0
TECHNICAL PAPERS

Hidden Markov Model-based Tool Wear Monitoring in Turning

[+] Author and Article Information
Litao Wang, Mostafa G. Mehrabi, Elijah Kannatey-Asibu

Department of Mechanical Engineering, Engineering Research Center for Reconfigurable Machining Systems, University of Michigan, Ann Arbor, MI 48109-2125

J. Manuf. Sci. Eng 124(3), 651-658 (Jul 11, 2002) (8 pages) doi:10.1115/1.1475320 History: Received May 01, 2001; Revised October 01, 2001; Online July 11, 2002
Copyright © 2002 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
A first-order, three state hidden Markov model
Grahic Jump Location
Decision-making process of an earthworm
Grahic Jump Location
Flow chart of the HMM training procedure
Grahic Jump Location
Block diagram of the procedure for tool condition detection
Grahic Jump Location
(a) Time domain vibration signals (b) variation of wavelet coefficients for different tool states
Grahic Jump Location
Feature elements in a codebook
Grahic Jump Location
An observed vibration signal from a sharp tool
Grahic Jump Location
Feature vectors for sharp and worn tools (cutting speed: 300 sfpm; feed rate: 0.005 ipr)
Grahic Jump Location
Feature vectors for sharp and worn tools (cutting speed: 250 sfpm; feed rate: 0.006 ipr)
Grahic Jump Location
Feature vectors for sharp and worn tools (cutting speed: 350 sfpm; feed rate: 0.004 ipr)
Grahic Jump Location
Detection rate versus length of training data (3-state HMM with observation sequence length of 5 and codebook size of 10)
Grahic Jump Location
Detection rate versus observation sequence length (3-state HMM with codebook size of 10)
Grahic Jump Location
Decision space for sharp and worn tools

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In