Drilling Wear Recognition Based on Fuzzy C-Means Clustering Algorithm

Abstract:

Fuzzy c-means clustering algorithm was introduced in detail to classify a set of original sampling data on drilling wear in this paper. Simulation results by Matlab programming show that drill wear modes can be successfully represented by four fuzzy grades after fuzzy clustering and classification. The analysis result indicates that fuzzy description can properly reflect drill wear, FCM can effectively identify different wear modes. It is suggested that the severe degree of membership of wear be used as a criterion for replacement of a drill. This technique is simple and is adaptable to different environment in automatic manufacturing

• Periodical: Advanced Materials Research (Volumes 538-541)
• Pages: 1408-1412
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.538-541.1408
• Online since: June 2012
• Authors: Ming Xia Yan
• Keywords: Drilling Wear, Fault Diagnosis, Fuzzy C-Means Clustering, MATLAB

References

[1] Dunn,J.C: J.Cybernet.3(1973),p.32

[2] Bezdek,J.C: Pattern Recognition with Fuzzy Objective Function Algorithms(Plenum Press, New York 1981)

[3] Bezdek,J.C: J.IEEE PAMI.1(1980),p.1

[4] Zhen Ding: Acta Electronica Sinica.Vol.25,5(1997),p.39(in Chinese)

[5] Bangli Zhang:  Computer Engineering and Applications.3,(2002),p.254(in Chinese)

[6] Boqiang Shi: MATLAB mathematics calculation example tutorial(Railway Publishing House of China, Beijing 2004)