0
Research Papers

Tool Condition Monitoring in Turning by Applying Machine Vision

[+] Author and Article Information
Samik Dutta

Precision Engineering and Metrology Department,
CSIR-Central Mechanical Engineering
Research Institute,
Durgapur 713209, West Bengal, India
e-mail: s_dutta@cmeri.res.in

Surjya K. Pal

Professor
Department of Mechanical Engineering,
Indian Institute of Technology Kharagpur,
Kharagpur 721302, West Bengal, India
e-mail: skpal@mech.iitkgp.ernet.in

Ranjan Sen

Precision Engineering and Metrology Department,
CSIR-Central Mechanical Engineering
Research Institute,
Durgapur 713209, West Bengal, India
e-mail: rsen@cmeri.res.in

1Corresponding author.

Contributed by the Manufacturing Engineering Division of ASME for publication in the JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING. Manuscript received April 18, 2015; final manuscript received October 5, 2015; published online November 19, 2015. Assoc. Editor: Robert Gao.

J. Manuf. Sci. Eng 138(5), 051008 (Nov 19, 2015) (17 pages) Paper No: MANU-15-1182; doi: 10.1115/1.4031770 History: Received April 18, 2015; Revised October 05, 2015

In this paper, a method for predicting progressive tool flank wear using extracted features from turned surface images has been proposed. Acquired turned surface images are analyzed by using texture analyses, viz., gray level co-occurrence matrix (GLCM), Voronoi tessellation (VT), and discrete wavelet transform (DWT) based methods to obtain information about waviness, feed marks, and roughness from machined surface images for describing tool flank wear. Two features from each texture analyses are extracted and fed into support vector machine (SVM) based regression models for predicting progressive tool flank wear. Mean correlation coefficient between the measured and predicted tool flank wear is found as 0.991.

FIGURES IN THIS ARTICLE
<>
Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Tool flank wear image showing three zones, A, B, and C and the measurement of VBaveragefrom zone B at VBaverage = 245 μm

Grahic Jump Location
Fig. 2

Experimental setup

Grahic Jump Location
Fig. 3

Turned surface images produced (a) by a fresh tool and (b) by a worn tool (VBaverage = 362 μm)

Grahic Jump Location
Fig. 4

Turned surface image (a) before preprocessing and (b) after preprocessing. (c) Histogram of (a) and (d) histogram of (b).

Grahic Jump Location
Fig. 5

(a) An image fragment and (b) its GLCM

Grahic Jump Location
Fig. 6

Preprocessed images of (a) Fig. 3(a) and (b) Fig. 3(b), (c) and (d) corresponding Canny edge-detected images of (a) and (b), and (e) and (f) VT of (c) and (d)

Grahic Jump Location
Fig. 13

Variation of ENE with machining time for turning at (a) V = 110 m/min, (b) V = 150 m/min and f = 0.2 mm/rev, (c) V = 150 m/min and f = 0.24 mm/rev, and (d) V = 150 m/min and f = 0.28 mm/rev

Grahic Jump Location
Fig. 12

Variation of Gq with machining time for turning at (a) V = 110 m/min, (b) V = 150 m/min and f = 0.2 mm/rev, (c) V = 150 m/min and f = 0.24 mm/rev, and (d) V = 150 m/min and f = 0.28 mm/rev

Grahic Jump Location
Fig. 11

Variation of TAP with machining time for turning at (a) V = 110 m/min, (b) V = 150 m/min and f = 0.2 mm/rev, (c) V = 150 m/min and f = 0.24 mm/rev, and (d) V = 150 m/min and f = 0.28 mm/rev

Grahic Jump Location
Fig. 10

Variation of NPZCM with machining time for turning at (a) V = 110 m/min, (b) V = 150 m/min and f = 0.2 mm/rev, (c) V = 150 m/min and f = 0.24 mm/rev, and (d) V = 150 m/min and f = 0.28 mm/rev

Grahic Jump Location
Fig. 9

Variation of SDM with machining time for turning at (a) V = 110 m/min, (b) V = 150 m/min and f = 0.2 mm/rev, (c) V = 150 m/min and f = 0.24 mm/rev, and (d) V = 150 m/min and f = 0.28 mm/rev

Grahic Jump Location
Fig. 8

Variation of CON with machining time for turning at (a) V = 110 m/min, (b) V = 150 m/min and f = 0.2 mm/rev, (c) V = 150 m/min and f = 0.24 mm/rev, and (d) V = 150 m/min and f = 0.28 mm/rev

Grahic Jump Location
Fig. 7

Soft margin loss for (a) a linear SVR model and (b) its loss function

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In