Rough Set Based Intelligent Welding Quality Classification
The knowledge base of welding defect recognition is
essentially incomplete. This characteristic determines that the recognition results do not reflect the actual situation. It also has a further influence on the classification of welding quality. This paper is
concerned with the study of a rough set based method to reduce the influence and improve the classification accuracy. At first, a rough set
model of welding quality intelligent classification has been built. Both condition and decision attributes have been specified. Later on, groups
of the representative multiple compound defects have been chosen
from the defect library and then classified correctly to form the
decision table. Finally, the redundant information of the decision table has been reducted and the optimal decision rules have been reached. By this method, we are able to reclassify the misclassified defects to
the right quality level. Compared with the ordinary ones, this method
has higher accuracy and better robustness.
[1] B. Jin, N. Park, K.M. George, "Modeling and analysis of soft-test/repair
for CCD-based digital X-ray systems," IEEE Trans. Instrumentation and
Measurement, vol. 52, pp. 1713-1721, Nov. 2003.
[2] L.M. Wang, X.Q. Gai, X.L. Yan, "Research on tracking recognition algorithm of steel pipe welding seam image," in Proc. International Symposium on Information Science and Engineering, Wuhan, 2008, pp.
239-243.
[3] G.J. Li, G.R. Wang, J.G. Zhong, "A genetic algorithm on welding seam
image segmentation," in Proc. 5th World Congress on Intelligent Control
and Automation, Guangzhou, 2004, pp. 2176-2178.
[4] S. Suwanjandee, A. Leelasantitham, S. Kiattisin, "A detection of welding
trace using X-ray images based on 2-D wavelet transform," in Proc.
International Symposium on Intelligent Signal Processing and
Communication Systems, Bangkok, 2010, pp. 1-4.
[5] Y. Zou, Y.H. Li, L.P. Jiang, "Weld pool image processing algorithm for seam tracking of welding robot," in Proc. IEEE Conf. on Industrial
Electronics and Applications, Beijing, 2011, pp. 161-165.
[6] H.B. Yan, L.N. Zhao, H. Ju, "Research on SVM based classification for
welding defects in radiographic testing," in Proc. International Conf. on
Image and Signal Processing, Chengdu, 2009, pp. 1-5.
[7] A.N. Luo, C.H. Shen, B. Yi, "Method of multi-classification by improved
binary tree based on SVM for welding defects recognition," Trans. of The
China Welding Institution, vol. 31, no. 7, pp. 51-55, Jul. 2010.
[8] G.R. Cai, D.Du, Y. Tian, "Defect detection of X-ray images of weld using
optimized heuristic search based on image information fusion," Trans. of
The China Welding Institution, vol. 28, no. 2, pp. 29-32, Feb. 2007.
[9] D.T. Li, C.H. Pan, S.M. Du, "The multi-information fusion quality
judgement of spot welding based on rough sets," Trans. of The China
Welding Institution, vol. 30, no.7, pp. 21-25, Jul. 2009.
[10] F.J. Meng, S. Zhu, Y. Cao, "Fuzzy synthesis estimation of bead surface
quality for pilse MAG welding prototyping," Trans. of The China Welding Institution, vol. 29, no. 7, pp. 24-29, Jul. 2008.
[11] T.H. Zhang, Y.C. Chen, P.J. Yan, "Reliability distribution of welding
defect size," in Proc. International Conf. on Mechanic Automation and
Control Engineering, Kunming, 2010, pp. 3649-3651.
[12] S.X. Chen, L.X. Song, "The automatic classification of the welding defects," in Proc. IEEE Conf. on Acoustics, Speech, and Signal Processing, Harbin, 2003, pp. 618-621.
[13] J.J. Peng, "A method for recognition of defects in welding lines," in Proc.
International Conf. on Artificial Intelligence and Computational
Intelligence, Shanghai, 2009, pp. 366-369.
[14] A. Kusiak, "Rough set theory: a data mining tool for semiconductor
manufacturing," IEEE Trans. on Electronics Packaging Manufacturing,
vol. 24, pp. 44-50, Apr. 2002.
[15] C. Thilagavathy, R. Rajesh, "A note on rough set theory," in Proc. 3rd
International Conf. on Electronics Computer Technology, Coimbatore,
2011, pp. 39-41.
[1] B. Jin, N. Park, K.M. George, "Modeling and analysis of soft-test/repair
for CCD-based digital X-ray systems," IEEE Trans. Instrumentation and
Measurement, vol. 52, pp. 1713-1721, Nov. 2003.
[2] L.M. Wang, X.Q. Gai, X.L. Yan, "Research on tracking recognition algorithm of steel pipe welding seam image," in Proc. International Symposium on Information Science and Engineering, Wuhan, 2008, pp.
239-243.
[3] G.J. Li, G.R. Wang, J.G. Zhong, "A genetic algorithm on welding seam
image segmentation," in Proc. 5th World Congress on Intelligent Control
and Automation, Guangzhou, 2004, pp. 2176-2178.
[4] S. Suwanjandee, A. Leelasantitham, S. Kiattisin, "A detection of welding
trace using X-ray images based on 2-D wavelet transform," in Proc.
International Symposium on Intelligent Signal Processing and
Communication Systems, Bangkok, 2010, pp. 1-4.
[5] Y. Zou, Y.H. Li, L.P. Jiang, "Weld pool image processing algorithm for seam tracking of welding robot," in Proc. IEEE Conf. on Industrial
Electronics and Applications, Beijing, 2011, pp. 161-165.
[6] H.B. Yan, L.N. Zhao, H. Ju, "Research on SVM based classification for
welding defects in radiographic testing," in Proc. International Conf. on
Image and Signal Processing, Chengdu, 2009, pp. 1-5.
[7] A.N. Luo, C.H. Shen, B. Yi, "Method of multi-classification by improved
binary tree based on SVM for welding defects recognition," Trans. of The
China Welding Institution, vol. 31, no. 7, pp. 51-55, Jul. 2010.
[8] G.R. Cai, D.Du, Y. Tian, "Defect detection of X-ray images of weld using
optimized heuristic search based on image information fusion," Trans. of
The China Welding Institution, vol. 28, no. 2, pp. 29-32, Feb. 2007.
[9] D.T. Li, C.H. Pan, S.M. Du, "The multi-information fusion quality
judgement of spot welding based on rough sets," Trans. of The China
Welding Institution, vol. 30, no.7, pp. 21-25, Jul. 2009.
[10] F.J. Meng, S. Zhu, Y. Cao, "Fuzzy synthesis estimation of bead surface
quality for pilse MAG welding prototyping," Trans. of The China Welding Institution, vol. 29, no. 7, pp. 24-29, Jul. 2008.
[11] T.H. Zhang, Y.C. Chen, P.J. Yan, "Reliability distribution of welding
defect size," in Proc. International Conf. on Mechanic Automation and
Control Engineering, Kunming, 2010, pp. 3649-3651.
[12] S.X. Chen, L.X. Song, "The automatic classification of the welding defects," in Proc. IEEE Conf. on Acoustics, Speech, and Signal Processing, Harbin, 2003, pp. 618-621.
[13] J.J. Peng, "A method for recognition of defects in welding lines," in Proc.
International Conf. on Artificial Intelligence and Computational
Intelligence, Shanghai, 2009, pp. 366-369.
[14] A. Kusiak, "Rough set theory: a data mining tool for semiconductor
manufacturing," IEEE Trans. on Electronics Packaging Manufacturing,
vol. 24, pp. 44-50, Apr. 2002.
[15] C. Thilagavathy, R. Rajesh, "A note on rough set theory," in Proc. 3rd
International Conf. on Electronics Computer Technology, Coimbatore,
2011, pp. 39-41.
@article{"International Journal of Chemical, Materials and Biomolecular Sciences:53836", author = "L. Tao and T. J. Sun and Z. H. Li", title = "Rough Set Based Intelligent Welding Quality Classification", abstract = "The knowledge base of welding defect recognition is
essentially incomplete. This characteristic determines that the recognition results do not reflect the actual situation. It also has a further influence on the classification of welding quality. This paper is
concerned with the study of a rough set based method to reduce the influence and improve the classification accuracy. At first, a rough set
model of welding quality intelligent classification has been built. Both condition and decision attributes have been specified. Later on, groups
of the representative multiple compound defects have been chosen
from the defect library and then classified correctly to form the
decision table. Finally, the redundant information of the decision table has been reducted and the optimal decision rules have been reached. By this method, we are able to reclassify the misclassified defects to
the right quality level. Compared with the ordinary ones, this method
has higher accuracy and better robustness.", keywords = "intelligent decision, rough set, welding defects, welding quality level", volume = "5", number = "12", pages = "1097-4", }
