Study on the Identification Method of Tool Wear State Based on SLLE and SVM in NC Machining

Rui Pan; Zheng Qiang Li; Peng Nie

doi:10.4028/www.scientific.net/AMM.602-605.765

Paper Titles

Computerized Simulation on Energy Saving Characteristics of Variable Displacement of Double Action Vane Pump
p.747

Simulation Analysis and Design of Intake Restrictor of FSAE Race Car
p.751

Study on Discharge Parameters of Surface Strengthening with Powder Mixed Near Dry EDM for H13 Steel
p.757

Finite Element Analysis on the Redistribution of Reaction at Support
p.761

Study on the Identification Method of Tool Wear State Based on SLLE and SVM in NC Machining
p.765

Research on Prediction Model of End-Point Phosphorus Content for AOD Furnace Smelting Ferrochrome Based on RBF Neural Network
p.769

The Resistivity Logging Response through Casing of Nine-Layer Formations with Crude Oil
p.773

The Logging Response of Step Conductivity Formations with Crude Oil Emulsion Both in Axial and in Radial
p.776

Corn-Seed Modeling and Simulation Analysis Based on Shape Features
p.779

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 602-605Study on the Identification Method of Tool Wear...

Study on the Identification Method of Tool Wear State Based on SLLE and SVM in NC Machining

Abstract:

Aiming at the nonlinear features of Acoustic Emission reflecting the tool wear state, an identification method of tool wear state is proposed based on SLLE and lib-SVM. SLLE can overcome the problems of redundant parameters of the original nonlinear algorithms, low convergence rate, and tiny local areas in the reflecting process, etc. It can realize the reflecting from the high-dimensional data points into a global low dimensional coordinate system. It can also maintain the original topological structures of the lowered dimensional data. By using KC9125 cutting tools to cut 40CrNiMoA alloy steel to collect the acoustic signals, the collected data is vector space reconstructed. Then the high-dimensional space data are reflected into low-dimensional space data by means of SLLE in order to extract the features of the tool wear state. And LIB-SVM classification machine is used to identify and classify the tool wear state. The result shows: this method can accurately identify the tool wear state, and should be extended to a larger prevalence.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 602-605)

Pages:

765-768

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.602-605.765

Citation:

Cite this paper

Online since:

August 2014

Authors:

Rui Pan*, Zheng Qiang Li, Peng Nie

Keywords:

Lib-SVM, SLLE, Tool Wear

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Nie Peng Chen Xin, Prediction of tool VB value based on PCA and BP neural network, Journal of Beijing University of Aeronautics and Astronautics, 2011 No. 3 37(3), pp: 364-373.

Google Scholar

[2] Nie Peng, Wang Donglei, Xu Tao, Guanshan, Application of Frequency Band Energy Character Method in Cutter Wear Monitoring System Using Acoustic Emission, 2009 No. 2 (43), pp: 24-26.

Google Scholar

[3] Sam T R, Lawrence K S. Nonlinear dimensionality analysis by locally linear embedding. Science, 2000, 290(12), pp: 2323-2326.

Google Scholar

[4] Lawrence K S, Sam T R. An introduction to locally linear embedding [EBOL]. http: www. cs. toron-to. edu/~roweislle, (2001).

Google Scholar

[5] DICK D R, ROBERT P W. Locallv linear embedding for classification「EB/OL. http: /www. ph. tntudelft. n1/~dick/ ph 2002 01. pdf, 2002-1.

Google Scholar