RETRACTED: Tool Wear Intelligence Measure in Cutting Process Based on HMM

RETRACTED PAPER: 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.

By email View Pdf

You might also be interested in these eBooks

Advances in Mechanical Engineering (ICME)

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 52-54)

Pages:

482-487

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.52-54.482

Online since:

March 2011

Authors:

Jing Kang, Li Na Guan

Keywords:

Discrete Hidden Markov Model (DHMM), Intelligence Measure, Tool Wear

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

Citation:

References

[1] L. Atlas, M. Ostendod, G. D. Bernard: HIDDEN MARKOV MODELS FOR MONITORING MACHINING TOOL-WEAR, proceedings of IEEE ICASSP'00 3887~3890.

Google Scholar

[2] H. M. Ertunc, K. A. Loparo, E. Ozdernir etc: Real Time Monitoring of Tool Wear Using Multiple Modeling Method, proceedings of IEEE IEMDC20 687~ 691 Oct.(2001).

DOI: 10.1109/iemdc.2001.939388

Google Scholar

[3] Gao Hong-li: The Investigation of Intelligent Tool Wear Monitoring Techniques for Metal Cutting Process，Ph.D. Southwest Jiaotong University，China, Sep. (2005).

Google Scholar

[4] Wang Wei：Research on Too1 Condition Monitoring and on-line Compensation Technology in Milling Special Spiral Rod，Ph.D. Northeast University，Feb.(2006).

Google Scholar

[5] Gao Hong-li, Xu Ming-heng, Fu Pan etc, Tool Wear Monitoring Based on Dynamic Tree, J. CHINESE JOURNAL OF MECHANICAL ENGINEERING. Vol. 42,No. 7, Jul. (2006).

Google Scholar

[6] FENG Chang-jian, HMM Dynamical Pattern Recognition Theories, Methods and Applications in Faults Diagnosis of Rotating Machine, ,Ph.D, Zhejiang University, Nov. (2002).

Google Scholar

[7] Ding Qiquan, Feng Changjian, Li Zhinong, Wu Zhaotong, Study on DHMM Fault Diagnostic Methods for Rotating Machinery during Run-up,, J. Journal of Vibration Engineering, Vol. 16 no. 1,Jan. (2003).

Google Scholar

[8] HE Qiang, MAO Shi-yi ,ZHANG You-wei, Re-estimation of Continuous Hidden Markov Model with Multiple Observation without Overflow,, J. ACTA ELECTRONICA SINICA, Vol28(10) , pp.98-101.

Google Scholar

[9] Varsta, M., Heikkonen, J., Lampinen, J., and del R. Millán, J. Temporal Kohonen map and recurrent Self-Organizing Map: Analytical and experimental comparision. Neural Processing Letters, 2001;13(3):237-251.

DOI: 10.1023/a:1011353011837

Google Scholar

[10] Jing KANG, Ni KANG, Chang-jian FENG, Hong-ying HU, Research on Tool Failure Prediction and wear Monitoring Based on HMM Pattern Recognition Theory,, Proceedings of IEEE-ICWAPR2007, 2007.11, p.1167~1172.

DOI: 10.1109/icwapr.2007.4421609

Google Scholar