Classification of weld defects based on the analytical hierarchy process and Dempster–Shafer evidence theory
- 110 Downloads
Weld quality management is currently one of the most concerning issues in the manufacturing industry. In this paper, a novel method is proposed for weld defect classification based on the analytical hierarchy process (AHP) and Dempster–Shafer (DS) evidence theory. First, to overcome the problem of traditional DS methods, which weigh every feature equally in classification, a method is proposed based on AHP to calculate the weight of features (WF) of a weld defect, which can then be utilized in classification. Then, an improved method based on DS evidence theory is presented to improve the accuracy of classification, which includes calculation of the standard value of features based on frequency histograms analysis and an improved Dempster’s rule for combination based on WF. A case study on the classification of steam turbine weld defects is provided to illustrate and evaluate the proposed techniques. The results show that the proposed method increases the correct recognition rate of classification with limited samples, making DS evidence theory applicable to weld defect classification.
KeywordsRadiographic testing Classification Analytical hierarchy process (AHP) Dempster–Shafer (DS) Evidence theory
The authors sincerely thank the referees for their helpful suggestions and comments, which greatly improved the quality of the paper. This research was supported by the National Natural Science Foundation of China (Grant No. 51375375).
- da Silva, R. R., & Mery, D. (2007a). The state of the art of weld seam radiographic testing: Part I–image processing. Materials Evaluation, 65(6), 643–647.Google Scholar
- da Silva, R. R., & Mery, D. (2007b). The state of the art of weld seam radiographic testing: Part II–pattern recognition. Materials Evaluation, 65(9), 833–838.Google Scholar
- Dempster, A. P. (1968). A generalization of Bayesian inference. Journal of the Royal Statistical Society: Series B (Methodology), 30(2), 205–247.Google Scholar
- Dudewicz, E. J. (1999). Basic statistical methods. In J. M. Juran & A. B. Godfrey (Eds.), Juran’s quality handbook (5th ed., pp. 44.1–44.112). New York: McGraw-Hill.Google Scholar
- Du, X., Shen, Y., & Wang, Y. (2008). Weld defect classification in ultrasonic testing basing on time-frequency discriminant features. Transactions-China Welding Institution, 29(2), 89–92.Google Scholar
- Gao, H., Shen, X., Jiang, Z., Yang, H., & Yan, L. (2012). Image subcategory classification based on Dempster–Shafer evidence theory. In International Conference on Computer Science and Service System (pp. 2289–2292). Nanjing: CHN, August 11–13, 2012. https://doi.org/10.1109/CSSS.2012.568
- Gu, K., Zhai, G., Yang, X., & Zhang, W. (2013). A new reduced-reference image quality assessment using structural degradation model. In 2013 IEEE international symposium on circuits and systems (ISCAS). (pp. 1095–1098). Beijing: CHN, May 19–23, 2013. https://doi.org/10.1109/ISCAS.2013.6572041.
- Maruthur, N. M., Joy, S., Dolan, J., Segal, J. B., Shihab, H. M., & Singh, S. (2013). Systematic assessment of benefits and risks: Study protocol for a multi-criteria decision analysis using the analytic hierarchy process for comparative effectiveness research. F1000Research, 2, 160. https://doi.org/10.12688/f1000research.2-160.v1
- Mu, W., Gao, J., Wang, Z., Jiang, H., Chen, F., & Dang, C. (2013). Radiographic image assessment approach based on human visual system. Journal of Xi’an Jiaotong University, 47(7), 91–95.Google Scholar
- Nacereddine, N., Hamami, L., & Ziou, D. (2006). Thresholding techniques and their performance evaluation for weld defect detection in radiographic testing. International Journal of Machine Graphics and Vision, 15(3), 557–566.Google Scholar
- Pan, J., Jiang, H., Gao, J., & Yang, P. (2011). Condition diagnosis with complex network-time series analysis. In Proceedings of Annual Reliability and Maintainability Symposium, Lake Buena Vista, FL, USA (pp. 1–6), January 24–27, 2011. https://doi.org/10.1109/RAMS.2011.5754502.
- Saaty, T. L. (1980). The analytic hierarchy process. New York: McGraw-Hill.Google Scholar
- Salchak, Y., Tverdokhlebova, T., Sharavina, S., & Lider, A. (2016). The classification of weld seam defects for quantitative analysis by means of ultrasonic testing. IOP Conference Series: Materials Science and Engineering, 132, 012027. https://doi.org/10.1088/1757-899X/132/1/012027.CrossRefGoogle Scholar
- Shafer, G. (1976). A mathematical theory of evidence. Princeton: Princeton University Press.Google Scholar
- Sreedhar, U., Krishnamurthy, C. V., Balasubramaniam, K., Raghupathy, V. D., & Ravisankar, S. (2012). Automatic defect identification using thermal image analysis for online weld quality monitoring. Journal of Materials Processing Technology, 212(7), 1557–1566. https://doi.org/10.1016/j.jmatprotec.2012.03.002.CrossRefGoogle Scholar
- Zahran, O., & Al-Nuaimy, W. (2002). Recent developments in ultrasonic techniques for rail-track inspection. In Proceedings of the Annual Conference of the British Institute of Non-destructive Testing (BINDT 2002) (pp. 55–60). Southport: GBR, September 17–19, 2002.Google Scholar
- Zapata, J., Vilar, R., & Ruiz, R. (2012). Automatic inspection system of welding radiographic images based on ANN under a regularisation process. Journal of Nondestructive Evaluation, 31(1), 34–45. https://doi.org/10.1007/s10921-011-0118-4.
- Zhang, X., Zhu, Z., Xu, J., & Ren, S. (2005). The classification algorithm of defects in weld image based on asymmetrical SVMs. In International Conference on Control Automation 2005 (ICCA ’05) (pp. 1215–1219). Budapest: HUN, June 26–29, 2005. https://doi.org/10.1109/ICCA.2005.1528306
- Zhu, P., Yin, C., Cheng, Y., Huang, X., Cao, J., Vong, C.-M., et al. (2017). An improved feature extraction algorithm for automatic defect identification based on eddy current pulsed thermography. Mechanical Systems and Signal Processing. https://doi.org/10.1016/j.ymssp.2017.02.045.