Tool Wear Image Segmentation Based on Markov Random Field Model

Si Chang Xiong; Ling Ping Dong; Dong Hui Wen

doi:10.4028/www.scientific.net/AMR.102-104.600

Paper Titles

Research and Application of Metal Cold Extrusion Forming Utilising Floating Die and Divided Flow
p.583

Statistical Analysis on Lapping Parameters for Sapphire Wafer
p.587

Study on the Effect of Ultrasonic Surface Rolling Processing Parameters on the Surface Roughness of Q345 Hydraulic Prop
p.591

Research on Hole Expanding with Spiral-Fluted Electrode in ECM
p.595

Tool Wear Image Segmentation Based on Markov Random Field Model
p.600

Layer Face Milling Cutter Parametric Modeling and Modal Analysis
p.605

The Real-Time Prediction of Surface Roughness Based on Genetic Wavelet Network
p.610

Study on the Cutting Deforming Force of Single Abrasive Grit for Ultrasonic Vibration Assisted Grinding along Normal Direction
p.615

Crossbeam Analysis and Structure Optimization of Special-Shaped Stone Combined Machining Center
p.620

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 102-104Tool Wear Image Segmentation Based on Markov...

Tool Wear Image Segmentation Based on Markov Random Field Model

Abstract:

In this article, we propose a tool wear image segmentation algorithm based on Markov Random Field model. In this algorithm, the wear area was divided into wear area, background area and body area, in terms of the MAP (maximum a posteriori) criterion, and we got the pre-segmentation image. Afterwards, the aiming area (region B) was segmented out from the wear area by using peak-band algorithm and the edges are integrated in mathematical morphology theorem. As a result, we obtained an integrated tool wear region. Experiments indicate that the segmentation algorithm can be used to evaluate the degree of tool wear and applied to synchronously monitor tool wear condition effectively.

You might also be interested in these eBooks

Digital Design and Manufacturing Technology

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 102-104)

Pages:

600-604

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.102-104.600

Citation:

Cite this paper

Online since:

March 2010

Authors:

Si Chang Xiong, Ling Ping Dong, Dong Hui Wen

Keywords:

Condition Monitoring, Image Segmentation, Markov Random Field, Tool Wear

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Besag J. On the Statistical Analysis of Dirty Picture [J]. Journal of Royal Statistical Society, 1986, B48: 259~302.

Google Scholar

[2] Cross G R，Jain A K，Markov Random Field Texture Models，IEEE Trans. PAMI, 1983, 5(1): 25-39.

DOI: 10.1109/tpami.1983.4767341

Google Scholar

[3] Dimla E, Dimla Snr, Sensor signals for tool-wear monitoring in mental cutting operations-a review of methods, Int J of Machine Tools and Manufacture, 2000. 40: 1037-1098.

DOI: 10.1016/s0890-6955(99)00122-4

Google Scholar

[4] Min-yang Yang, Oh-dal Kwon, A tool condition recognition system using image processing, Control Engineering Practice, 1998. 6: 1389-1395.

DOI: 10.1016/s0967-0661(98)00117-8

Google Scholar

[5] Cui Zhang, Sudan Li, SAR Image Segmentation Based on Markov Random Field Model, Remote Sensing Technology and Application, 2001. 16(1): 66-68.

Google Scholar

[6] An Ping, Zhang Zhao-yang, Ma Ran, Hierarchical MRF/GRF Model Based Disparity Estimation and Segmentation for Stereo Image, 2003. 31(4): 597-601.

Google Scholar

[7] Wei-qiang Liu, Chen Hong, De-shen Xia, Markov Random Field Based Fast Segmentation, Journal of Image and Graphics, 2001. 6(3): 228-233. B Area (mm 2) Working time (min).

Google Scholar