Tool wear intelligence measure in cutting process based on HMM

Author

Qiang, Shao ; Cheng, Shao ; Jing, Kang

Author_Institution

Inst. of Adv. control Technol., Dalian Univ. of Technol., Dalian, China

fYear

2009

fDate

5-7 Aug. 2009

Firstpage

1563

Lastpage

1567

Abstract

A method of tool wear intelligence measure based on discrete hidden Markov models (DHMM) is proposed to monitor tool wear and to predict tool failure. FFT features are first extracted from the vibration signal and cutting force in cutting process, and then FFT vectors are presorted and converted into integers by SOM. Finally, these codes are introduced to DHMM for machine learning and 3 models for different tool wear stage are built up. Pattern of HMM is recognised by calculating probability. The results of tool wear intelligence measure and pattern recognition of tool wear experiments show that the method is effective.

Keywords

condition monitoring; cutting; cutting tools; failure analysis; fast Fourier transforms; feature extraction; hidden Markov models; learning (artificial intelligence); probability; production engineering computing; self-organising feature maps; vibrations; wear; DHMM; FFT; SOM; cutting process; discrete hidden Markov model; feature extraction; machine learning; pattern recognition; probability; tool failure prediction; tool wear intelligence measure; tool wear monitoring; vibration signal; Automation; Condition monitoring; Extraterrestrial measurements; Feature extraction; Hidden Markov models; Learning systems; Pattern recognition; Probability; Signal processing; Vibrations; Discrete Hidden Markov Model (DHMM); Intelligence Measure; Pattern Recognition; Tool wear;

fLanguage

English

Publisher

ieee

Conference_Titel

Automation and Logistics, 2009. ICAL '09. IEEE International Conference on

Conference_Location

Shenyang

Print_ISBN

978-1-4244-4794-7

Electronic_ISBN

978-1-4244-4795-4

Type

conf

DOI

10.1109/ICAL.2009.5262708

Filename

5262708