Pulsed Eddy Current Data Analysis for the Characterization of the Second-Layer Discontinuities
Pulsed eddy current (PEC) technique has been applied as a viable method to detect hidden discontinuities in metallic structures. Conventionally, selected time-domain features are employed to characterize the PEC data, such as peak value, lift-off point of intersection, rising point, crossing time, and differential time to peak. The research presented in this paper continues the effort in a previous study on detecting the radial cracks starting from the fastener hole in second layer of a two-layer mock-up aircraft structure. A large diameter excitation coil with ferrite core is used to induce a strong pulse, and the magnetic field generated by eddy current is detected by Hall sensors. Instead of analyzing the limited time-domain features, we propose using machine learning methods to interpret the raw data without feature extraction. Thus, the second-layer discontinuities can be characterized presumably with all the information contained in a waveform. An automated detection framework is proposed in this paper and the experimental results demonstrate the effectiveness of the proposed method.
KeywordsPulse eddy current Lift-off intersection Second-layer crack Machine learning Classification
Mr. Marc Genest at National Research Council of Canada is acknowledged for his valuable comments and feedback, which help improve the quality of this paper.
- 1.Sophian, A., Tian, G.Y., Taylor, D., Rudlin, J.: Electromagnetic and eddy current NDT: a review. INSIGHT 43(5), 302–306 (2001)Google Scholar
- 9.Safizadeh, M.S., Forsyth, D.S., Liu, Z., Lepine, B.A., Liao, M.: Pulsed eddy current inspections of aircraft structures in support of holistic damage tolerance. In: Proceedings of the Aerospace Manufacturing Technology Conference & Exposition. SAE International (2003)Google Scholar
- 17.Butt, D.M., Underhill, P.R., Krause, T.W.: Examination of pulsed eddy current for inspection of second layer aircraft wing lap-joint structures using outlier detection methods. CINDE J. 37(5), 6–10 (2016)Google Scholar
- 18.Butt, D., Underhill, R., Krause,T.W.: Pulsed eddy current detection of second layer cracks at ferrous fasteners in aircraft lap-joint structures. In: Proceedings of the 19th World Conference on Non-Destructive Testing, pp. 1–8, Munich, Germany (2016)Google Scholar
- 21.Hosseini, S.M.S.: Detection of hidden corrosion by pulsed eddy current using time frequency analysis. Ph.D. Thesis, Universite de Montreal, Montreal, Quebec, Canada (2012)Google Scholar
- 24.Mandache, C., Whalen, P.: A gradual approach for the detection of second layer cracks using the pulsed eddy current technique. In: Proceedings of the Aircraft Airworthiness&Sustainment Conference (2012)Google Scholar
- 27.John, V., Mita, S., Liu, Z., Qi, B.: Pedestrian detection in thermal images using adaptive fuzzy c-means clustering and convolutional neural networks. In: Proceedings of the 2015 14th IAPR International Conference on Machine Vision Applications (MVA), pp. 246–249. IEEE (2015)Google Scholar
- 30.Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986)Google Scholar
- 31.Ho, T.K.: Random decision forests. In: Proceedings of the Third International Conference on Document Analysis and Recognition, vol. 1, pp. 278–282. IEEE (1995)Google Scholar
- 33.Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. ICML 96, 148–156 (1996)Google Scholar
- 37.Oshiro, T.M., Perez, P.S., Baranauskas, J.A.: How many trees in a random forest? In: Proceedings of the MLDM, pp. 154–168. Springer (2012)Google Scholar