Improving pulse eddy current and ultrasonic testing stress measurement accuracy using neural network data fusion

Abbas Habibalahi; Mahdieh Dashtbani Moghari; Kaveh Samadian; Seyed Sajad Mousavi; Mir Saeed Safizadeh

Improving pulse eddy current and ultrasonic testing stress measurement accuracy using neural network data fusion

View Fulltext

Author(s): Abbas Habibalahi ¹ ; Mahdieh Dashtbani Moghari ² ; Kaveh Samadian ³ ; Seyed Sajad Mousavi ⁴ ; Mir Saeed Safizadeh ¹
- Affiliations: 1: School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran;
  2: Department of Electrical and Computer Engineering, Semnan University, Semnan, Iran;
  3: School of Mechanical Engineering, Amirkabir University, Tehran, Iran;
  4: School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran
Source: Volume 9, Issue 4, July 2015, p. 514 – 521
DOI: 10.1049/iet-smt.2014.0211 , Print ISSN 1751-8822, Online ISSN 1751-8830

Received 09/07/2014, Accepted 20/10/2014, Revised 19/09/2014, Published 09/03/2015

Stress and residual stress are two crucial factors which play important roles in mechanical performance of materials, including fatigue and creep, hence measuring them is highly in demand. Pulse eddy current (PEC) and ultrasonic testing (UT) are two non-destructive tests (NDT) which are nominated to measure stresses and residual stresses by numerous scholars. However, both techniques suffer from lack of accuracy and reliability. One technique to tackle these challenges is data fusion, which has numerous approaches. This study introduces a promising one called neural network data fusion, which shows effective performance. First, stresses are simulated in an aluminium alloy 2024 specimen and then PEC and UT signals related to stresses are acquired and processed. Afterward, useful information obtained is fused using artificial neural network procedure and stresses are estimated by fused data. Finally, the accuracy of fused data are compared with PEC and UT information and results show the capability of neural network data fusion to improve stress measurement accuracy.

References

1. 1)
  - 25. Egle, D.M., Bray, D.E.: ‘Measurement of acoustoelastic and third-order elastic constants for rail steel’, J. Acoust. Soc. Am., 1976, 60, (3), pp. 741–744 (doi: 10.1121/1.381146).
2. 2)
  - 16. Javadi, Y.: ‘Ultrasonic measurement of hoop residual stress in stainless steel pipes’, Manuf. Ind. Eng., 2013, 12, (1–2), pp. 1–6.
3. 3)
  - 35. Yu, F., Nagy, P.B.: ‘Dynamic pizoresistivity calibration for eddy current nondestructive residual stress measurement’, J. Nondestruct. Eval., 2005, 24, pp. 143–151 (doi: 10.1007/s10921-005-8783-9).
4. 4)
  - 5. Vangy, D.: ‘Stress evaluation by pulse echo ultrasonic longitudinal wave’, Exp. Mech., 2001, 41, pp. 277–281 (doi: 10.1007/BF02323145).
5. 5)
  - 2. Javadi, Y.: ‘Investigation of clamping effect on the welding residual stress and deformation of Monel plates by using the ultrasonic stress measurement and finite element method’, J. Press. Vessel Technol., 2014, 137, (1), pp. 1–7 (doi: 10.1115/1.4027514).
6. 6)
  - 24. Lawrence, A.K.: ‘Sensor and data fusion: a tool for information assessment and decision making’. SPIE, Lake Buena Vista, USA, 2004.
7. 7)
  - 3. Withers, P.J., Bhadeshia, K.D.H.: ‘Residual stress: part 1 – measurement techniques’, J. Mater. Sci. Technol., 2001, 17, pp. 355–365 (doi: 10.1179/026708301101509980).
8. 8)
  - 31. Katidiotis, A., Tsagkaris, K., Demestichas, P.: ‘Performance evaluation of artiﬁcial neural network-based learning schemes for cognitive radio systems’, Comput. Electr. Eng., 2010, 36, pp. 518–35 (doi: 10.1016/j.compeleceng.2009.12.005).
9. 9)
  - 3. Blodgett, M.P., Nagy, P.B.: ‘Eddy current assessment of near-surface residual stress in shot peened nickel base superalloys’, J. Nondestruct. Eval., 2004, 23, pp. 107–123 (doi: 10.1023/B:JONE.0000048866.40648.fe).
10. 10)
  - 26. Horn, D., Mayo, W.R.: ‘NDE reliability gains from combining eddy-current and ultrasonic testing’, NDT&E Int., 2000, 33, pp. 351–362 (doi: 10.1016/S0963-8695(99)00058-4).
11. 11)
  - 34. Santos, T.G., Silva, B.S., Vilaça, P.S., Quintino, L., Sousa, J.M.C.: ‘Data fusion in non-destructive testing using fuzzy logic to evaluate friction stir welding’, Weld. Int., 2008, 22, pp. 826–833 (doi: 10.1080/09507110802591327).
12. 12)
  - 32. Hedman, H.: ‘Performance evaluation of artificial neural networks in the foreign exchange market’, Department of Mathematics, Royal Institute of Technology, Master's Thesis (TMTHM), Spring2012.
13. 13)
  - 18. Javadi, Y., Akhlaghi, M., Najafabadi, M.A.: ‘Using finite element and ultrasonic method to evaluate welding longitudinal residual stress through the thickness in austenitic stainless steel plates’, Mater. Des., 2013, 45, pp. 628–642 (doi: 10.1016/j.matdes.2012.09.038).
14. 14)
  - 17. Javadi, Y., Afzali, O., Raeisi, M.H., Najafabadi, M.A.: ‘Nondestructive evaluation of welding residual stresses in dissimilar welded pipes’, J. Nondestruct. Eval., 2013, 32, (2), pp. 177–187 (doi: 10.1007/s10921-013-0171-2).
15. 15)
  - 12. Morozov, M., Tian, G.Y., Withers, P.J.: ‘Noncontact evaluation of the dependency of electrical conductivity on stress for various Al alloys as a function of plastic deformation and annealing’, J. Appl. Phys., 2010, 108, pp. 1–9 (doi: 10.1063/1.3456996).
16. 16)
  - 22. Uzuna, F., Bilgea, A.N.: ‘Immersion ultrasonic technique for investigation of total welding residual stress’, Procedia Eng., 2011, 10, pp. 3098–3103 (doi: 10.1016/j.proeng.2011.04.513).
17. 17)
  - 11. Yu, F., Nagy, P.B.: ‘On the influence of cold work on eddy current characterization of near-surface residual stress in shot peened nickel base superalloys’, J. Nondestruct. Eval., 2006, 25, pp. 107–122 (doi: 10.1007/s10921-006-0009-2).
18. 18)
  - 21. Habibalahi, A., Safizadeh, M.S.: ‘Forward to residual stress measurement by using pulsed eddy current technique’, Insight, 2013, 55, pp. 492–497 (doi: 10.1784/insi.2012.55.9.492).
19. 19)
  - 33. Haykin, S.: ‘Neural networks’ (Englewood Cliffs, NJ, Prentice-Hall, 1998).
20. 20)
  - 10. James, M.N., Hughes, D.J., Chen, Z., et al: ‘Residual stresses and fatigue performance’, Eng. Failure Anal., 2007, 14, (2), pp. 384–395 (doi: 10.1016/j.engfailanal.2006.02.011).
21. 21)
  - 28. Boss, T., Diekmann, V., Jurgens, R., Becker, W.: ‘Sensory fusion by neural networks using spatially represented information’, Biol. Cybern, 2001, 85, pp. 371–385 (doi: 10.1007/s004220100271).
22. 22)
  - 19. Sadeghi, S., Najafabadi, M.A., Javadi, Y., Mohammadisefat, M.: ‘Using ultrasonic waves and finite element method to evaluate through-thickness residual stresses distribution in the friction stir welding of aluminum plates’, Mater. Des., 2013, 52, pp. 870–880 (doi: 10.1016/j.matdes.2013.06.032).
23. 23)
  - 8. Qozam, H., Chaki, S., Bourse, G., Robin, C., Walaszek, H., Bouteille, P.: ‘Microstructure effect on the Lcr elastic wave for welding residual stress measurement’, Exp. Mech., 2010, 50, pp. 179–185 (doi: 10.1007/s11340-009-9283-0).
24. 24)
  - 13. Abu-Nabah, B.A., Hassan, W.T., Ryan, D., Blodgett, M.P., Nagy, P.B.: ‘The effect of hardness on eddy current residual stress profiling in shot peened nickel alloy’, J. Nondestruct. Eval., 2010, 29, pp. 143–153 (doi: 10.1007/s10921-010-0072-6).
25. 25)
  - 6. Hauk, V.: ‘Structural and residual stress analysis by nondestructive methods’ (Elsevier, Amsterdam, Netherlands, 1997).
26. 26)
  - 27. Gautier, S.: ‘X-ray and ultrasound data fusion’, Image Process., 1998, 3, pp. 366–369.
27. 27)
  - 29. Ataei, S., Aghakouchak, A.A., Marefat, M.S., Mohammadzadeh, S.: ‘Sensor fusion of a railway bridge load test using neural networks’, Expert Syst. Appl., 2005, 29, pp. 678–683 (doi: 10.1016/j.eswa.2005.04.038).
28. 28)
  - 23. Habibalahi, A., Safizadeh, M.S.: ‘Pulsed eddy current and ultrasonic data fusion applied to stress measurement’, Meas. Sci. Technol., 2014, 25, (5), pp. 055601 (doi: 10.1088/0957-0233/25/5/055601).
29. 29)
  - 2. Withers, P.J.: ‘Residual stress and its role in failure’, Rep. Prog. Phys., 2007, 70, (12), pp. 2211–2264 (doi: 10.1088/0034-4885/70/12/R04).
30. 30)
  - 4. Dell'Isola, F., Guarascio, M., Hutter, K.: ‘A variational approach for the deformation of a saturated porous solid. A second-gradient theory extending Terzaghi's effective stress principle’, Arch. Appl. Mech., 2000, 70, pp. 323–337 (doi: 10.1007/s004199900020).
31. 31)
  - 15. Javadi, Y., Najafabadi, M.A.: ‘Comparison between contact and immersion ultrasonic method to evaluate welding residual stresses of dissimilar joints’, Mater. Des., 2013, 47, pp. 473–482 (doi: 10.1016/j.matdes.2012.12.069).
32. 32)
  - 14. Javadi, Y., Sadeghi, S., Najafabadi, M.A.: ‘Taguchi optimization and ultrasonic measurement of residual stresses in the friction stir welding’, Mater. Des., 2014, 55, pp. 27–34 (doi: 10.1016/j.matdes.2013.10.021).
33. 33)
  - 9. Shaw, B.A., Aylott, C., O'hara, P., Brimble, K.: ‘The role of residual stress on the fatigue strength of high performance gearing’, Int. J. Fatigue, 2003, 25, (9), pp. 1279–1283 (doi: 10.1016/j.ijfatigue.2003.08.014).
34. 34)
  - 20. Javadi, Y., Hloch, S.: ‘Employing the waves to measure longitudinal residual stresses in different depths of a stainless steel welded plate’, Advances in Materials Science and Engineering, 2013.

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Improving pulse eddy current and ultrasonic testing stress measurement accuracy using neural network data fusion

References

Related content