Feature selection and a method to improve the performance of tool condition monitoring

Tool condition monitoring (TCM) is especially important in the modern machining process. In order to distinguish different tool wear states accurately and reduce the computation cost, it is of great significance to extract and select appropriate features that can reflect changes in tool wear states but are insensitive to cutting parameters. In this work, Fisher’s discriminant ratio (FDR) is adopted as the criterion for feature selection by evaluates every feature’s classification ability. However, it is found that the continuous hidden Markov models (CHMM) trained based on the features selected by the conventional method could recognize some tool state well, but have poor ability to classify other wear states. The reasons for this phenomenon have been analyzed, then a simple and effective method that used two feature sets for TCM has been proposed to improve the recognition performance. Four tests with different cutting parameters are carried out, and the new method has been implemented and verified its usefulness and validity.

[1]  Zhengyou Xie,et al.  An integrated wireless vibration sensing tool holder for milling tool condition monitoring , 2018 .

[2]  Yong Lu,et al.  Multi-scale hybrid HMM for tool wear condition monitoring , 2016 .

[3]  Geok Soon Hong,et al.  Multi-category micro-milling tool wear monitoring with continuous hidden Markov models , 2009 .

[4]  Yong Lu,et al.  Multi-scale statistical signal processing of cutting force in cutting tool condition monitoring , 2015 .

[5]  P. Y. Sevilla-Camacho,et al.  Tool breakage detection in CNC high-speed milling based in feed-motor current signals , 2011 .

[6]  P. Y. Sevilla-Camacho,et al.  Tool failure detection method for high-speed milling using vibration signal and reconfigurable bandpass digital filtering , 2015 .

[7]  Krzysztof Jemielniak,et al.  Advanced monitoring of machining operations , 2010 .

[8]  Jianguang Li,et al.  Development and testing of an integrated smart tool holder for four-component cutting force measurement , 2017 .

[9]  Xiang Li,et al.  Feature selection for tool wear monitoring: A comparative study , 2012, 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[10]  Shuang Liang,et al.  A weighted hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction , 2016, The International Journal of Advanced Manufacturing Technology.

[11]  Xifan Yao,et al.  Tool Condition Monitoring and Remaining Useful Life Prognostic Based on a Wireless Sensor in Dry Milling Operations , 2016, Sensors.

[12]  Xiang Li,et al.  A Physically Segmented Hidden Markov Model Approach for Continuous Tool Condition Monitoring: Diagnostics and Prognostics , 2012, IEEE Transactions on Industrial Informatics.

[13]  Jie Wang,et al.  CHMM for tool condition monitoring and remaining useful life prediction , 2012 .

[14]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[15]  Geok Soon Hong,et al.  A COMPARATIVE STUDY OF FEATURE SELECTION FOR HIDDEN MARKOV MODEL-BASED MICRO-MILLING TOOL WEAR MONITORING , 2008 .

[16]  Yan Wang,et al.  Real-time FDM machine condition monitoring and diagnosis based on acoustic emission and hidden semi-Markov model , 2017 .

[17]  Geok Soon Hong,et al.  Wavelet analysis of sensor signals for tool condition monitoring: A review and some new results , 2009 .

[18]  Wong Yoke San,et al.  Multiscale Singularity Analysis of Cutting Forces for Micromilling Tool-Wear Monitoring , 2011, IEEE Transactions on Industrial Electronics.

[19]  Ning Li,et al.  Gaussian process regression for tool wear prediction , 2018 .

[20]  P. S. Heyns,et al.  An industrial tool wear monitoring system for interrupted turning , 2004 .

[21]  Xiuli He,et al.  Comparative study of hybrid laser–MIG leading configuration on porosity in aluminum alloy bead-on-plate welding , 2017 .

[22]  Surjya K. Pal,et al.  Tool condition classification in turning process using hidden Markov model based on texture analysis of machined surface images , 2016 .