• Jun 14, 2017 News!Vol.6, No.3 has been indexed by EI(Inspec)!   [Click]
  • May 03, 2016 News!Vol.5, No.5 has been indexed by EI(Inspec)!   [Click]
  • May 03, 2016 News!Vol.5, No.4 has been indexed by EI(Inspec)!   [Click]
General Information
    • ISSN: 2010-3700
    • Frequency: Bimonthly
    • DOI: 10.18178/IJMLC
    • Editor-in-Chief: Dr. Lin Huang
    • Executive Editor:  Ms. Cherry L. Chen
    • Abstracing/Indexing: Engineering & Technology Digital Library, Google Scholar, Crossref, ProQuest, Electronic Journals Library, DOAJ and EI (INSPEC, IET).
    • E-mail: ijmlc@ejournal.net
Editor-in-chief
Dr. Lin Huang
Metropolitan State University of Denver, USA
It's my honor to take on the position of editor in chief of IJMLC. We encourage authors to submit papers concerning any branch of machine learning and computing.
IJMLC 2016 Vol.6(5): 256-259 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2016.6.5.607

Anomaly Detection via Unsupervised Learning for Tool Breakage Monitoring

Chengming Shi, Bo Luo, Hongqi Li, Bin Li, Xinyong Mao, and Fangyu Peng
Abstract—Machining and manufacturing of mechanical equipment is developing towards the direction of high speed, precision and efficiency. The tool health condition can be reflected by the massive data which can promote tool condition monitoring into the big data field, so it is a new challenge for the field that mining the characteristics which can describes tool condition. As an unsupervised hard clustering method, the advantage of K-means clustering is to mine the information from the massive data sets and clustering it efficiently and rapidly. Meanwhile, with the latest achievement in the field of machine learning, we can combine deep learning with the K-means clustering and propose a method of monitoring the health condition of the tool with unsupervised learning. The method that carries out the unsupervised pre-training of the tool vibration signal to get rid of the disadvantage that we must rely on the artificial diagnosis experience has the advantage in adaptively extracting the fault features from the tool signals. Through the design experiments and results show that the method can realize the adaptively unsupervised extraction of tool fault characteristics and the accurately identification of tool condition under the condition of large sample and multi-tool condition.

Index Terms—K-means clustering, massive data, tool breakage, unsupervised learning.

Chengming Shi and Bo Luo are with School of Mechanical Science and Engineering, Huazhong University of Science and Technology, 1037 Luoyu Road, Wuhan, Hubei Province, PR China (e-mail: 18771978627@163.com, hglobo@163.com).
Hongqi Liu, Xinyong Mao, and Fangyu Peng are with National NC System Engineering Research Center, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, 1037 Luoyu Road, Wuhan, Hubei Province 430074, PR China.
Bin Li is with State Key Laboratory of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, 1037 Luoyu Road, Wuhan, Hubei Province 430074, PR China.

[PDF]

Cite: Chengming Shi, Bo Luo, Hongqi Li, Bin Li, Xinyong Mao, and Fangyu Peng, "Anomaly Detection via Unsupervised Learning for Tool Breakage Monitoring," International Journal of Machine Learning and Computing vol. 6, no. 5, pp. 256-259, 2016.

Copyright © 2008-2015. International Journal of Machine Learning and Computing. All rights reserved.
E-mail: ijmlc@ejournal.net