Defect Detection in CK45 Steel Structures through C-scan Images Using Deep Learning Method

Updata:01-01-1970

Source:
By:Navid Moshtaghi Yazdani

DOI: https://doi.org/10.30564/aia.v3i1.3074

Abstract:

In the present paper, a method for reliable estimation of defect profile in CK45 steel structures is presented using an eddy current testing based measurement system and post-processing system based on deep learning technique. So a deep learning method is used to determine the defect characteristics in metallic structures by magnetic field C-scan images obtained by an anisotropic magneto-resistive sensor. Having designed and adjusting the deep convolution neural network and applied it to C-scan images obtained from the measurement system, the performance of deep learning method proposed is compared with conventional artificial neural network methods such as multilayer perceptron and radial basis function on a number of metallic specimens with different defects. The results confirm the superiority of the proposed method for characterizing defects compared to other classical training-oriented methods.

References:

[1] J. Blitz, “Electrical and magnetic methods of nondestructive testing,”Springer Science & BusinessMedia,vol. 3,2012. [2] B. Guo, Z. Zhang and R. Li, “Ultrasonic and eddy current non-destructive evaluation for property assessment of 6063 aluminum alloy,” NDT & E International, vol. 93, pp. 34-39, 2018. [3] R.James, M. Faisal Haider, V. Giurgiutiu, and D. Lilienthal, “A Simulative and Experimental Approach toward Eddy Current Nondestructive Evaluation of Manufacturing Flaws and Operational Damage in CFRP Composites,” ASME. ASME J Nondestructive Evaluation, vol. 3, no. 1, 2020. [4] S.Nagata and M. Numachi, “Eddy Current Non Destructive Evaluation for Healthiness of Radiator Structure,”IEEE Transactions on Magnetics, vol. 53, no.11,pp.1-4, 2017. [5] S. H. H. Sadeghi and D. Mirshekar-Syahkal, “A new technique for sizing cracks in metals, utilizing an induced surface magnetic field,” Review ofProgress in Quantitative Nondestructive Evaluation, pp. 593-600, 1990. [6] W. Dehui, S. Lingxin, W. Xiaohong, “A Novel Nondestructive testing Method by Measuring the Change Rate of Magnetic Flux Leakage,” J Non destruct Eval, vol. 4,2017. [7] H. G. Ramos and A. L. Ribeiro, “Present and Future Impact of Magnetic Sensors in NDE,” Procedia Engineering, vol. 86, pp. 406-419, December 2014. [8] H. Dongfeng, “Eddy-current NDE Using an AMR Magnetometer,” Progress in Electro magnetics Research Symposium Proceedings, Moscow, Russia, August 2009. [9] L. Udpa, and S. Udpa, “Optimization and Validation of Rotating Current Excitation with GMR Array Sensors for Riveted Structures Inspection,” Sensors, vol. 16, no. 9, 2016. [10] F. Franco, F. A. Cardoso, L. S. Rosado, R. Ferreira, S. Cardoso, M. Piedade and P. P. Freitas,“Advanced NDT inspection tools for titanium surfaces based on high performance magneto resistive sensors,” IEEE Transactions on Magnetics, vol. 53, no. 4, pp. 1-5, 2016. [11] D. F. He, M. Shiwa, J. P. Jia, J. Takatsubo and S. Moriya, “Multi-frequency ECT with AMR sensor,” NDT & E International, vol.44, no. 5,pp. 438-441, 2011. [12] A. Jander, C. Smith and R. Schneider, “Magneto resistive sensors for nondestructive evaluation,” In Advanced Sensor Technologies for Nondestructive Evaluation and Structural Health Monitoring, vol. 5770,pp. 1-14, May, 2005. [13] M. Li and D. A. Lowther, “The application of topological gradients todefect identification in magnetic flux leakage-type,” IEEE Transactions onmagnetics,vol. 46, no. 8, pp. 3221-3224, 2010. [14] A. Noroozi, R. Hasanzadeh and M. Ravan, “A Fuzzy Learning Approachfor Identification of Arbitrary Crack Profiles Using ACFM Technique”,IEEE Transactions on Magnetics, vol. 49, no. 9, pp. 5016-5027, 2013. [15] M. Wrzuszczakand and J. Wrzuszczak, “Eddy current flaw detection with neural network applications,” Measurement, vol. 38, no. 2, pp. 132-136, 2005. [16] G. Psuj, “Multi-Sensor Data Integration Using Deep Learning for Characterization of Defects in Steel Elements,” Sensors, vol. 18, no. 2,pp. 292, January 2018. [17] D. f. He and M. Shiwa, “Deep Defect Detection Using Eddy Current Testing with AMR Sensor,” PIERS Proceedings, pp. 12-15, 2013. [18] J. Schmidhuber, “Deep learning in neural networks: An overview, ”Neural networks, vol. 61, pp. 85-117, 2015. [19] S. Zhou, Y. Chen, D. Zhang, J. Xie and Y. Zhou, “Classification of surface defects on steel sheet using convolutional neural networks, ”Mater, Techno, vol. 51, pp. 123–131, 2017. [20] J. A. Buck, P. R. Underhill, J. E. Morelli and T. W. Krause, “Simultaneous multi parameter measurement in pulsed eddy current steam generator data using artificial neural networks.”IEEE Transactions on Instrumentation and Measurement, Vol. 65, no. 3, pp. 672-679, 2016.

Tags: