Research of Ultrasonic Detection for Bonding Quality of Thin Plate Based on Fuzzy Pattern Recognition

Abstract:

The application of fuzzy pattern recognition to ultrasonic detection for bonding quality of thin composite plate is studied. In this paper, firstly, the fuzzy membership function between each characteristic and bonding quality is established by BP neural network. Simulation results show that this method is convenient, simple, and it conforms to the practical application. Accordingly，the fuzzy subsets of standard modules and unknown bonding quality modules are established. Secondly, the fuzzy pattern recognition algorithm, which is designed by the nearest principle as the judging standard to judge bonding quality, is given. Experimental results show that the algorithm is very exact for quantitative recognition of bonding quality.

• Periodical: Advanced Materials Research (Volume 346)
• Pages: 493-500
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.346.493
• Online since: September 2011
• Authors: Xiao Juan Wang, Ze Zhang, Hai Tao Wang
• Keywords: Approach Degree, Fuzzy Pattern Recognition, Membership Function, Nearest Principle, Ultrasonic Detection

References

[1] Cawley P. The sensitivity of the mechanical impedance method of nondestructive testing [J], NDT international, 1987, 20(4): 209～215.

DOI: 10.1016/0308-9126(87)90243-4

[2] Smith A C, Yang H. Ultrasonic study of adhesive bond quality at a steel to rubber interface by using quadrature phase detection techniques [J], Materials Evaluation, 1989, 27(12): 1389～1400.

DOI: 10.1016/0963-8695(92)90591-4

[3] Zhang Haiyan. Application of wavelet analysis and fuzzy pattern recognition to flaw identification in ultrasonic testing[J], Nondestructive Testing. 2000, 22(2): 51～54. A.

[4] Zhang Haiyan., Liu Zhenqing. Application of fuzzy mathmatics to ultrasonic testing[J], Nondestructive Testing 2001, 23(6), 260～263.

[5] Zhigang Li, Shouren Hu，Honyi Lu. Feedforward Neuarl Networks Design By Evolutionary Programming, Proceedings of The Third Word Congress on Expert System, Feb., Soul, Korea, 1996, Ⅱ , 31247～1254.

[6] LI YAWEI, CHEN SHOUYU, NIE XIANGTIAN, Fuzzy Pattern Recognition Approach to Construction Contractor Selection[J], Fuzzy Optimization and Decision Making, 2005, (4): 103～118.

DOI: 10.1007/s10700-004-5867-4

[7] Wang Chengming, Yan Yunhui, Li Jun, Zhao Yao. Fuzzy neural network method and its application in pattern recognition of cold steel strip surface defect [J]，COMPUTER INTEGRATED MANUFACTURING SYSTEMS，2007，13(9)：1774～1779.

[8] Yang Linyu, Zhang Wei, Ma Guowei, Chen Bingya. Composite material defect recognition based on fuzzy theory in ultrasonic testing. JOURNAL OF NANCHANG INSTITUTE OF AERONAUTICAL TECHNOLOGY（NATURAL SCIENCES EDITION）, 2006, 20(1).

[9] Zhang Ze, Gao Zhi-qi, Ren Yue-qing and Liu Kun, Characteristic Extraction of Ultrasonic Detection of Bond Interface of Thin Composite Plate Based on Wavelet Transformation, Proceedings of the IEEE International Conference on Automation and Logistics, Qingdao, China September (2008).

DOI: 10.1109/ical.2008.4636467