain conditional random field model , 2013, Eng. Appl. Artif. Intell..

[16]  R. Moore,et al.  Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[17]  Peter Løvendahl,et al.  Combining Cattle Activity and Progesterone Measurements Using Hidden Semi-Markov Models , 2011 .

[18]  Kenneth A. Loparo,et al.  Tool wear condition monitoring in drilling operations using hidden Markov models (HMMs) , 2001 .

[19]  S. C. Choi,et al.  Maximum Likelihood Estimation of the Parameters of the Gamma Distribution and Their Bias , 1969 .

[20]  Yang He,et al.  Efficient utilization of variable duration information in HMM based HWR systems , 1997, Proceedings of International Conference on Image Processing.

[21]  Mari Ostendorf,et al.  Multi-rate hidden Markov models and their application to machining tool-wear classification , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[22]  Ashraf A. Kassim,et al.  Tool condition classification using Hidden Markov Model based on fractal analysis of machined surface textures , 2006, Machine Vision and Applications.

[23]  Surjya K. Pal,et al.  Tool condition classification in turning process using hidden Markov model based on texture analysis of machined surface images , 2016 .

[24]  Elijah Kannatey-Asibu,et al.  Hidden Markov model-based tool wear monitoring in turning , 2002 .

[25]  H.J.J. Kals,et al.  Developments and Trends in Monitoring and Control of Machining Processes , 1988 .

[26]  P. Baruah,et al.  HMMs for diagnostics and prognostics in machining processes , 2005 .

[27]  Rajiv Tiwari,et al.  Optimum multi-fault classification of gears with integration of evolutionary and SVM algorithms , 2014 .

[28]  David He,et al.  A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology , 2007 .

[29]  Y. Guédon.  Estimating Hidden Semi-Markov Chains From Discrete Sequences , 2003 .

[30]  David He,et al.  Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis , 2007, Eur. J. Oper. Res..

[31]  B. F. von Turkovich,et al.  A Comprehensive Tool Wear Model , 1986 .