Tool wear condition monitoring based on continuous wavelet transform and blind source separation

被引:57
作者
Benkedjouh, Tarak [1 ]
Zerhouni, N. [2 ]
Rechak, S. [3 ]
机构
[1] EMP, LMS, Algiers 16046, Algeria
[2] UTBM, Automat Control & Micromechatron Syst Dept, CNRS, UMR 6174,UFC,ENSMM,FEMTO ST Inst, 24 Rue Alain Savary, F-25000 Besancon, France
[3] ENP, LGMI, Algiers, Algeria
关键词
CNC milling; Tools wear; CWT; BSS; Feature extraction; RUL; INDEPENDENT COMPONENT ANALYSIS; CONDITION-BASED MAINTENANCE; FEATURE-EXTRACTION; CHATTER DETECTION; CUTTING FORCE; SIGNALS; DIAGNOSIS; CLASSIFICATION; PROGNOSTICS; STATISTICS;
D O I
10.1007/s00170-018-2018-6
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Prognostics and health management (PHM) for condition monitoring systems have been proposed for predicting faults and estimating the remaining useful life (RUL) of components. In fact, in order to produce quickly, economically, with high quality and reduce machine tool downtime, a new intelligent method for tool wear condition monitoring is based on continuous wavelet transform (CWT) and blind source separation (BSS) techniques. CWT is one of the most powerful signal processing methods and has been widely applied in tool wear condition monitoring. The CWT used to transform one set of one-dimensional series into multiple sets of one-dimensional series for preprocessing. After that, BSS was applied to analyze the wavelet coefficients. The signal energy evolution of each independent source obtained by BSS was used for health assessment and RUL estimation, the idea is based on the computation of a nonlinear regression function in a high-dimensional feature space where the input data were mapped via a nonlinear function. Experimental results show that the proposed CWT-BSS method can reflect effectively the performance degradation of cutting tools for the milling process. The proposed method is applied on real-world RUL estimation for a given wear limit based on extracted features.
引用
收藏
页码:3311 / 3323
页数:13
相关论文
共 41 条
[1]   Tool condition monitoring by SVM classification of machined surface images in turning [J].
Bhat, Nagaraj N. ;
Dutta, Samik ;
Vashisth, Tarun ;
Pal, Srikanta ;
Pal, Surjya K. ;
Sen, Ranjan .
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2016, 83 (9-12) :1487-1502
[2]  
Bhuiyan M., 2014, Comprehensive Materials Processing, V13, P539, DOI DOI 10.1016/B978-0-08-096532-1.01330-3
[3]   Novel cyclostationarity-based blind source separation algorithm using second order statistical properties: Theory and application to the bearing defect diagnosis [J].
Bouguerriou, N ;
Haritopoulos, M ;
Capdessus, C ;
Allam, L .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2005, 19 (06) :1260-1281
[4]  
Chen X, 2013, J VIB CONTROL, V21, P1757
[5]   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
[6]  
Fast AH, 1999, IEEE T NEURAL NETWOR, V10, P626
[7]   Reliability analysis and condition-based maintenance of systems with dependent degrading components based on thermodynamic physics-of-failure [J].
Feng, Qianmei ;
Jiang, Lei ;
Coit, David W. .
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2016, 86 (1-4) :913-923
[8]   Automatic feature constructing from vibration signals for machining state monitoring [J].
Fu, Yang ;
Zhang, Yun ;
Gao, Huang ;
Mao, Ting ;
Zhou, Huamin ;
Sun, Ronglei ;
Li, Dequn .
JOURNAL OF INTELLIGENT MANUFACTURING, 2019, 30 (03) :995-1008
[9]   Blind separation of manufacturing variability with independent component analysis: A convolutive approach [J].
Gandini, M. ;
Lombardi, F. ;
Vaccarino, F. .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (08) :9939-9946
[10]   Multi-scale statistical signal processing of cutting force in cutting tool condition monitoring [J].
Gao, Dong ;
Liao, Zhirong ;
Lv, Zekun ;
Lu, Yong .
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2015, 80 (9-12) :1843-1853