Monitoring of a machining process using kernel principal component analysis and kernel density estimation

Tool wear is one of the consequences of a machining process. Excessive tool wear can lead to poor surface finish, and result in a defective product. It can also lead to premature tool failure, and may result in process downtime and damaged components. With this in mind, it has long been desired to monitor tool wear/tool condition. Kernel principal component analysis (KPCA) is proposed as an effective and efficient method for monitoring the tool condition in a machining process. The KPCA-based method may be used to identify faults (abnormalities) in a process through the fusion of multi-sensor signals. The method employs a control chart monitoring approach that uses Hotelling’s T 2 -statistic and Q -statistic to identify the faults in conjunction with control limits, which are computed by kernel density estimation (KDE). KDE is a non-parametric technique to approximate a probability density function. Four performance metrics, abnormality detection rate, false detection rate, detection delay, and prediction accuracy, are employed to test the reliability of the monitoring system and are used to compare the KPCA-based method with PCA-based method. Application of the proposed monitoring system to experimental data shows that the KPCA based method can effectively monitor the tool wear.

[1]  Xue-feng Yan,et al.  Weighted kernel principal component analysis based on probability density estimation and moving window and its application in nonlinear chemical process monitoring , 2013 .

[2]  Wei Xindong,et al.  Soil Moisture Analysis of Bamboo-Style Water Harvesting Ditches in the Hilly Loess Region of Northern Shaanxi Province, China , 2013 .

[3]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[4]  Rui Liu,et al.  Application of audible sound signals for tool wear monitoring using machine learning techniques in end milling , 2017, The International Journal of Advanced Manufacturing Technology.

[5]  Xiaoli Li,et al.  Detection of tool flute breakage in end milling using feed-motor current signatures , 2001 .

[6]  Yuan Zhejun,et al.  Tool wear monitoring with wavelet packet transform—fuzzy clustering method , 1998 .

[7]  Guofeng Wang,et al.  A new tool wear monitoring method based on multi-scale PCA , 2019, J. Intell. Manuf..

[8]  Naomi S. Altman,et al.  Points of Significance: Principal component analysis , 2017, Nature Methods.

[9]  David J. Sandoz,et al.  The application of principal component analysis and kernel density estimation to enhance process monitoring , 2000 .

[10]  G. Królczyk,et al.  Investigation of wear and tool life of coated carbide and cubic boron nitride cutting tools in high speed milling , 2015 .

[11]  Connor Jennings,et al.  Cloud-Based Parallel Machine Learning for Tool Wear Prediction , 2018 .

[12]  Sohyung Cho,et al.  Design of multisensor fusion-based tool condition monitoring system in end milling , 2010 .

[13]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[14]  Sophie Hallstedt,et al.  A model-based approach for sustainability and value assessment in the aerospace value chain , 2015 .

[15]  Snr. D. E. Dimla.  The Correlation of Vibration Signal Features to Cutting Tool Wear in a Metal Turning Operation , 2002 .

[16]  Noureddine Ellouze,et al.  Practical Selection of SVM Supervised Parameters with Different Feature Representations for Vowel Recognition , 2015, ArXiv.

[17]  M. Kulahci,et al.  On the structure of dynamic principal component analysis used in statistical process monitoring , 2017 .

[18]  Colin Bradley,et al.  A review of machine vision sensors for tool condition monitoring , 1997 .

[19]  Yi Zhu,et al.  Nonlinear process monitoring using wavelet kernel principal component analysis , 2012, 2012 International Conference on Systems and Informatics (ICSAI2012).

[20]  Reza Langari,et al.  A Neuro-Fuzzy System for Tool Condition Monitoring in Metal Cutting , 2001 .

[21]  Jianbo Yu,et al.  Machine Tool Condition Monitoring Based on an Adaptive Gaussian Mixture Model , 2012 .

[22]  Jose Vicente Abellan-Nebot,et al.  A review of machining monitoring systems based on artificial intelligence process models , 2010 .

[23]  Yi Cao,et al.  Fault detection in a multivariate process based on kernel PCA and kernel density estimation , 2014, 2014 20th International Conference on Automation and Computing.

[24]  Quan Wang,et al.  Kernel Principal Component Analysis and its Applications in Face Recognition and Active Shape Models , 2012, ArXiv.

[25]  C. Yoo,et al.  Nonlinear process monitoring using kernel principal component analysis , 2004 .

[26]  Jin Hyun Park,et al.  Fault detection and identification of nonlinear processes based on kernel PCA , 2005 .

[27]  H. Abdi,et al.  Principal component analysis , 2010 .

[28]  AbdiHervé,et al.  Principal Component Analysis , 2010, Essentials of Pattern Recognition.

[29]  Mia Hubert,et al.  Overview of PCA-Based Statistical Process-Monitoring Methods for Time-Dependent, High-Dimensional Data , 2015 .

[30]  Roberto Teti,et al.  Multiple sensor monitoring in nickel alloy turning for tool wear assessment via sensor fusion , 2013 .

[31]  Hong-li Gao,et al.  On-line Tool Condition Monitoring Based on PCA and Integrated Neural Networks for Cold Blast Machining Operation , 2017 .

[32]  John W. Sutherland,et al.  Development of an Intelligent Tool Condition Monitoring System to Identify Manufacturing Tradeoffs and Optimal Machining Conditions , 2019, Procedia Manufacturing.

[33]  B. Silverman.  Density estimation for statistics and data analysis , 1986 .

[34]  Shang-Liang Chen,et al.  Data fusion neural network for tool condition monitoring in CNC milling machining , 2000 .

[35]  Surjya K. Pal,et al.  Tool Condition Monitoring in Turning by Applying Machine Vision , 2016 .