Tool wear monitoring by machine learning techniques and singular spectrum analysis

被引：95

作者：

Kilundu, Bovic ^{[1
]}

Dehombreux, Pierre ^{[1
]}

Chiementin, Xavier ^{[2
]}

机构：

[1] Univ Mons, Fac Polytech Mons, Risk Res Ctr, B-7000 Mons, Belgium

[2] Univ Reims, GRESPI, F-51687 Reims 2, France

来源：

MECHANICAL SYSTEMS AND SIGNAL PROCESSING | 2011年 / 25卷 / 01期

关键词：

Data mining; Vibration signal; Singular spectrum analysis; Tool condition monitoring; NEURAL-NETWORK; VIBRATION SIGNALS; SENSOR FUSION;

D O I：

10.1016/j.ymssp.2010.07.014

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

This paper explores the use of data mining techniques for tool condition monitoring in metal cutting. Pseudo-local singular spectrum analysis (SSA) is performed on vibration signals measured on the toolholder. This is coupled to a band-pass filter to allow definition and extraction of features which are sensitive to tool wear. These features are defined, in some frequency bands, from sums of Fourier coefficients of reconstructed and residual signals obtained by SSA. This study highlights two important aspects: strong relevance of information in high frequency vibration components and benefits of the combination of SSA and band-pass filtering to get rid of useless components (noise). (C) 2010 Elsevier Ltd. All rights reserved.

引用

页码：400 / 415

页数：16

共 30 条

[1] Drilling wear detection and classification using vibration signals and artificial neural network [J].

Abu-Mahfouz, I .

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, 2003, 43 (07) :707-720

[2] Use of electrical power for online monitoring of tool condition [J].

Al-Sulaiman, FA ;

Baseer, MA ;

Sheikh, AK .

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2005, 166 (03) :364-371

[3] Tool wear condition monitoring using a sensor fusion model based on fuzzy inference system [J].

Aliustaoglu, Cuneyt ;

Ertunc, H. Metin ;

Ocak, Hasan .

MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2009, 23 (02) :539-546

[4] Analysis of the structure of vibration signals for tool wear detection [J].

Alonso, F. J. ;

Salgado, D. R. .

MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2008, 22 (03) :735-748

[5] Tool condition monitoring using artificial intelligence methods [J].

Balazinski, M ;

Czogala, E ;

Jemielniak, K ;

Leski, J .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2002, 15 (01) :73-80

[6]

Bertholds M., 2003, INTELLIGENT DATA ANA

[7] EXTRACTING QUALITATIVE DYNAMICS FROM EXPERIMENTAL-DATA [J].

BROOMHEAD, DS ;

KING, GP .

PHYSICA D, 1986, 20 (2-3) :217-236

[8]

Chi M., 2002, REV GEOPHYS, V40, P11

[9] On-line metal cutting tool condition monitoring. I: force and vibration analyses [J].

Dimla, DE ;

Lister, PM .

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, 2000, 40 (05) :739-768

[10] Sensor signals for tool-wear monitoring in metal cutting operations - a review of methods [J].

Dimla, DE .

INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, 2000, 40 (08) :1073-1098

← 1 2 3 →