شناسایی عیب در اتصالات چسبی با استفاده از روش انتشار امواج فراصوت مبتنی بر هوش مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده مهندسی مکانیک، دانشگاه علم و صنعت، تهران، ایران.

چکیده

وجود عیب در اتصالات چسبی یک مسئله مهم در ساخت سازه‌های فضایی می‌باشد. در این مقاله با استفاده از امواج لمب، ویژگی‌های مناسب جهت شناسایی اندازه و موقعیت عیوب اتصالات چسبی به‌دست‌آمده‌ است. با استفاده از شبیه‌سازی المان محدود به بررسی اثر عیب بر انتشار امواج لمب پرداخته شده است. شبیه‌سازی برای سه ضخامت متفاوت چسب، سه سایز متفاوت عیب دایره‌ای در ۹ موقعیت مختلف صورت‌گرفته است و تأثیر هر یک از آنها بر موج عبوری از اتصال بررسی شده است. سیگنال‌های به‌دست‌آمده از اتصالات معیوب با سیگنال حاصل از اتصال سالم مقایسه گردیده و ناحیه موردنظر جهت تحلیل‌های بعدی از کل سیگنال دریافتی جدا شد. تفکیک مناسب و صحیح عیوب نیازمند یافتن مشخصه‌هایی مناسب برای آن است به همین جهت 34 ویژگی جهت ایجاد تمایز و تفکیک عیوب بررسی گردید. در ادامه با فراهم آمدن پایه‌های ایجاد الگوهایی مناسب برای تفکیک عیوب، از شبکه عصبی استفاده شد. درصد تشخیص صحیح شبکه عصبی برای تفکیک ضخامت چسب 93/8 درصد، برای تفکیک مساحت عیوب از منظر اندازه ۱۰۰ درصد و برای تفکیک موقعیت عیب در دو محور افقی و عمودی به ترتیب 96/1 و 95/1 درصد به دست آمد. نتایج به‌دست‌آمده نشان‌دهنده کارایی روش تکامل فاصله بهبودیافته و ویژگی‌های انتخاب شده جهت تفکیک عیوب این‌گونه از اتصالات است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Use of Artificial Intelligence to Identify Adhesive Joints Defects by Using Ultrasonic

نویسندگان [English]

  • Mahshad Rastegarmoghaddam
  • majid rajabi
  • seyed davoud nikkhouy tanha
Student, Mechanical Engineering, IUST
چکیده [English]

Defects in adhesive joints are an important issue in the construction of space structures. In this paper, using lamp waves, suitable properties have been obtained to identify the size and position of the defects of the adhesive joints. Using finite element simulations, the effect of the defect on the propagation of the lamp waves has been investigated. Simulations have been performed for three different adhesive thicknesses, three different sizes of circular defects in 9 different positions, and the effect of each of them on the wave passing through the joint has been investigated. The signals obtained from the faulty connections were compared with the signal obtained from the healthy connection and the desired area was isolated from the total received signal for further analysis. The proper and correct separation of defects requires finding suitable characteristics for it. Therefore, 34 features were examined to differentiate and separate defects. Then, the neural network was used to provide the basis for creating appropriate patterns for the separation of defects. The percentage of correct detection of neural network for adhesive thickness separation was 93.8%, for defect area separation in terms of size 100% and for defect position separation in X and Y axes were 96.1 and 95.1%, respectively. The obtained results show the efficiency of the improved distance evolution method and the features selected to distinguish the defects of such connections.

کلیدواژه‌ها [English]

  • Non-destructive evaluation
  • Limb wave
  • Adhesive bonding
  • Status monitoring
  • Neural network
[1] Z. Tang, A. Cheng, J.D. Achenbach, An ultrasonic technique to detect nonlinear behavior related to degradation of adhesive bonds, in:  Review of Progress in Quantitative Nondestructive Evaluation, Springer, 1998, pp. 1347-1354.
[2] A. Pilarski, J.L. Rose, A transverse‐wave ultrasonic oblique‐incidence technique for interfacial weakness detection in adhesive bonds, Journal of Applied Physics, 63(2) (1988) 300-307.
[3] V. Kinra, V. Dayal, A new technique for ultrasonic-nondestructive evaluation of thin specimens, Experimental Mechanics, 28(3) (1988) 288-297.
[4] W. Kern, C. Spier, E. Hanneman, T. Miller, M. Matzner, T. Grogan, Neural cell adhesion molecule-positive peripheral T-cell lymphoma,  (2011).
[5] A. Moidu, A. Sinclair, J. Spelt, A new ultrasonic technique for the interfacial characterization of adhesive joints, in:  1996 IEEE Ultrasonics Symposium. Proceedings, IEEE, 1996, pp. 757-760.
[6] C. Brotherhood, B. Drinkwater, S. Dixon, The detectability of kissing bonds in adhesive joints using ultrasonic techniques, Ultrasonics, 41(7) (2003) 521-529.
[7] H. Lamb, On waves in an elastic plate, Proceedings of the Royal Society of London. Series A, Containing papers of a mathematical and physical character, 93(648) (1917) 114-128.
[8] P. Cawley, D. Alleyne, The use of Lamb waves for the long range inspection of large structures, Ultrasonics, 34(2-5) (1996) 287-290.
[9] J.L. Rose, Dispersion curves in guided wave testing, Materials Evaluation, 61(1) (2003) 20-22.
[10] A. Pilarski, J.L. Rose, Lamb wave mode selection concepts for interfacial weakness analysis, Journal of nondestructive evaluation, 11(3-4) (1992) 237-249.
[11] L. Singher, Y. Segal, E. Segal, J. Shamir, Considerations in bond strength evaluation by ultrasonic guided waves, The Journal of the Acoustical Society of America, 96(4) (1994) 2497-2505.
[12] V. Mustafa, A. Chahbaz, D.R. Hay, M. Brassard, S. Dubois, Imaging of disbond in adhesive joints with Lamb waves, in:  Nondestructive Evaluation of Materials and Composites, International Society for Optics and Photonics, 1996, pp. 87-97.
[13] M.J. Lowe, D.N. Alleyne, P. Cawley, Defect detection in pipes using guided waves, Ultrasonics, 36(1-5) (1998) 147-154.
[14] M. Lowe, R. Challis, C. Chan, The transmission of Lamb waves across adhesively bonded lap joints, The Journal of the Acoustical Society of America, 107(3) (2000) 1333-1345.
[15] F.L. di Scalea, M. Bonomo, D. Tuzzeo, Ultrasonic guided wave inspection of bonded lap joints: Noncontact method and photoelastic visualization, Journal of Research in Nondestructive Evaluation, 13(3) (2001) 153-171.
[16] P.K. Puthillath, H. Kannajosyula, C.J. Lissenden, J.L. Rose, ULTRASONIC GUIDED WAVE INSPECTION OF ADHESIVE JOINTS: A PARAMETRIC STUDY FOR A STEP‐LAP JOINT, in:  AIP Conference Proceedings, American Institute of Physics, 2009, pp. 1127-1133.
[17] B. Le Crom, M. Castaings, Shear horizontal guided wave modes to infer the shear stiffness of adhesive bond layers, The Journal of the Acoustical Society of America, 127(4) (2010) 2220-2230.
[18] C.P. Todd, R.E. Challis, Quantitative classification of adhesive bondline dimensions using Lamb waves and artificial neural networks, IEEE transactions on ultrasonics, ferroelectrics, and frequency control, 46(1) (1999) 167-181.
[19] U. Bork, R. Challis, Non-destructive evaluation of the adhesive fillet size in a T-peel joint using ultrasonic Lamb waves and a linear network for data discrimination, Measurement Science and Technology, 6(1) (1995) 72.
[20] M. Rautela, S. Gopalakrishnan, Ultrasonic guided wave based structural damage detection and localization using model assisted convolutional and recurrent neural networks, Expert Systems with Applications, 167 (2021) 114189.
[21] Y. Liu, Choose the best element size to yield accurate FEA results while reduce FE model's complexity,  (2013).
[22] H. Salehi, R. Burgueño, Pattern recognition framework using asynchronous discrete binary data for condition and damage assessment in plate-like structures, Journal of Intelligent Material Systems and Structures, 30(8) (2019) 1200-1215.