Application of machine vision method in tool wear monitoring

Aiming at the low tool utilization rate caused by tool wear in the milling process, a tool wear automatic monitoring system based on machine vision is proposed. The tool wear images are automatically acquired by a charge-coupled device (CCD) camera. The system selects the image with obvious characteristics and cuts the wear area for processing, thus extracting the tool wear value. On one hand, the reliability of using the wear area of flank face as a technical index to judge the degree of tool wear is explored. On the other hand, the changes in the surface texture of workpiece are also analyzed by the gray-level co-occurrence matrix (GLCM) method. A milling experiment was carried out and the wear value measured by the monitoring system was compared with the real wear value. The result showed that the accuracy of the monitoring system met the industrial requirements. The wear area of the flank face and the wear width are consistent in trend under different cutting parameters, which means that the wear area of the flank face could be used as an index for judging the degree of tool wear. In addition, the characteristic parameters of the surface texture of workpiece change regularly with the tool wear, which shows that the tool wear can be characterized from another aspect.

[1]  Z.M. Li,et al.  Incremental learning for online tool condition monitoring using Ellipsoid ARTMAP network model , 2015, Appl. Soft Comput..

[2]  S. Senthil Kumaran,et al.  An investigation of tool wear using acoustic emission and genetic algorithm , 2015 .

[3]  Mohd Amri Sulaiman,et al.  Wear mechanism and notch wear location prediction model in ball nose end milling of Inconel 718 , 2013 .

[4]  A. E. Diniz,et al.  Effect of the gray cast iron microstructure on milling tool life and cutting force , 2013 .

[5]  Liu Ming-jun,et al.  Research on surface integrity in milling Inconel718 superalloy , 2017 .

[6]  Xin Wang,et al.  Investigation on universal tool wear measurement technique using image-based cross-correlation analysis , 2021 .

[7]  Jie Sun,et al.  Development and testing of a wireless rotating triaxial vibration measuring tool holder system for milling process , 2020 .

[8]  Fengbiao Wang,et al.  Research on tool wear of milling nickel-based superalloy in cryogenic , 2017 .

[9]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[10]  Liang Guo,et al.  Research on automatic monitoring method of face milling cutter wear based on dynamic image sequence , 2020, The International Journal of Advanced Manufacturing Technology.

[11]  Víctor González-Castro,et al.  A computer vision approach to analyse and classify tool wear level in milling processes using shape descriptors and machine learning techniques , 2016 .

[12]  Márcio Bacci da Silva,et al.  Tool wear monitoring in micromilling using Support Vector Machine with vibration and sound sensors , 2021 .

[13]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[14]  Ratko Obradovic,et al.  Novel texture-based descriptors for tool wear condition monitoring , 2018 .

[15]  B. Julesz.  Textons, the elements of texture perception, and their interactions , 1981, Nature.

[16]  H. Metin Ertunc,et al.  Tool wear condition monitoring using a sensor fusion model based on fuzzy inference system , 2009 .

[17]  Yunbo Hu,et al.  Study of Tool Wear Monitoring Using Machine Vision , 2020, Automatic Control and Computer Sciences.

[18]  G. Zhang,et al.  Single-Point Grinding of Alumina and Zirconia Ceramics Under Two-Dimensional Compressive Prestress , 2020, International Journal of Precision Engineering and Manufacturing.

[19]  Lihong Li,et al.  An in-depth study of tool wear monitoring technique based on image segmentation and texture analysis , 2016 .

[20]  Xin Lin,et al.  Image edge detection based tool condition monitoring with morphological component analysis. , 2017, ISA transactions.

[21]  Kunpeng Zhu,et al.  The monitoring of micro milling tool wear conditions by wear area estimation , 2017 .

[22]  Colin Bradley,et al.  A machine vision system for tool wear assessment , 1997 .

[23]  Xianyin Duan,et al.  Tool wear estimation and life prognostics in milling: Model extension and generalization , 2021 .

[24]  Martin B.G. Jun,et al.  Tool wear monitoring of micro-milling operations , 2009 .

[25]  Bintao Sun,et al.  A tool condition monitoring method based on two-layer angle kernel extreme learning machine and binary differential evolution for milling , 2020 .

[26]  Ning He,et al.  A Novel Tool (Single-Flute) Condition Monitoring Method for End Milling Process Based on Intelligent Processing of Milling Force Data by Machine Learning Algorithms , 2020, International Journal of Precision Engineering and Manufacturing.

[27]  Xiang Li,et al.  Tool wear monitoring and prognostics challenges: a comparison of connectionist methods toward an adaptive ensemble model , 2018, J. Intell. Manuf..

[28]  Ruitao Peng,et al.  Effect of prestress on cutting of nickel-based superalloy GH4169 , 2018, The International Journal of Advanced Manufacturing Technology.

[29]  Pei Li,et al.  Manufacturing services collaboration: connotation, framework, key technologies, and research issues , 2020 .

[30]  Sam Turner,et al.  Tool wear monitoring using naïve Bayes classifiers , 2014, The International Journal of Advanced Manufacturing Technology.

[31]  Zsolt János Viharos,et al.  Off-line geometrical and microscopic & on-line vibration based cutting tool wear analysis for micro-milling of ceramics , 2020 .

[32]  Konstantinos Salonitis,et al.  Reliability assessment of cutting tool life based on surrogate approximation methods , 2014 .

[33]  Zhichao You,et al.  On-line milling cutter wear monitoring in a wide field-of-view camera , 2020 .

[34]  Paul J. Scott,et al.  Indirect cutting tool wear classification using deep learning and chip colour analysis , 2020, The International Journal of Advanced Manufacturing Technology.

[35]  María Teresa García-Ordás,et al.  Tool wear monitoring using an online, automatic and low cost system based on local texture , 2018, Mechanical Systems and Signal Processing.